add_subdirectory(src)
add_subdirectory(qa)
-add_subdirectory(monitoring)
-
add_subdirectory(doc)
if(WITH_MANPAGE)
add_subdirectory(man)
endif()
option(WITH_GRAFANA "install grafana dashboards" OFF)
-if(WITH_GRAFANA)
- add_subdirectory(monitoring/grafana/dashboards)
-endif()
+add_subdirectory(monitoring/ceph-mixin)
CMAKE_DEPENDENT_OPTION(WITH_BOOST_VALGRIND "Boost support for valgrind" OFF
"NOT WITH_SYSTEM_BOOST" OFF)
mkdir -p %{buildroot}%{_localstatedir}/lib/ceph/bootstrap-rbd-mirror
# prometheus alerts
-install -m 644 -D monitoring/prometheus/alerts/ceph_default_alerts.yml %{buildroot}/etc/prometheus/ceph/ceph_default_alerts.yml
+install -m 644 -D monitoring/ceph-mixin/prometheus_alerts.yaml %{buildroot}/etc/prometheus/ceph/ceph_default_alerts.yml
%if 0%{?suse_version}
# create __pycache__ directories and their contents
%endif
%attr(0755,root,root) %dir %{_sysconfdir}/grafana/dashboards/ceph-dashboard
%config %{_sysconfdir}/grafana/dashboards/ceph-dashboard/*
-%doc monitoring/grafana/dashboards/README
-%doc monitoring/grafana/README.md
%files prometheus-alerts
%if 0%{?suse_version}
install -m 755 src/cephadm/cephadm $(DESTDIR)/usr/sbin/cephadm
- install -m 644 -D monitoring/prometheus/alerts/ceph_default_alerts.yml $(DESTDIR)/etc/prometheus/ceph/ceph_default_alerts.yml
+ install -m 644 -D monitoring/ceph-mixin/prometheus_alerts.yaml $(DESTDIR)/etc/prometheus/ceph/ceph_default_alerts.yml
# doc/changelog is a directory, which confuses dh_installchangelogs
override_dh_installchangelogs:
+++ /dev/null
-add_subdirectory(prometheus)
--- /dev/null
+../../src/pybind/mgr/dashboard/.pylintrc
\ No newline at end of file
--- /dev/null
+if(WITH_GRAFANA)
+ set(CEPH_GRAFANA_DASHBOARDS_DIR "${CMAKE_INSTALL_SYSCONFDIR}/grafana/dashboards/ceph-dashboard"
+ CACHE PATH "Location for grafana dashboards")
+ file(GLOB CEPH_GRAFANA_DASHBOARDS "dashboards_out/*.json")
+ install(FILES
+ ${CEPH_GRAFANA_DASHBOARDS}
+ DESTINATION ${CEPH_GRAFANA_DASHBOARDS_DIR})
+ if(WITH_TESTS)
+ ExternalProject_Add(jsonnet-bundler
+ GIT_REPOSITORY "https://github.com/jsonnet-bundler/jsonnet-bundler.git"
+ GIT_TAG "v0.4.0"
+ GIT_SHALLOW TRUE
+ SOURCE_DIR ${CMAKE_CURRENT_BINARY_DIR}/src/jsonnet-bundler
+ CONFIGURE_COMMAND ""
+ DOWNLOAD_DIR ${CMAKE_CURRENT_BINARY_DIR}/src
+ BUILD_COMMAND make build
+ BUILD_IN_SOURCE 1
+ INSTALL_COMMAND cp <SOURCE_DIR>/_output/jb <INSTALL_DIR>)
+
+ set(CEPH_BUILD_VIRTUALENV $ENV{TMPDIR})
+ if(NOT CEPH_BUILD_VIRTUALENV)
+ include(AddCephTest)
+ set(CEPH_BUILD_VIRTUALENV ${CMAKE_BINARY_DIR})
+ add_tox_test(grafana-lint TOX_ENVS lint)
+ add_tox_test(jsonnet-lint TOX_ENVS jsonnet-lint)
+ add_tox_test(jsonnet-check TOX_ENVS jsonnet-check)
+ add_tox_test(alerts-check TOX_ENVS alerts-check)
+ add_tox_test(alerts-lint TOX_ENVS alerts-lint)
+ add_tox_test(promql-query-test TOX_ENVS promql-query-test)
+ endif()
+
+ if(DEFINED PROMTOOL_EXECUTABLE)
+ set(promtool_executable_checked TRUE)
+ endif()
+
+ find_program(PROMTOOL_EXECUTABLE promtool)
+ if(PROMTOOL_EXECUTABLE)
+ execute_process(
+ COMMAND ${PROMTOOL_EXECUTABLE} test rules /dev/null
+ RESULT_VARIABLE rc
+ OUTPUT_QUIET)
+ if(NOT rc)
+ add_ceph_test(run-promtool-unittests
+ ${PROMTOOL_EXECUTABLE} test rules ${CMAKE_SOURCE_DIR}/monitoring/ceph-mixin/tests_alerts/test_alerts.yml)
+ elseif(NOT promtool_executable_checked)
+ message(WARNING "'${PROMTOOL_EXECUTABLE} test rules' does not work, "
+ "please use a newer prometheus")
+ endif()
+ elseif(NOT promtool_executable_checked)
+ message(WARNING "run-promtool-unittests is skipped due to missing promtool")
+ endif()
+ endif()
+endif()
--- /dev/null
+all: fmt generate lint test
+
+fmt:
+ ./lint-jsonnet.sh -i
+
+generate: dashboards_out
+
+vendor: jsonnetfile.lock.json
+ tox -ejsonnet-bundler-install
+
+dashboards_out: vendor $(JSONNETS_FILES)
+ tox -ejsonnet-fix
+
+lint:
+ tox -ejsonnet-lint
+ tox -ealerts-lint
+
+test: generate
+ tox -ejsonnet-check
+ tox -epromql-query-test
+ tox -ealerts-check
+check: test
+
+.PHONY: all fmt generate lint test check
--- /dev/null
+## Prometheus Monitoring Mixin for Ceph
+A set of Grafana dashboards and Prometheus alerts for Ceph.
+
+All the Grafana dashboards are already generated in the `dashboards_out`
+directory and alerts in the `prometheus_alerts.yaml` file.
+
+You can use the Grafana dashboards and alerts with Jsonnet like any other
+prometheus mixin. You can find more ressources about mixins in general on
+[monitoring.mixins.dev](https://monitoring.mixins.dev/).
+
+### Grafana dashboards for Ceph
+In `dashboards_out` you can find a collection of
+[Grafana](https://grafana.com/grafana) dashboards for Ceph Monitoring.
+
+These dashboards are based on metrics collected
+from [prometheus](https://prometheus.io/) scraping the [prometheus mgr
+plugin](http://docs.ceph.com/en/latest/mgr/prometheus/) and the
+[node_exporter](https://github.com/prometheus/node_exporter).
+
+#### Requirements
+
+- [Status Panel](https://grafana.com/plugins/vonage-status-panel) installed on
+ your Grafana instance
+- [Pie Chart Panel](https://grafana.com/grafana/plugins/grafana-piechart-panel/)
+ installed on your Grafana instance
+
+
+### Prometheus alerts
+In `prometheus_alerts.yaml` you'll find a set of Prometheus
+alert rules that should provide a decent set of default alerts for a
+Ceph cluster. Just put this file in a place according to your Prometheus
+configuration (wherever the `rules` configuration stanza points).
+
+#### SNMP
+Ceph provides a MIB (CEPH-PROMETHEUS-ALERT-MIB.txt) to support sending Prometheus
+alerts through to an SNMP management platform. The translation from Prometheus
+alert to SNMP trap requires the Prometheus alert to contain an OID that maps to
+a definition within the MIB. When making changes to the Prometheus alert rules
+file, developers should include any necessary changes to the MIB.
+
+### Building from Jsonnet
+
+- Install [jsonnet](https://jsonnet.org/)
+ - By installing the package `jsonnet` in most of the distro and
+ `golang-github-google-jsonnet` in fedora
+- Install [jsonnet-bundler](https://github.com/jsonnet-bundler/jsonnet-bundler)
+
+To rebuild all the generated files, you can run `tox -egrafonnet-fix`.
+
+The jsonnet code located in this directory depends on some Jsonnet third party
+libraries. To update those libraries you can run `jb update` and then update
+the generated files using `tox -egrafonnet-fix`.
--- /dev/null
+{
+ prometheusAlerts+:: std.parseYaml(importstr 'prometheus_alerts.yaml'),
+}
--- /dev/null
+local dashboards = (import 'mixin.libsonnet').grafanaDashboards;
+
+{
+ [name]: dashboards[name]
+ for name in std.objectFields(dashboards)
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'cephfs-overview.json':
+ local CephfsOverviewGraphPanel(title, formatY1, labelY1, expr, legendFormat, x, y, w, h) =
+ u.graphPanelSchema({},
+ title,
+ '',
+ 'null',
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ 0,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr, 1, 'time_series', legendFormat)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'MDS Performance',
+ '',
+ 'tbO9LAiZz',
+ 'now-1h',
+ '15s',
+ 16,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('mds_servers',
+ '$datasource',
+ 'label_values(ceph_mds_inodes, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ 'MDS Server',
+ '')
+ )
+ .addPanels([
+ u.addRowSchema(false, true, 'MDS Performance') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } },
+ CephfsOverviewGraphPanel(
+ 'MDS Workload - $mds_servers',
+ 'none',
+ 'Reads(-) / Writes (+)',
+ 'sum(rate(ceph_objecter_op_r{ceph_daemon=~"($mds_servers).*"}[1m]))',
+ 'Read Ops',
+ 0,
+ 1,
+ 12,
+ 9
+ )
+ .addTarget(u.addTargetSchema(
+ 'sum(rate(ceph_objecter_op_w{ceph_daemon=~"($mds_servers).*"}[1m]))',
+ 1,
+ 'time_series',
+ 'Write Ops'
+ ))
+ .addSeriesOverride(
+ { alias: '/.*Reads/', transform: 'negative-Y' }
+ ),
+ CephfsOverviewGraphPanel(
+ 'Client Request Load - $mds_servers',
+ 'none',
+ 'Client Requests',
+ 'ceph_mds_server_handle_client_request{ceph_daemon=~"($mds_servers).*"}',
+ '{{ceph_daemon}}',
+ 12,
+ 1,
+ 12,
+ 9
+ ),
+ ]),
+ },
+}
--- /dev/null
+(import 'cephfs.libsonnet') +
+(import 'host.libsonnet') +
+(import 'osd.libsonnet') +
+(import 'pool.libsonnet') +
+(import 'rbd.libsonnet') +
+(import 'rgw.libsonnet')
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'hosts-overview.json':
+ local HostsOverviewSingleStatPanel(format,
+ title,
+ description,
+ valueName,
+ expr,
+ targetFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'],
+ '$datasource',
+ format,
+ title,
+ description,
+ valueName,
+ false,
+ 100,
+ false,
+ false,
+ '')
+ .addTarget(
+ u.addTargetSchema(expr, 1, targetFormat, '')
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ local HostsOverviewGraphPanel(title, description, formatY1, expr, legendFormat, x, y, w, h) =
+ u.graphPanelSchema(
+ {}, title, description, 'null', false, formatY1, 'short', null, null, 0, 1, '$datasource'
+ )
+ .addTargets(
+ [u.addTargetSchema(
+ expr, 1, 'time_series', legendFormat
+ )]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'Host Overview',
+ '',
+ 'y0KGL0iZz',
+ 'now-1h',
+ '10s',
+ 16,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='singlestat', name='Singlestat', version='5.0.0'
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'default',
+ label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('osd_hosts',
+ '$datasource',
+ 'label_values(ceph_disk_occupation, exported_instance)',
+ 1,
+ true,
+ 1,
+ null,
+ '([^.]*).*')
+ )
+ .addTemplate(
+ u.addTemplateSchema('mon_hosts',
+ '$datasource',
+ 'label_values(ceph_mon_metadata, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ null,
+ 'mon.(.*)')
+ )
+ .addTemplate(
+ u.addTemplateSchema('mds_hosts',
+ '$datasource',
+ 'label_values(ceph_mds_inodes, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ null,
+ 'mds.(.*)')
+ )
+ .addTemplate(
+ u.addTemplateSchema('rgw_hosts',
+ '$datasource',
+ 'label_values(ceph_rgw_metadata, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ null,
+ 'rgw.(.*)')
+ )
+ .addPanels([
+ HostsOverviewSingleStatPanel(
+ 'none',
+ 'OSD Hosts',
+ '',
+ 'current',
+ 'count(sum by (hostname) (ceph_osd_metadata))',
+ 'time_series',
+ 0,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewSingleStatPanel(
+ 'percentunit',
+ 'AVG CPU Busy',
+ 'Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster',
+ 'current',
+ 'avg(\n 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode=\'idle\',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode=\'idle\',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )',
+ 'time_series',
+ 4,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewSingleStatPanel(
+ 'percentunit',
+ 'AVG RAM Utilization',
+ 'Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)',
+ 'current',
+ 'avg (((node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemTotal_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"})- (\n (node_memory_MemFree{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemFree_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) + \n (node_memory_Cached{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Cached_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) + \n (node_memory_Buffers{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Buffers_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) +\n (node_memory_Slab{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Slab_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"})\n )) /\n (node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemTotal_bytes{instance=~"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*"} ))',
+ 'time_series',
+ 8,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewSingleStatPanel(
+ 'none',
+ 'Physical IOPS',
+ 'IOPS Load at the device as reported by the OS on all OSD hosts',
+ 'current',
+ 'sum ((irate(node_disk_reads_completed{instance=~"($osd_hosts).*"}[5m]) or irate(node_disk_reads_completed_total{instance=~"($osd_hosts).*"}[5m]) ) + \n(irate(node_disk_writes_completed{instance=~"($osd_hosts).*"}[5m]) or irate(node_disk_writes_completed_total{instance=~"($osd_hosts).*"}[5m])))',
+ 'time_series',
+ 12,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewSingleStatPanel(
+ 'percent',
+ 'AVG Disk Utilization',
+ 'Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)',
+ 'current',
+ 'avg (\n label_replace((irate(node_disk_io_time_ms[5m]) / 10 ) or\n (irate(node_disk_io_time_seconds_total[5m]) * 100), "instance", "$1", "instance", "([^.:]*).*"\n ) *\n on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($osd_hosts).*"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^.:]*).*")\n)',
+ 'time_series',
+ 16,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewSingleStatPanel(
+ 'bytes',
+ 'Network Load',
+ 'Total send/receive network load across all hosts in the ceph cluster',
+ 'current',
+ |||
+ sum (
+ (
+ irate(node_network_receive_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m]) or
+ irate(node_network_receive_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m])
+ ) unless on (device, instance)
+ label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)")
+ ) +
+ sum (
+ (
+ irate(node_network_transmit_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m]) or
+ irate(node_network_transmit_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m])
+ ) unless on (device, instance)
+ label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)")
+ )
+ |||
+ ,
+ 'time_series',
+ 20,
+ 0,
+ 4,
+ 5
+ ),
+ HostsOverviewGraphPanel(
+ 'CPU Busy - Top 10 Hosts',
+ 'Show the top 10 busiest hosts by cpu',
+ 'percent',
+ 'topk(10,100 * ( 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode=\'idle\',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode=\'idle\',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )\n)',
+ '{{instance}}',
+ 0,
+ 5,
+ 12,
+ 9
+ ),
+ HostsOverviewGraphPanel(
+ 'Network Load - Top 10 Hosts', 'Top 10 hosts by network load', 'Bps', |||
+ topk(10, (sum by(instance) (
+ (
+ irate(node_network_receive_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m]) or
+ irate(node_network_receive_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m])
+ ) +
+ (
+ irate(node_network_transmit_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m]) or
+ irate(node_network_transmit_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m])
+ ) unless on (device, instance)
+ label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)"))
+ ))
+ |||
+ , '{{instance}}', 12, 5, 12, 9
+ ),
+ ]),
+ 'host-details.json':
+ local HostDetailsSingleStatPanel(format,
+ title,
+ description,
+ valueName,
+ expr,
+ targetFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'],
+ '$datasource',
+ format,
+ title,
+ description,
+ valueName,
+ false,
+ 100,
+ false,
+ false,
+ '')
+ .addTarget(u.addTargetSchema(expr,
+ 1,
+ targetFormat,
+ '')) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ local HostDetailsGraphPanel(alias,
+ title,
+ description,
+ nullPointMode,
+ formatY1,
+ labelY1,
+ expr,
+ legendFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema(alias,
+ title,
+ description,
+ nullPointMode,
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ null,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr,
+ 1,
+ 'time_series',
+ legendFormat)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'Host Details',
+ '',
+ 'rtOg0AiWz',
+ 'now-1h',
+ '10s',
+ 16,
+ ['overview'],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='singlestat', name='Singlestat', version='5.0.0'
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard'
+ )
+ )
+ .addTemplate(
+ g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('ceph_hosts', '$datasource', 'label_values(node_scrape_collector_success, instance) ', 1, false, 3, 'Hostname', '([^.:]*).*')
+ )
+ .addPanels([
+ u.addRowSchema(false, true, '$ceph_hosts System Overview') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } },
+ HostDetailsSingleStatPanel(
+ 'none',
+ 'OSDs',
+ '',
+ 'current',
+ "count(sum by (ceph_daemon) (ceph_osd_metadata{hostname='$ceph_hosts'}))",
+ 'time_series',
+ 0,
+ 1,
+ 3,
+ 5
+ ),
+ HostDetailsGraphPanel(
+ {
+ interrupt: '#447EBC',
+ steal: '#6D1F62',
+ system: '#890F02',
+ user: '#3F6833',
+ wait: '#C15C17',
+ }, 'CPU Utilization', "Shows the CPU breakdown. When multiple servers are selected, only the first host's cpu data is shown", 'null', 'percent', '% Utilization', 'sum by (mode) (\n irate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[1m]) or\n irate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[1m])\n) / scalar(\n sum(irate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?"}[1m]) or\n irate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[1m]))\n) * 100', '{{mode}}', 3, 1, 6, 10
+ ),
+ HostDetailsGraphPanel(
+ {
+ Available: '#508642',
+ Free: '#508642',
+ Total: '#bf1b00',
+ Used: '#bf1b00',
+ total: '#bf1b00',
+ used: '#0a50a1',
+ },
+ 'RAM Usage',
+ '',
+ 'null',
+ 'bytes',
+ 'RAM used',
+ 'node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} ',
+ 'Free',
+ 9,
+ 1,
+ 6,
+ 10
+ )
+ .addTargets(
+ [
+ u.addTargetSchema('node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} ', 1, 'time_series', 'total'),
+ u.addTargetSchema('(node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n(node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) +\n(node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) \n', 1, 'time_series', 'buffers/cache'),
+ u.addTargetSchema('(node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"})- (\n (node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n (node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n (node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) +\n (node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"})\n )\n \n', 1, 'time_series', 'used'),
+ ]
+ )
+ .addSeriesOverride(
+ {
+ alias: 'total',
+ color: '#bf1b00',
+ fill: 0,
+ linewidth: 2,
+ stack: false,
+ }
+ ),
+ HostDetailsGraphPanel(
+ {},
+ 'Network Load',
+ "Show the network load (rx,tx) across all interfaces (excluding loopback 'lo')",
+ 'null',
+ 'decbytes',
+ 'Send (-) / Receive (+)',
+ 'sum by (device) (\n irate(node_network_receive_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m]) or \n irate(node_network_receive_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m])\n)',
+ '{{device}}.rx',
+ 15,
+ 1,
+ 6,
+ 10
+ )
+ .addTargets(
+ [
+ u.addTargetSchema('sum by (device) (\n irate(node_network_transmit_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m])\n)', 1, 'time_series', '{{device}}.tx'),
+ ]
+ )
+ .addSeriesOverride(
+ { alias: '/.*tx/', transform: 'negative-Y' }
+ ),
+ HostDetailsGraphPanel(
+ {},
+ 'Network drop rate',
+ '',
+ 'null',
+ 'pps',
+ 'Send (-) / Receive (+)',
+ 'irate(node_network_receive_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_receive_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
+ '{{device}}.rx',
+ 21,
+ 1,
+ 3,
+ 5
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ 'irate(node_network_transmit_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_transmit_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])', 1, 'time_series', '{{device}}.tx'
+ ),
+ ]
+ )
+ .addSeriesOverride(
+ {
+ alias: '/.*tx/',
+ transform: 'negative-Y',
+ }
+ ),
+ HostDetailsSingleStatPanel(
+ 'bytes',
+ 'Raw Capacity',
+ 'Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.',
+ 'current',
+ 'sum(ceph_osd_stat_bytes and on (ceph_daemon) ceph_disk_occupation{instance=~"($ceph_hosts)([\\\\.:].*)?"})',
+ 'time_series',
+ 0,
+ 6,
+ 3,
+ 5
+ ),
+ HostDetailsGraphPanel(
+ {},
+ 'Network error rate',
+ '',
+ 'null',
+ 'pps',
+ 'Send (-) / Receive (+)',
+ 'irate(node_network_receive_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_receive_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
+ '{{device}}.rx',
+ 21,
+ 6,
+ 3,
+ 5
+ )
+ .addTargets(
+ [u.addTargetSchema(
+ 'irate(node_network_transmit_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_transmit_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])', 1, 'time_series', '{{device}}.tx'
+ )]
+ )
+ .addSeriesOverride(
+ {
+ alias: '/.*tx/',
+ transform: 'negative-Y',
+ }
+ ),
+ u.addRowSchema(false,
+ true,
+ 'OSD Disk Performance Statistics') + { gridPos: { x: 0, y: 11, w: 24, h: 1 } },
+ HostDetailsGraphPanel(
+ {},
+ '$ceph_hosts Disk IOPS',
+ "For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it's name and corresponding OSD id value",
+ 'connected',
+ 'ops',
+ 'Read (-) / Write (+)',
+ 'label_replace(\n (\n irate(node_disk_writes_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or\n irate(node_disk_writes_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n "device",\n "$1",\n "device",\n "/dev/(.*)"\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n )',
+ '{{device}}({{ceph_daemon}}) writes',
+ 0,
+ 12,
+ 11,
+ 9
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ 'label_replace(\n (irate(node_disk_reads_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_reads_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n "device",\n "$1",\n "device",\n "/dev/(.*)"\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n )',
+ 1,
+ 'time_series',
+ '{{device}}({{ceph_daemon}}) reads'
+ ),
+ ]
+ )
+ .addSeriesOverride(
+ { alias: '/.*reads/', transform: 'negative-Y' }
+ ),
+ HostDetailsGraphPanel(
+ {},
+ '$ceph_hosts Throughput by Disk',
+ 'For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id',
+ 'connected',
+ 'Bps',
+ 'Read (-) / Write (+)',
+ 'label_replace((irate(node_disk_bytes_written{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_written_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ '{{device}}({{ceph_daemon}}) write',
+ 12,
+ 12,
+ 11,
+ 9
+ )
+ .addTargets(
+ [u.addTargetSchema(
+ 'label_replace((irate(node_disk_bytes_read{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_read_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ 1,
+ 'time_series',
+ '{{device}}({{ceph_daemon}}) read'
+ )]
+ )
+ .addSeriesOverride(
+ { alias: '/.*read/', transform: 'negative-Y' }
+ ),
+ HostDetailsGraphPanel(
+ {},
+ '$ceph_hosts Disk Latency',
+ "For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it's corresponding OSD id",
+ 'null as zero',
+ 's',
+ '',
+ 'max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) ) / clamp_min(irate(node_disk_writes_completed_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]), 0.001) or (irate(node_disk_read_time_seconds_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) ) / clamp_min(irate(node_disk_reads_completed_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]), 0.001), "instance", "$1", "instance", "([^:.]*).*")) * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($ceph_hosts)([\\\\.:].*)?"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ '{{device}}({{ceph_daemon}})',
+ 0,
+ 21,
+ 11,
+ 9
+ ),
+ HostDetailsGraphPanel(
+ {},
+ '$ceph_hosts Disk utilization',
+ 'Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.',
+ 'connected',
+ 'percent',
+ '%Util',
+ 'label_replace(((irate(node_disk_io_time_ms{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) / 10 ) or irate(node_disk_io_time_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) * 100), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($ceph_hosts)([\\\\.:].*)?"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ '{{device}}({{ceph_daemon}})',
+ 12,
+ 21,
+ 11,
+ 9
+ ),
+ ]),
+ },
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'osds-overview.json':
+ local OsdOverviewStyle(alias, pattern, type, unit) =
+ u.addStyle(alias, null, [
+ 'rgba(245, 54, 54, 0.9)',
+ 'rgba(237, 129, 40, 0.89)',
+ 'rgba(50, 172, 45, 0.97)',
+ ], 'YYYY-MM-DD HH:mm:ss', 2, 1, pattern, [], type, unit, []);
+ local OsdOverviewGraphPanel(alias,
+ title,
+ description,
+ formatY1,
+ labelY1,
+ min,
+ expr,
+ legendFormat1,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema(alias,
+ title,
+ description,
+ 'null',
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ min,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr, 1, 'time_series', legendFormat1)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+ local OsdOverviewPieChartPanel(alias, description, title) =
+ u.addPieChartSchema(alias,
+ '$datasource',
+ description,
+ 'Under graph',
+ 'pie',
+ title,
+ 'current');
+ local OsdOverviewSingleStatPanel(colors,
+ format,
+ title,
+ description,
+ valueName,
+ colorValue,
+ gaugeMaxValue,
+ gaugeShow,
+ sparkLineShow,
+ thresholds,
+ expr,
+ targetFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.addSingleStatSchema(
+ colors,
+ '$datasource',
+ format,
+ title,
+ description,
+ valueName,
+ colorValue,
+ gaugeMaxValue,
+ gaugeShow,
+ sparkLineShow,
+ thresholds
+ )
+ .addTarget(
+ u.addTargetSchema(expr, 1, targetFormat, '')
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'OSD Overview',
+ '',
+ 'lo02I1Aiz',
+ 'now-1h',
+ '10s',
+ 16,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='grafana-piechart-panel', name='Pie Chart', version='1.3.3'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='table', name='Table', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
+ )
+ .addPanels([
+ OsdOverviewGraphPanel(
+ { '@95%ile': '#e0752d' },
+ 'OSD Read Latencies',
+ '',
+ 'ms',
+ null,
+ '0',
+ 'avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)',
+ 'AVG read',
+ 0,
+ 0,
+ 8,
+ 8
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ 'max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)',
+ 1,
+ 'time_series',
+ 'MAX read'
+ ),
+ u.addTargetSchema(
+ 'quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)', 1, 'time_series', '@95%ile'
+ ),
+ ],
+ ),
+ u.addTableSchema(
+ '$datasource',
+ "This table shows the osd's that are delivering the 10 highest read latencies within the cluster",
+ { col: 2, desc: true },
+ [
+ OsdOverviewStyle('OSD ID', 'ceph_daemon', 'string', 'short'),
+ OsdOverviewStyle('Latency (ms)', 'Value', 'number', 'none'),
+ OsdOverviewStyle('', '/.*/', 'hidden', 'short'),
+ ],
+ 'Highest READ Latencies',
+ 'table'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n ))\n)\n\n', 1, 'table', ''
+ )
+ ) + { gridPos: { x: 8, y: 0, w: 4, h: 8 } },
+ OsdOverviewGraphPanel(
+ {
+ '@95%ile write': '#e0752d',
+ },
+ 'OSD Write Latencies',
+ '',
+ 'ms',
+ null,
+ '0',
+ 'avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)',
+ 'AVG write',
+ 12,
+ 0,
+ 8,
+ 8
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ 'max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)',
+ 1,
+ 'time_series',
+ 'MAX write'
+ ),
+ u.addTargetSchema(
+ 'quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)', 1, 'time_series', '@95%ile write'
+ ),
+ ],
+ ),
+ u.addTableSchema(
+ '$datasource',
+ "This table shows the osd's that are delivering the 10 highest write latencies within the cluster",
+ { col: 2, desc: true },
+ [
+ OsdOverviewStyle(
+ 'OSD ID', 'ceph_daemon', 'string', 'short'
+ ),
+ OsdOverviewStyle('Latency (ms)', 'Value', 'number', 'none'),
+ OsdOverviewStyle('', '/.*/', 'hidden', 'short'),
+ ],
+ 'Highest WRITE Latencies',
+ 'table'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n',
+ 1,
+ 'table',
+ ''
+ )
+ ) + { gridPos: { x: 20, y: 0, w: 4, h: 8 } },
+ OsdOverviewPieChartPanel(
+ {}, '', 'OSD Types Summary'
+ )
+ .addTarget(
+ u.addTargetSchema('count by (device_class) (ceph_osd_metadata)', 1, 'time_series', '{{device_class}}')
+ ) + { gridPos: { x: 0, y: 8, w: 4, h: 8 } },
+ OsdOverviewPieChartPanel(
+ { 'Non-Encrypted': '#E5AC0E' }, '', 'OSD Objectstore Types'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'count(ceph_bluefs_wal_total_bytes)', 1, 'time_series', 'bluestore'
+ )
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'absent(ceph_bluefs_wal_total_bytes)*count(ceph_osd_metadata)', 1, 'time_series', 'filestore'
+ )
+ ) + { gridPos: { x: 4, y: 8, w: 4, h: 8 } },
+ OsdOverviewPieChartPanel(
+ {}, 'The pie chart shows the various OSD sizes used within the cluster', 'OSD Size Summary'
+ )
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes < 1099511627776)', 1, 'time_series', '<1TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 1099511627776 < 2199023255552)', 1, 'time_series', '<2TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 2199023255552 < 3298534883328)', 1, 'time_series', '<3TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 3298534883328 < 4398046511104)', 1, 'time_series', '<4TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 4398046511104 < 6597069766656)', 1, 'time_series', '<6TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 6597069766656 < 8796093022208)', 1, 'time_series', '<8TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 8796093022208 < 10995116277760)', 1, 'time_series', '<10TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 10995116277760 < 13194139533312)', 1, 'time_series', '<12TB'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'count(ceph_osd_stat_bytes >= 13194139533312)', 1, 'time_series', '<12TB+'
+ )) + { gridPos: { x: 8, y: 8, w: 4, h: 8 } },
+ g.graphPanel.new(bars=true,
+ datasource='$datasource',
+ title='Distribution of PGs per OSD',
+ x_axis_buckets=20,
+ x_axis_mode='histogram',
+ x_axis_values=['total'],
+ formatY1='short',
+ formatY2='short',
+ labelY1='# of OSDs',
+ min='0',
+ nullPointMode='null')
+ .addTarget(u.addTargetSchema(
+ 'ceph_osd_numpg\n', 1, 'time_series', 'PGs per OSD'
+ )) + { gridPos: { x: 12, y: 8, w: 8, h: 8 } },
+ OsdOverviewSingleStatPanel(
+ ['#d44a3a', '#299c46'],
+ 'percentunit',
+ 'OSD onode Hits Ratio',
+ 'This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster',
+ 'current',
+ true,
+ 1,
+ true,
+ false,
+ '.75',
+ 'sum(ceph_bluestore_onode_hits)/(sum(ceph_bluestore_onode_hits) + sum(ceph_bluestore_onode_misses))',
+ 'time_series',
+ 20,
+ 8,
+ 4,
+ 8
+ ),
+ u.addRowSchema(false,
+ true,
+ 'R/W Profile') + { gridPos: { x: 0, y: 16, w: 24, h: 1 } },
+ OsdOverviewGraphPanel(
+ {},
+ 'Read/Write Profile',
+ 'Show the read/write workload profile overtime',
+ 'short',
+ null,
+ null,
+ 'round(sum(irate(ceph_pool_rd[30s])))',
+ 'Reads',
+ 0,
+ 17,
+ 24,
+ 8
+ )
+ .addTargets([u.addTargetSchema(
+ 'round(sum(irate(ceph_pool_wr[30s])))', 1, 'time_series', 'Writes'
+ )]),
+ ]),
+ 'osd-device-details.json':
+ local OsdDeviceDetailsPanel(title,
+ description,
+ formatY1,
+ labelY1,
+ expr1,
+ expr2,
+ legendFormat1,
+ legendFormat2,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema({},
+ title,
+ description,
+ 'null',
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ null,
+ 1,
+ '$datasource')
+ .addTargets(
+ [
+ u.addTargetSchema(expr1,
+ 1,
+ 'time_series',
+ legendFormat1),
+ u.addTargetSchema(expr2, 1, 'time_series', legendFormat2),
+ ]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'OSD device details',
+ '',
+ 'CrAHE0iZz',
+ 'now-3h',
+ '',
+ 16,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'default',
+ label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('osd',
+ '$datasource',
+ 'label_values(ceph_osd_metadata,ceph_daemon)',
+ 1,
+ false,
+ 1,
+ 'OSD',
+ '(.*)')
+ )
+ .addPanels([
+ u.addRowSchema(
+ false, true, 'OSD Performance'
+ ) + { gridPos: { x: 0, y: 0, w: 24, h: 1 } },
+ OsdDeviceDetailsPanel(
+ '$osd Latency',
+ '',
+ 's',
+ 'Read (-) / Write (+)',
+ 'irate(ceph_osd_op_r_latency_sum{ceph_daemon=~"$osd"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m])',
+ 'irate(ceph_osd_op_w_latency_sum{ceph_daemon=~"$osd"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m])',
+ 'read',
+ 'write',
+ 0,
+ 1,
+ 6,
+ 9
+ )
+ .addSeriesOverride(
+ {
+ alias: 'read',
+ transform: 'negative-Y',
+ }
+ ),
+ OsdDeviceDetailsPanel(
+ '$osd R/W IOPS',
+ '',
+ 'short',
+ 'Read (-) / Write (+)',
+ 'irate(ceph_osd_op_r{ceph_daemon=~"$osd"}[1m])',
+ 'irate(ceph_osd_op_w{ceph_daemon=~"$osd"}[1m])',
+ 'Reads',
+ 'Writes',
+ 6,
+ 1,
+ 6,
+ 9
+ )
+ .addSeriesOverride(
+ { alias: 'Reads', transform: 'negative-Y' }
+ ),
+ OsdDeviceDetailsPanel(
+ '$osd R/W Bytes',
+ '',
+ 'bytes',
+ 'Read (-) / Write (+)',
+ 'irate(ceph_osd_op_r_out_bytes{ceph_daemon=~"$osd"}[1m])',
+ 'irate(ceph_osd_op_w_in_bytes{ceph_daemon=~"$osd"}[1m])',
+ 'Read Bytes',
+ 'Write Bytes',
+ 12,
+ 1,
+ 6,
+ 9
+ )
+ .addSeriesOverride({ alias: 'Read Bytes', transform: 'negative-Y' }),
+ u.addRowSchema(
+ false, true, 'Physical Device Performance'
+ ) + { gridPos: { x: 0, y: 10, w: 24, h: 1 } },
+ OsdDeviceDetailsPanel(
+ 'Physical Device Latency for $osd',
+ '',
+ 's',
+ 'Read (-) / Write (+)',
+ '(label_replace(irate(node_disk_read_time_seconds_total[1m]) / irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*"))',
+ '(label_replace(irate(node_disk_write_time_seconds_total[1m]) / irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*"))',
+ '{{instance}}/{{device}} Reads',
+ '{{instance}}/{{device}} Writes',
+ 0,
+ 11,
+ 6,
+ 9
+ )
+ .addSeriesOverride(
+ { alias: '/.*Reads/', transform: 'negative-Y' }
+ ),
+ OsdDeviceDetailsPanel(
+ 'Physical Device R/W IOPS for $osd',
+ '',
+ 'short',
+ 'Read (-) / Write (+)',
+ 'label_replace(irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ 'label_replace(irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ '{{device}} on {{instance}} Writes',
+ '{{device}} on {{instance}} Reads',
+ 6,
+ 11,
+ 6,
+ 9
+ )
+ .addSeriesOverride(
+ { alias: '/.*Reads/', transform: 'negative-Y' }
+ ),
+ OsdDeviceDetailsPanel(
+ 'Physical Device R/W Bytes for $osd',
+ '',
+ 'Bps',
+ 'Read (-) / Write (+)',
+ 'label_replace(irate(node_disk_read_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ 'label_replace(irate(node_disk_written_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ '{{instance}} {{device}} Reads',
+ '{{instance}} {{device}} Writes',
+ 12,
+ 11,
+ 6,
+ 9
+ )
+ .addSeriesOverride(
+ { alias: '/.*Reads/', transform: 'negative-Y' }
+ ),
+ u.graphPanelSchema(
+ {},
+ 'Physical Device Util% for $osd',
+ '',
+ 'null',
+ false,
+ 'percentunit',
+ 'short',
+ null,
+ null,
+ null,
+ 1,
+ '$datasource'
+ )
+ .addTarget(u.addTargetSchema(
+ 'label_replace(irate(node_disk_io_time_seconds_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
+ 1,
+ 'time_series',
+ '{{device}} on {{instance}}'
+ )) + { gridPos: { x: 18, y: 11, w: 6, h: 9 } },
+ ]),
+ },
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'pool-overview.json':
+ local PoolOverviewSingleStatPanel(format,
+ title,
+ description,
+ valueName,
+ expr,
+ targetFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'],
+ '$datasource',
+ format,
+ title,
+ description,
+ valueName,
+ false,
+ 100,
+ false,
+ false,
+ '')
+ .addTarget(u.addTargetSchema(expr, 1, targetFormat, '')) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ local PoolOverviewStyle(alias,
+ pattern,
+ type,
+ unit,
+ colorMode,
+ thresholds,
+ valueMaps) =
+ u.addStyle(alias,
+ colorMode,
+ [
+ 'rgba(245, 54, 54, 0.9)',
+ 'rgba(237, 129, 40, 0.89)',
+ 'rgba(50, 172, 45, 0.97)',
+ ],
+ 'YYYY-MM-DD HH:mm:ss',
+ 2,
+ 1,
+ pattern,
+ thresholds,
+ type,
+ unit,
+ valueMaps);
+
+ local PoolOverviewGraphPanel(title,
+ description,
+ formatY1,
+ labelY1,
+ expr,
+ targetFormat,
+ legendFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema({},
+ title,
+ description,
+ 'null as zero',
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ 0,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr,
+ 1,
+ 'time_series',
+ legendFormat)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'Ceph Pools Overview',
+ '',
+ 'z99hzWtmk',
+ 'now-1h',
+ '15s',
+ 22,
+ [],
+ '',
+ { refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'], time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'] }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'Dashboard1',
+ label='Data Source')
+ )
+ .addTemplate(
+ g.template.custom(label='TopK',
+ name='topk',
+ current='15',
+ query='15')
+ )
+ .addPanels([
+ PoolOverviewSingleStatPanel(
+ 'none',
+ 'Pools',
+ '',
+ 'avg',
+ 'count(ceph_pool_metadata)',
+ 'table',
+ 0,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'none',
+ 'Pools with Compression',
+ 'Count of the pools that have compression enabled',
+ 'current',
+ 'count(ceph_pool_metadata{compression_mode!="none"})',
+ '',
+ 3,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'bytes',
+ 'Total Raw Capacity',
+ 'Total raw capacity available to the cluster',
+ 'current',
+ 'sum(ceph_osd_stat_bytes)',
+ '',
+ 6,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'bytes',
+ 'Raw Capacity Consumed',
+ 'Total raw capacity consumed by user data and associated overheads (metadata + redundancy)',
+ 'current',
+ 'sum(ceph_pool_bytes_used)',
+ '',
+ 9,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'bytes',
+ 'Logical Stored ',
+ 'Total of client data stored in the cluster',
+ 'current',
+ 'sum(ceph_pool_stored)',
+ '',
+ 12,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'bytes',
+ 'Compression Savings',
+ 'A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression',
+ 'current',
+ 'sum(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used)',
+ '',
+ 15,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'percent',
+ 'Compression Eligibility',
+ 'Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data\n',
+ 'current',
+ '(sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_stored_raw and ceph_pool_compress_under_bytes > 0)) * 100',
+ 'table',
+ 18,
+ 0,
+ 3,
+ 3
+ ),
+ PoolOverviewSingleStatPanel(
+ 'none',
+ 'Compression Factor',
+ 'This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)',
+ 'current',
+ 'sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_compress_bytes_used > 0)',
+ '',
+ 21,
+ 0,
+ 3,
+ 3
+ ),
+ u.addTableSchema(
+ '$datasource',
+ '',
+ { col: 5, desc: true },
+ [
+ PoolOverviewStyle('', 'Time', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('', 'instance', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('', 'job', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('Pool Name', 'name', 'string', 'short', null, [], []),
+ PoolOverviewStyle('Pool ID', 'pool_id', 'hidden', 'none', null, [], []),
+ PoolOverviewStyle('Compression Factor', 'Value #A', 'number', 'none', null, [], []),
+ PoolOverviewStyle('% Used', 'Value #D', 'number', 'percentunit', 'value', ['70', '85'], []),
+ PoolOverviewStyle('Usable Free', 'Value #B', 'number', 'bytes', null, [], []),
+ PoolOverviewStyle('Compression Eligibility', 'Value #C', 'number', 'percent', null, [], []),
+ PoolOverviewStyle('Compression Savings', 'Value #E', 'number', 'bytes', null, [], []),
+ PoolOverviewStyle('Growth (5d)', 'Value #F', 'number', 'bytes', 'value', ['0', '0'], []),
+ PoolOverviewStyle('IOPS', 'Value #G', 'number', 'none', null, [], []),
+ PoolOverviewStyle('Bandwidth', 'Value #H', 'number', 'Bps', null, [], []),
+ PoolOverviewStyle('', '__name__', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('', 'type', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('', 'compression_mode', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('Type', 'description', 'string', 'short', null, [], []),
+ PoolOverviewStyle('Stored', 'Value #J', 'number', 'bytes', null, [], []),
+ PoolOverviewStyle('', 'Value #I', 'hidden', 'short', null, [], []),
+ PoolOverviewStyle('Compression', 'Value #K', 'string', 'short', null, [], [{ text: 'ON', value: '1' }]),
+ ],
+ 'Pool Overview',
+ 'table'
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ '(ceph_pool_compress_under_bytes / ceph_pool_compress_bytes_used > 0) and on(pool_id) (((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100 > 0.5)',
+ 1,
+ 'table',
+ 'A'
+ ),
+ u.addTargetSchema(
+ 'ceph_pool_max_avail * on(pool_id) group_left(name) ceph_pool_metadata',
+ 1,
+ 'table',
+ 'B'
+ ),
+ u.addTargetSchema(
+ '((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100',
+ 1,
+ 'table',
+ 'C'
+ ),
+ u.addTargetSchema(
+ '(ceph_pool_percent_used * on(pool_id) group_left(name) ceph_pool_metadata)',
+ 1,
+ 'table',
+ 'D'
+ ),
+ u.addTargetSchema(
+ '(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used > 0)',
+ 1,
+ 'table',
+ 'E'
+ ),
+ u.addTargetSchema(
+ 'delta(ceph_pool_stored[5d])', 1, 'table', 'F'
+ ),
+ u.addTargetSchema(
+ 'rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])',
+ 1,
+ 'table',
+ 'G'
+ ),
+ u.addTargetSchema(
+ 'rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])',
+ 1,
+ 'table',
+ 'H'
+ ),
+ u.addTargetSchema(
+ 'ceph_pool_metadata', 1, 'table', 'I'
+ ),
+ u.addTargetSchema(
+ 'ceph_pool_stored * on(pool_id) group_left ceph_pool_metadata',
+ 1,
+ 'table',
+ 'J'
+ ),
+ u.addTargetSchema(
+ 'ceph_pool_metadata{compression_mode!="none"}', 1, 'table', 'K'
+ ),
+ u.addTargetSchema('', '', '', 'L'),
+ ]
+ ) + { gridPos: { x: 0, y: 3, w: 24, h: 6 } },
+ PoolOverviewGraphPanel(
+ 'Top $topk Client IOPS by Pool',
+ 'This chart shows the sum of read and write IOPS from all clients by pool',
+ 'short',
+ 'IOPS',
+ 'topk($topk,round((rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])),1) * on(pool_id) group_left(instance,name) ceph_pool_metadata) ',
+ 'time_series',
+ '{{name}} ',
+ 0,
+ 9,
+ 12,
+ 8
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk($topk,rate(ceph_pool_wr[30s]) + on(pool_id) group_left(instance,name) ceph_pool_metadata) ',
+ 1,
+ 'time_series',
+ '{{name}} - write'
+ )
+ ),
+ PoolOverviewGraphPanel(
+ 'Top $topk Client Bandwidth by Pool',
+ 'The chart shows the sum of read and write bytes from all clients, by pool',
+ 'Bps',
+ 'Throughput',
+ 'topk($topk,(rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])) * on(pool_id) group_left(instance,name) ceph_pool_metadata)',
+ 'time_series',
+ '{{name}}',
+ 12,
+ 9,
+ 12,
+ 8
+ ),
+ PoolOverviewGraphPanel(
+ 'Pool Capacity Usage (RAW)',
+ 'Historical view of capacity usage, to help identify growth and trends in pool consumption',
+ 'bytes',
+ 'Capacity Used',
+ 'ceph_pool_bytes_used * on(pool_id) group_right ceph_pool_metadata',
+ '',
+ '{{name}}',
+ 0,
+ 17,
+ 24,
+ 7
+ ),
+ ]),
+ 'pool-detail.json':
+ local PoolDetailSingleStatPanel(format,
+ title,
+ description,
+ valueName,
+ colorValue,
+ gaugeMaxValue,
+ gaugeShow,
+ sparkLineShow,
+ thresholds,
+ expr,
+ targetFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'],
+ '$datasource',
+ format,
+ title,
+ description,
+ valueName,
+ colorValue,
+ gaugeMaxValue,
+ gaugeShow,
+ sparkLineShow,
+ thresholds)
+ .addTarget(u.addTargetSchema(expr, 1, targetFormat, '')) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ local PoolDetailGraphPanel(alias,
+ title,
+ description,
+ formatY1,
+ labelY1,
+ expr,
+ targetFormat,
+ legendFormat,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema(alias,
+ title,
+ description,
+ 'null as zero',
+ false,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ null,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr, 1, 'time_series', legendFormat)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'Ceph Pool Details',
+ '',
+ '-xyV8KCiz',
+ 'now-1h',
+ '15s',
+ 22,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='singlestat', name='Singlestat', version='5.0.0'
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'Prometheus admin.virt1.home.fajerski.name:9090',
+ label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('pool_name',
+ '$datasource',
+ 'label_values(ceph_pool_metadata,name)',
+ 1,
+ false,
+ 1,
+ 'Pool Name',
+ '')
+ )
+ .addPanels([
+ PoolDetailSingleStatPanel(
+ 'percentunit',
+ 'Capacity used',
+ '',
+ 'current',
+ true,
+ 1,
+ true,
+ true,
+ '.7,.8',
+ '(ceph_pool_stored / (ceph_pool_stored + ceph_pool_max_avail)) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
+ 'time_series',
+ 0,
+ 0,
+ 7,
+ 7
+ ),
+ PoolDetailSingleStatPanel(
+ 's',
+ 'Time till full',
+ 'Time till pool is full assuming the average fill rate of the last 6 hours',
+ false,
+ 100,
+ false,
+ false,
+ '',
+ 'current',
+ '(ceph_pool_max_avail / deriv(ceph_pool_stored[6h])) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"} > 0',
+ 'time_series',
+ 7,
+ 0,
+ 5,
+ 7
+ ),
+ PoolDetailGraphPanel(
+ {
+ read_op_per_sec:
+ '#3F6833',
+ write_op_per_sec: '#E5AC0E',
+ },
+ '$pool_name Object Ingress/Egress',
+ '',
+ 'ops',
+ 'Objects out(-) / in(+) ',
+ 'deriv(ceph_pool_objects[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
+ 'time_series',
+ 'Objects per second',
+ 12,
+ 0,
+ 12,
+ 7
+ ),
+ PoolDetailGraphPanel(
+ {
+ read_op_per_sec: '#3F6833',
+ write_op_per_sec: '#E5AC0E',
+ }, '$pool_name Client IOPS', '', 'iops', 'Read (-) / Write (+)', 'irate(ceph_pool_rd[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}', 'time_series', 'reads', 0, 7, 12, 7
+ )
+ .addSeriesOverride({ alias: 'reads', transform: 'negative-Y' })
+ .addTarget(
+ u.addTargetSchema(
+ 'irate(ceph_pool_wr[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}', 1, 'time_series', 'writes'
+ )
+ ),
+ PoolDetailGraphPanel(
+ {
+ read_op_per_sec: '#3F6833',
+ write_op_per_sec: '#E5AC0E',
+ },
+ '$pool_name Client Throughput',
+ '',
+ 'Bps',
+ 'Read (-) / Write (+)',
+ 'irate(ceph_pool_rd_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
+ 'time_series',
+ 'reads',
+ 12,
+ 7,
+ 12,
+ 7
+ )
+ .addSeriesOverride({ alias: 'reads', transform: 'negative-Y' })
+ .addTarget(
+ u.addTargetSchema(
+ 'irate(ceph_pool_wr_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
+ 1,
+ 'time_series',
+ 'writes'
+ )
+ ),
+ PoolDetailGraphPanel(
+ {
+ read_op_per_sec: '#3F6833',
+ write_op_per_sec: '#E5AC0E',
+ },
+ '$pool_name Objects',
+ '',
+ 'short',
+ 'Objects',
+ 'ceph_pool_objects * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
+ 'time_series',
+ 'Number of Objects',
+ 0,
+ 14,
+ 12,
+ 7
+ ),
+ ]),
+ },
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'rbd-details.json':
+ local RbdDetailsPanel(title, formatY1, expr1, expr2, x, y, w, h) =
+ u.graphPanelSchema({},
+ title,
+ '',
+ 'null as zero',
+ false,
+ formatY1,
+ formatY1,
+ null,
+ null,
+ 0,
+ 1,
+ '$Datasource')
+ .addTargets(
+ [
+ u.addTargetSchema(expr1,
+ 1,
+ 'time_series',
+ '{{pool}} Write'),
+ u.addTargetSchema(expr2, 1, 'time_series', '{{pool}} Read'),
+ ]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'RBD Details',
+ 'Detailed Performance of RBD Images (IOPS/Throughput/Latency)',
+ 'YhCYGcuZz',
+ 'now-1h',
+ false,
+ 16,
+ [],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.3.3'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('Datasource', 'prometheus', 'default', label=null)
+ )
+ .addTemplate(
+ u.addTemplateSchema('Pool',
+ '$Datasource',
+ 'label_values(pool)',
+ 1,
+ false,
+ 0,
+ '',
+ '')
+ )
+ .addTemplate(
+ u.addTemplateSchema('Image',
+ '$Datasource',
+ 'label_values(image)',
+ 1,
+ false,
+ 0,
+ '',
+ '')
+ )
+ .addPanels([
+ RbdDetailsPanel(
+ 'IOPS',
+ 'iops',
+ 'irate(ceph_rbd_write_ops{pool="$Pool", image="$Image"}[30s])',
+ 'irate(ceph_rbd_read_ops{pool="$Pool", image="$Image"}[30s])',
+ 0,
+ 0,
+ 8,
+ 9
+ ),
+ RbdDetailsPanel(
+ 'Throughput',
+ 'Bps',
+ 'irate(ceph_rbd_write_bytes{pool="$Pool", image="$Image"}[30s])',
+ 'irate(ceph_rbd_read_bytes{pool="$Pool", image="$Image"}[30s])',
+ 8,
+ 0,
+ 8,
+ 9
+ ),
+ RbdDetailsPanel(
+ 'Average Latency',
+ 'ns',
+ 'irate(ceph_rbd_write_latency_sum{pool="$Pool", image="$Image"}[30s]) / irate(ceph_rbd_write_latency_count{pool="$Pool", image="$Image"}[30s])',
+ 'irate(ceph_rbd_read_latency_sum{pool="$Pool", image="$Image"}[30s]) / irate(ceph_rbd_read_latency_count{pool="$Pool", image="$Image"}[30s])',
+ 16,
+ 0,
+ 8,
+ 9
+ ),
+ ]),
+ 'rbd-overview.json':
+ local RgwOverviewStyle(alias, pattern, type, unit) =
+ u.addStyle(alias,
+ null,
+ ['rgba(245, 54, 54, 0.9)', 'rgba(237, 129, 40, 0.89)', 'rgba(50, 172, 45, 0.97)'],
+ 'YYYY-MM-DD HH:mm:ss',
+ 2,
+ 1,
+ pattern,
+ [],
+ type,
+ unit,
+ []);
+ local RbdOverviewPanel(title,
+ formatY1,
+ expr1,
+ expr2,
+ legendFormat1,
+ legendFormat2,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema({},
+ title,
+ '',
+ 'null',
+ false,
+ formatY1,
+ 'short',
+ null,
+ null,
+ 0,
+ 1,
+ '$datasource')
+ .addTargets(
+ [
+ u.addTargetSchema(expr1,
+ 1,
+ 'time_series',
+ legendFormat1),
+ u.addTargetSchema(expr2,
+ 1,
+ 'time_series',
+ legendFormat2),
+ ]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'RBD Overview',
+ '',
+ '41FrpeUiz',
+ 'now-1h',
+ '30s',
+ 16,
+ ['overview'],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.4.2'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addRequired(
+ type='datasource', id='prometheus', name='Prometheus', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='table', name='Table', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'default',
+ label='Data Source')
+ )
+ .addPanels([
+ RbdOverviewPanel(
+ 'IOPS',
+ 'short',
+ 'round(sum(irate(ceph_rbd_write_ops[30s])))',
+ 'round(sum(irate(ceph_rbd_read_ops[30s])))',
+ 'Writes',
+ 'Reads',
+ 0,
+ 0,
+ 8,
+ 7
+ ),
+ RbdOverviewPanel(
+ 'Throughput',
+ 'Bps',
+ 'round(sum(irate(ceph_rbd_write_bytes[30s])))',
+ 'round(sum(irate(ceph_rbd_read_bytes[30s])))',
+ 'Write',
+ 'Read',
+ 8,
+ 0,
+ 8,
+ 7
+ ),
+ RbdOverviewPanel(
+ 'Average Latency',
+ 'ns',
+ 'round(sum(irate(ceph_rbd_write_latency_sum[30s])) / sum(irate(ceph_rbd_write_latency_count[30s])))',
+ 'round(sum(irate(ceph_rbd_read_latency_sum[30s])) / sum(irate(ceph_rbd_read_latency_count[30s])))',
+ 'Write',
+ 'Read',
+ 16,
+ 0,
+ 8,
+ 7
+ ),
+ u.addTableSchema(
+ '$datasource',
+ '',
+ { col: 3, desc: true },
+ [
+ RgwOverviewStyle('Pool', 'pool', 'string', 'short'),
+ RgwOverviewStyle('Image', 'image', 'string', 'short'),
+ RgwOverviewStyle('IOPS', 'Value', 'number', 'iops'),
+ RgwOverviewStyle('', '/.*/', 'hidden', 'short'),
+ ],
+ 'Highest IOPS',
+ 'table'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on (image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))',
+ 1,
+ 'table',
+ ''
+ )
+ ) + { gridPos: { x: 0, y: 7, w: 8, h: 7 } },
+ u.addTableSchema(
+ '$datasource',
+ '',
+ { col: 3, desc: true },
+ [
+ RgwOverviewStyle('Pool', 'pool', 'string', 'short'),
+ RgwOverviewStyle('Image', 'image', 'string', 'short'),
+ RgwOverviewStyle('Throughput', 'Value', 'number', 'Bps'),
+ RgwOverviewStyle('', '/.*/', 'hidden', 'short'),
+ ],
+ 'Highest Throughput',
+ 'table'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk(10, sort(sum(irate(ceph_rbd_read_bytes[30s]) + irate(ceph_rbd_write_bytes[30s])) by (pool, image, namespace)))',
+ 1,
+ 'table',
+ ''
+ )
+ ) + { gridPos: { x: 8, y: 7, w: 8, h: 7 } },
+ u.addTableSchema(
+ '$datasource',
+ '',
+ { col: 3, desc: true },
+ [
+ RgwOverviewStyle('Pool', 'pool', 'string', 'short'),
+ RgwOverviewStyle('Image', 'image', 'string', 'short'),
+ RgwOverviewStyle('Latency', 'Value', 'number', 'ns'),
+ RgwOverviewStyle('', '/.*/', 'hidden', 'short'),
+ ],
+ 'Highest Latency',
+ 'table'
+ )
+ .addTarget(
+ u.addTargetSchema(
+ 'topk(10,\n sum(\n irate(ceph_rbd_write_latency_sum[30s]) / clamp_min(irate(ceph_rbd_write_latency_count[30s]), 1) +\n irate(ceph_rbd_read_latency_sum[30s]) / clamp_min(irate(ceph_rbd_read_latency_count[30s]), 1)\n ) by (pool, image, namespace)\n)',
+ 1,
+ 'table',
+ ''
+ )
+ ) + { gridPos: { x: 16, y: 7, w: 8, h: 7 } },
+ ]),
+ },
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+local u = import 'utils.libsonnet';
+
+{
+ grafanaDashboards+:: {
+ 'radosgw-sync-overview.json':
+ local RgwSyncOverviewPanel(title, formatY1, labelY1, rgwMetric, x, y, w, h) =
+ u.graphPanelSchema({},
+ title,
+ '',
+ 'null as zero',
+ true,
+ formatY1,
+ 'short',
+ labelY1,
+ null,
+ 0,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema('sum by (source_zone) (rate(%s[30s]))' % rgwMetric,
+ 1,
+ 'time_series',
+ '{{source_zone}}')]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'RGW Sync Overview',
+ '',
+ 'rgw-sync-overview',
+ 'now-1h',
+ '15s',
+ 16,
+ ['overview'],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ u.addTemplateSchema('rgw_servers', '$datasource', 'prometehus', 1, true, 1, '', '')
+ )
+ .addTemplate(
+ g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
+ )
+ .addPanels([
+ RgwSyncOverviewPanel(
+ 'Replication (throughput) from Source Zone',
+ 'Bps',
+ null,
+ 'ceph_data_sync_from_zone_fetch_bytes_sum',
+ 0,
+ 0,
+ 8,
+ 7
+ ),
+ RgwSyncOverviewPanel(
+ 'Replication (objects) from Source Zone',
+ 'short',
+ 'Objects/s',
+ 'ceph_data_sync_from_zone_fetch_bytes_count',
+ 8,
+ 0,
+ 8,
+ 7
+ ),
+ RgwSyncOverviewPanel(
+ 'Polling Request Latency from Source Zone',
+ 'ms',
+ null,
+ 'ceph_data_sync_from_zone_poll_latency_sum',
+ 16,
+ 0,
+ 8,
+ 7
+ ),
+ RgwSyncOverviewPanel(
+ 'Unsuccessful Object Replications from Source Zone',
+ 'short',
+ 'Count/s',
+ 'ceph_data_sync_from_zone_fetch_errors',
+ 0,
+ 7,
+ 8,
+ 7
+ ),
+ ]),
+ 'radosgw-overview.json':
+ local RgwOverviewPanel(
+ title,
+ description,
+ formatY1,
+ formatY2,
+ expr1,
+ legendFormat1,
+ x,
+ y,
+ w,
+ h,
+ datasource='$datasource',
+ legend_alignAsTable=false,
+ legend_avg=false,
+ legend_min=false,
+ legend_max=false,
+ legend_current=false,
+ legend_values=false
+ ) =
+ u.graphPanelSchema(
+ {},
+ title,
+ description,
+ 'null',
+ false,
+ formatY1,
+ formatY2,
+ null,
+ null,
+ 0,
+ 1,
+ datasource,
+ legend_alignAsTable,
+ legend_avg,
+ legend_min,
+ legend_max,
+ legend_current,
+ legend_values
+ )
+ .addTargets(
+ [u.addTargetSchema(expr1, 1, 'time_series', legendFormat1)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'RGW Overview',
+ '',
+ 'WAkugZpiz',
+ 'now-1h',
+ '15s',
+ 16,
+ ['overview'],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.0.0'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ u.addTemplateSchema(
+ 'rgw_servers',
+ '$datasource',
+ 'label_values(ceph_rgw_metadata, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ '',
+ ''
+ )
+ )
+ .addTemplate(
+ u.addTemplateSchema(
+ 'code',
+ '$datasource',
+ 'label_values(haproxy_server_http_responses_total{instance=~"$ingress_service"}, code)',
+ 1,
+ true,
+ 1,
+ 'HTTP Code',
+ ''
+ )
+ )
+ .addTemplate(
+ u.addTemplateSchema(
+ 'ingress_service',
+ '$datasource',
+ 'label_values(haproxy_server_status, instance)',
+ 1,
+ true,
+ 1,
+ 'Ingress Service',
+ ''
+ )
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'default',
+ label='Data Source')
+ )
+ .addPanels([
+ u.addRowSchema(false,
+ true,
+ 'RGW Overview - All Gateways') +
+ {
+ gridPos: { x: 0, y: 0, w: 24, h: 1 },
+ },
+ RgwOverviewPanel(
+ 'Average GET/PUT Latencies',
+ '',
+ 's',
+ 'short',
+ 'rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata',
+ 'GET AVG',
+ 0,
+ 1,
+ 8,
+ 7
+ ).addTargets(
+ [
+ u.addTargetSchema(
+ 'rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata',
+ 1,
+ 'time_series',
+ 'PUT AVG'
+ ),
+ ]
+ ),
+ RgwOverviewPanel(
+ 'Total Requests/sec by RGW Instance',
+ '',
+ 'none',
+ 'short',
+ 'sum by (rgw_host) (label_replace(rate(ceph_rgw_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, "rgw_host", "$1", "ceph_daemon", "rgw.(.*)"))',
+ '{{rgw_host}}',
+ 8,
+ 1,
+ 7,
+ 7
+ ),
+ RgwOverviewPanel(
+ 'GET Latencies by RGW Instance',
+ 'Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts',
+ 's',
+ 'short',
+ 'label_replace(\n rate(ceph_rgw_get_initial_lat_sum[30s]) /\n rate(ceph_rgw_get_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n"rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
+ '{{rgw_host}}',
+ 15,
+ 1,
+ 6,
+ 7
+ ),
+ RgwOverviewPanel(
+ 'Bandwidth Consumed by Type',
+ 'Total bytes transferred in/out of all radosgw instances within the cluster',
+ 'bytes',
+ 'short',
+ 'sum(rate(ceph_rgw_get_b[30s]))',
+ 'GETs',
+ 0,
+ 8,
+ 8,
+ 6
+ ).addTargets(
+ [u.addTargetSchema('sum(rate(ceph_rgw_put_b[30s]))',
+ 1,
+ 'time_series',
+ 'PUTs')]
+ ),
+ RgwOverviewPanel(
+ 'Bandwidth by RGW Instance',
+ 'Total bytes transferred in/out through get/put operations, by radosgw instance',
+ 'bytes',
+ 'short',
+ 'label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b[30s]) + \n rate(ceph_rgw_put_b[30s])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, "rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
+ '{{rgw_host}}',
+ 8,
+ 8,
+ 7,
+ 6
+ ),
+ RgwOverviewPanel(
+ 'PUT Latencies by RGW Instance',
+ 'Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts',
+ 's',
+ 'short',
+ 'label_replace(\n rate(ceph_rgw_put_initial_lat_sum[30s]) /\n rate(ceph_rgw_put_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n"rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
+ '{{rgw_host}}',
+ 15,
+ 8,
+ 6,
+ 6
+ ),
+ u.addRowSchema(
+ false, true, 'RGW Overview - HAProxy Metrics'
+ ) + { gridPos: { x: 0, y: 12, w: 9, h: 12 } },
+ RgwOverviewPanel(
+ 'Total responses by HTTP code',
+ '',
+ 'short',
+ 'short',
+ 'sum(irate(haproxy_frontend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"frontend"}[5m])) by (code)',
+ 'Frontend {{ code }}',
+ 0,
+ 12,
+ 5,
+ 12,
+ '$datasource',
+ true,
+ true,
+ true,
+ true,
+ true,
+ true
+ )
+ .addTargets(
+ [u.addTargetSchema('sum(irate(haproxy_backend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"backend"}[5m])) by (code)', 1, 'time_series', 'Backend {{ code }}')]
+ )
+ .addSeriesOverride([
+ {
+ alias: '/.*Back.*/',
+ transform: 'negative-Y',
+ },
+ { alias: '/.*1.*/' },
+ { alias: '/.*2.*/' },
+ { alias: '/.*3.*/' },
+ { alias: '/.*4.*/' },
+ { alias: '/.*5.*/' },
+ { alias: '/.*other.*/' },
+ ]),
+ RgwOverviewPanel(
+ 'Total requests / responses',
+ '',
+ 'short',
+ 'short',
+ 'sum(irate(haproxy_frontend_http_requests_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)',
+ 'Requests',
+ 5,
+ 12,
+ 5,
+ 12,
+ '$datasource',
+ true,
+ true,
+ true,
+ true,
+ true,
+ true
+ )
+ .addTargets(
+ [
+ u.addTargetSchema('sum(irate(haproxy_backend_response_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Response errors'),
+ u.addTargetSchema('sum(irate(haproxy_frontend_request_errors_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Requests errors'),
+ u.addTargetSchema('sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend redispatch'),
+ u.addTargetSchema('sum(irate(haproxy_backend_retry_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend retry'),
+ u.addTargetSchema('sum(irate(haproxy_frontend_requests_denied_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Request denied'),
+ u.addTargetSchema('sum(haproxy_backend_current_queue{proxy=~"backend",instance=~"$ingress_service"}) by (instance)', 2, 'time_series', 'Backend Queued'),
+ ]
+ )
+ .addSeriesOverride([
+ {
+ alias: '/.*Response.*/',
+ transform: 'negative-Y',
+ },
+ {
+ alias: '/.*Backend.*/',
+ transform: 'negative-Y',
+ },
+ ]),
+ RgwOverviewPanel(
+ 'Total number of connections',
+ '',
+ 'short',
+ 'short',
+ 'sum(irate(haproxy_frontend_connections_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)',
+ 'Front',
+ 10,
+ 12,
+ 5,
+ 12,
+ '$datasource',
+ true,
+ true,
+ true,
+ true,
+ true,
+ true
+ )
+ .addTargets(
+ [
+ u.addTargetSchema('sum(irate(haproxy_backend_connection_attempts_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back'),
+ u.addTargetSchema('sum(irate(haproxy_backend_connection_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back errors'),
+ ]
+ )
+ .addSeriesOverride([
+ {
+ alias: '/.*Back.*/',
+ transform: 'negative-Y',
+ },
+ ]),
+ RgwOverviewPanel(
+ 'Current total of incoming / outgoing bytes',
+ '',
+ 'short',
+ 'short',
+ 'sum(irate(haproxy_frontend_bytes_in_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)',
+ 'IN Front',
+ 15,
+ 12,
+ 6,
+ 12,
+ '$datasource',
+ true,
+ true,
+ true,
+ true,
+ true,
+ true
+ )
+ .addTargets(
+ [
+ u.addTargetSchema('sum(irate(haproxy_frontend_bytes_out_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Front'),
+ u.addTargetSchema('sum(irate(haproxy_backend_bytes_in_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'IN Back'),
+ u.addTargetSchema('sum(irate(haproxy_backend_bytes_out_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Back'),
+ ]
+ )
+ .addSeriesOverride([
+ {
+ alias: '/.*OUT.*/',
+ transform: 'negative-Y',
+ },
+ ]),
+ ]),
+ 'radosgw-detail.json':
+ local RgwDetailsPanel(aliasColors,
+ title,
+ description,
+ formatY1,
+ formatY2,
+ expr1,
+ expr2,
+ legendFormat1,
+ legendFormat2,
+ x,
+ y,
+ w,
+ h) =
+ u.graphPanelSchema(aliasColors,
+ title,
+ description,
+ 'null',
+ false,
+ formatY1,
+ formatY2,
+ null,
+ null,
+ 0,
+ 1,
+ '$datasource')
+ .addTargets(
+ [u.addTargetSchema(expr1, 1, 'time_series', legendFormat1), u.addTargetSchema(expr2, 1, 'time_series', legendFormat2)]
+ ) + { gridPos: { x: x, y: y, w: w, h: h } };
+
+ u.dashboardSchema(
+ 'RGW Instance Detail',
+ '',
+ 'x5ARzZtmk',
+ 'now-1h',
+ '15s',
+ 16,
+ ['overview'],
+ '',
+ {
+ refresh_intervals: ['5s', '10s', '15s', '30s', '1m', '5m', '15m', '30m', '1h', '2h', '1d'],
+ time_options: ['5m', '15m', '1h', '6h', '12h', '24h', '2d', '7d', '30d'],
+ }
+ )
+ .addAnnotation(
+ u.addAnnotationSchema(
+ 1,
+ '-- Grafana --',
+ true,
+ true,
+ 'rgba(0, 211, 255, 1)',
+ 'Annotations & Alerts',
+ 'dashboard'
+ )
+ )
+ .addRequired(
+ type='grafana', id='grafana', name='Grafana', version='5.0.0'
+ )
+ .addRequired(
+ type='panel',
+ id='grafana-piechart-panel',
+ name='Pie Chart',
+ version='1.3.3'
+ )
+ .addRequired(
+ type='panel', id='graph', name='Graph', version='5.0.0'
+ )
+ .addTemplate(
+ g.template.datasource('datasource',
+ 'prometheus',
+ 'default',
+ label='Data Source')
+ )
+ .addTemplate(
+ u.addTemplateSchema('rgw_servers',
+ '$datasource',
+ 'label_values(ceph_rgw_metadata, ceph_daemon)',
+ 1,
+ true,
+ 1,
+ '',
+ '')
+ )
+ .addPanels([
+ u.addRowSchema(false, true, 'RGW Host Detail : $rgw_servers') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } },
+ RgwDetailsPanel(
+ {},
+ '$rgw_servers GET/PUT Latencies',
+ '',
+ 's',
+ 'short',
+ 'sum by (instance_id) (rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'sum by (instance_id) (rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'GET {{ceph_daemon}}',
+ 'PUT {{ceph_daemon}}',
+ 0,
+ 1,
+ 6,
+ 8
+ ),
+ RgwDetailsPanel(
+ {},
+ 'Bandwidth by HTTP Operation',
+ '',
+ 'bytes',
+ 'short',
+ 'rate(ceph_rgw_get_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'rate(ceph_rgw_put_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'GETs {{ceph_daemon}}',
+ 'PUTs {{ceph_daemon}}',
+ 6,
+ 1,
+ 7,
+ 8
+ ),
+ RgwDetailsPanel(
+ {
+ GETs: '#7eb26d',
+ Other: '#447ebc',
+ PUTs: '#eab839',
+ Requests: '#3f2b5b',
+ 'Requests Failed': '#bf1b00',
+ },
+ 'HTTP Request Breakdown',
+ '',
+ 'short',
+ 'short',
+ 'rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 'Requests Failed {{ceph_daemon}}',
+ 'GETs {{ceph_daemon}}',
+ 13,
+ 1,
+ 7,
+ 8
+ )
+ .addTargets(
+ [
+ u.addTargetSchema(
+ 'rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'PUTs {{ceph_daemon}}'
+ ),
+ u.addTargetSchema(
+ '(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'Other {{ceph_daemon}}'
+ ),
+ ]
+ ),
+ u.addPieChartSchema(
+ {
+ GETs: '#7eb26d',
+ 'Other (HEAD,POST,DELETE)': '#447ebc',
+ PUTs: '#eab839',
+ Requests: '#3f2b5b',
+ Failures: '#bf1b00',
+ }, '$datasource', '', 'Under graph', 'pie', 'Workload Breakdown', 'current'
+ )
+ .addTarget(u.addTargetSchema(
+ 'rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'Failures {{ceph_daemon}}'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'GETs {{ceph_daemon}}'
+ ))
+ .addTarget(u.addTargetSchema(
+ 'rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'PUTs {{ceph_daemon}}'
+ ))
+ .addTarget(u.addTargetSchema(
+ '(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
+ 1,
+ 'time_series',
+ 'Other (DELETE,LIST) {{ceph_daemon}}'
+ )) + { gridPos: { x: 20, y: 1, w: 4, h: 8 } },
+ ]),
+ },
+}
--- /dev/null
+local g = import 'grafonnet/grafana.libsonnet';
+
+{
+ dashboardSchema(title,
+ description,
+ uid,
+ time_from,
+ refresh,
+ schemaVersion,
+ tags,
+ timezone,
+ timepicker)::
+ g.dashboard.new(title=title,
+ description=description,
+ uid=uid,
+ time_from=time_from,
+ refresh=refresh,
+ schemaVersion=schemaVersion,
+ tags=tags,
+ timezone=timezone,
+ timepicker=timepicker),
+
+ graphPanelSchema(aliasColors,
+ title,
+ description,
+ nullPointMode,
+ stack,
+ formatY1,
+ formatY2,
+ labelY1,
+ labelY2,
+ min,
+ fill,
+ datasource,
+ legend_alignAsTable=false,
+ legend_avg=false,
+ legend_min=false,
+ legend_max=false,
+ legend_current=false,
+ legend_values=false)::
+ g.graphPanel.new(aliasColors=aliasColors,
+ title=title,
+ description=description,
+ nullPointMode=nullPointMode,
+ stack=stack,
+ formatY1=formatY1,
+ formatY2=formatY2,
+ labelY1=labelY1,
+ labelY2=labelY2,
+ min=min,
+ fill=fill,
+ datasource=datasource,
+ legend_alignAsTable=legend_alignAsTable,
+ legend_avg=legend_avg,
+ legend_min=legend_min,
+ legend_max=legend_max,
+ legend_current=legend_current,
+ legend_values=legend_values),
+
+
+ addTargetSchema(expr, intervalFactor, format, legendFormat)::
+ g.prometheus.target(expr=expr,
+ intervalFactor=intervalFactor,
+ format=format,
+ legendFormat=legendFormat),
+
+ addTemplateSchema(name,
+ datasource,
+ query,
+ refresh,
+ includeAll,
+ sort,
+ label,
+ regex)::
+ g.template.new(name=name,
+ datasource=datasource,
+ query=query,
+ refresh=refresh,
+ includeAll=includeAll,
+ sort=sort,
+ label=label,
+ regex=regex),
+
+ addAnnotationSchema(builtIn,
+ datasource,
+ enable,
+ hide,
+ iconColor,
+ name,
+ type)::
+ g.annotation.datasource(builtIn=builtIn,
+ datasource=datasource,
+ enable=enable,
+ hide=hide,
+ iconColor=iconColor,
+ name=name,
+ type=type),
+
+ addRowSchema(collapse, showTitle, title)::
+ g.row.new(collapse=collapse, showTitle=showTitle, title=title),
+
+ addSingleStatSchema(colors,
+ datasource,
+ format,
+ title,
+ description,
+ valueName,
+ colorValue,
+ gaugeMaxValue,
+ gaugeShow,
+ sparklineShow,
+ thresholds)::
+ g.singlestat.new(colors=colors,
+ datasource=datasource,
+ format=format,
+ title=title,
+ description=description,
+ valueName=valueName,
+ colorValue=colorValue,
+ gaugeMaxValue=gaugeMaxValue,
+ gaugeShow=gaugeShow,
+ sparklineShow=sparklineShow,
+ thresholds=thresholds),
+
+ addPieChartSchema(aliasColors,
+ datasource,
+ description,
+ legendType,
+ pieType,
+ title,
+ valueName)::
+ g.pieChartPanel.new(aliasColors=aliasColors,
+ datasource=datasource,
+ description=description,
+ legendType=legendType,
+ pieType=pieType,
+ title=title,
+ valueName=valueName),
+
+ addTableSchema(datasource, description, sort, styles, title, transform)::
+ g.tablePanel.new(datasource=datasource,
+ description=description,
+ sort=sort,
+ styles=styles,
+ title=title,
+ transform=transform),
+
+ addStyle(alias,
+ colorMode,
+ colors,
+ dateFormat,
+ decimals,
+ mappingType,
+ pattern,
+ thresholds,
+ type,
+ unit,
+ valueMaps)::
+ {
+ alias: alias,
+ colorMode: colorMode,
+ colors: colors,
+ dateFormat: dateFormat,
+ decimals: decimals,
+ mappingType: mappingType,
+ pattern: pattern,
+ thresholds: thresholds,
+ type: type,
+ unit: unit,
+ valueMaps: valueMaps,
+ },
+}
--- /dev/null
+{
+ "__requires": [
+ {
+ "type": "grafana",
+ "id": "grafana",
+ "name": "Grafana",
+ "version": "5.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "graph",
+ "name": "Graph",
+ "version": "5.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "heatmap",
+ "name": "Heatmap",
+ "version": "5.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "singlestat",
+ "name": "Singlestat",
+ "version": "5.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "vonage-status-panel",
+ "name": "Status Panel",
+ "version": "1.0.8"
+ }
+ ],
+ "annotations": {
+ "list": []
+ },
+ "description": "Ceph cluster overview",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "id": null,
+ "iteration": 1525415495309,
+ "links": [],
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": true,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 128, 45, 0.9)",
+ "rgba(237, 129, 40, 0.9)",
+ "rgb(255, 0, 0)"
+ ],
+ "datasource": "$datasource",
+ "editable": false,
+ "error": false,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 2,
+ "x": 0,
+ "y": 0
+ },
+ "hideTimeOverride": true,
+ "id": 21,
+ "interval": "1m",
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "ceph_health_status",
+ "format": "time_series",
+ "instant": true,
+ "interval": "$interval",
+ "intervalFactor": 1,
+ "refId": "A",
+ "step": 60
+ }
+ ],
+ "thresholds": "1,2",
+ "timeFrom": null,
+ "title": "Health Status",
+ "transparent": false,
+ "type": "singlestat",
+ "valueFontSize": "50%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "OK",
+ "value": "0"
+ },
+ {
+ "op": "=",
+ "text": "WARN",
+ "value": "1"
+ },
+ {
+ "op": "=",
+ "text": "ERR",
+ "value": "2"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "colorMode": "Panel",
+ "colors": {
+ "crit": "rgb(255, 0, 0)",
+ "disable": "rgba(128, 128, 128, 0.9)",
+ "ok": "rgba(50, 128, 45, 0.9)",
+ "warn": "rgba(237, 129, 40, 0.9)"
+ },
+ "cornerRadius": 0,
+ "datasource": "$datasource",
+ "displayName": "",
+ "flipCard": false,
+ "flipTime": 5,
+ "fontFormat": "Regular",
+ "gridPos": {
+ "h": 3,
+ "w": 2,
+ "x": 2,
+ "y": 0
+ },
+ "id": 43,
+ "isAutoScrollOnOverflow": false,
+ "isGrayOnNoData": false,
+ "isHideAlertsOnDisable": false,
+ "isIgnoreOKColors": false,
+ "links": [],
+ "targets": [
+ {
+ "aggregation": "Last",
+ "alias": "All",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "count(ceph_osd_metadata)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "All",
+ "refId": "A",
+ "units": "none",
+ "valueHandler": "Number Threshold"
+ },
+ {
+ "aggregation": "Last",
+ "alias": "In",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "sum(ceph_osd_in)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "In",
+ "refId": "B",
+ "units": "none",
+ "valueHandler": "Number Threshold"
+ },
+ {
+ "aggregation": "Last",
+ "alias": "Out",
+ "decimals": 2,
+ "displayAliasType": "Warning / Critical",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "sum(ceph_osd_in == bool 0)",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Out",
+ "refId": "C",
+ "units": "none",
+ "valueHandler": "Number Threshold",
+ "warn": 1
+ },
+ {
+ "aggregation": "Last",
+ "alias": "Up",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "sum(ceph_osd_up)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Up",
+ "refId": "D",
+ "units": "none",
+ "valueHandler": "Number Threshold"
+ },
+ {
+ "aggregation": "Last",
+ "alias": "Down",
+ "crit": 2,
+ "decimals": 2,
+ "displayAliasType": "Warning / Critical",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "sum(ceph_osd_up == bool 0)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Down",
+ "refId": "E",
+ "units": "none",
+ "valueHandler": "Number Threshold",
+ "warn": 1
+ }
+ ],
+ "title": "OSDs",
+ "type": "vonage-status-panel"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "decimals": 2,
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 1,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 4,
+ "x": 4,
+ "y": 0
+ },
+ "id": 47,
+ "interval": null,
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": true
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_osd_stat_bytes_used)/sum(ceph_osd_stat_bytes)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Used",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "0.7,0.8",
+ "title": "Capacity used",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 0,
+ "gridPos": {
+ "h": 6,
+ "w": 8,
+ "x": 8,
+ "y": 0
+ },
+ "id": 53,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Active",
+ "color": "#508642",
+ "fill": 1,
+ "stack": "A"
+ },
+ {
+ "alias": "Total",
+ "color": "#f9e2d2"
+ },
+ {
+ "alias": "Degraded",
+ "color": "#eab839"
+ },
+ {
+ "alias": "Undersized",
+ "color": "#f9934e"
+ },
+ {
+ "alias": "Inconsistent",
+ "color": "#e24d42"
+ },
+ {
+ "alias": "Down",
+ "color": "#bf1b00"
+ },
+ {
+ "alias": "Inactive",
+ "color": "#bf1b00",
+ "fill": 4,
+ "linewidth": 0,
+ "stack": "A"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(ceph_pg_total)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Total",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(ceph_pg_active)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Active",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(ceph_pg_total - ceph_pg_active)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Inactive",
+ "refId": "G"
+ },
+ {
+ "expr": "sum(ceph_pg_undersized)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Undersized",
+ "refId": "F"
+ },
+ {
+ "expr": "sum(ceph_pg_degraded)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Degraded",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(ceph_pg_inconsistent)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Inconsistent",
+ "refId": "D"
+ },
+ {
+ "expr": "sum(ceph_pg_down)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Down",
+ "refId": "E"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "PG States",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 0,
+ "gridPos": {
+ "h": 6,
+ "w": 8,
+ "x": 16,
+ "y": 0
+ },
+ "id": 66,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Avg Apply Latency",
+ "color": "#7eb26d"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "quantile(0.95, ceph_osd_apply_latency_ms)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Apply Latency P_95",
+ "refId": "A"
+ },
+ {
+ "expr": "quantile(0.95, ceph_osd_commit_latency_ms)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Commit Latency P_95",
+ "refId": "B"
+ },
+ {
+ "expr": "avg(ceph_osd_apply_latency_ms)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Avg Apply Latency",
+ "refId": "C"
+ },
+ {
+ "expr": "avg(ceph_osd_commit_latency_ms)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Avg Commit Latency",
+ "refId": "D"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "OSD Latencies",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "ms",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "clusterName": "",
+ "colorMode": "Panel",
+ "colors": {
+ "crit": "rgba(245, 54, 54, 0.9)",
+ "disable": "rgba(128, 128, 128, 0.9)",
+ "ok": "rgba(50, 128, 45, 0.9)",
+ "warn": "rgba(237, 129, 40, 0.9)"
+ },
+ "cornerRadius": 1,
+ "datasource": "$datasource",
+ "displayName": "",
+ "flipCard": false,
+ "flipTime": 5,
+ "fontFormat": "Regular",
+ "gridPos": {
+ "h": 3,
+ "w": 2,
+ "x": 0,
+ "y": 3
+ },
+ "id": 41,
+ "isAutoScrollOnOverflow": false,
+ "isGrayOnNoData": false,
+ "isHideAlertsOnDisable": false,
+ "isIgnoreOKColors": false,
+ "links": [],
+ "targets": [
+ {
+ "aggregation": "Last",
+ "alias": "In Quorum",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "sum(ceph_mon_quorum_status)",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "In Quorum",
+ "refId": "A",
+ "units": "none",
+ "valueHandler": "Text Only"
+ },
+ {
+ "aggregation": "Last",
+ "alias": "Total",
+ "crit": 1,
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "count(ceph_mon_quorum_status)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Total",
+ "refId": "B",
+ "units": "none",
+ "valueHandler": "Text Only",
+ "warn": 2
+ },
+ {
+ "aggregation": "Last",
+ "alias": "MONs out of Quorum",
+ "crit": 1.6,
+ "decimals": 2,
+ "displayAliasType": "Warning / Critical",
+ "displayType": "Annotation",
+ "displayValueWithAlias": "Never",
+ "expr": "count(ceph_mon_quorum_status) / sum(ceph_mon_quorum_status)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "MONs out of Quorum",
+ "refId": "C",
+ "units": "none",
+ "valueHandler": "Number Threshold",
+ "warn": 1.1
+ }
+ ],
+ "title": "Monitors",
+ "type": "vonage-status-panel"
+ },
+ {
+ "colorMode": "Panel",
+ "colors": {
+ "crit": "rgba(245, 54, 54, 0.9)",
+ "disable": "rgba(128, 128, 128, 0.9)",
+ "ok": "rgba(50, 128, 45, 0.9)",
+ "warn": "rgba(237, 129, 40, 0.9)"
+ },
+ "cornerRadius": 0,
+ "datasource": "$datasource",
+ "displayName": "",
+ "flipCard": false,
+ "flipTime": 5,
+ "fontFormat": "Regular",
+ "gridPos": {
+ "h": 3,
+ "w": 2,
+ "x": 2,
+ "y": 3
+ },
+ "id": 68,
+ "isAutoScrollOnOverflow": false,
+ "isGrayOnNoData": false,
+ "isHideAlertsOnDisable": false,
+ "isIgnoreOKColors": false,
+ "links": [],
+ "targets": [
+ {
+ "aggregation": "Last",
+ "alias": "Active",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "count(ceph_mgr_status == 1) or vector(0)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Active",
+ "refId": "A",
+ "units": "none",
+ "valueHandler": "Number Threshold"
+ },
+ {
+ "aggregation": "Last",
+ "alias": "Standby",
+ "decimals": 2,
+ "displayAliasType": "Always",
+ "displayType": "Regular",
+ "displayValueWithAlias": "When Alias Displayed",
+ "expr": "count(ceph_mgr_status == 0) or vector(0)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Standby",
+ "refId": "B",
+ "units": "none",
+ "valueHandler": "Number Threshold"
+ }
+ ],
+ "title": "MGRs",
+ "type": "vonage-status-panel"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 6
+ },
+ "id": 45,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 0.5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Reads",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(ceph_osd_op_w_in_bytes[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Writes",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(irate(ceph_osd_op_r_out_bytes[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Reads",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Cluster I/O",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 6
+ },
+ "id": 62,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(deriv(ceph_pool_stored[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "In-/Egress",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": " Egress (-) / Ingress (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "cards": {
+ "cardPadding": null,
+ "cardRound": 1
+ },
+ "color": {
+ "cardColor": "rgb(0, 254, 255)",
+ "colorScale": "sqrt",
+ "colorScheme": "interpolateBlues",
+ "exponent": 0.5,
+ "min": null,
+ "mode": "spectrum"
+ },
+ "dataFormat": "timeseries",
+ "datasource": "$datasource",
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 0,
+ "y": 15
+ },
+ "heatmap": {},
+ "highlightCards": true,
+ "id": 55,
+ "legend": {
+ "show": true
+ },
+ "links": [],
+ "span": 12,
+ "targets": [
+ {
+ "expr": "ceph_osd_stat_bytes_used / ceph_osd_stat_bytes",
+ "format": "time_series",
+ "interval": "1m",
+ "intervalFactor": 1,
+ "legendFormat": "Util (%)",
+ "refId": "A",
+ "step": 60
+ }
+ ],
+ "timeFrom": null,
+ "title": "OSD Capacity Utilization",
+ "tooltip": {
+ "show": true,
+ "showHistogram": false
+ },
+ "type": "heatmap",
+ "xAxis": {
+ "show": true
+ },
+ "xBucketNumber": null,
+ "xBucketSize": "",
+ "yAxis": {
+ "decimals": 2,
+ "format": "percentunit",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true,
+ "splitFactor": null
+ },
+ "yBucketNumber": null,
+ "yBucketSize": null
+ },
+ {
+ "cards": {
+ "cardPadding": null,
+ "cardRound": 1
+ },
+ "color": {
+ "cardColor": "#b4ff00",
+ "colorScale": "sqrt",
+ "colorScheme": "interpolateBlues",
+ "exponent": 0.5,
+ "mode": "spectrum"
+ },
+ "dataFormat": "timeseries",
+ "datasource": "$datasource",
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 6,
+ "y": 15
+ },
+ "heatmap": {},
+ "highlightCards": true,
+ "id": 59,
+ "legend": {
+ "show": true
+ },
+ "links": [],
+ "targets": [
+ {
+ "expr": "ceph_osd_numpg",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "#PGs",
+ "refId": "A"
+ }
+ ],
+ "title": "PGs per OSD",
+ "tooltip": {
+ "show": true,
+ "showHistogram": false
+ },
+ "type": "heatmap",
+ "xAxis": {
+ "show": true
+ },
+ "xBucketNumber": null,
+ "xBucketSize": "",
+ "yAxis": {
+ "decimals": null,
+ "format": "none",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true,
+ "splitFactor": null
+ },
+ "yBucketNumber": null,
+ "yBucketSize": null
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 15
+ },
+ "id": 64,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(ceph_osd_recovery_ops[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Op/s",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Recovery Rate",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": "Recovery Ops/s",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "30s",
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "ceph",
+ "cluster"
+ ],
+ "templating": {
+ "list": [
+ {
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "auto": true,
+ "auto_count": 10,
+ "auto_min": "1m",
+ "current": {
+ "text": "auto",
+ "value": "$__auto_interval_interval"
+ },
+ "datasource": null,
+ "hide": 0,
+ "includeAll": false,
+ "label": "Interval",
+ "multi": false,
+ "name": "interval",
+ "options": [
+ {
+ "selected": true,
+ "text": "auto",
+ "value": "$__auto_interval_interval"
+ },
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "30m",
+ "value": "30m"
+ },
+ {
+ "selected": false,
+ "text": "1h",
+ "value": "1h"
+ },
+ {
+ "selected": false,
+ "text": "6h",
+ "value": "6h"
+ },
+ {
+ "selected": false,
+ "text": "12h",
+ "value": "12h"
+ },
+ {
+ "selected": false,
+ "text": "1d",
+ "value": "1d"
+ },
+ {
+ "selected": false,
+ "text": "7d",
+ "value": "7d"
+ },
+ {
+ "selected": false,
+ "text": "14d",
+ "value": "14d"
+ },
+ {
+ "selected": false,
+ "text": "30d",
+ "value": "30d"
+ }
+ ],
+ "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
+ "refresh": 2,
+ "type": "interval"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-6h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "Ceph - Cluster",
+ "version": 13
+ }
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "MDS Performance",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*Reads/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(ceph_objecter_op_r{ceph_daemon=~\"($mds_servers).*\"}[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Read Ops",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(rate(ceph_objecter_op_w{ceph_daemon=~\"($mds_servers).*\"}[1m]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Write Ops",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "MDS Workload - $mds_servers",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "none",
+ "label": "Reads(-) / Writes (+)",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "ceph_mds_server_handle_client_request{ceph_daemon=~\"($mds_servers).*\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ceph_daemon}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Client Request Load - $mds_servers",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "none",
+ "label": "Client Requests",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "MDS Server",
+ "multi": false,
+ "name": "mds_servers",
+ "options": [ ],
+ "query": "label_values(ceph_mds_inodes, ceph_daemon)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "MDS Performance",
+ "uid": "tbO9LAiZz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ },
+ {
+ "id": "singlestat",
+ "name": "Singlestat",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "$ceph_hosts System Overview",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 3,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "count(sum by (ceph_daemon) (ceph_osd_metadata{hostname='$ceph_hosts'}))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "OSDs",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "aliasColors": {
+ "interrupt": "#447EBC",
+ "steal": "#6D1F62",
+ "system": "#890F02",
+ "user": "#3F6833",
+ "wait": "#C15C17"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Shows the CPU breakdown. When multiple servers are selected, only the first host's cpu data is shown",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 6,
+ "x": 3,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (mode) (\n irate(node_cpu{instance=~\"($ceph_hosts)([\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[1m]) or\n irate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[1m])\n) / scalar(\n sum(irate(node_cpu{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[1m]) or\n irate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[1m]))\n) * 100",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{mode}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Utilization",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": "% Utilization",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "Available": "#508642",
+ "Free": "#508642",
+ "Total": "#bf1b00",
+ "Used": "#bf1b00",
+ "total": "#bf1b00",
+ "used": "#0a50a1"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 6,
+ "x": 9,
+ "y": 1
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "total",
+ "color": "#bf1b00",
+ "fill": 0,
+ "linewidth": 2,
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_MemFree{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"} ",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Free",
+ "refId": "A"
+ },
+ {
+ "expr": "node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"} ",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "total",
+ "refId": "B"
+ },
+ {
+ "expr": "(node_memory_Cached{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n(node_memory_Buffers{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) +\n(node_memory_Slab{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) \n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "buffers/cache",
+ "refId": "C"
+ },
+ {
+ "expr": "(node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"})- (\n (node_memory_MemFree{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n (node_memory_Cached{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n (node_memory_Buffers{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) +\n (node_memory_Slab{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"})\n )\n \n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "used",
+ "refId": "D"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "RAM Usage",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "RAM used",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Show the network load (rx,tx) across all interfaces (excluding loopback 'lo')",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 6,
+ "x": 15,
+ "y": 1
+ },
+ "id": 6,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*tx/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (device) (\n irate(node_network_receive_bytes{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m]) or \n irate(node_network_receive_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m])\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.rx",
+ "refId": "A"
+ },
+ {
+ "expr": "sum by (device) (\n irate(node_network_transmit_bytes{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m])\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.tx",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network Load",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "decbytes",
+ "label": "Send (-) / Receive (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 5,
+ "w": 3,
+ "x": 21,
+ "y": 1
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*tx/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(node_network_receive_drop{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_receive_drop_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.rx",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(node_network_transmit_drop{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_transmit_drop_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.tx",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network drop rate",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "Send (-) / Receive (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 3,
+ "x": 0,
+ "y": 6
+ },
+ "id": 8,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_osd_stat_bytes and on (ceph_daemon) ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"})",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Raw Capacity",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 5,
+ "w": 3,
+ "x": 21,
+ "y": 6
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*tx/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(node_network_receive_errs{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_receive_errs_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.rx",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(node_network_transmit_errs{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_transmit_errs_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}.tx",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network error rate",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": "Send (-) / Receive (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 11
+ },
+ "id": 10,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "OSD Disk Performance Statistics",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it's name and corresponding OSD id value",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 11,
+ "x": 0,
+ "y": 12
+ },
+ "id": 11,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*reads/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(\n (\n irate(node_disk_writes_completed{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or\n irate(node_disk_writes_completed_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n )",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}}) writes",
+ "refId": "A"
+ },
+ {
+ "expr": "label_replace(\n (irate(node_disk_reads_completed{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_reads_completed_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n )",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}}) reads",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$ceph_hosts Disk IOPS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 11,
+ "x": 12,
+ "y": 12
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*read/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace((irate(node_disk_bytes_written{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_written_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}}) write",
+ "refId": "A"
+ },
+ {
+ "expr": "label_replace((irate(node_disk_bytes_read{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_read_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}}) read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$ceph_hosts Throughput by Disk",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it's corresponding OSD id",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 11,
+ "x": 0,
+ "y": 21
+ },
+ "id": 13,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) ) / clamp_min(irate(node_disk_writes_completed_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]), 0.001) or (irate(node_disk_read_time_seconds_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) ) / clamp_min(irate(node_disk_reads_completed_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]), 0.001), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")) * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}})",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$ceph_hosts Disk Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 11,
+ "x": 12,
+ "y": 21
+ },
+ "id": 14,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(((irate(node_disk_io_time_ms{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) / 10 ) or irate(node_disk_io_time_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}({{ceph_daemon}})",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$ceph_hosts Disk utilization",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": "%Util",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "10s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "overview"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Hostname",
+ "multi": false,
+ "name": "ceph_hosts",
+ "options": [ ],
+ "query": "label_values(node_scrape_collector_success, instance) ",
+ "refresh": 1,
+ "regex": "([^.:]*).*",
+ "sort": 3,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "Host Details",
+ "uid": "rtOg0AiWz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ },
+ {
+ "id": "singlestat",
+ "name": "Singlestat",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "count(sum by (hostname) (ceph_osd_metadata))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "OSD Hosts",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster",
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 4,
+ "y": 0
+ },
+ "id": 3,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "avg(\n 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "AVG CPU Busy",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)",
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 8,
+ "y": 0
+ },
+ "id": 4,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "avg (((node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"})- (\n (node_memory_MemFree{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemFree_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) + \n (node_memory_Cached{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Cached_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) + \n (node_memory_Buffers{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Buffers_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) +\n (node_memory_Slab{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Slab_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"})\n )) /\n (node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*\"} ))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "AVG RAM Utilization",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "IOPS Load at the device as reported by the OS on all OSD hosts",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 12,
+ "y": 0
+ },
+ "id": 5,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum ((irate(node_disk_reads_completed{instance=~\"($osd_hosts).*\"}[5m]) or irate(node_disk_reads_completed_total{instance=~\"($osd_hosts).*\"}[5m]) ) + \n(irate(node_disk_writes_completed{instance=~\"($osd_hosts).*\"}[5m]) or irate(node_disk_writes_completed_total{instance=~\"($osd_hosts).*\"}[5m])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Physical IOPS",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 16,
+ "y": 0
+ },
+ "id": 6,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "avg (\n label_replace((irate(node_disk_io_time_ms[5m]) / 10 ) or\n (irate(node_disk_io_time_seconds_total[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\"\n ) *\n on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($osd_hosts).*\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\")\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "AVG Disk Utilization",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Total send/receive network load across all hosts in the ceph cluster",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 4,
+ "x": 20,
+ "y": 0
+ },
+ "id": 7,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum (\n (\n irate(node_network_receive_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m]) or\n irate(node_network_receive_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n ) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n) +\nsum (\n (\n irate(node_network_transmit_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n ) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n )\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Network Load",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Show the top 10 busiest hosts by cpu",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 5
+ },
+ "id": 8,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "topk(10,100 * ( 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Busy - Top 10 Hosts",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Top 10 hosts by network load",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 5
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "topk(10, (sum by(instance) (\n(\n irate(node_network_receive_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m]) or\n irate(node_network_receive_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m])\n) +\n(\n irate(node_network_transmit_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m])\n) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\"))\n))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network Load - Top 10 Hosts",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "10s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "osd_hosts",
+ "options": [ ],
+ "query": "label_values(ceph_disk_occupation, exported_instance)",
+ "refresh": 1,
+ "regex": "([^.]*).*",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "mon_hosts",
+ "options": [ ],
+ "query": "label_values(ceph_mon_metadata, ceph_daemon)",
+ "refresh": 1,
+ "regex": "mon.(.*)",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "mds_hosts",
+ "options": [ ],
+ "query": "label_values(ceph_mds_inodes, ceph_daemon)",
+ "refresh": 1,
+ "regex": "mds.(.*)",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "rgw_hosts",
+ "options": [ ],
+ "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
+ "refresh": 1,
+ "regex": "rgw.(.*)",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "Host Overview",
+ "uid": "y0KGL0iZz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "OSD Performance",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "read",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_osd_op_r_latency_sum{ceph_daemon=~\"$osd\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "read",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_osd_op_w_latency_sum{ceph_daemon=~\"$osd\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "write",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$osd Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 6,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "Reads",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_osd_op_r{ceph_daemon=~\"$osd\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Reads",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_osd_op_w{ceph_daemon=~\"$osd\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$osd R/W IOPS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 12,
+ "y": 1
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "Read Bytes",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_osd_op_r_out_bytes{ceph_daemon=~\"$osd\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Read Bytes",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_osd_op_w_in_bytes{ceph_daemon=~\"$osd\"}[1m])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Write Bytes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$osd R/W Bytes",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 10
+ },
+ "id": 6,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Physical Device Performance",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 0,
+ "y": 11
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*Reads/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "(label_replace(irate(node_disk_read_time_seconds_total[1m]) / irate(node_disk_reads_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}}/{{device}} Reads",
+ "refId": "A"
+ },
+ {
+ "expr": "(label_replace(irate(node_disk_write_time_seconds_total[1m]) / irate(node_disk_writes_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}}/{{device}} Writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Physical Device Latency for $osd",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 6,
+ "y": 11
+ },
+ "id": 8,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*Reads/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(irate(node_disk_writes_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} on {{instance}} Writes",
+ "refId": "A"
+ },
+ {
+ "expr": "label_replace(irate(node_disk_reads_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} on {{instance}} Reads",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Physical Device R/W IOPS for $osd",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 12,
+ "y": 11
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "/.*Reads/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(irate(node_disk_read_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}} {{device}} Reads",
+ "refId": "A"
+ },
+ {
+ "expr": "label_replace(irate(node_disk_written_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{instance}} {{device}} Writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Physical Device R/W Bytes for $osd",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 18,
+ "y": 11
+ },
+ "id": 10,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(irate(node_disk_io_time_seconds_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Physical Device Util% for $osd",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "OSD",
+ "multi": false,
+ "name": "osd",
+ "options": [ ],
+ "query": "label_values(ceph_osd_metadata,ceph_daemon)",
+ "refresh": 1,
+ "regex": "(.*)",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-3h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "OSD device details",
+ "uid": "CrAHE0iZz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.0.0"
+ },
+ {
+ "id": "grafana-piechart-panel",
+ "name": "Pie Chart",
+ "type": "panel",
+ "version": "1.3.3"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ },
+ {
+ "id": "table",
+ "name": "Table",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "aliasColors": {
+ "@95%ile": "#e0752d"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 8,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "AVG read",
+ "refId": "A"
+ },
+ {
+ "expr": "max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "MAX read",
+ "refId": "B"
+ },
+ {
+ "expr": "quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "@95%ile",
+ "refId": "C"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "OSD Read Latencies",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ms",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ }
+ ]
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "This table shows the osd's that are delivering the 10 highest read latencies within the cluster",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 8,
+ "y": 0
+ },
+ "id": 3,
+ "links": [ ],
+ "sort": {
+ "col": 2,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "OSD ID",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "ceph_daemon",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Latency (ms)",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "none",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "/.*/",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n ))\n)\n\n",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Highest READ Latencies",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "aliasColors": {
+ "@95%ile write": "#e0752d"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 8,
+ "x": 12,
+ "y": 0
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "AVG write",
+ "refId": "A"
+ },
+ {
+ "expr": "max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "MAX write",
+ "refId": "B"
+ },
+ {
+ "expr": "quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "@95%ile write",
+ "refId": "C"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "OSD Write Latencies",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ms",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ }
+ ]
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 20,
+ "y": 0
+ },
+ "id": 5,
+ "links": [ ],
+ "sort": {
+ "col": 2,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "OSD ID",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "ceph_daemon",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Latency (ms)",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "none",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "/.*/",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Highest WRITE Latencies",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "aliasColors": { },
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 0,
+ "y": 8
+ },
+ "id": 6,
+ "legend": {
+ "percentage": true,
+ "show": true,
+ "values": true
+ },
+ "legendType": "Under graph",
+ "pieType": "pie",
+ "targets": [
+ {
+ "expr": "count by (device_class) (ceph_osd_metadata)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device_class}}",
+ "refId": "A"
+ }
+ ],
+ "title": "OSD Types Summary",
+ "type": "grafana-piechart-panel",
+ "valueName": "current"
+ },
+ {
+ "aliasColors": {
+ "Non-Encrypted": "#E5AC0E"
+ },
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 4,
+ "y": 8
+ },
+ "id": 7,
+ "legend": {
+ "percentage": true,
+ "show": true,
+ "values": true
+ },
+ "legendType": "Under graph",
+ "pieType": "pie",
+ "targets": [
+ {
+ "expr": "count(ceph_bluefs_wal_total_bytes)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "bluestore",
+ "refId": "A"
+ },
+ {
+ "expr": "absent(ceph_bluefs_wal_total_bytes)*count(ceph_osd_metadata)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "filestore",
+ "refId": "B"
+ }
+ ],
+ "title": "OSD Objectstore Types",
+ "type": "grafana-piechart-panel",
+ "valueName": "current"
+ },
+ {
+ "aliasColors": { },
+ "datasource": "$datasource",
+ "description": "The pie chart shows the various OSD sizes used within the cluster",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 8,
+ "y": 8
+ },
+ "id": 8,
+ "legend": {
+ "percentage": true,
+ "show": true,
+ "values": true
+ },
+ "legendType": "Under graph",
+ "pieType": "pie",
+ "targets": [
+ {
+ "expr": "count(ceph_osd_stat_bytes < 1099511627776)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<1TB",
+ "refId": "A"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 1099511627776 < 2199023255552)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<2TB",
+ "refId": "B"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 2199023255552 < 3298534883328)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<3TB",
+ "refId": "C"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 3298534883328 < 4398046511104)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<4TB",
+ "refId": "D"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 4398046511104 < 6597069766656)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<6TB",
+ "refId": "E"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 6597069766656 < 8796093022208)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<8TB",
+ "refId": "F"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 8796093022208 < 10995116277760)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<10TB",
+ "refId": "G"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 10995116277760 < 13194139533312)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<12TB",
+ "refId": "H"
+ },
+ {
+ "expr": "count(ceph_osd_stat_bytes >= 13194139533312)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "<12TB+",
+ "refId": "I"
+ }
+ ],
+ "title": "OSD Size Summary",
+ "type": "grafana-piechart-panel",
+ "valueName": "current"
+ },
+ {
+ "aliasColors": { },
+ "bars": true,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 8,
+ "x": 12,
+ "y": 8
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "ceph_osd_numpg\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PGs per OSD",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Distribution of PGs per OSD",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": 20,
+ "mode": "histogram",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "# of OSDs",
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ }
+ ]
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": true,
+ "colors": [
+ "#d44a3a",
+ "#299c46"
+ ],
+ "datasource": "$datasource",
+ "description": "This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster",
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 1,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 20,
+ "y": 8
+ },
+ "id": 10,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_bluestore_onode_hits)/(sum(ceph_bluestore_onode_hits) + sum(ceph_bluestore_onode_misses))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": ".75",
+ "title": "OSD onode Hits Ratio",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 16
+ },
+ "id": 11,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "R/W Profile",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Show the read/write workload profile overtime",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 24,
+ "x": 0,
+ "y": 17
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "round(sum(irate(ceph_pool_rd[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Reads",
+ "refId": "A"
+ },
+ {
+ "expr": "round(sum(irate(ceph_pool_wr[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Read/Write Profile",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "10s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "OSD Overview",
+ "uid": "lo02I1Aiz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ },
+ {
+ "id": "singlestat",
+ "name": "Singlestat",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": true,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 1,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 7,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": true
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "(ceph_pool_stored / (ceph_pool_stored + ceph_pool_max_avail)) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": ".7,.8",
+ "title": "Capacity used",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": 100,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Time till pool is full assuming the average fill rate of the last 6 hours",
+ "format": "s",
+ "gauge": {
+ "maxValue": false,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 5,
+ "x": 7,
+ "y": 0
+ },
+ "id": 3,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": ""
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "(ceph_pool_max_avail / deriv(ceph_pool_stored[6h])) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"} > 0",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "current",
+ "title": "Time till full",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": false
+ },
+ {
+ "aliasColors": {
+ "read_op_per_sec": "#3F6833",
+ "write_op_per_sec": "#E5AC0E"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 0
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "deriv(ceph_pool_objects[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Objects per second",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$pool_name Object Ingress/Egress",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": "Objects out(-) / in(+) ",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "read_op_per_sec": "#3F6833",
+ "write_op_per_sec": "#E5AC0E"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 7
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "reads",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_pool_rd[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "reads",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_pool_wr[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$pool_name Client IOPS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "iops",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "read_op_per_sec": "#3F6833",
+ "write_op_per_sec": "#E5AC0E"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 7
+ },
+ "id": 6,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "reads",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_pool_rd_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "reads",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_pool_wr_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "writes",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$pool_name Client Throughput",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "Read (-) / Write (+)",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "read_op_per_sec": "#3F6833",
+ "write_op_per_sec": "#E5AC0E"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 14
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "ceph_pool_objects * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Number of Objects",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$pool_name Objects",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Objects",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 22,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "Prometheus admin.virt1.home.fajerski.name:9090",
+ "value": "Prometheus admin.virt1.home.fajerski.name:9090"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Pool Name",
+ "multi": false,
+ "name": "pool_name",
+ "options": [ ],
+ "query": "label_values(ceph_pool_metadata,name)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "Ceph Pool Details",
+ "uid": "-xyV8KCiz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "count(ceph_pool_metadata)",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Pools",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "avg"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Count of the pools that have compression enabled",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 3,
+ "y": 0
+ },
+ "id": 3,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "count(ceph_pool_metadata{compression_mode!=\"none\"})",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Pools with Compression",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Total raw capacity available to the cluster",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 6,
+ "y": 0
+ },
+ "id": 4,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_osd_stat_bytes)",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Total Raw Capacity",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Total raw capacity consumed by user data and associated overheads (metadata + redundancy)",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 9,
+ "y": 0
+ },
+ "id": 5,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_pool_bytes_used)",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Raw Capacity Consumed",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Total of client data stored in the cluster",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 12,
+ "y": 0
+ },
+ "id": 6,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_pool_stored)",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Logical Stored ",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression",
+ "format": "bytes",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 15,
+ "y": 0
+ },
+ "id": 7,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used)",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Compression Savings",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data\n",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 18,
+ "y": 0
+ },
+ "id": 8,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "(sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_stored_raw and ceph_pool_compress_under_bytes > 0)) * 100",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Compression Eligibility",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "description": "This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 3,
+ "x": 21,
+ "y": 0
+ },
+ "id": 9,
+ "interval": null,
+ "links": [ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_compress_bytes_used > 0)",
+ "format": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Compression Factor",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 6,
+ "w": 24,
+ "x": 0,
+ "y": 3
+ },
+ "id": 10,
+ "links": [ ],
+ "sort": {
+ "col": 5,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Time",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "instance",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "job",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Pool Name",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "name",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Pool ID",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "pool_id",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "none",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Compression Factor",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #A",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "none",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "% Used",
+ "colorMode": "value",
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #D",
+ "thresholds": [
+ "70",
+ "85"
+ ],
+ "type": "number",
+ "unit": "percentunit",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Usable Free",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #B",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "bytes",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Compression Eligibility",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #C",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "percent",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Compression Savings",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #E",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "bytes",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Growth (5d)",
+ "colorMode": "value",
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #F",
+ "thresholds": [
+ "0",
+ "0"
+ ],
+ "type": "number",
+ "unit": "bytes",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "IOPS",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #G",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "none",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Bandwidth",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #H",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "Bps",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "__name__",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "type",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "compression_mode",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Type",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "description",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Stored",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #J",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "bytes",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #I",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Compression",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #K",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [
+ {
+ "text": "ON",
+ "value": "1"
+ }
+ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "(ceph_pool_compress_under_bytes / ceph_pool_compress_bytes_used > 0) and on(pool_id) (((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100 > 0.5)",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "A",
+ "refId": "A"
+ },
+ {
+ "expr": "ceph_pool_max_avail * on(pool_id) group_left(name) ceph_pool_metadata",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "B",
+ "refId": "B"
+ },
+ {
+ "expr": "((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "C",
+ "refId": "C"
+ },
+ {
+ "expr": "(ceph_pool_percent_used * on(pool_id) group_left(name) ceph_pool_metadata)",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "D",
+ "refId": "D"
+ },
+ {
+ "expr": "(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used > 0)",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "E",
+ "refId": "E"
+ },
+ {
+ "expr": "delta(ceph_pool_stored[5d])",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "F",
+ "refId": "F"
+ },
+ {
+ "expr": "rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "G",
+ "refId": "G"
+ },
+ {
+ "expr": "rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "H",
+ "refId": "H"
+ },
+ {
+ "expr": "ceph_pool_metadata",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "I",
+ "refId": "I"
+ },
+ {
+ "expr": "ceph_pool_stored * on(pool_id) group_left ceph_pool_metadata",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "J",
+ "refId": "J"
+ },
+ {
+ "expr": "ceph_pool_metadata{compression_mode!=\"none\"}",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "K",
+ "refId": "K"
+ },
+ {
+ "expr": "",
+ "format": "",
+ "intervalFactor": "",
+ "legendFormat": "L",
+ "refId": "L"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Pool Overview",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "This chart shows the sum of read and write IOPS from all clients by pool",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 9
+ },
+ "id": 11,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "topk($topk,round((rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])),1) * on(pool_id) group_left(instance,name) ceph_pool_metadata) ",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{name}} ",
+ "refId": "A"
+ },
+ {
+ "expr": "topk($topk,rate(ceph_pool_wr[30s]) + on(pool_id) group_left(instance,name) ceph_pool_metadata) ",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{name}} - write",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Top $topk Client IOPS by Pool",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "IOPS",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "The chart shows the sum of read and write bytes from all clients, by pool",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 9
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "topk($topk,(rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])) * on(pool_id) group_left(instance,name) ceph_pool_metadata)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{name}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Top $topk Client Bandwidth by Pool",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "Throughput",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Historical view of capacity usage, to help identify growth and trends in pool consumption",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 24,
+ "x": 0,
+ "y": 17
+ },
+ "id": 13,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "ceph_pool_bytes_used * on(pool_id) group_right ceph_pool_metadata",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{name}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Pool Capacity Usage (RAW)",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "Capacity Used",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 22,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "Dashboard1",
+ "value": "Dashboard1"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "15",
+ "value": "15"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "TopK",
+ "multi": false,
+ "name": "topk",
+ "options": [
+ {
+ "text": "15",
+ "value": "15"
+ }
+ ],
+ "query": "15",
+ "refresh": 0,
+ "type": "custom"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "Ceph Pools Overview",
+ "uid": "z99hzWtmk",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.0.0"
+ },
+ {
+ "id": "grafana-piechart-panel",
+ "name": "Pie Chart",
+ "type": "panel",
+ "version": "1.3.3"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "RGW Host Detail : $rgw_servers",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 6,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (instance_id) (rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GET {{ceph_daemon}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum by (instance_id) (rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUT {{ceph_daemon}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "$rgw_servers GET/PUT Latencies",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 7,
+ "x": 6,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(ceph_rgw_get_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs {{ceph_daemon}}",
+ "refId": "A"
+ },
+ {
+ "expr": "rate(ceph_rgw_put_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs {{ceph_daemon}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Bandwidth by HTTP Operation",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "GETs": "#7eb26d",
+ "Other": "#447ebc",
+ "PUTs": "#eab839",
+ "Requests": "#3f2b5b",
+ "Requests Failed": "#bf1b00"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 8,
+ "w": 7,
+ "x": 13,
+ "y": 1
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Requests Failed {{ceph_daemon}}",
+ "refId": "A"
+ },
+ {
+ "expr": "rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs {{ceph_daemon}}",
+ "refId": "B"
+ },
+ {
+ "expr": "rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs {{ceph_daemon}}",
+ "refId": "C"
+ },
+ {
+ "expr": "(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Other {{ceph_daemon}}",
+ "refId": "D"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "HTTP Request Breakdown",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "Failures": "#bf1b00",
+ "GETs": "#7eb26d",
+ "Other (HEAD,POST,DELETE)": "#447ebc",
+ "PUTs": "#eab839",
+ "Requests": "#3f2b5b"
+ },
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 8,
+ "w": 4,
+ "x": 20,
+ "y": 1
+ },
+ "id": 6,
+ "legend": {
+ "percentage": true,
+ "show": true,
+ "values": true
+ },
+ "legendType": "Under graph",
+ "pieType": "pie",
+ "targets": [
+ {
+ "expr": "rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Failures {{ceph_daemon}}",
+ "refId": "A"
+ },
+ {
+ "expr": "rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs {{ceph_daemon}}",
+ "refId": "B"
+ },
+ {
+ "expr": "rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs {{ceph_daemon}}",
+ "refId": "C"
+ },
+ {
+ "expr": "(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Other (DELETE,LIST) {{ceph_daemon}}",
+ "refId": "D"
+ }
+ ],
+ "title": "Workload Breakdown",
+ "type": "grafana-piechart-panel",
+ "valueName": "current"
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "overview"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "",
+ "multi": false,
+ "name": "rgw_servers",
+ "options": [ ],
+ "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "RGW Instance Detail",
+ "uid": "x5ARzZtmk",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.0.0"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "RGW Overview - All Gateways",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GET AVG",
+ "refId": "A"
+ },
+ {
+ "expr": "rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUT AVG",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Average GET/PUT Latencies",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 7,
+ "x": 8,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (rgw_host) (label_replace(rate(ceph_rgw_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Total Requests/sec by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 6,
+ "x": 15,
+ "y": 1
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum[30s]) /\n rate(ceph_rgw_get_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n\"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "GET Latencies by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Total bytes transferred in/out of all radosgw instances within the cluster",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 6,
+ "w": 8,
+ "x": 0,
+ "y": 8
+ },
+ "id": 6,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(ceph_rgw_get_b[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(rate(ceph_rgw_put_b[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Bandwidth Consumed by Type",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Total bytes transferred in/out through get/put operations, by radosgw instance",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 6,
+ "w": 7,
+ "x": 8,
+ "y": 8
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b[30s]) + \n rate(ceph_rgw_put_b[30s])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Bandwidth by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 6,
+ "w": 6,
+ "x": 15,
+ "y": 8
+ },
+ "id": 8,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum[30s]) /\n rate(ceph_rgw_put_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n\"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "PUT Latencies by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 12,
+ "w": 9,
+ "x": 0,
+ "y": 12
+ },
+ "id": 9,
+ "panels": [ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "RGW Overview - HAProxy Metrics",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 5,
+ "x": 0,
+ "y": 12
+ },
+ "id": 10,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ [
+ {
+ "alias": "/.*Back.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*1.*/"
+ },
+ {
+ "alias": "/.*2.*/"
+ },
+ {
+ "alias": "/.*3.*/"
+ },
+ {
+ "alias": "/.*4.*/"
+ },
+ {
+ "alias": "/.*5.*/"
+ },
+ {
+ "alias": "/.*other.*/"
+ }
+ ]
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(haproxy_frontend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"frontend\"}[5m])) by (code)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Frontend {{ code }}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"backend\"}[5m])) by (code)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Backend {{ code }}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Total responses by HTTP code",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 5,
+ "x": 5,
+ "y": 12
+ },
+ "id": 11,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ [
+ {
+ "alias": "/.*Response.*/",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/.*Backend.*/",
+ "transform": "negative-Y"
+ }
+ ]
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(haproxy_frontend_http_requests_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Requests",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_response_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Response errors",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(irate(haproxy_frontend_request_errors_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Requests errors",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Backend redispatch",
+ "refId": "D"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_retry_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Backend retry",
+ "refId": "E"
+ },
+ {
+ "expr": "sum(irate(haproxy_frontend_requests_denied_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Request denied",
+ "refId": "F"
+ },
+ {
+ "expr": "sum(haproxy_backend_current_queue{proxy=~\"backend\",instance=~\"$ingress_service\"}) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Backend Queued",
+ "refId": "G"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Total requests / responses",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 5,
+ "x": 10,
+ "y": 12
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ [
+ {
+ "alias": "/.*Back.*/",
+ "transform": "negative-Y"
+ }
+ ]
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(haproxy_frontend_connections_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Front",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_connection_attempts_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Back",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_connection_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Back errors",
+ "refId": "C"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Total number of connections",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 12,
+ "w": 6,
+ "x": 15,
+ "y": 12
+ },
+ "id": 13,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ [
+ {
+ "alias": "/.*OUT.*/",
+ "transform": "negative-Y"
+ }
+ ]
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(haproxy_frontend_bytes_in_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "IN Front",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(irate(haproxy_frontend_bytes_out_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "OUT Front",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_bytes_in_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "IN Back",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(irate(haproxy_backend_bytes_out_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "OUT Back",
+ "refId": "D"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current total of incoming / outgoing bytes",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "overview"
+ ],
+ "templating": {
+ "list": [
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "",
+ "multi": false,
+ "name": "rgw_servers",
+ "options": [ ],
+ "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "HTTP Code",
+ "multi": false,
+ "name": "code",
+ "options": [ ],
+ "query": "label_values(haproxy_server_http_responses_total{instance=~\"$ingress_service\"}, code)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "Ingress Service",
+ "multi": false,
+ "name": "ingress_service",
+ "options": [ ],
+ "query": "label_values(haproxy_server_status, instance)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "RGW Overview",
+ "uid": "WAkugZpiz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.0.0"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_sum[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{source_zone}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Replication (throughput) from Source Zone",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 0
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_count[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{source_zone}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Replication (objects) from Source Zone",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Objects/s",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 0
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_poll_latency_sum[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{source_zone}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Polling Request Latency from Source Zone",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ms",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 7
+ },
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_errors[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{source_zone}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Unsuccessful Object Replications from Source Zone",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": "Count/s",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": "15s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "overview"
+ ],
+ "templating": {
+ "list": [
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": "",
+ "multi": false,
+ "name": "rgw_servers",
+ "options": [ ],
+ "query": "prometehus",
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "RGW Sync Overview",
+ "uid": "rgw-sync-overview",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.3.3"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "Detailed Performance of RBD Images (IOPS/Throughput/Latency)",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$Datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 8,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_rbd_write_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Write",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_rbd_read_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "IOPS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "iops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "iops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$Datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 8,
+ "x": 8,
+ "y": 0
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_rbd_write_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Write",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_rbd_read_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Throughput",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$Datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 8,
+ "x": 16,
+ "y": 0
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "irate(ceph_rbd_write_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_write_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Write",
+ "refId": "A"
+ },
+ {
+ "expr": "irate(ceph_rbd_read_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_read_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pool}} Read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Average Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ns",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ns",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "refresh": false,
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "Datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$Datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "",
+ "multi": false,
+ "name": "Pool",
+ "options": [ ],
+ "query": "label_values(pool)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": { },
+ "datasource": "$Datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "",
+ "multi": false,
+ "name": "Image",
+ "options": [ ],
+ "query": "label_values(image)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "RBD Details",
+ "uid": "YhCYGcuZz",
+ "version": 0
+}
--- /dev/null
+{
+ "__inputs": [ ],
+ "__requires": [
+ {
+ "id": "grafana",
+ "name": "Grafana",
+ "type": "grafana",
+ "version": "5.4.2"
+ },
+ {
+ "id": "graph",
+ "name": "Graph",
+ "type": "panel",
+ "version": "5.0.0"
+ },
+ {
+ "id": "prometheus",
+ "name": "Prometheus",
+ "type": "datasource",
+ "version": "5.0.0"
+ },
+ {
+ "id": "table",
+ "name": "Table",
+ "type": "panel",
+ "version": "5.0.0"
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "showIn": 0,
+ "tags": [ ],
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "",
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [ ],
+ "panels": [
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "round(sum(irate(ceph_rbd_write_ops[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Writes",
+ "refId": "A"
+ },
+ {
+ "expr": "round(sum(irate(ceph_rbd_read_ops[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Reads",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "IOPS",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 0
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "round(sum(irate(ceph_rbd_write_bytes[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Write",
+ "refId": "A"
+ },
+ {
+ "expr": "round(sum(irate(ceph_rbd_read_bytes[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Throughput",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": { },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 0
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "round(sum(irate(ceph_rbd_write_latency_sum[30s])) / sum(irate(ceph_rbd_write_latency_count[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Write",
+ "refId": "A"
+ },
+ {
+ "expr": "round(sum(irate(ceph_rbd_read_latency_sum[30s])) / sum(irate(ceph_rbd_read_latency_count[30s])))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Read",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Average Latency",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [ ]
+ },
+ "yaxes": [
+ {
+ "format": "ns",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 7
+ },
+ "id": 5,
+ "links": [ ],
+ "sort": {
+ "col": 3,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "Pool",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "pool",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Image",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "image",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "IOPS",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "iops",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "/.*/",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on (image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Highest IOPS",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 7
+ },
+ "id": 6,
+ "links": [ ],
+ "sort": {
+ "col": 3,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "Pool",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "pool",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Image",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "image",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Throughput",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "Bps",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "/.*/",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "topk(10, sort(sum(irate(ceph_rbd_read_bytes[30s]) + irate(ceph_rbd_write_bytes[30s])) by (pool, image, namespace)))",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Highest Throughput",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "columns": [ ],
+ "datasource": "$datasource",
+ "description": "",
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 7
+ },
+ "id": 7,
+ "links": [ ],
+ "sort": {
+ "col": 3,
+ "desc": true
+ },
+ "styles": [
+ {
+ "alias": "Pool",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "pool",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Image",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "image",
+ "thresholds": [ ],
+ "type": "string",
+ "unit": "short",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "Latency",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value",
+ "thresholds": [ ],
+ "type": "number",
+ "unit": "ns",
+ "valueMaps": [ ]
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "/.*/",
+ "thresholds": [ ],
+ "type": "hidden",
+ "unit": "short",
+ "valueMaps": [ ]
+ }
+ ],
+ "targets": [
+ {
+ "expr": "topk(10,\n sum(\n irate(ceph_rbd_write_latency_sum[30s]) / clamp_min(irate(ceph_rbd_write_latency_count[30s]), 1) +\n irate(ceph_rbd_read_latency_sum[30s]) / clamp_min(irate(ceph_rbd_read_latency_count[30s]), 1)\n ) by (pool, image, namespace)\n)",
+ "format": "table",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Highest Latency",
+ "transform": "table",
+ "type": "table"
+ }
+ ],
+ "refresh": "30s",
+ "rows": [ ],
+ "schemaVersion": 16,
+ "style": "dark",
+ "tags": [
+ "overview"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "15s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "",
+ "title": "RBD Overview",
+ "uid": "41FrpeUiz",
+ "version": 0
+}
--- /dev/null
+{
+ "version": 1,
+ "dependencies": [
+ {
+ "source": {
+ "git": {
+ "remote": "https://github.com/grafana/grafonnet-lib.git",
+ "subdir": "grafonnet"
+ }
+ },
+ "version": "master"
+ }
+ ],
+ "legacyImports": true
+}
--- /dev/null
+{
+ "version": 1,
+ "dependencies": [
+ {
+ "source": {
+ "git": {
+ "remote": "https://github.com/grafana/grafonnet-lib.git",
+ "subdir": "grafonnet"
+ }
+ },
+ "version": "3626fc4dc2326931c530861ac5bebe39444f6cbf",
+ "sum": "gF8foHByYcB25jcUOBqP6jxk0OPifQMjPvKY0HaCk6w="
+ }
+ ],
+ "legacyImports": false
+}
--- /dev/null
+#!/bin/sh -e
+
+JSONNETS_FILES=$(find . -name 'vendor' -prune -o \
+ -name '*.jsonnet' -print -o -name '*.libsonnet' -print)
+jsonnetfmt "$@" ${JSONNETS_FILES}
--- /dev/null
+(import 'config.libsonnet') +
+(import 'dashboards/dashboards.libsonnet') +
+(import 'alerts.libsonnet')
--- /dev/null
+groups:
+ - name: cluster health
+ rules:
+ - alert: CephHealthError
+ expr: ceph_health_status == 2
+ for: 5m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.2.1
+ annotations:
+ summary: Cluster is in an ERROR state
+ description: >
+ Ceph in HEALTH_ERROR state for more than 5 minutes.
+ Please check "ceph health detail" for more information.
+
+ - alert: CephHealthWarning
+ expr: ceph_health_status == 1
+ for: 15m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: Cluster is in a WARNING state
+ description: >
+ Ceph has been in HEALTH_WARN for more than 15 minutes.
+ Please check "ceph health detail" for more information.
+
+ - name: mon
+ rules:
+ - alert: CephMonDownQuorumAtRisk
+ expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1
+ for: 30s
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.3.1
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
+ summary: Monitor quorum is at risk
+ description: |
+ {{ $min := query "floor(count(ceph_mon_metadata) / 2) +1" | first | value }}Quorum requires a majority of monitors (x {{ $min }}) to be active
+ Without quorum the cluster will become inoperable, affecting all connected clients and services.
+
+ The following monitors are down:
+ {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }}
+ - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
+ {{- end }}
+ - alert: CephMonDown
+ expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1))
+ for: 30s
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
+ summary: One of more ceph monitors are down
+ description: |
+ {{ $down := query "count(ceph_mon_quorum_status == 0)" | first | value }}{{ $s := "" }}{{ if gt $down 1.0 }}{{ $s = "s" }}{{ end }}You have {{ $down }} monitor{{ $s }} down.
+ Quorum is still intact, but the loss of further monitors will make your cluster inoperable.
+
+ The following monitors are down:
+ {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }}
+ - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
+ {{- end }}
+ - alert: CephMonDiskspaceCritical
+ expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.3.2
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit
+ summary: Disk space on at least one monitor is critically low
+ description: |
+ The free space available to a monitor's store is critically low (<5% by default).
+ You should increase the space available to the monitor(s). The
+ default location for the store sits under /var/lib/ceph. Your monitor hosts are;
+ {{- range query "ceph_mon_metadata"}}
+ - {{ .Labels.hostname }}
+ {{- end }}
+
+ - alert: CephMonDiskspaceLow
+ expr: ceph_health_detail{name="MON_DISK_LOW"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low
+ summary: Disk space on at least one monitor is approaching full
+ description: |
+ The space available to a monitor's store is approaching full (>70% is the default).
+ You should increase the space available to the monitor store. The
+ default location for the store sits under /var/lib/ceph. Your monitor hosts are;
+ {{- range query "ceph_mon_metadata"}}
+ - {{ .Labels.hostname }}
+ {{- end }}
+
+ - alert: CephMonClockSkew
+ expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew
+ summary: Clock skew across the Monitor hosts detected
+ description: |
+ The ceph monitors rely on a consistent time reference to maintain
+ quorum and cluster consistency. This event indicates that at least
+ one of your mons is not sync'd correctly.
+
+ Review the cluster status with ceph -s. This will show which monitors
+ are affected. Check the time sync status on each monitor host.
+
+ - name: osd
+ rules:
+ - alert: CephOSDDownHigh
+ expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.1
+ annotations:
+ summary: More than 10% of OSDs are down
+ description: |
+ {{ $value | humanize }}% or {{ with query "count(ceph_osd_up == 0)" }}{{ . | first | value }}{{ end }} of {{ with query "count(ceph_osd_up)" }}{{ . | first | value }}{{ end }} OSDs are down (>= 10%).
+
+ The following OSDs are down:
+ {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }}
+ - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
+ {{- end }}
+ - alert: CephOSDHostDown
+ expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.8
+ annotations:
+ summary: An OSD host is offline
+ description: |
+ The following OSDs are down:
+ {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }}
+ - {{ .Labels.hostname }} : {{ .Labels.ceph_daemon }}
+ {{- end }}
+ - alert: CephOSDDown
+ expr: ceph_health_detail{name="OSD_DOWN"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.2
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down
+ summary: An OSD has been marked down/unavailable
+ description: |
+ {{ $num := query "count(ceph_osd_up == 0)" | first | value }}{{ $s := "" }}{{ if gt $num 1.0 }}{{ $s = "s" }}{{ end }}{{ $num }} OSD{{ $s }} down for over 5mins.
+
+ The following OSD{{ $s }} {{ if eq $s "" }}is{{ else }}are{{ end }} down:
+ {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0"}}
+ - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
+ {{- end }}
+
+ - alert: CephOSDNearFull
+ expr: ceph_health_detail{name="OSD_NEARFULL"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.3
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull
+ summary: OSD(s) running low on free space (NEARFULL)
+ description: |
+ One or more OSDs have reached their NEARFULL threshold
+
+ Use 'ceph health detail' to identify which OSDs have reached this threshold.
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - alert: CephOSDFull
+ expr: ceph_health_detail{name="OSD_FULL"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.6
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full
+ summary: OSD(s) is full, writes blocked
+ description: |
+ An OSD has reached it's full threshold. Writes from all pools that share the
+ affected OSD will be blocked.
+
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - alert: CephOSDBackfillFull
+ expr: ceph_health_detail{name="OSD_BACKFILLFULL"} > 0
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull
+ summary: OSD(s) too full for backfill operations
+ description: |
+ An OSD has reached it's BACKFILL FULL threshold. This will prevent rebalance operations
+ completing for some pools. Check the current capacity utilisation with 'ceph df'
+
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - alert: CephOSDTooManyRepairs
+ expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 1
+ for: 30s
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs
+ summary: OSD has hit a high number of read errors
+ description: |
+ Reads from an OSD have used a secondary PG to return data to the client, indicating
+ a potential failing disk.
+ - alert: CephOSDTimeoutsPublicNetwork
+ expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: Network issues delaying OSD heartbeats (public network)
+ description: |
+ OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network
+ for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
+ - alert: CephOSDTimeoutsClusterNetwork
+ expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: Network issues delaying OSD heartbeats (cluster network)
+ description: |
+ OSD heartbeats on the cluster's 'cluster' network (backend) are running slow. Investigate the network
+ for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
+ - alert: CephOSDInternalDiskSizeMismatch
+ expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch
+ summary: OSD size inconsistency error
+ description: |
+ One or more OSDs have an internal inconsistency between the size of the physical device and it's metadata.
+ This could lead to the OSD(s) crashing in future. You should redeploy the effected OSDs.
+ - alert: CephDeviceFailurePredicted
+ expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2
+ summary: Device(s) have been predicted to fail soon
+ description: |
+ The device health module has determined that one or more devices will fail
+ soon. To review the device states use 'ceph device ls'. To show a specific
+ device use 'ceph device info <dev id>'.
+
+ Mark the OSD as out (so data may migrate to other OSDs in the cluster). Once
+ the osd is empty remove and replace the OSD.
+ - alert: CephDeviceFailurePredictionTooHigh
+ expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.7
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany
+ summary: Too many devices have been predicted to fail, unable to resolve
+ description: |
+ The device health module has determined that the number of devices predicted to
+ fail can not be remediated automatically, since it would take too many osd's out of
+ the cluster, impacting performance and potentially availabililty. You should add new
+ OSDs to the cluster to allow data to be relocated to avoid the data integrity issues.
+ - alert: CephDeviceFailureRelocationIncomplete
+ expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use
+ summary: A device failure is predicted, but unable to relocate data
+ description: |
+ The device health module has determined that one or more devices will fail
+ soon, but the normal process of relocating the data on the device to other
+ OSDs in the cluster is blocked.
+
+ Check the the cluster has available freespace. It may be necessary to add
+ more disks to the cluster to allow the data from the failing device to
+ successfully migrate.
+
+ - alert: CephOSDFlapping
+ expr: |
+ (
+ rate(ceph_osd_up[5m])
+ * on(ceph_daemon) group_left(hostname) ceph_osd_metadata
+ ) * 60 > 1
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.4
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds
+ summary: Network issues are causing OSD's to flap (mark each other out)
+ description: >
+ OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} was
+ marked down and back up at {{ $value | humanize }} times once a
+ minute for 5 minutes. This could indicate a network issue (latency,
+ packet drop, disruption) on the clusters "cluster network". Check the
+ network environment on the listed host(s).
+
+ - alert: CephOSDReadErrors
+ expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1
+ for: 30s
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors
+ summary: Device read errors detected
+ description: >
+ An OSD has encountered read errors, but the OSD has recovered by retrying
+ the reads. This may indicate an issue with the Hardware or Kernel.
+ # alert on high deviation from average PG count
+ - alert: CephPGImbalance
+ expr: |
+ abs(
+ (
+ (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0) by (job)
+ ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)
+ ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.5
+ annotations:
+ summary: PG allocations are not balanced across devices
+ description: >
+ OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} deviates
+ by more than 30% from average PG count.
+ # alert on high commit latency...but how high is too high
+
+ - name: mds
+ rules:
+ - alert: CephFilesystemDamaged
+ expr: ceph_health_detail{name="MDS_DAMAGE"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.1
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
+ summary: Ceph filesystem is damaged.
+ description: >
+ The filesystems metadata has been corrupted. Data access
+ may be blocked.
+
+ Either analyse the output from the mds daemon admin socket, or
+ escalate to support
+ - alert: CephFilesystemOffline
+ expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.3
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down
+ summary: Ceph filesystem is offline
+ description: >
+ All MDS ranks are unavailable. The ceph daemons providing the metadata
+ for the Ceph filesystem are all down, rendering the filesystem offline.
+ - alert: CephFilesystemDegraded
+ expr: ceph_health_detail{name="FS_DEGRADED"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.4
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded
+ summary: Ceph filesystem is degraded
+ description: >
+ One or more metdata daemons (MDS ranks) are failed or in a
+ damaged state. At best the filesystem is partially available,
+ worst case is the filesystem is completely unusable.
+ - alert: CephFilesystemMDSRanksLow
+ expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max
+ summary: Ceph MDS daemon count is lower than configured
+ description: >
+ The filesystem's "max_mds" setting defined the number of MDS ranks in
+ the filesystem. The current number of active MDS daemons is less than
+ this setting.
+ - alert: CephFilesystemInsufficientStandby
+ expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby
+ summary: Ceph filesystem standby daemons too low
+ description: >
+ The minimum number of standby daemons determined by standby_count_wanted
+ is less than the actual number of standby daemons. Adjust the standby count
+ or increase the number of mds daemons within the filesystem.
+ - alert: CephFilesystemFailureNoStandby
+ expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.5
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds
+ summary: Ceph MDS daemon failed, no further standby available
+ description: >
+ An MDS daemon has failed, leaving only one active rank without
+ further standby. Investigate the cause of the failure or add a
+ standby daemon
+ - alert: CephFilesystemReadOnly
+ expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.2
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
+ summary: Ceph filesystem in read only mode, due to write error(s)
+ description: >
+ The filesystem has switched to READ ONLY due to an unexpected
+ write error, when writing to the metadata pool
+
+ Either analyse the output from the mds daemon admin socket, or
+ escalate to support
+
+ - name: mgr
+ rules:
+ - alert: CephMgrModuleCrash
+ expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1
+ for: 5m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.6.1
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash
+ summary: A mgr module has recently crashed
+ description: >
+ One or more mgr modules have crashed and are yet to be acknowledged by the administrator. A
+ crashed module may impact functionality within the cluster. Use the 'ceph crash' commands to
+ investigate which module has failed, and archive it to acknowledge the failure.
+ - alert: CephMgrPrometheusModuleInactive
+ expr: up{job="ceph"} == 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.6.2
+ annotations:
+ summary: Ceph's mgr/prometheus module is not available
+ description: >
+ The mgr/prometheus module at {{ $labels.instance }} is unreachable. This
+ could mean that the module has been disabled or the mgr itself is down.
+
+ Without the mgr/prometheus module metrics and alerts will no longer
+ function. Open a shell to ceph and use 'ceph -s' to to determine whether the
+ mgr is active. If the mgr is not active, restart it, otherwise you can check
+ the mgr/prometheus module is loaded with 'ceph mgr module ls' and if it's
+ not listed as enabled, enable it with 'ceph mgr module enable prometheus'
+
+ - name: pgs
+ rules:
+ - alert: CephPGsInactive
+ expr: ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_active) > 0
+ for: 5m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.1
+ annotations:
+ summary: One or more Placement Groups are inactive
+ description: >
+ {{ $value }} PGs have been inactive for more than 5 minutes in pool {{ $labels.name }}.
+ Inactive placement groups aren't able to serve read/write
+ requests.
+ - alert: CephPGsUnclean
+ expr: ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_clean) > 0
+ for: 15m
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.2
+ annotations:
+ summary: One or more platcment groups are marked unclean
+ description: >
+ {{ $value }} PGs haven't been clean for more than 15 minutes in pool {{ $labels.name }}.
+ Unclean PGs haven't been able to completely recover from a previous failure.
+ - alert: CephPGsDamaged
+ expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1
+ for: 5m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.4
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged
+ summary: Placement group damaged, manual intervention needed
+ description: >
+ During data consistency checks (scrub), at least one PG has been flagged as being
+ damaged or inconsistent.
+
+ Check to see which PG is affected, and attempt a manual repair if neccessary. To list
+ problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use
+ the 'ceph pg repair <pg_num>' command.
+ - alert: CephPGRecoveryAtRisk
+ expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.5
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full
+ summary: OSDs are too full for automatic recovery
+ description: >
+ Data redundancy may be reduced, or is at risk, since one or more OSDs are at or above their
+ 'full' threshold. Add more capacity to the cluster, or delete unwanted data.
+ - alert: CephPGUnavilableBlockingIO
+ # PG_AVAILABILITY, but an OSD is not in a DOWN state
+ expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"})) == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.3
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability
+ summary: Placement group is unavailable, blocking some I/O
+ description: >
+ Data availability is reduced impacting the clusters abilty to service I/O to some data. One or
+ more placement groups (PGs) are in a state that blocks IO.
+ - alert: CephPGBackfillAtRisk
+ expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.6
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full
+ summary: Backfill operations are blocked, due to lack of freespace
+ description: >
+ Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs
+ have breached their 'backfillfull' threshold. Add more capacity, or delete unwanted data.
+ - alert: CephPGNotScrubbed
+ expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed
+ summary: Placement group(s) have not been scrubbed
+ description: |
+ One or more PGs have not been scrubbed recently. The scrub process is a data integrity
+ feature, protectng against bit-rot. It checks that objects and their metadata (size and
+ attributes) match across object replicas. When PGs miss their scrub window, it may
+ indicate the scrub window is too small, or PGs were not in a 'clean' state during the
+ scrub window.
+
+ You can manually initiate a scrub with: ceph pg scrub <pgid>
+ - alert: CephPGsHighPerOSD
+ expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs
+ summary: Placement groups per OSD is too high
+ description: |
+ The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).
+
+ Check that the pg_autoscaler hasn't been disabled for any of the pools, with 'ceph osd pool autoscale-status'
+ and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide
+ the autoscaler based on the expected relative size of the pool
+ (i.e. 'ceph osd pool set cephfs.cephfs.meta target_size_ratio .1')
+ - alert: CephPGNotDeepScrubbed
+ expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed
+ summary: Placement group(s) have not been deep scrubbed
+ description: |
+ One or more PGs have not been deep scrubbed recently. Deep scrub is a data integrity
+ feature, protectng against bit-rot. It compares the contents of objects and their
+ replicas for inconsistency. When PGs miss their deep scrub window, it may indicate
+ that the window is too small or PGs were not in a 'clean' state during the deep-scrub
+ window.
+
+ You can manually initiate a deep scrub with: ceph pg deep-scrub <pgid>
+
+ - name: nodes
+ rules:
+ - alert: CephNodeRootFilesystemFull
+ expr: node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 5
+ for: 5m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.1
+ annotations:
+ summary: Root filesystem is dangerously full
+ description: >
+ Root volume (OSD and MON store) is dangerously full: {{ $value | humanize }}% free.
+
+ # alert on nic packet errors and drops rates > 1% packets/s
+ - alert: CephNodeNetworkPacketDrops
+ expr: |
+ (
+ increase(node_network_receive_drop_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_drop_total{device!="lo"}[1m])
+ ) / (
+ increase(node_network_receive_packets_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_packets_total{device!="lo"}[1m])
+ ) >= 0.0001 or (
+ increase(node_network_receive_drop_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_drop_total{device!="lo"}[1m])
+ ) >= 10
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.2
+ annotations:
+ summary: One or more Nics is seeing packet drops
+ description: >
+ Node {{ $labels.instance }} experiences packet drop > 0.01% or >
+ 10 packets/s on interface {{ $labels.device }}.
+
+ - alert: CephNodeNetworkPacketErrors
+ expr: |
+ (
+ increase(node_network_receive_errs_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_errs_total{device!="lo"}[1m])
+ ) / (
+ increase(node_network_receive_packets_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_packets_total{device!="lo"}[1m])
+ ) >= 0.0001 or (
+ increase(node_network_receive_errs_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_errs_total{device!="lo"}[1m])
+ ) >= 10
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.3
+ annotations:
+ summary: One or more Nics is seeing packet errors
+ description: >
+ Node {{ $labels.instance }} experiences packet errors > 0.01% or
+ > 10 packets/s on interface {{ $labels.device }}.
+
+ # Restrict to device names beginning with '/' to skip false alarms from
+ # tmpfs, overlay type filesystems
+ - alert: CephNodeDiskspaceWarning
+ expr: |
+ predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *
+ on(instance) group_left(nodename) node_uname_info < 0
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.4
+ annotations:
+ summary: Host filesystem freespace is getting low
+ description: >
+ Mountpoint {{ $labels.mountpoint }} on {{ $labels.nodename }}
+ will be full in less than 5 days assuming the average fill-up
+ rate of the past 48 hours.
+
+ - alert: CephNodeInconsistentMTU
+ expr: |
+ node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
+ scalar(
+ max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
+ quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
+ )
+ or
+ node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
+ scalar(
+ min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
+ quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
+ )
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: MTU settings across Ceph hosts are inconsistent
+ description: >
+ Node {{ $labels.instance }} has a different MTU size ({{ $value }})
+ than the median of devices named {{ $labels.device }}.
+
+ - name: pools
+ rules:
+ - alert: CephPoolGrowthWarning
+ expr: |
+ (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id)
+ group_right ceph_pool_metadata) >= 95
+ labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.9.2
+ annotations:
+ summary: Pool growth rate may soon exceed it's capacity
+ description: >
+ Pool '{{ $labels.name }}' will be full in less than 5 days
+ assuming the average fill-up rate of the past 48 hours.
+ - alert: CephPoolBackfillFull
+ expr: ceph_health_detail{name="POOL_BACKFILLFULL"} > 0
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: Freespace in a pool is too low for recovery/rebalance
+ description: >
+ A pool is approaching it's near full threshold, which will
+ prevent rebalance operations from completing. You should
+ consider adding more capacity to the pool.
+
+ - alert: CephPoolFull
+ expr: ceph_health_detail{name="POOL_FULL"} > 0
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.9.1
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full
+ summary: Pool is full - writes are blocked
+ description: |
+ A pool has reached it's MAX quota, or the OSDs supporting the pool
+ have reached their FULL threshold. Until this is resolved, writes to
+ the pool will be blocked.
+ Pool Breakdown (top 5)
+ {{- range query "topk(5, sort_desc(ceph_pool_percent_used * on(pool_id) group_right ceph_pool_metadata))" }}
+ - {{ .Labels.name }} at {{ .Value }}%
+ {{- end }}
+ Either increase the pools quota, or add capacity to the cluster first
+ then increase it's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
+ - alert: CephPoolNearFull
+ expr: ceph_health_detail{name="POOL_NEAR_FULL"} > 0
+ for: 5m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ summary: One or more Ceph pools are getting full
+ description: |
+ A pool has exceeeded it warning (percent full) threshold, or the OSDs
+ supporting the pool have reached their NEARFULL thresholds. Writes may
+ continue, but you are at risk of the pool going read only if more capacity
+ isn't made available.
+
+ Determine the affected pool with 'ceph df detail', for example looking
+ at QUOTA BYTES and STORED. Either increase the pools quota, or add
+ capacity to the cluster first then increase it's quota
+ (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
+ - name: healthchecks
+ rules:
+ - alert: CephSlowOps
+ expr: ceph_healthcheck_slow_ops > 0
+ for: 30s
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
+ summary: MON/OSD operations are slow to complete
+ description: >
+ {{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)
+# cephadm alerts
+ - name: cephadm
+ rules:
+ - alert: CephadmUpgradeFailed
+ expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0
+ for: 30s
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.11.2
+ annotations:
+ summary: Ceph version upgrade has failed
+ description: >
+ The cephadm cluster upgrade process has failed. The cluster remains in
+ an undetermined state.
+
+ Please review the cephadm logs, to understand the nature of the issue
+ - alert: CephadmDaemonFailed
+ expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0
+ for: 30s
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.11.1
+ annotations:
+ summary: A ceph daemon manged by cephadm is down
+ description: >
+ A daemon managed by cephadm is no longer active. Determine, which
+ daemon is down with 'ceph health detail'. you may start daemons with
+ the 'ceph orch daemon start <daemon_id>'
+ - alert: CephadmPaused
+ expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0
+ for: 1m
+ labels:
+ severity: warning
+ type: ceph_default
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused
+ summary: Orchestration tasks via cephadm are PAUSED
+ description: >
+ Cluster management has been paused manually. This will prevent the
+ orchestrator from service management and reconciliation. If this is
+ not intentional, resume cephadm operations with 'ceph orch resume'
+
+# prometheus alerts
+ - name: PrometheusServer
+ rules:
+ - alert: PrometheusJobMissing
+ expr: absent(up{job="ceph"})
+ for: 30s
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.12.1
+ annotations:
+ summary: The scrape job for Ceph is missing from Prometheus
+ description: |
+ The prometheus job that scrapes from Ceph is no longer defined, this
+ will effectively mean you'll have no metrics or alerts for the cluster.
+
+ Please review the job definitions in the prometheus.yml file of the prometheus
+ instance.
+# Object related events
+ - name: rados
+ rules:
+ - alert: CephObjectMissing
+ expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1
+ for: 30s
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.10.1
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound
+ summary: Object(s) has been marked UNFOUND
+ description: |
+ A version of a RADOS object can not be found, even though all OSDs are up. I/O
+ requests for this object from clients will block (hang). Resolving this issue may
+ require the object to be rolled back to a prior version manually, and manually verified.
+# Generic
+ - name: generic
+ rules:
+ - alert: CephDaemonCrash
+ expr: ceph_health_detail{name="RECENT_CRASH"} == 1
+ for: 1m
+ labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.1.2
+ annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash
+ summary: One or more Ceph daemons have crashed, and are pending acknowledgement
+ description: |
+ One or more daemons have crashed recently, and need to be acknowledged. This notification
+ ensures that software crashes don't go unseen. To acknowledge a crash, use the
+ 'ceph crash archive <id>' command.
--- /dev/null
+pyyaml==6.0
+bs4
--- /dev/null
+attrs==21.2.0
+behave==1.2.6
+py==1.10.0
+pyparsing==2.4.7
+PyYAML==6.0
+types-PyYAML==6.0.0
+typing-extensions==3.10.0.2
+termcolor==1.1.0
+types-termcolor==1.1.2
+dataclasses==0.6
+types-dataclasses==0.6.1
+six==1.16.0
+toml==0.10.2
+pylint==2.6.0
+isort==5.10.0
+mypy==0.910
+mypy-extensions==0.4.3
+prettytable==2.4.0
--- /dev/null
+#!/bin/sh -e
+
+TEMPDIR=$(mktemp -d)
+BASEDIR=$(dirname "$0")
+
+jsonnet -J vendor -m ${TEMPDIR} $BASEDIR/dashboards.jsonnet
+
+truncate -s 0 ${TEMPDIR}/json_difference.log
+for file in ${BASEDIR}/dashboards_out/*.json
+do
+ file_name="$(basename $file)"
+ for generated_file in ${TEMPDIR}/*.json
+ do
+ generated_file_name="$(basename $generated_file)"
+ if [ "$file_name" == "$generated_file_name" ]; then
+ jsondiff --indent 2 "${generated_file}" "${file}" \
+ | tee -a ${TEMPDIR}/json_difference.log
+ fi
+ done
+done
+
+err=0
+if [ $(wc -l < ${TEMPDIR}/json_difference.log) -eq 0 ]
+then
+ rm -rf ${TEMPDIR}
+ echo "Congratulations! Grafonnet Check Passed"
+else
+ rm -rf ${TEMPDIR}
+ echo "Grafonnet Check Failed, failed comparing generated file with existing"
+ exit 1
+fi
--- /dev/null
+
+## Alert Rule Standards
+
+The alert rules should adhere to the following principles
+- each alert must have a unique name
+- each alert should define a common structure
+ - labels : must contain severity and type
+ - annotations : must provide description
+ - expr : must define the promql expression
+ - alert : defines the alert name
+- alerts that have a corresponding section within docs.ceph.com must include a
+ documentation field in the annotations section
+- critical alerts should declare an oid in the labels section
+- critical alerts should have a corresponding entry in the Ceph MIB
+
+
+## Testing Prometheus Rules
+Once you have updated the `ceph_default_alerts.yml` file, you should use the
+`validate_rules.py` script directly, or via `tox` to ensure the format of any update
+or change aligns to our rule structure guidelines. The validate_rules.py script will
+process the rules and look for any configuration anomalies and output a report if
+problems are detected.
+
+Here's an example run, to illustrate the format and the kinds of issues detected.
+
+```
+[paul@myhost tests]$ ./validate_rules.py
+
+Checking rule groups
+ cluster health : ..
+ mon : E.W..
+ osd : E...W......W.E..
+ mds : WW
+ mgr : WW
+ pgs : ..WWWW..
+ nodes : .EEEE
+ pools : EEEW.
+ healthchecks : .
+ cephadm : WW.
+ prometheus : W
+ rados : W
+
+Summary
+
+Rule file : ../alerts/ceph_default_alerts.yml
+Unit Test file : test_alerts.yml
+
+Rule groups processed : 12
+Rules processed : 51
+Rule errors : 10
+Rule warnings : 16
+Rule name duplicates : 0
+Unit tests missing : 4
+
+Problem Report
+
+ Group Severity Alert Name Problem Description
+ ----- -------- ---------- -------------------
+ cephadm Warning Cluster upgrade has failed critical level alert is missing an SNMP oid entry
+ cephadm Warning A daemon managed by cephadm is down critical level alert is missing an SNMP oid entry
+ mds Warning Ceph Filesystem damage detected critical level alert is missing an SNMP oid entry
+ mds Warning Ceph Filesystem switched to READ ONLY critical level alert is missing an SNMP oid entry
+ mgr Warning mgr module failure critical level alert is missing an SNMP oid entry
+ mgr Warning mgr prometheus module is not active critical level alert is missing an SNMP oid entry
+ mon Error Monitor down, quorum is at risk documentation link error: #mon-downwah not found on the page
+ mon Warning Ceph mon disk space critically low critical level alert is missing an SNMP oid entry
+ nodes Error network packets dropped invalid alert structure. Missing field: for
+ nodes Error network packet errors invalid alert structure. Missing field: for
+ nodes Error storage filling up invalid alert structure. Missing field: for
+ nodes Error MTU Mismatch invalid alert structure. Missing field: for
+ osd Error 10% OSDs down invalid alert structure. Missing field: for
+ osd Error Flapping OSD invalid alert structure. Missing field: for
+ osd Warning OSD Full critical level alert is missing an SNMP oid entry
+ osd Warning Too many devices predicted to fail critical level alert is missing an SNMP oid entry
+ pgs Warning Placement Group (PG) damaged critical level alert is missing an SNMP oid entry
+ pgs Warning Recovery at risk, cluster too full critical level alert is missing an SNMP oid entry
+ pgs Warning I/O blocked to some data critical level alert is missing an SNMP oid entry
+ pgs Warning Cluster too full, automatic data recovery impaired critical level alert is missing an SNMP oid entry
+ pools Error pool full invalid alert structure. Missing field: for
+ pools Error pool filling up (growth forecast) invalid alert structure. Missing field: for
+ pools Error Ceph pool is too full for recovery/rebalance invalid alert structure. Missing field: for
+ pools Warning Ceph pool is full - writes blocked critical level alert is missing an SNMP oid entry
+ prometheus Warning Scrape job is missing critical level alert is missing an SNMP oid entry
+ rados Warning Data not found/missing critical level alert is missing an SNMP oid entry
+
+Unit tests are incomplete. Tests missing for the following alerts;
+ - Placement Group (PG) damaged
+ - OSD Full
+ - storage filling up
+ - pool filling up (growth forecast)
+
+```
--- /dev/null
+import os
+
+ALERTS_FILE = '../prometheus_alerts.yaml'
+UNIT_TESTS_FILE = 'test_alerts.yml'
+MIB_FILE = '../../snmp/CEPH-MIB.txt'
+
+current_dir = os.path.dirname(os.path.abspath(__file__))
+
+ALERTS_FILE = os.path.join(current_dir, ALERTS_FILE)
+UNIT_TESTS_FILE = os.path.join(current_dir, UNIT_TESTS_FILE)
+MIB_FILE = os.path.join(current_dir, MIB_FILE)
--- /dev/null
+rule_files:
+ - ../prometheus_alerts.yaml
+evaluation_interval: 5m
+tests:
+ # health error
+ - interval: 5m
+ input_series:
+ - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
+ values: '2 2 2 2 2 2 2'
+ promql_expr_test:
+ - expr: ceph_health_status == 2
+ eval_time: 5m
+ exp_samples:
+ - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
+ value: 2
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephHealthError
+ - eval_time: 6m
+ alertname: CephHealthError
+ exp_alerts:
+ - exp_labels:
+ instance: ceph:9283
+ job: ceph
+ oid: 1.3.6.1.4.1.50495.1.2.1.2.1
+ type: ceph_default
+ severity: critical
+ exp_annotations:
+ summary: Cluster is in an ERROR state
+ description: >
+ Ceph in HEALTH_ERROR state for more than 5 minutes.
+ Please check "ceph health detail" for more information.
+
+ # health warning
+ - interval: 5m
+ input_series:
+ - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
+ values: '1 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_status == 1
+ eval_time: 15m
+ exp_samples:
+ - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 10m
+ alertname: CephHealthWarning
+ - eval_time: 20m
+ alertname: CephHealthWarning
+ exp_alerts:
+ - exp_labels:
+ instance: ceph:9283
+ job: ceph
+ type: ceph_default
+ severity: warning
+ exp_annotations:
+ summary: Cluster is in a WARNING state
+ description: >
+ Ceph has been in HEALTH_WARN for more than 15 minutes.
+ Please check "ceph health detail" for more information.
+
+ # 10% OSDs down
+ - interval: 1m
+ input_series:
+ - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
+ values: '1 1 1 1 1'
+ - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
+ values: '0 0 0 0 0'
+ - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
+ values: '1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1'
+ promql_expr_test:
+ - expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10
+ eval_time: 1m
+ exp_samples:
+ - labels: '{}'
+ value: 3.333333333333333E+01
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDDownHigh
+ exp_alerts:
+ - exp_labels:
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.1
+ type: ceph_default
+ severity: critical
+ exp_annotations:
+ summary: More than 10% of OSDs are down
+ description: |
+ 33.33% or 1 of 3 OSDs are down (>= 10%).
+
+ The following OSDs are down:
+ - osd.1 on ceph
+
+ # flapping OSD
+ - interval: 1s
+ input_series:
+ - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
+ values: '1+1x100'
+ - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
+ values: '1+0x100'
+ - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
+ values: '1+0x100'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: |
+ (
+ rate(ceph_osd_up[5m])
+ * on(ceph_daemon) group_left(hostname) ceph_osd_metadata
+ ) * 60 > 1
+ eval_time: 1m
+ exp_samples:
+ - labels: '{ceph_daemon="osd.0", hostname="ceph", instance="ceph:9283",
+ job="ceph"}'
+ value: 1.2200000000000001E+01
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: CephOSDFlapping
+ exp_alerts:
+ - exp_labels:
+ ceph_daemon: osd.0
+ hostname: ceph
+ instance: ceph:9283
+ job: ceph
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.4
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds
+ summary: Network issues are causing OSD's to flap (mark each other out)
+ description: >
+ OSD osd.0 on ceph was
+ marked down and back up at 20.1 times once a minute for 5 minutes.
+ This could indicate a network issue (latency, packet drop, disruption)
+ on the clusters "cluster network". Check the network environment on the
+ listed host(s).
+
+ # high pg count deviation
+ - interval: 1m
+ input_series:
+ - series: 'ceph_osd_numpg{ceph_daemon="osd.0",instance="ceph:9283",
+ job="ceph"}'
+ values: '100 100 100 100 100 160'
+ - series: 'ceph_osd_numpg{ceph_daemon="osd.1",instance="ceph:9283",
+ job="ceph"}'
+ values: '100 100 100 100 100 320'
+ - series: 'ceph_osd_numpg{ceph_daemon="osd.2",instance="ceph:9283",
+ job="ceph"}'
+ values: '100 100 100 100 100 160'
+ - series: 'ceph_osd_numpg{ceph_daemon="osd.3",instance="ceph:9283",
+ job="ceph"}'
+ values: '100 100 100 100 100 160'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.3",
+ ceph_version="ceph version 17.0.0-189-g3558fd72
+ (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
+ cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
+ hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
+ public_addr="172.20.0.2"}'
+ values: '1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: |
+ abs(
+ (
+ (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0)
+ by (job)
+ ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)
+ ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30
+
+ eval_time: 5m
+ exp_samples:
+ - labels: '{ceph_daemon="osd.1", hostname="ceph", instance="ceph:9283",
+ job="ceph"}'
+ value: 6E-01
+ alert_rule_test:
+ - eval_time: 10m
+ alertname: CephPGImbalance
+ exp_alerts:
+ - exp_labels:
+ ceph_daemon: osd.1
+ hostname: ceph
+ instance: ceph:9283
+ job: ceph
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.5
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: PG allocations are not balanced across devices
+ description: >
+ OSD osd.1 on ceph deviates
+ by more than 30% from average PG count.
+
+ # pgs inactive
+ - interval: 1m
+ input_series:
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="2"}'
+ values: '1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="3"}'
+ values: '1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
+ values: '32 32 32 32 32 32 32 32'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
+ values: '33 32 32 32 32 33 33 32'
+ - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="2"}'
+ values: '32 32 32 32 32 32 32 32'
+ - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="3"}'
+ values: '32 32 32 32 32 32 32 32'
+ promql_expr_test:
+ - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
+ (ceph_pg_total - ceph_pg_active) > 0
+ eval_time: 5m
+ exp_samples:
+ - labels: '{instance="ceph:9283", job="ceph",
+ name="device_health_metrics",
+ pool_id="3"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: CephPGsInactive
+ exp_alerts:
+ - exp_labels:
+ instance: ceph:9283
+ job: ceph
+ name: device_health_metrics
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.1
+ pool_id: 3
+ severity: critical
+ type: ceph_default
+ exp_annotations:
+ summary: One or more Placement Groups are inactive
+ description: >
+ 1 PGs have been inactive for more than 5 minutes in pool
+ device_health_metrics.
+ Inactive placement groups aren't able to serve read/write
+ requests.
+
+ #pgs unclean
+ - interval: 1m
+ input_series:
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="2"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="device_health_metrics",pool_id="3"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
+ values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
+ 32 32 32'
+ - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
+ values: '33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33
+ 33 33'
+ - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="2"}'
+ values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
+ 32 32'
+ - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="3"}'
+ values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
+ 32 32'
+ promql_expr_test:
+ - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
+ (ceph_pg_total - ceph_pg_clean) > 0
+ eval_time: 15m
+ exp_samples:
+ - labels: '{instance="ceph:9283", job="ceph",
+ name="device_health_metrics", pool_id="3"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 16m
+ alertname: CephPGsUnclean
+ exp_alerts:
+ - exp_labels:
+ instance: ceph:9283
+ job: ceph
+ name: device_health_metrics
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.2
+ pool_id: 3
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: One or more platcment groups are marked unclean
+ description: >
+ 1 PGs haven't been clean for more than 15 minutes in pool
+ device_health_metrics.
+ Unclean PGs haven't been able to completely recover from a
+ previous failure.
+
+ # root volume full
+ - interval: 1m
+ input_series:
+ - series: 'node_filesystem_avail_bytes{device="/dev/mapper/fedora_localhost
+ --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
+ mountpoint="/"}'
+ values: '35336400896 35336400896 35336400896 35336400896 35336400896
+ 3525385519.104 3533640089'
+ - series: 'node_filesystem_size_bytes{device="/dev/mapper/fedora_localhost
+ --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
+ mountpoint="/"}'
+ values: '73445531648 73445531648 73445531648 73445531648 73445531648
+ 73445531648 73445531648'
+ promql_expr_test:
+ - expr: node_filesystem_avail_bytes{mountpoint="/"} /
+ node_filesystem_size_bytes{mountpoint="/"} * 100 < 5
+ eval_time: 5m
+ exp_samples:
+ - labels: '{device="/dev/mapper/fedora_localhost --live-home",
+ fstype="ext4", instance="node-exporter", job="node-exporter",
+ mountpoint="/"}'
+ value: 4.8E+00
+ alert_rule_test:
+ - eval_time: 10m
+ alertname: CephNodeRootFilesystemFull
+ exp_alerts:
+ - exp_labels:
+ device: /dev/mapper/fedora_localhost --live-home
+ fstype: ext4
+ instance: node-exporter
+ job: node-exporter
+ mountpoint: /
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.1
+ severity: critical
+ type: ceph_default
+ exp_annotations:
+ summary: Root filesystem is dangerously full
+ description: >
+ Root volume (OSD and MON store) is dangerously full: 4.811% free.
+
+ # network packets dropped
+ - interval: 1s
+ input_series:
+ - series: 'node_network_receive_drop_total{device="eth0",
+ instance="node-exporter",job="node-exporter"}'
+ values: '1+1x500'
+ - series: 'node_network_transmit_drop_total{device="eth0",
+ instance="node-exporter",job="node-exporter"}'
+ values: '1+1x500'
+ promql_expr_test:
+ - expr: |
+ (
+ increase(node_network_receive_drop_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_drop_total{device!="lo"}[1m])
+ ) / (
+ increase(node_network_receive_packets_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_packets_total{device!="lo"}[1m])
+ ) >= 0.0001 or (
+ increase(node_network_receive_drop_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_drop_total{device!="lo"}[1m])
+ ) >= 10
+
+ eval_time: 5m
+ exp_samples:
+ - labels: '{device="eth0", instance="node-exporter",
+ job="node-exporter"}'
+ value: 1.2E+02
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: CephNodeNetworkPacketDrops
+ exp_alerts:
+ - exp_labels:
+ device: eth0
+ instance: node-exporter
+ job: node-exporter
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.2
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: One or more Nics is seeing packet drops
+ description: >
+ Node node-exporter experiences packet drop > 0.01% or >
+ 10 packets/s on interface eth0.
+
+ # network packets errors
+ - interval: 1s
+ input_series:
+ - series: 'node_network_receive_errs_total{device="eth0",
+ instance="node-exporter",job="node-exporter"}'
+ values: '1+1x500'
+ - series: 'node_network_transmit_errs_total{device="eth0",
+ instance="node-exporter",job="node-exporter"}'
+ values: '1+1x500'
+ promql_expr_test:
+ - expr: |
+ (
+ increase(node_network_receive_errs_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_errs_total{device!="lo"}[1m])
+ ) / (
+ increase(node_network_receive_packets_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_packets_total{device!="lo"}[1m])
+ ) >= 0.0001 or (
+ increase(node_network_receive_errs_total{device!="lo"}[1m]) +
+ increase(node_network_transmit_errs_total{device!="lo"}[1m])
+ ) >= 10
+
+ eval_time: 5m
+ exp_samples:
+ - labels: '{device="eth0", instance="node-exporter",
+ job="node-exporter"}'
+ value: 1.2E+02
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: CephNodeNetworkPacketErrors
+ exp_alerts:
+ - exp_labels:
+ device: eth0
+ instance: node-exporter
+ job: node-exporter
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.3
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: One or more Nics is seeing packet errors
+ description: >
+ Node node-exporter experiences packet errors > 0.01% or > 10
+ packets/s on interface eth0.
+
+# Node Storage disk space filling up
+ - interval: 1m
+ # 20GB = 21474836480, 256MB = 268435456
+ input_series:
+ - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
+ fstype="xfs",instance="node-1",mountpoint="/rootfs"}'
+ values: '21474836480-268435456x48'
+ - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
+ fstype="xfs",instance="node-2",mountpoint="/rootfs"}'
+ values: '21474836480+0x48'
+ - series: 'node_uname_info{instance="node-1", nodename="node-1.unittests.com"}'
+ values: 1+0x48
+ - series: 'node_uname_info{instance="node-2", nodename="node-2.unittests.com"}'
+ values: 1+0x48
+ promql_expr_test:
+ - expr: |
+ predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *
+ on(instance) group_left(nodename) node_uname_info < 0
+ eval_time: 5m
+ exp_samples:
+ - labels: '{device="/dev/mapper/vg-root",instance="node-1",fstype="xfs",
+ mountpoint="/rootfs",nodename="node-1.unittests.com"}'
+ value: -1.912602624E+12
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: CephNodeDiskspaceWarning
+ exp_alerts:
+ - exp_labels:
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.8.4
+ device: /dev/mapper/vg-root
+ fstype: xfs
+ instance: node-1
+ mountpoint: /rootfs
+ nodename: node-1.unittests.com
+ exp_annotations:
+ summary: Host filesystem freespace is getting low
+ description: >
+ Mountpoint /rootfs on node-1.unittests.com
+ will be full in less than 5 days assuming the average fill-up
+ rate of the past 48 hours.
+ # MTU Mismatch
+ - interval: 1m
+ input_series:
+ - series: 'node_network_mtu_bytes{device="eth0",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1500 1500 1500 1500 1500'
+ - series: 'node_network_mtu_bytes{device="eth1",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1500 1500 1500 1500 1500'
+ - series: 'node_network_mtu_bytes{device="eth2",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1500 1500 1500 1500 1500'
+ - series: 'node_network_mtu_bytes{device="eth3",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1500 1500 1500 1500 1500'
+ - series: 'node_network_mtu_bytes{device="eth4",instance="node-exporter",
+ job="node-exporter"}'
+ values: '9000 9000 9000 9000 9000'
+ - series: 'node_network_mtu_bytes{device="eth4",instance="hostname1",
+ job="node-exporter"}'
+ values: '2200 2200 2200 2200 2200'
+ - series: 'node_network_mtu_bytes{device="eth4",instance="hostname2",
+ job="node-exporter"}'
+ values: '2400 2400 2400 2400 2400'
+ - series: 'node_network_up{device="eth0",instance="node-exporter",
+ job="node-exporter"}'
+ values: '0 0 0 0 0'
+ - series: 'node_network_up{device="eth1",instance="node-exporter",
+ job="node-exporter"}'
+ values: '0 0 0 0 0'
+ - series: 'node_network_up{device="eth2",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1 1 1 1 1'
+ - series: 'node_network_up{device="eth3",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1 1 1 1 1'
+ - series: 'node_network_up{device="eth4",instance="node-exporter",
+ job="node-exporter"}'
+ values: '1 1 1 1 1'
+ - series: 'node_network_up{device="eth4",instance="hostname1",
+ job="node-exporter"}'
+ values: '1 1 1 1 1'
+ - series: 'node_network_up{device="eth4",instance="hostname2",
+ job="node-exporter"}'
+ values: '0 0 0 0 0'
+ promql_expr_test:
+ - expr: |
+ node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
+ scalar(
+ max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
+ quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
+ )
+ or
+ node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
+ scalar(
+ min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
+ quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
+ )
+ eval_time: 1m
+ exp_samples:
+ - labels: '{device="eth4", instance="node-exporter", job="node-exporter"}'
+ value: 9000
+ - labels: '{device="eth4", instance="hostname1", job="node-exporter"}'
+ value: 2200
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephNodeInconsistentMTU
+ exp_alerts:
+ - exp_labels:
+ device: eth4
+ instance: hostname1
+ job: node-exporter
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: MTU settings across Ceph hosts are inconsistent
+ description: >
+ Node hostname1 has a different MTU size (2200)
+ than the median of devices named eth4.
+ - exp_labels:
+ device: eth4
+ instance: node-exporter
+ job: node-exporter
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: MTU settings across Ceph hosts are inconsistent
+ description: >
+ Node node-exporter has a different MTU size (9000)
+ than the median of devices named eth4.
+
+ # pool full, data series has 6 but using topk(5) so to ensure the
+ # results are working as expected
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="POOL_FULL"}'
+ values: '0 0 0 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_percent_used{pool_id="1"}'
+ values: '32+0x10'
+ - series: 'ceph_pool_percent_used{pool_id="2"}'
+ values: '96+0x10'
+ - series: 'ceph_pool_percent_used{pool_id="3"}'
+ values: '90+0x10'
+ - series: 'ceph_pool_percent_used{pool_id="4"}'
+ values: '72+0x10'
+ - series: 'ceph_pool_percent_used{pool_id="5"}'
+ values: '19+0x10'
+ - series: 'ceph_pool_percent_used{pool_id="6"}'
+ values: '10+0x10'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="cephfs_data",pool_id="1"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="rbd",pool_id="2"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="iscsi",pool_id="3"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="default.rgw.index",pool_id="4"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="default.rgw.log",pool_id="5"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
+ name="dummy",pool_id="6"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="POOL_FULL"} > 0
+ eval_time: 5m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="POOL_FULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPoolFull
+ - eval_time: 10m
+ alertname: CephPoolFull
+ exp_alerts:
+ - exp_labels:
+ name: POOL_FULL
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.9.1
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full
+ summary: Pool is full - writes are blocked
+ description: |
+ A pool has reached it's MAX quota, or the OSDs supporting the pool
+ have reached their FULL threshold. Until this is resolved, writes to
+ the pool will be blocked.
+ Pool Breakdown (top 5)
+ - rbd at 96%
+ - iscsi at 90%
+ - default.rgw.index at 72%
+ - cephfs_data at 32%
+ - default.rgw.log at 19%
+ Either increase the pools quota, or add capacity to the cluster first
+ then increase it's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
+ # slow OSD ops
+ - interval : 1m
+ input_series:
+ - series: 'ceph_healthcheck_slow_ops{instance="ceph:9283",job="ceph"}'
+ values: '1+0x120'
+ promql_expr_test:
+ - expr: ceph_healthcheck_slow_ops > 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_healthcheck_slow_ops", instance="ceph:9283",
+ job="ceph"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 20m
+ alertname: CephSlowOps
+ exp_alerts:
+ - exp_labels:
+ instance: ceph:9283
+ job: ceph
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
+ summary: MON/OSD operations are slow to complete
+ description: >
+ 1 OSD requests are taking too long to process
+ (osd_op_complaint_time exceeded)
+
+# CEPHADM orchestrator alert triggers
+ - interval: 30s
+ input_series:
+ - series: 'ceph_health_detail{name="UPGRADE_EXCEPTION"}'
+ values: '1+0x40'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="UPGRADE_EXCEPTION"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephadmUpgradeFailed
+ - eval_time: 5m
+ alertname: CephadmUpgradeFailed
+ exp_alerts:
+ - exp_labels:
+ name: UPGRADE_EXCEPTION
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.11.2
+ exp_annotations:
+ summary: Ceph version upgrade has failed
+ description: >
+ The cephadm cluster upgrade process has failed. The cluster remains in
+ an undetermined state.
+
+ Please review the cephadm logs, to understand the nature of the issue
+ - interval: 30s
+ input_series:
+ - series: 'ceph_health_detail{name="CEPHADM_FAILED_DAEMON"}'
+ values: '1+0x40'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="CEPHADM_FAILED_DAEMON"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephadmDaemonFailed
+ - eval_time: 5m
+ alertname: CephadmDaemonFailed
+ exp_alerts:
+ - exp_labels:
+ name: CEPHADM_FAILED_DAEMON
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.11.1
+ exp_annotations:
+ summary: A ceph daemon manged by cephadm is down
+ description: >
+ A daemon managed by cephadm is no longer active. Determine, which
+ daemon is down with 'ceph health detail'. you may start daemons with
+ the 'ceph orch daemon start <daemon_id>'
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="CEPHADM_PAUSED"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="CEPHADM_PAUSED"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephadmPaused
+ - eval_time: 5m
+ alertname: CephadmPaused
+ exp_alerts:
+ - exp_labels:
+ name: CEPHADM_PAUSED
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused
+ summary: Orchestration tasks via cephadm are PAUSED
+ description: >
+ Cluster management has been paused manually. This will prevent the
+ orchestrator from service management and reconciliation. If this is
+ not intentional, resume cephadm operations with 'ceph orch resume'
+# MDS
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MDS_DAMAGE"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MDS_DAMAGE"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MDS_DAMAGE"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemDamaged
+ - eval_time: 5m
+ alertname: CephFilesystemDamaged
+ exp_alerts:
+ - exp_labels:
+ name: MDS_DAMAGE
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.1
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
+ summary: Ceph filesystem is damaged.
+ description: >
+ The filesystems metadata has been corrupted. Data access
+ may be blocked.
+
+ Either analyse the output from the mds daemon admin socket, or
+ escalate to support
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MDS_HEALTH_READ_ONLY"}'
+ values: '1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MDS_HEALTH_READ_ONLY"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemReadOnly
+ - eval_time: 5m
+ alertname: CephFilesystemReadOnly
+ exp_alerts:
+ - exp_labels:
+ name: MDS_HEALTH_READ_ONLY
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.2
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
+ summary: Ceph filesystem in read only mode, due to write error(s)
+ description: >
+ The filesystem has switched to READ ONLY due to an unexpected
+ write error, when writing to the metadata pool
+
+ Either analyse the output from the mds daemon admin socket, or
+ escalate to support
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MDS_ALL_DOWN"}'
+ values: '0 0 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MDS_ALL_DOWN"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemOffline
+ - eval_time: 10m
+ alertname: CephFilesystemOffline
+ exp_alerts:
+ - exp_labels:
+ name: MDS_ALL_DOWN
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.3
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down
+ summary: Ceph filesystem is offline
+ description: >
+ All MDS ranks are unavailable. The ceph daemons providing the metadata
+ for the Ceph filesystem are all down, rendering the filesystem offline.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="FS_DEGRADED"}'
+ values: '0 0 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="FS_DEGRADED"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="FS_DEGRADED"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemDegraded
+ - eval_time: 10m
+ alertname: CephFilesystemDegraded
+ exp_alerts:
+ - exp_labels:
+ name: FS_DEGRADED
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.4
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded
+ summary: Ceph filesystem is degraded
+ description: >
+ One or more metdata daemons (MDS ranks) are failed or in a
+ damaged state. At best the filesystem is partially available,
+ worst case is the filesystem is completely unusable.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"}'
+ values: '0 0 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MDS_INSUFFICIENT_STANDBY"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemInsufficientStandby
+ - eval_time: 10m
+ alertname: CephFilesystemInsufficientStandby
+ exp_alerts:
+ - exp_labels:
+ name: MDS_INSUFFICIENT_STANDBY
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby
+ summary: Ceph filesystem standby daemons too low
+ description: >
+ The minimum number of standby daemons determined by standby_count_wanted
+ is less than the actual number of standby daemons. Adjust the standby count
+ or increase the number of mds daemons within the filesystem.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="FS_WITH_FAILED_MDS"}'
+ values: '0 0 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="FS_WITH_FAILED_MDS"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemFailureNoStandby
+ - eval_time: 10m
+ alertname: CephFilesystemFailureNoStandby
+ exp_alerts:
+ - exp_labels:
+ name: FS_WITH_FAILED_MDS
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.5.5
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds
+ summary: Ceph MDS daemon failed, no further standby available
+ description: >
+ An MDS daemon has failed, leaving only one active rank without
+ further standby. Investigate the cause of the failure or add a
+ standby daemon
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"}'
+ values: '0 0 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0
+ eval_time: 2m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MDS_UP_LESS_THAN_MAX"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephFilesystemMDSRanksLow
+ - eval_time: 10m
+ alertname: CephFilesystemMDSRanksLow
+ exp_alerts:
+ - exp_labels:
+ name: MDS_UP_LESS_THAN_MAX
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max
+ summary: Ceph MDS daemon count is lower than configured
+ description: >
+ The filesystem's "max_mds" setting defined the number of MDS ranks in
+ the filesystem. The current number of active MDS daemons is less than
+ this setting.
+# MGR
+ - interval: 1m
+ input_series:
+ - series: 'up{job="ceph", instance="ceph-mgr:9283"}'
+ values: '1+0x2 0+0x10'
+ promql_expr_test:
+ - expr: up{job="ceph"} == 0
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="up", job="ceph", instance="ceph-mgr:9283"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMgrPrometheusModuleInactive
+ - eval_time: 10m
+ alertname: CephMgrPrometheusModuleInactive
+ exp_alerts:
+ - exp_labels:
+ instance: ceph-mgr:9283
+ job: ceph
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.6.2
+ exp_annotations:
+ summary: Ceph's mgr/prometheus module is not available
+ description: >
+ The mgr/prometheus module at ceph-mgr:9283 is unreachable. This
+ could mean that the module has been disabled or the mgr itself is down.
+
+ Without the mgr/prometheus module metrics and alerts will no longer
+ function. Open a shell to ceph and use 'ceph -s' to to determine whether the
+ mgr is active. If the mgr is not active, restart it, otherwise you can check
+ the mgr/prometheus module is loaded with 'ceph mgr module ls' and if it's
+ not listed as enabled, enable it with 'ceph mgr module enable prometheus'
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="RECENT_MGR_MODULE_CRASH"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMgrModuleCrash
+ - eval_time: 15m
+ alertname: CephMgrModuleCrash
+ exp_alerts:
+ - exp_labels:
+ name: RECENT_MGR_MODULE_CRASH
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.6.1
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash
+ summary: A mgr module has recently crashed
+ description: >
+ One or more mgr modules have crashed and are yet to be acknowledged by the administrator. A
+ crashed module may impact functionality within the cluster. Use the 'ceph crash' commands to
+ investigate which module has failed, and archive it to acknowledge the failure.
+# MON
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MON_DISK_CRIT"}'
+ values: '0+0x2 1+0x10'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
+ values: '1+0x13'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MON_DISK_CRIT"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMonDiskspaceCritical
+ - eval_time: 10m
+ alertname: CephMonDiskspaceCritical
+ exp_alerts:
+ - exp_labels:
+ name: "MON_DISK_CRIT"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.3.2
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit
+ summary: Disk space on at least one monitor is critically low
+ description: |
+ The free space available to a monitor's store is critically low (<5% by default).
+ You should increase the space available to the monitor(s). The
+ default location for the store sits under /var/lib/ceph. Your monitor hosts are;
+ - ceph-mon-a
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MON_DISK_LOW"}'
+ values: '0+0x2 1+0x10'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
+ values: '1+0x13'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MON_DISK_LOW"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MON_DISK_LOW"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMonDiskspaceLow
+ - eval_time: 10m
+ alertname: CephMonDiskspaceLow
+ exp_alerts:
+ - exp_labels:
+ name: "MON_DISK_LOW"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low
+ summary: Disk space on at least one monitor is approaching full
+ description: |
+ The space available to a monitor's store is approaching full (>70% is the default).
+ You should increase the space available to the monitor store. The
+ default location for the store sits under /var/lib/ceph. Your monitor hosts are;
+ - ceph-mon-a
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MON_CLOCK_SKEW"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="MON_CLOCK_SKEW"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMonClockSkew
+ - eval_time: 10m
+ alertname: CephMonClockSkew
+ exp_alerts:
+ - exp_labels:
+ name: "MON_CLOCK_SKEW"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew
+ summary: Clock skew across the Monitor hosts detected
+ description: |
+ The ceph monitors rely on a consistent time reference to maintain
+ quorum and cluster consistency. This event indicates that at least
+ one of your mons is not sync'd correctly.
+
+ Review the cluster status with ceph -s. This will show which monitors
+ are affected. Check the time sync status on each monitor host.
+
+# Check 3 mons one down, quorum at risk
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="MON_DOWN"}'
+ values: '0+0x2 1+0x12'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
+ values: '1+0x2 0+0x12'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
+ values: '1+0x14'
+ promql_expr_test:
+ - expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMonDownQuorumAtRisk
+ # shouldn't fire
+ - eval_time: 10m
+ alertname: CephMonDownQuorumAtRisk
+ exp_alerts:
+ - exp_labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.3.1
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
+ summary: Monitor quorum is at risk
+ description: |
+ Quorum requires a majority of monitors (x 2) to be active
+ Without quorum the cluster will become inoperable, affecting all connected clients and services.
+
+ The following monitors are down:
+ - mon.c on ceph-mon-3
+# check 5 mons, 1 down - warning only
+ - interval: 1m
+ input_series:
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.d"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_quorum_status{ceph_daemon="mon.e"}'
+ values: '1+0x2 0+0x12'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.d", hostname="ceph-mon-4"}'
+ values: '1+0x14'
+ - series: 'ceph_mon_metadata{ceph_daemon="mon.e", hostname="ceph-mon-5"}'
+ values: '1+0x14'
+ promql_expr_test:
+ - expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1))
+ eval_time: 3m
+ exp_samples:
+ - labels: '{}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephMonDown
+ - eval_time: 10m
+ alertname: CephMonDown
+ exp_alerts:
+ - exp_labels:
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
+ summary: One of more ceph monitors are down
+ description: |
+ You have 1 monitor down.
+ Quorum is still intact, but the loss of further monitors will make your cluster inoperable.
+
+ The following monitors are down:
+ - mon.e on ceph-mon-5
+# Device Health
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="DEVICE_HEALTH"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephDeviceFailurePredicted
+ - eval_time: 10m
+ alertname: CephDeviceFailurePredicted
+ exp_alerts:
+ - exp_labels:
+ name: "DEVICE_HEALTH"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2
+ summary: Device(s) have been predicted to fail soon
+ description: |
+ The device health module has determined that one or more devices will fail
+ soon. To review the device states use 'ceph device ls'. To show a specific
+ device use 'ceph device info <dev id>'.
+
+ Mark the OSD as out (so data may migrate to other OSDs in the cluster). Once
+ the osd is empty remove and replace the OSD.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_TOOMANY"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephDeviceFailurePredictionTooHigh
+ - eval_time: 10m
+ alertname: CephDeviceFailurePredictionTooHigh
+ exp_alerts:
+ - exp_labels:
+ name: "DEVICE_HEALTH_TOOMANY"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.7
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany
+ summary: Too many devices have been predicted to fail, unable to resolve
+ description: |
+ The device health module has determined that the number of devices predicted to
+ fail can not be remediated automatically, since it would take too many osd's out of
+ the cluster, impacting performance and potentially availabililty. You should add new
+ OSDs to the cluster to allow data to be relocated to avoid the data integrity issues.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="DEVICE_HEALTH_IN_USE"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_IN_USE"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephDeviceFailureRelocationIncomplete
+ - eval_time: 10m
+ alertname: CephDeviceFailureRelocationIncomplete
+ exp_alerts:
+ - exp_labels:
+ name: "DEVICE_HEALTH_IN_USE"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use
+ summary: A device failure is predicted, but unable to relocate data
+ description: |
+ The device health module has determined that one or more devices will fail
+ soon, but the normal process of relocating the data on the device to other
+ OSDs in the cluster is blocked.
+
+ Check the the cluster has available freespace. It may be necessary to add
+ more disks to the cluster to allow the data from the failing device to
+ successfully migrate.
+# OSD
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_HOST_DOWN"}'
+ values: '0+0x2 1+0x10'
+ - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
+ values: '1+0x2 0+0x10'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
+ values: '1+0x12'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_HOST_DOWN"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDHostDown
+ - eval_time: 10m
+ alertname: CephOSDHostDown
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_HOST_DOWN"
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.8
+ exp_annotations:
+ summary: An OSD host is offline
+ description: |
+ The following OSDs are down:
+ - ceph-osd-1 : osd.0
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_FRONT"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDTimeoutsPublicNetwork
+ - eval_time: 10m
+ alertname: CephOSDTimeoutsPublicNetwork
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_SLOW_PING_TIME_FRONT"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: Network issues delaying OSD heartbeats (public network)
+ description: |
+ OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network
+ for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_BACK"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDTimeoutsClusterNetwork
+ - eval_time: 10m
+ alertname: CephOSDTimeoutsClusterNetwork
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_SLOW_PING_TIME_BACK"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: Network issues delaying OSD heartbeats (cluster network)
+ description: |
+ OSD heartbeats on the cluster's 'cluster' network (backend) are running slow. Investigate the network
+ for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="BLUESTORE_DISK_SIZE_MISMATCH"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDInternalDiskSizeMismatch
+ - eval_time: 10m
+ alertname: CephOSDInternalDiskSizeMismatch
+ exp_alerts:
+ - exp_labels:
+ name: "BLUESTORE_DISK_SIZE_MISMATCH"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch
+ summary: OSD size inconsistency error
+ description: |
+ One or more OSDs have an internal inconsistency between the size of the physical device and it's metadata.
+ This could lead to the OSD(s) crashing in future. You should redeploy the effected OSDs.
+ - interval: 30s
+ input_series:
+ - series: 'ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDReadErrors
+ - eval_time: 10m
+ alertname: CephOSDReadErrors
+ exp_alerts:
+ - exp_labels:
+ name: "BLUESTORE_SPURIOUS_READ_ERRORS"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors
+ summary: Device read errors detected
+ description: >
+ An OSD has encountered read errors, but the OSD has recovered by retrying
+ the reads. This may indicate an issue with the Hardware or Kernel.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_DOWN"}'
+ values: '0+0x2 1+0x10'
+ - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
+ values: '1+0x12'
+ - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
+ values: '1+0x2 0+0x10'
+ - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
+ values: '1+0x12'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
+ values: '1+0x12'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.1", hostname="ceph-osd-2"}'
+ values: '1+0x12'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.2", hostname="ceph-osd-3"}'
+ values: '1+0x12'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_DOWN"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_DOWN"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDDown
+ - eval_time: 10m
+ alertname: CephOSDDown
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_DOWN"
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.2
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down
+ summary: An OSD has been marked down/unavailable
+ description: |
+ 1 OSD down for over 5mins.
+
+ The following OSD is down:
+ - osd.1 on ceph-osd-2
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_NEARFULL"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_NEARFULL"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_NEARFULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDNearFull
+ - eval_time: 10m
+ alertname: CephOSDNearFull
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_NEARFULL"
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.3
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull
+ summary: OSD(s) running low on free space (NEARFULL)
+ description: |
+ One or more OSDs have reached their NEARFULL threshold
+
+ Use 'ceph health detail' to identify which OSDs have reached this threshold.
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_FULL"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_FULL"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_FULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDFull
+ - eval_time: 10m
+ alertname: CephOSDFull
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_FULL"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.4.6
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full
+ summary: OSD(s) is full, writes blocked
+ description: |
+ An OSD has reached it's full threshold. Writes from all pools that share the
+ affected OSD will be blocked.
+
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_BACKFILLFULL"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_BACKFILLFULL"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_BACKFILLFULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDBackfillFull
+ - eval_time: 10m
+ alertname: CephOSDBackfillFull
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_BACKFILLFULL"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull
+ summary: OSD(s) too full for backfill operations
+ description: |
+ An OSD has reached it's BACKFILL FULL threshold. This will prevent rebalance operations
+ completing for some pools. Check the current capacity utilisation with 'ceph df'
+
+ To resolve, either add capacity to the cluster, or delete unwanted data
+ - interval: 30s
+ input_series:
+ - series: 'ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="OSD_TOO_MANY_REPAIRS"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephOSDTooManyRepairs
+ - eval_time: 10m
+ alertname: CephOSDTooManyRepairs
+ exp_alerts:
+ - exp_labels:
+ name: "OSD_TOO_MANY_REPAIRS"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs
+ summary: OSD has hit a high number of read errors
+ description: |
+ Reads from an OSD have used a secondary PG to return data to the client, indicating
+ a potential failing disk.
+# Pools
+ # trigger percent full prediction on pools 1 and 2 only
+ - interval: 12h
+ input_series:
+ - series: 'ceph_pool_percent_used{pool_id="1"}'
+ values: '70 75 80 87 92'
+ - series: 'ceph_pool_percent_used{pool_id="2"}'
+ values: '22 22 23 23 24'
+ - series: 'ceph_pool_metadata{pool_id="1",name="rbd",type="replicated"}'
+ values: '1 1 1 1 1'
+ - series: 'ceph_pool_metadata{pool_id="2",name="default.rgw.index",type="replicated"}'
+ values: '1 1 1 1 1'
+ promql_expr_test:
+ - expr: |
+ (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id)
+ group_right ceph_pool_metadata) >= 95
+ eval_time: 36h
+ exp_samples:
+ - labels: '{name="rbd",pool_id="1",type="replicated"}'
+ value: 1.424E+02 # 142%
+ alert_rule_test:
+ - eval_time: 48h
+ alertname: CephPoolGrowthWarning
+ exp_alerts:
+ - exp_labels:
+ name: rbd
+ pool_id: 1
+ severity: warning
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.9.2
+ exp_annotations:
+ summary: Pool growth rate may soon exceed it's capacity
+ description: >
+ Pool 'rbd' will be full in less than 5 days
+ assuming the average fill-up rate of the past 48 hours.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="POOL_BACKFILLFULL"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="POOL_BACKFILLFULL"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="POOL_BACKFILLFULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPoolBackfillFull
+ - eval_time: 5m
+ alertname: CephPoolBackfillFull
+ exp_alerts:
+ - exp_labels:
+ name: "POOL_BACKFILLFULL"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: Freespace in a pool is too low for recovery/rebalance
+ description: >
+ A pool is approaching it's near full threshold, which will
+ prevent rebalance operations from completing. You should
+ consider adding more capacity to the pool.
+
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="POOL_NEAR_FULL"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="POOL_NEAR_FULL"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="POOL_NEAR_FULL"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPoolNearFull
+ - eval_time: 10m
+ alertname: CephPoolNearFull
+ exp_alerts:
+ - exp_labels:
+ name: "POOL_NEAR_FULL"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ summary: One or more Ceph pools are getting full
+ description: |
+ A pool has exceeeded it warning (percent full) threshold, or the OSDs
+ supporting the pool have reached their NEARFULL thresholds. Writes may
+ continue, but you are at risk of the pool going read only if more capacity
+ isn't made available.
+
+ Determine the affected pool with 'ceph df detail', for example looking
+ at QUOTA BYTES and STORED. Either increase the pools quota, or add
+ capacity to the cluster first then increase it's quota
+ (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
+
+# PGs
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_NOT_SCRUBBED"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="PG_NOT_SCRUBBED"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGNotScrubbed
+ - eval_time: 10m
+ alertname: CephPGNotScrubbed
+ exp_alerts:
+ - exp_labels:
+ name: "PG_NOT_SCRUBBED"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed
+ summary: Placement group(s) have not been scrubbed
+ description: |
+ One or more PGs have not been scrubbed recently. The scrub process is a data integrity
+ feature, protectng against bit-rot. It checks that objects and their metadata (size and
+ attributes) match across object replicas. When PGs miss their scrub window, it may
+ indicate the scrub window is too small, or PGs were not in a 'clean' state during the
+ scrub window.
+
+ You can manually initiate a scrub with: ceph pg scrub <pgid>
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_DAMAGED"}'
+ values: '0+0x4 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1
+ eval_time: 5m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="PG_DAMAGED"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGsDamaged
+ - eval_time: 10m
+ alertname: CephPGsDamaged
+ exp_alerts:
+ - exp_labels:
+ name: "PG_DAMAGED"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.4
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged
+ summary: Placement group damaged, manual intervention needed
+ description: >
+ During data consistency checks (scrub), at least one PG has been flagged as being
+ damaged or inconsistent.
+
+ Check to see which PG is affected, and attempt a manual repair if neccessary. To list
+ problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use
+ the 'ceph pg repair <pg_num>' command.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="TOO_MANY_PGS"}'
+ values: '0+0x4 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1
+ eval_time: 5m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="TOO_MANY_PGS"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGsHighPerOSD
+ - eval_time: 10m
+ alertname: CephPGsHighPerOSD
+ exp_alerts:
+ - exp_labels:
+ name: "TOO_MANY_PGS"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs
+ summary: Placement groups per OSD is too high
+ description: |
+ The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).
+
+ Check that the pg_autoscaler hasn't been disabled for any of the pools, with 'ceph osd pool autoscale-status'
+ and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide
+ the autoscaler based on the expected relative size of the pool
+ (i.e. 'ceph osd pool set cephfs.cephfs.meta target_size_ratio .1')
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_RECOVERY_FULL"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="PG_RECOVERY_FULL"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGRecoveryAtRisk
+ - eval_time: 10m
+ alertname: CephPGRecoveryAtRisk
+ exp_alerts:
+ - exp_labels:
+ name: "PG_RECOVERY_FULL"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.5
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full
+ summary: OSDs are too full for automatic recovery
+ description: >
+ Data redundancy may be reduced, or is at risk, since one or more OSDs are at or above their
+ 'full' threshold. Add more capacity to the cluster, or delete unwanted data.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_BACKFILL_FULL"}'
+ values: '0+0x2 1+0x20'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 0
+ eval_time: 1m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="PG_BACKFILL_FULL"}'
+ value: 0
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGBackfillAtRisk
+ - eval_time: 10m
+ alertname: CephPGBackfillAtRisk
+ exp_alerts:
+ - exp_labels:
+ name: "PG_BACKFILL_FULL"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.6
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full
+ summary: Backfill operations are blocked, due to lack of freespace
+ description: >
+ Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs
+ have breached their 'backfillfull' threshold. Add more capacity, or delete unwanted data.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_AVAILABILITY"}'
+ values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_health_detail{name="OSD_DOWN"}'
+ values: '0 0 0 1 1 1 1 1 1 0 0 0 0 0 0 0'
+ promql_expr_test:
+ - expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"}))
+ eval_time: 1m
+ # empty set at 1m
+ exp_samples:
+ alert_rule_test:
+ # PG_AVAILABILITY and OSD_DOWN not firing .. no alert
+ - eval_time: 1m
+ alertname: CephPGUnavilableBlockingIO
+ exp_alerts:
+ # PG_AVAILABILITY firing, but osd_down is active .. no alert
+ - eval_time: 5m
+ alertname: CephPGUnavilableBlockingIO
+ exp_alerts:
+ # PG_AVAILABILITY firing, AND OSD_DOWN is not active...raise the alert
+ - eval_time: 15m
+ alertname: CephPGUnavilableBlockingIO
+ exp_alerts:
+ - exp_labels:
+ name: "PG_AVAILABILITY"
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.7.3
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability
+ summary: Placement group is unavailable, blocking some I/O
+ description: >
+ Data availability is reduced impacting the clusters abilty to service I/O to some data. One or
+ more placement groups (PGs) are in a state that blocks IO.
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"}'
+ values: '0+0x2 1+0x10'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1
+ eval_time: 3m
+ exp_samples:
+ - labels: '{__name__="ceph_health_detail", name="PG_NOT_DEEP_SCRUBBED"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 1m
+ alertname: CephPGNotDeepScrubbed
+ - eval_time: 10m
+ alertname: CephPGNotDeepScrubbed
+ exp_alerts:
+ - exp_labels:
+ name: "PG_NOT_DEEP_SCRUBBED"
+ severity: warning
+ type: ceph_default
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed
+ summary: Placement group(s) have not been deep scrubbed
+ description: |
+ One or more PGs have not been deep scrubbed recently. Deep scrub is a data integrity
+ feature, protectng against bit-rot. It compares the contents of objects and their
+ replicas for inconsistency. When PGs miss their deep scrub window, it may indicate
+ that the window is too small or PGs were not in a 'clean' state during the deep-scrub
+ window.
+
+ You can manually initiate a deep scrub with: ceph pg deep-scrub <pgid>
+
+# Prometheus
+ - interval: 1m
+ input_series:
+ - series: 'up{job="myjob"}'
+ values: '1+0x10'
+ promql_expr_test:
+ - expr: absent(up{job="ceph"})
+ eval_time: 1m
+ exp_samples:
+ - labels: '{job="ceph"}'
+ value: 1
+ alert_rule_test:
+ - eval_time: 5m
+ alertname: PrometheusJobMissing
+ exp_alerts:
+ - exp_labels:
+ job: ceph
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.12.1
+ exp_annotations:
+ summary: The scrape job for Ceph is missing from Prometheus
+ description: |
+ The prometheus job that scrapes from Ceph is no longer defined, this
+ will effectively mean you'll have no metrics or alerts for the cluster.
+
+ Please review the job definitions in the prometheus.yml file of the prometheus
+ instance.
+# RADOS
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="OBJECT_UNFOUND"}'
+ values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
+ values: '1 1 1 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.0"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.1"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ - series: 'ceph_osd_metadata{ceph_daemon="osd.2"}'
+ values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1
+ eval_time: 1m
+ exp_samples:
+ alert_rule_test:
+ # OBJECT_UNFOUND but osd.2 is down, so don't fire
+ - eval_time: 5m
+ alertname: CephObjectMissing
+ exp_alerts:
+ # OBJECT_UNFOUND and all osd's are online, so fire
+ - eval_time: 15m
+ alertname: CephObjectMissing
+ exp_alerts:
+ - exp_labels:
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.10.1
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound
+ summary: Object(s) has been marked UNFOUND
+ description: |
+ A version of a RADOS object can not be found, even though all OSDs are up. I/O
+ requests for this object from clients will block (hang). Resolving this issue may
+ require the object to be rolled back to a prior version manually, and manually verified.
+# Generic Alerts
+ - interval: 1m
+ input_series:
+ - series: 'ceph_health_detail{name="RECENT_CRASH"}'
+ values: '0 0 0 1 1 1 1 1 1 1 1'
+ promql_expr_test:
+ - expr: ceph_health_detail{name="RECENT_CRASH"} == 1
+ eval_time: 1m
+ exp_samples:
+ alert_rule_test:
+ # not firing
+ - eval_time: 1m
+ alertname: CephDaemonCrash
+ exp_alerts:
+ # firing
+ - eval_time: 10m
+ alertname: CephDaemonCrash
+ exp_alerts:
+ - exp_labels:
+ name: RECENT_CRASH
+ severity: critical
+ type: ceph_default
+ oid: 1.3.6.1.4.1.50495.1.2.1.1.2
+ exp_annotations:
+ documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash
+ summary: One or more Ceph daemons have crashed, and are pending acknowledgement
+ description: |
+ One or more daemons have crashed recently, and need to be acknowledged. This notification
+ ensures that software crashes don't go unseen. To acknowledge a crash, use the
+ 'ceph crash archive <id>' command.
--- /dev/null
+import pytest
+import os
+import yaml
+from .utils import promtool_available, call
+from .settings import ALERTS_FILE, UNIT_TESTS_FILE
+
+
+def load_yaml(file_name):
+ yaml_data = None
+ with open(file_name, 'r') as alert_file:
+ raw = alert_file.read()
+ try:
+ yaml_data = yaml.safe_load(raw)
+ except yaml.YAMLError as e:
+ pass
+
+ return yaml_data
+
+
+def test_alerts_present():
+ assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found"
+
+
+def test_unittests_present():
+ assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found"
+
+
+@pytest.mark.skipif(not os.path.exists(ALERTS_FILE), reason=f"{ALERTS_FILE} missing")
+def test_rules_format():
+ assert load_yaml(ALERTS_FILE)
+
+
+@pytest.mark.skipif(not os.path.exists(UNIT_TESTS_FILE), reason=f"{UNIT_TESTS_FILE} missing")
+def test_unittests_format():
+ assert load_yaml(UNIT_TESTS_FILE)
+
+
+@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to check syntax")
+def test_rule_syntax():
+ completion = call(f"promtool check rules {ALERTS_FILE}")
+ assert completion.returncode == 0
+ assert b"SUCCESS" in completion.stdout
--- /dev/null
+import pytest
+import os
+from .utils import promtool_available, call
+from .settings import ALERTS_FILE, UNIT_TESTS_FILE
+
+
+def test_alerts_present():
+ assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found"
+
+
+def test_unittests_present():
+ assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found"
+
+
+@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to run unit tests")
+def test_run_unittests():
+ completion = call(f"promtool test rules {UNIT_TESTS_FILE}")
+ assert completion.returncode == 0
+ assert b"SUCCESS" in completion.stdout
--- /dev/null
+import pytest
+import shutil
+import subprocess
+
+
+def promtool_available() -> bool:
+ return shutil.which('promtool') is not None
+
+
+def call(cmd):
+ completion = subprocess.run(cmd.split(), stdout=subprocess.PIPE)
+ return completion
--- /dev/null
+#!/usr/bin/env python3
+#
+# Check the Prometheus rules for format, and integration
+# with the unit tests. This script has the following exit
+# codes:
+# 0 .. Everything worked
+# 4 .. rule problems or missing unit tests
+# 8 .. Missing fields in YAML
+# 12 .. Invalid YAML - unable to load
+# 16 .. Missing input files
+#
+# Externals
+# snmptranslate .. used to determine the oid's in the MIB to verify the rule -> MIB is correct
+#
+
+import re
+import os
+import sys
+import yaml
+import shutil
+import string
+from bs4 import BeautifulSoup
+from typing import List, Any, Dict, Set, Optional, Tuple
+import subprocess
+
+import urllib.request
+import urllib.error
+from urllib.parse import urlparse
+
+from settings import ALERTS_FILE, MIB_FILE, UNIT_TESTS_FILE
+
+DOCLINK_NAME = 'documentation'
+
+
+def isascii(s: str) -> bool:
+ try:
+ s.encode('ascii')
+ except UnicodeEncodeError:
+ return False
+ return True
+
+
+def read_file(file_name: str) -> Tuple[str, str]:
+ try:
+ with open(file_name, 'r') as input_file:
+ raw_data = input_file.read()
+ except OSError:
+ return '', f"Unable to open {file_name}"
+
+ return raw_data, ''
+
+
+def load_yaml(file_name: str) -> Tuple[Dict[str, Any], str]:
+ data = {}
+ errs = ''
+
+ raw_data, err = read_file(file_name)
+ if not err:
+
+ try:
+ data = yaml.safe_load(raw_data)
+ except yaml.YAMLError as e:
+ errs = f"filename '{file_name} is not a valid YAML file"
+
+ return data, errs
+
+
+def run_command(command: str):
+ c = command.split()
+ completion = subprocess.run(c, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ return (completion.returncode,
+ completion.stdout.decode('utf-8').split('\n'),
+ completion.stderr.decode('utf-8').split('\n'))
+
+
+class HTMLCache:
+ def __init__(self) -> None:
+ self.cache: Dict[str, Tuple[int, str]] = {}
+
+ def fetch(self, url_str: str) -> None:
+ parsed = urlparse(url_str)
+ url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
+
+ if url in self.cache:
+ return self.cache[url]
+
+ req = urllib.request.Request(url)
+ try:
+ r = urllib.request.urlopen(req)
+ except urllib.error.HTTPError as e:
+ self.cache[url] = e.code, e.reason
+ return self.cache[url]
+ except urllib.error.URLError as e:
+ self.cache[url] = 400, e.reason
+ return self.cache[url]
+
+ if r.status == 200:
+ html = r.read().decode('utf-8')
+ self.cache[url] = 200, html
+ return self.cache[url]
+
+ self.cache[url] = r.status, r.reason
+ return r.status, r.reason
+
+ @property
+ def cached_pages(self) -> List[str]:
+ return self.cache.keys()
+
+ @property
+ def cached_pages_total(self) -> int:
+ return len(self.cache.keys())
+
+class PrometheusRule:
+ expected_attrs = [
+ 'alert',
+ 'expr',
+ 'labels',
+ 'annotations'
+ ]
+
+ def __init__(self, rule_group, rule_data: Dict[str, Any]):
+
+ assert 'alert' in rule_data
+ self.group: RuleGroup = rule_group
+ self.name = rule_data.get('alert')
+ self.rule = rule_data
+ self.errors: List[str] = []
+ self.warnings: List[str] = []
+ self.validate()
+
+ @property
+ def has_oid(self):
+ return True if self.rule.get('labels', {}).get('oid', '') else False
+
+ @property
+ def labels(self) -> Dict[str, str]:
+ return self.rule.get('labels', {})
+
+ @property
+ def annotations(self) -> Dict[str, str]:
+ return self.rule.get('annotations', {})
+
+ def _check_alert_name(self):
+ # this is simplistic, but works in the context of the alert name
+ if self.name[0] in string.ascii_uppercase and \
+ self.name != self.name.lower() and \
+ self.name != self.name.upper() and \
+ " " not in self.name and \
+ "_" not in self.name:
+ return
+
+ self.warnings.append("Alert name is not in CamelCase format")
+
+ def _check_structure(self):
+ rule_attrs = self.rule.keys()
+ missing_attrs = [a for a in PrometheusRule.expected_attrs if a not in rule_attrs]
+
+ if missing_attrs:
+ self.errors.append(
+ f"invalid alert structure. Missing field{'s' if len(missing_attrs) > 1 else ''}"
+ f": {','.join(missing_attrs)}")
+
+ def _check_labels(self):
+ for rqd in ['severity', 'type']:
+ if rqd not in self.labels.keys():
+ self.errors.append(f"rule is missing {rqd} label definition")
+
+ def _check_annotations(self):
+ for rqd in ['summary', 'description']:
+ if rqd not in self.annotations:
+ self.errors.append(f"rule is missing {rqd} annotation definition")
+
+ def _check_doclink(self):
+ doclink = self.annotations.get(DOCLINK_NAME, '')
+
+ if doclink:
+ url = urlparse(doclink)
+ status, content = self.group.fetch_html_page(doclink)
+ if status == 200:
+ if url.fragment:
+ soup = BeautifulSoup(content, 'html.parser')
+ if not soup.find(id=url.fragment):
+ self.errors.append(f"documentation link error: {url.fragment} anchor not found on the page")
+ else:
+ # catch all
+ self.errors.append(f"documentation link error: {status} {content}")
+
+ def _check_snmp(self):
+ oid = self.labels.get('oid', '')
+
+ if self.labels.get('severity', '') == 'critical' and not oid:
+ self.warnings.append("critical level alert is missing an SNMP oid entry")
+ if oid and not re.search('^1.3.6.1.4.1.50495.1.2.\\d+.\\d+.\\d+$', oid):
+ self.errors.append("invalid OID format provided")
+ if self.group.get_oids():
+ if oid and oid not in self.group.get_oids():
+ self.errors.append(f"rule defines an OID {oid} that is missing from the MIB file({os.path.basename(MIB_FILE)})")
+
+ def _check_ascii(self):
+ if 'oid' not in self.labels:
+ return
+
+ desc = self.annotations.get('description', '')
+ summary = self.annotations.get('summary', '')
+ if not isascii(desc):
+ self.errors.append(f"non-ascii characters found in 'description' field will cause issues in associated snmp trap.")
+ if not isascii(summary):
+ self.errors.append(f"non-ascii characters found in 'summary' field will cause issues in associated snmp trap.")
+
+ def validate(self):
+
+ self._check_alert_name()
+ self._check_structure()
+ self._check_labels()
+ self._check_annotations()
+ self._check_doclink()
+ self._check_snmp()
+ self._check_ascii()
+ char = '.'
+
+ if self.errors:
+ char = 'E'
+ self.group.update('error', self.name)
+ elif self.warnings:
+ char = 'W'
+ self.group.update('warning', self.name)
+
+ sys.stdout.write(char)
+
+
+class RuleGroup:
+
+ def __init__(self, rule_file, group_name: str, group_name_width: int):
+ self.rule_file: RuleFile = rule_file
+ self.group_name = group_name
+ self.rules: Dict[str, PrometheusRule] = {}
+ self.problems = {
+ "error": [],
+ "warning": [],
+ }
+
+ sys.stdout.write(f"\n\t{group_name:<{group_name_width}} : ")
+
+ def add_rule(self, rule_data:Dict[str, Any]):
+ alert_name = rule_data.get('alert')
+ self.rules[alert_name] = PrometheusRule(self, rule_data)
+
+ def update(self, problem_type:str, alert_name:str):
+ assert problem_type in ['error', 'warning']
+
+ self.problems[problem_type].append(alert_name)
+ self.rule_file.update(self.group_name)
+
+ def fetch_html_page(self, url):
+ return self.rule_file.fetch_html_page(url)
+
+ def get_oids(self):
+ return self.rule_file.oid_list
+
+ @property
+ def error_count(self):
+ return len(self.problems['error'])
+
+ def warning_count(self):
+ return len(self.problems['warning'])
+
+ @property
+ def count(self):
+ return len(self.rules)
+
+
+class RuleFile:
+
+ def __init__(self, parent, file_name, rules, oid_list):
+ self.parent = parent
+ self.file_name = file_name
+ self.rules: Dict[str, Any] = rules
+ self.oid_list = oid_list
+ self.problems: Set[str] = set()
+ self.group: Dict[str, RuleGroup] = {}
+ self.alert_names_seen: Set[str] = set()
+ self.duplicate_alert_names:List[str] = []
+ self.html_cache = HTMLCache()
+
+ assert 'groups' in self.rules
+ self.max_group_name_width = self.get_max_group_name()
+ self.load_groups()
+
+ def update(self, group_name):
+ self.problems.add(group_name)
+ self.parent.mark_invalid()
+
+ def fetch_html_page(self, url):
+ return self.html_cache.fetch(url)
+
+ @property
+ def group_count(self):
+ return len(self.rules['groups'])
+
+ @property
+ def rule_count(self):
+ rule_count = 0
+ for _group_name, rule_group in self.group.items():
+ rule_count += rule_group.count
+ return rule_count
+
+ @property
+ def oid_count(self):
+ oid_count = 0
+ for _group_name, rule_group in self.group.items():
+ for _rule_name, rule in rule_group.rules.items():
+ if rule.has_oid:
+ oid_count += 1
+ return oid_count
+
+ @property
+ def group_names(self):
+ return self.group.keys()
+
+ @property
+ def problem_count(self):
+ return len(self.problems)
+
+ def get_max_group_name(self):
+ group_name_list = []
+ for group in self.rules.get('groups'):
+ group_name_list.append(group['name'])
+ return max([len(g) for g in group_name_list])
+
+ def load_groups(self):
+ sys.stdout.write("\nChecking rule groups")
+ for group in self.rules.get('groups'):
+ group_name = group['name']
+ rules = group['rules']
+ self.group[group_name] = RuleGroup(self, group_name, self.max_group_name_width)
+ for rule_data in rules:
+ if 'alert' in rule_data:
+ alert_name = rule_data.get('alert')
+ if alert_name in self.alert_names_seen:
+ self.duplicate_alert_names.append(alert_name)
+ else:
+ self.alert_names_seen.add(alert_name)
+ self.group[group_name].add_rule(rule_data)
+ else:
+ # skipped recording rule
+ pass
+
+ def report(self):
+ def max_width(item_list: Set[str], min_width: int = 0) -> int:
+ return max([len(i) for i in item_list] + [min_width])
+
+ if not self.problems and not self.duplicate_alert_names:
+ print("\nNo problems detected in the rule file")
+ return
+
+ print("\nProblem Report\n")
+
+ group_width = max_width(self.problems, 5)
+ alert_names = set()
+ for g in self.problems:
+ group = self.group[g]
+ alert_names.update(group.problems.get('error', []))
+ alert_names.update(group.problems.get('warning', []))
+ alert_width = max_width(alert_names, 10)
+
+ template = " {group:<{group_width}} {severity:<8} {alert_name:<{alert_width}} {description}"
+
+ print(template.format(
+ group="Group",
+ group_width=group_width,
+ severity="Severity",
+ alert_name="Alert Name",
+ alert_width=alert_width,
+ description="Problem Description"))
+
+ print(template.format(
+ group="-----",
+ group_width=group_width,
+ severity="--------",
+ alert_name="----------",
+ alert_width=alert_width,
+ description="-------------------"))
+
+ for group_name in sorted(self.problems):
+ group = self.group[group_name]
+ rules = group.rules
+ for alert_name in group.problems.get('error', []):
+ for desc in rules[alert_name].errors:
+ print(template.format(
+ group=group_name,
+ group_width=group_width,
+ severity="Error",
+ alert_name=alert_name,
+ alert_width=alert_width,
+ description=desc))
+ for alert_name in group.problems.get('warning', []):
+ for desc in rules[alert_name].warnings:
+ print(template.format(
+ group=group_name,
+ group_width=group_width,
+ severity="Warning",
+ alert_name=alert_name,
+ alert_width=alert_width,
+ description=desc))
+ if self.duplicate_alert_names:
+ print("Duplicate alert names detected:")
+ for a in self.duplicate_alert_names:
+ print(f" - {a}")
+
+
+class UnitTests:
+ expected_attrs = [
+ 'rule_files',
+ 'tests',
+ 'evaluation_interval'
+ ]
+ def __init__(self, filename):
+ self.filename = filename
+ self.unit_test_data: Dict[str, Any] = {}
+ self.alert_names_seen: Set[str] = set()
+ self.problems: List[str] = []
+ self.load()
+
+ def load(self):
+ self.unit_test_data, errs = load_yaml(self.filename)
+ if errs:
+ print(f"\n\nError in unit tests file: {errs}")
+ sys.exit(12)
+
+ missing_attr = [a for a in UnitTests.expected_attrs if a not in self.unit_test_data.keys()]
+ if missing_attr:
+ print(f"\nMissing attributes in unit tests: {','.join(missing_attr)}")
+ sys.exit(8)
+
+ def _check_alert_names(self, alert_names: List[str]):
+ alerts_tested: Set[str] = set()
+ for t in self.unit_test_data.get('tests'):
+ test_cases = t.get('alert_rule_test', [])
+ if not test_cases:
+ continue
+ for case in test_cases:
+ alertname = case.get('alertname', '')
+ if alertname:
+ alerts_tested.add(alertname)
+
+ alerts_defined = set(alert_names)
+ self.problems = list(alerts_defined.difference(alerts_tested))
+
+ def process(self, defined_alert_names: List[str]):
+ self._check_alert_names(defined_alert_names)
+
+ def report(self) -> None:
+
+ if not self.problems:
+ print("\nNo problems detected in unit tests file")
+ return
+
+ print("\nUnit tests are incomplete. Tests missing for the following alerts;")
+ for p in self.problems:
+ print(f" - {p}")
+
+class RuleChecker:
+
+ def __init__(self, rules_filename: str = None, test_filename: str = None):
+ self.rules_filename = rules_filename or ALERTS_FILE
+ self.test_filename = test_filename or UNIT_TESTS_FILE
+ self.rule_file: Optional[RuleFile] = None
+ self.unit_tests: Optional[UnitTests] = None
+ self.rule_file_problems: bool = False
+ self.errors = {}
+ self.warnings = {}
+ self.error_count = 0
+ self.warning_count = 0
+ self.oid_count = 0
+
+ self.oid_list = self.build_oid_list()
+
+ def build_oid_list(self) -> List[str]:
+
+ cmd = shutil.which('snmptranslate')
+ if not cmd:
+ return []
+
+ rc, stdout, stderr = run_command(f"{cmd} -Pu -Tz -M ../../snmp:/usr/share/snmp/mibs -m CEPH-MIB")
+ if rc != 0:
+ return []
+
+ oid_list: List[str] = []
+ for line in stdout[:-1]:
+ _label, oid = line.replace('"', '').replace('\t', ' ').split()
+ oid_list.append(oid)
+
+ return oid_list
+
+ @property
+ def status(self):
+ if self.rule_file_problems or self.unit_tests.problems:
+ return 4
+
+ return 0
+
+ def mark_invalid(self):
+ self.rule_file_problems = True
+
+ def summarise_rule_file(self):
+ for group_name in self.rule_file.problems:
+ group = self.rule_file.group[group_name]
+ self.error_count += len(group.problems['error'])
+ self.warning_count += len(group.problems['warning'])
+
+ def ready(self):
+ errs: List[str] = []
+ ready_state = True
+ if not os.path.exists(self.rules_filename):
+ errs.append(f"rule file '{self.rules_filename}' not found")
+ ready_state = False
+
+ if not os.path.exists(self.test_filename):
+ errs.append(f"test file '{self.test_filename}' not found")
+ ready_state = False
+
+ return ready_state, errs
+
+ def run(self):
+
+ ready, errs = self.ready()
+ if not ready:
+ print("Unable to start:")
+ for e in errs:
+ print(f"- {e}")
+ sys.exit(16)
+
+ rules, errs = load_yaml(self.rules_filename)
+ if errs:
+ print(errs)
+ sys.exit(12)
+
+ self.rule_file = RuleFile(self, self.rules_filename, rules, self.oid_list)
+ self.summarise_rule_file()
+
+ self.unit_tests = UnitTests(self.test_filename)
+ self.unit_tests.process(self.rule_file.alert_names_seen)
+
+ def report(self):
+ print("\n\nSummary\n")
+ print(f"Rule file : {self.rules_filename}")
+ print(f"Unit Test file : {self.test_filename}")
+ print(f"\nRule groups processed : {self.rule_file.group_count:>3}")
+ print(f"Rules processed : {self.rule_file.rule_count:>3}")
+ print(f"SNMP OIDs declared : {self.rule_file.oid_count:>3} {'(snmptranslate missing, unable to cross check)' if not self.oid_list else ''}")
+ print(f"Rule errors : {self.error_count:>3}")
+ print(f"Rule warnings : {self.warning_count:>3}")
+ print(f"Rule name duplicates : {len(self.rule_file.duplicate_alert_names):>3}")
+ print(f"Unit tests missing : {len(self.unit_tests.problems):>3}")
+
+ self.rule_file.report()
+ self.unit_tests.report()
+
+
+def main():
+ checker = RuleChecker()
+
+ checker.run()
+ checker.report()
+ print()
+
+ sys.exit(checker.status)
+
+
+if __name__ == '__main__':
+ main()
--- /dev/null
+import re
+import subprocess
+import sys
+import tempfile
+from dataclasses import asdict, dataclass, field
+from typing import Any, List
+
+import yaml
+
+
+@dataclass
+class InputSeries:
+ series: str = ''
+ values: str = ''
+
+@dataclass
+class ExprSample:
+ labels: str = ''
+ value: float = -1
+
+@dataclass
+class PromqlExprTest:
+ expr: str = ''
+ eval_time: str = '1m'
+ exp_samples: List[ExprSample] = field(default_factory=list)
+
+@dataclass
+class Test:
+ interval: str = '1m'
+ input_series: List[InputSeries] = field(default_factory=list)
+ promql_expr_test: List[PromqlExprTest] = field(default_factory=list)
+
+
+@dataclass
+class TestFile:
+ evaluation_interval: str = '1m'
+ tests: List[Test] = field(default_factory=list)
+
+
+class PromqlTest:
+ """
+ Base class to provide prometheus query test capabilities. After setting up
+ the query test with its input and expected output it's expected to run promtool.
+
+ https://prometheus.io/docs/prometheus/latest/configuration/unit_testing_rules/#test-yml
+
+ The workflow of testing would be something like:
+
+ # add prometheus query to test
+ self.set_expression('bonding_slaves > 0')
+
+ # add some prometheus input series
+ self.add_series('bonding_slaves{master="bond0"}', '2')
+ self.add_series('bonding_slaves{master="bond1"}', '3')
+ self.add_series('node_network_receive_bytes{instance="127.0.0.1",
+ device="eth1"}', "10 100 230 22")
+
+ # expected output of the query
+ self.add_exp_samples('bonding_slaves{master="bond0"}', 2)
+ self.add_exp_samples('bonding_slaves{master="bond1"}', 3)
+
+ # at last, always call promtool with:
+ self.assertTrue(self.run_promtool())
+ # assertTrue means it expect promtool to succeed
+ """
+
+ def __init__(self):
+ self.test_output_file = tempfile.NamedTemporaryFile('w+')
+
+ self.test_file = TestFile()
+ self.test = Test()
+ self.promql_expr_test = PromqlExprTest()
+ self.test.promql_expr_test.append(self.promql_expr_test)
+ self.test_file.tests.append(self.test)
+
+ self.variables = {}
+
+ def __del__(self):
+ self.test_output_file.close()
+
+
+ def set_evaluation_interval(self, interval: int, unit: str = 'm') -> None:
+ """
+ Set the evaluation interval of the time series
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.test_file.evaluation_interval = f'{interval}{unit}'
+
+ def set_interval(self, interval: int, unit: str = 'm') -> None:
+ """
+ Set the duration of the time series
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.test.interval = f'{interval}{unit}'
+
+ def set_expression(self, expr: str) -> None:
+ """
+ Set the prometheus expression/query used to filter data.
+
+ Args:
+ expr(str): expression/query.
+ """
+ self.promql_expr_test.expr = expr
+
+ def add_series(self, series: str, values: str) -> None:
+ """
+ Add a series to the input.
+
+ Args:
+ series(str): Prometheus series.
+ Notation: '<metric name>{<label name>=<label value>, ...}'
+ values(str): Value of the series.
+ """
+ input_series = InputSeries(series=series, values=values)
+ self.test.input_series.append(input_series)
+
+ def set_eval_time(self, eval_time: int, unit: str = 'm') -> None:
+ """
+ Set the time when the expression will be evaluated
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.promql_expr_test.eval_time = f'{eval_time}{unit}'
+
+ def add_exp_samples(self, sample: str, values: Any) -> None:
+ """
+ Add an expected sample/output of the query given the series/input
+
+ Args:
+ sample(str): Expected sample.
+ Notation: '<metric name>{<label name>=<label value>, ...}'
+ values(Any): Value of the sample.
+ """
+ expr_sample = ExprSample(labels=sample, value=values)
+ self.promql_expr_test.exp_samples.append(expr_sample)
+
+ def set_variable(self, variable: str, value: str):
+ """
+ If a query makes use of grafonnet variables, for example
+ '$osd_hosts', you should change this to a real value. Example:
+
+
+ > self.set_expression('bonding_slaves{master="$osd_hosts"} > 0')
+ > self.set_variable('osd_hosts', '127.0.0.1')
+ > print(self.query)
+ > bonding_slaves{master="127.0.0.1"} > 0
+
+ Args:
+ variable(str): Variable name
+ value(str): Value to replace variable with
+
+ """
+ self.variables[variable] = value
+
+ def run_promtool(self):
+ """
+ Run promtool to test the query after setting up the input, output
+ and extra parameters.
+
+ Returns:
+ bool: True if successful, False otherwise.
+ """
+
+ for variable, value in self.variables.items():
+ expr = self.promql_expr_test.expr
+ new_expr = re.sub(r'\${0}'.format(variable), str(value), expr)
+ self.set_expression(new_expr)
+
+ test_as_dict = asdict(self.test_file)
+ yaml.dump(test_as_dict, self.test_output_file)
+
+ args = f'promtool test rules {self.test_output_file.name}'.split()
+ try:
+ subprocess.run(args, check=True)
+ return True
+ except subprocess.CalledProcessError as process_error:
+ print(yaml.dump(test_as_dict))
+ print(process_error.stderr)
+ return False
--- /dev/null
+Feature: Ceph Cluster Dashboard
+
+Scenario: "Test total PG States"
+ Given the following series:
+ | metrics | values |
+ | ceph_pg_total{foo="var"} | 10 100 |
+ | ceph_pg_total{foo="bar"} | 20 200 |
+ Then Grafana panel `PG States` with legend `Total` shows:
+ | metrics | values |
+ | {} | 300 |
+
+Scenario: "Test OSDs in"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_in{ceph_daemon="osd.0"} | 1.0 |
+ | ceph_osd_in{ceph_daemon="osd.1"} | 0.0 |
+ | ceph_osd_in{ceph_daemon="osd.2"} | 1.0 |
+ When variable `instance` is `.*`
+ Then Grafana panel `OSDs` with legend `In` shows:
+ | metrics | values |
+ | {} | 2 |
+
+Scenario: "Test OSDs down"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_up{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_up{ceph_daemon="osd.1", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_up{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `Down` shows:
+ | metrics | values |
+ | {} | 3 |
+
+Scenario: "Test OSDs out"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_in{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_in{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_in{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `Out` shows:
+ | metrics | values |
+ | {} | 2 |
+
+Scenario: "Test OSDs all"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_metadata{ceph_daemon="osd.0", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_metadata{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_metadata{ceph_daemon="osd.2", instance="127.0.0.1"} | 1.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `All` shows:
+ | metrics | values |
+ | {} | 3 |
--- /dev/null
+# type: ignore[no-redef]
+# pylint: disable=E0611,W0613,E0102
+import copy
+
+from behave import given, then, when
+from prettytable import PrettyTable
+
+from tests_dashboards import PromqlTest
+from tests_dashboards.util import get_dashboards_data, resolve_time_and_unit
+
+
+class GlobalContext:
+ def __init__(self):
+ self.tested_queries_count = 0
+ self.promql_expr_test = None
+ self.data = get_dashboards_data()
+ self.query_map = self.data['queries']
+
+ def reset_promql_test(self):
+ self.promql_expr_test = PromqlTest()
+ self.promql_expr_test.variables = copy.copy(self.data['variables'])
+
+ def print_query_stats(self):
+ total = len(self.query_map)
+ table = PrettyTable()
+ table.field_names = ['Name', 'Queries', 'Tested', 'Cover']
+
+ def percent(tested, total):
+ return str(round((tested / total) * 100, 2)) + '%'
+
+ def file_name(path):
+ return path.split('/')[-1]
+
+ total = 0
+ tested = 0
+ for path, stat in self.data['stats'].items():
+ assert stat['total']
+ table.add_row([file_name(path), stat['total'], stat['tested'],
+ percent(stat['tested'], stat['total'])])
+ total += stat['total']
+ tested += stat['tested']
+
+ assert total
+ table.add_row(['Total', total, tested, percent(tested, total)])
+ print(table)
+
+
+global_context = GlobalContext()
+
+# Behave function overloading
+# ===========================
+
+
+def before_scenario(context, scenario):
+ global_context.reset_promql_test()
+
+
+def after_scenario(context, scenario):
+ assert global_context.promql_expr_test.run_promtool()
+
+
+def after_all(context):
+ global_context.print_query_stats()
+
+
+@given("the following series")
+def step_impl(context):
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_series(metric, value)
+
+
+@when('evaluation interval is `{interval}`')
+def step_impl(context, interval):
+ interval_without_unit, unit = resolve_time_and_unit(interval)
+ if interval_without_unit is None:
+ raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_evaluation_interval(interval_without_unit, unit)
+
+
+@when('interval is `{interval}`')
+def step_impl(context, interval):
+ interval_without_unit, unit = resolve_time_and_unit(interval)
+ if interval_without_unit is None:
+ raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_interval(interval_without_unit, unit)
+
+
+@when('evaluation time is `{eval_time}`')
+def step_impl(context, eval_time):
+ eval_time_without_unit, unit = resolve_time_and_unit(eval_time)
+ if eval_time_without_unit is None:
+ raise ValueError(f'Invalid evalution time: {eval_time}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_eval_time(eval_time_without_unit, unit)
+
+
+@when('variable `{variable}` is `{value}`')
+def step_impl(context, variable, value):
+ global_context.promql_expr_test.set_variable(variable, value)
+
+
+@then('Grafana panel `{panel_name}` with legend `{legend}` shows')
+def step_impl(context, panel_name, legend):
+ """
+ This step can have an empty legend. As 'behave' doesn't provide a way
+ to say it's empty we use EMPTY to mark as empty.
+ """
+ if legend == "EMPTY":
+ legend = ''
+ query_id = panel_name + '-' + legend
+ if query_id not in global_context.query_map:
+ raise KeyError((f'Query with legend {legend} in panel "{panel_name}"'
+ 'couldn\'t be found'))
+
+ expr = global_context.query_map[query_id]['query']
+ global_context.promql_expr_test.set_expression(expr)
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_exp_samples(metric, float(value))
+ path = global_context.query_map[query_id]['path']
+ global_context.data['stats'][path]['tested'] += 1
+
+
+@then('query `{query}` produces')
+def step_impl(context, query):
+ global_context.promql_expr_test.set_expression(query)
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_exp_samples(metric, float(value))
--- /dev/null
+Feature: Host Details Dashboard
+
+Scenario: "Test OSD"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_metadata{back_iface="",ceph_daemon="osd.0",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ | ceph_osd_metadata{back_iface="",ceph_daemon="osd.1",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ | ceph_osd_metadata{back_iface="",ceph_daemon="osd.2",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ When variable `ceph_hosts` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 3 |
+
+# IOPS Panel - begin
+
+Scenario: "Test Disk IOPS - Writes - Several OSDs per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Writes - Single OSD per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Reads - Several OSDs per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Reads - Single OSD per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+# IOPS Panel - end
+
+# Node disk bytes written/read panel - begin
+
+Scenario: "Test disk throughput - read"
+ Given the following series:
+ | metrics | values |
+ | node_disk_read_bytes_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_bytes_total{device="sdb",instance="localhost:9100"} | 100+600x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) read` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
+
+Scenario: "Test disk throughput - write"
+ Given the following series:
+ | metrics | values |
+ | node_disk_written_bytes_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_written_bytes_total{device="sdb",instance="localhost:9100"} | 100+600x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) write` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
+
+# Node disk bytes written/read panel - end
+
+Scenario: "Test $ceph_hosts Disk Latency panel"
+ Given the following series:
+ | metrics | values |
+ | node_disk_write_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_write_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk Latency` with legend `{{device}}({{ceph_daemon}})` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test $ceph_hosts Disk utilization"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk utilization` with legend `{{device}}({{ceph_daemon}})` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 100 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 100 |
+
--- /dev/null
+Feature: Hosts Overview Dashboard
+
+Scenario: "Test network load succeeds"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ When variable `osd_hosts` is `127.0.0.1`
+ Then Grafana panel `Network Load` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 6 |
+
+Scenario: "Test network load with bonding succeeds"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When variable `osd_hosts` is `127.0.0.1`
+ Then Grafana panel `Network Load` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 6 |
+
+Scenario: "Test AVG Disk Utilization"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{device="sdc",instance="localhost:9100"} | 10 2000 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd_hosts` is `localhost`
+ Then Grafana panel `AVG Disk Utilization` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 100 |
--- /dev/null
+Feature: OSD device details
+
+Scenario: "Test Physical Device Latency for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 60 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 60 |
+ | node_disk_read_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
+ | node_disk_read_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 10 |
+
+Scenario: "Test Physical Device Latency for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 60 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 60 |
+ | node_disk_write_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
+ | node_disk_write_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 10 |
+
+Scenario: "Test Physical Device R/W IOPS for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W IOPS for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W Bytes for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W Bytes for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device Util% for $osd"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10 100 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Util% for $osd` with legend `{{device}} on {{instance}}` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
--- /dev/null
+Feature: OSD Overview
+
+Scenario: "Test OSD onode Hits Ratio"
+ Given the following series:
+ | metrics | values |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 5255 |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 5419 |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 5242 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 202 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 247 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 234 |
+ Then Grafana panel `OSD onode Hits Ratio` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 9.588529429483704E-01 |
+
--- /dev/null
+Feature: RGW Host Detail Dashboard
+
+Scenario: "Test $rgw_servers GET/PUT Latencies - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `GET {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance_id="58892247"} | 2.5000000000000004 |
+
+Scenario: "Test $rgw_servers GET/PUT Latencies - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `PUT {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1 |
+
+Scenario: "Test Bandwidth by HTTP Operation - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.1`
+ Then Grafana panel `Bandwidth by HTTP Operation` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1.6666666666666667 |
+
+Scenario: "Test Bandwidth by HTTP Operation - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.1`
+ Then Grafana panel `Bandwidth by HTTP Operation` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 |
+
+Scenario: "Test HTTP Request Breakdown - Requests Failed"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `Requests Failed {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 6.666666666666667e-02 |
+
+Scenario: "Test HTTP Request Breakdown - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .6666666666666666 |
+
+Scenario: "Test HTTP Request Breakdown - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.3333333333333335 |
+
+Scenario: "Test HTTP Request Breakdown - Other"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `Other {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
+
+Scenario: "Test Workload Breakdown - Failures"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `Failures {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 6.666666666666667e-02 |
+
+Scenario: "Test Workload Breakdown - GETs"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .6666666666666666 |
+
+Scenario: "Test Workload Breakdown - PUTs"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.3333333333333335 |
+
+Scenario: "Test Workload Breakdown - Other"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `Other (DELETE,LIST) {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
--- /dev/null
+Feature: RGW Overview Dashboard
+
+Scenario: "Test Average GET Latencies"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Average GET/PUT Latencies` with legend `GET AVG` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo",instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.5000000000000004 |
+
+Scenario: "Test Average PUT Latencies"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Average GET/PUT Latencies` with legend `PUT AVG` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo",instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 |
+
+Scenario: "Test Total Requests/sec by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {rgw_host="1"} | 1.6666666666666667 |
+
+Scenario: "Test GET Latencies by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `GET Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 2.5000000000000004 |
+
+Scenario: "Test Bandwidth Consumed by Type- GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows:
+ | metrics | values |
+ | {} | 1.6666666666666667 |
+
+Scenario: "Test Bandwidth Consumed by Type- PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows:
+ | metrics | values |
+ | {} | 1 |
+
+Scenario: "Test Bandwidth by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance_id="92806566", rgw_host="1"} | 2.666666666666667 |
+
+Scenario: "Test PUT Latencies by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `PUT Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |
+
+Scenario: "Test Total backend responses by HTTP code"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 |
+ | haproxy_backend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ When variable `code` is `200`
+ Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows:
+ | metrics | values |
+ | {code="200"} | 1.5 |
+
+Scenario: "Test Total frontend responses by HTTP code"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 |
+ | haproxy_frontend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ When variable `code` is `200`
+ Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows:
+ | metrics | values |
+ | {code="200"} | 1.5 |
+
+Scenario: "Test Total http frontend requests by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Requests` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend response errors by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Response errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend requests errors by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Requests errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend redispatch warnings by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend retry warnings by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend retry` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend requests denied by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Request denied` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend current queue by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 200 |
+
+Scenario: "Test Total frontend connections by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend connections attempts by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend connections error by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Back errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend bytes incoming by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total frontend bytes outgoing by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total backend bytes incoming by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total backend bytes outgoing by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
--- /dev/null
+Feature: Test tester
+
+Scenario: "Simple query works"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 100 |
+
+Scenario: "Query with evaluation time"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `0m`
+ Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
+
+Scenario: "Query with evaluation time and variable value"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `0m`
+ And variable `osd_hosts` is `127.0.0.1`
+ Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
+
+Scenario: "Query with interval time"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 300 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 300 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `2h`
+ And evaluation interval is `1h`
+ And interval is `1h`
+ And variable `osd_hosts` is `127.0.0.1`
+ Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 200 |
\ No newline at end of file
--- /dev/null
+# This file and steps files is needed even if its empty because of 'behave' :(
--- /dev/null
+attrs==21.2.0
+behave==1.2.6
+py==1.10.0
+pyparsing==2.4.7
+PyYAML==6.0
+types-PyYAML==6.0.0
+typing-extensions==3.10.0.2
+termcolor==1.1.0
+types-termcolor==1.1.2
+dataclasses==0.6
+types-dataclasses==0.6.1
+prettytable==2.4.0
--- /dev/null
+import json
+from pathlib import Path
+from typing import Any, Dict, Tuple, Union
+
+from termcolor import cprint
+
+UNITS = ['ms', 's', 'm', 'h', 'd', 'w', 'y']
+
+
+def resolve_time_and_unit(time: str) -> Union[Tuple[int, str], Tuple[None, None]]:
+ """
+ Divide time with its unit and return a tuple like (10, 'm')
+ Return None if its and invalid prometheus time
+ Valid units are inside UNITS.
+ """
+ if time[-1] in UNITS:
+ return int(time[:-1]), time[-1]
+ if time[-2:] in UNITS:
+ return int(time[:-2]), time[-2:]
+ return None, None
+
+
+def get_dashboards_data() -> Dict[str, Any]:
+ data: Dict[str, Any] = {'queries': {}, 'variables': {}, 'stats': {}}
+ for file in Path(__file__).parent.parent \
+ .joinpath('dashboards_out').glob('*.json'):
+ with open(file, 'r') as f:
+ dashboard_data = json.load(f)
+ data['stats'][str(file)] = {'total': 0, 'tested': 0}
+ add_dashboard_queries(data, dashboard_data, str(file))
+ add_dashboard_variables(data, dashboard_data)
+ return data
+
+
+def add_dashboard_queries(data: Dict[str, Any], dashboard_data: Dict[str, Any], path: str) -> None:
+ """
+ Grafana panels can have more than one target/query, in order to identify each
+ query in the panel we append the "legendFormat" of the target to the panel name.
+ format: panel_name-legendFormat
+ """
+ if 'panels' not in dashboard_data:
+ return
+ for panel in dashboard_data['panels']:
+ if (
+ 'title' in panel
+ and 'targets' in panel
+ and len(panel['targets']) > 0
+ and 'expr' in panel['targets'][0]
+ ):
+ for target in panel['targets']:
+ title = panel['title']
+ legend_format = target['legendFormat'] if 'legendFormat' in target else ""
+ query_id = title + '-' + legend_format
+ if query_id in data['queries']:
+ # NOTE: If two or more panels have the same name and legend it
+ # might suggest a refactoring is needed or add something else
+ # to identify each query.
+ cprint((f'WARNING: Query in panel "{title}" with legend "{legend_format}"'
+ ' already exists'), 'yellow')
+ data['queries'][query_id] = {'query': target['expr'], 'path': path}
+ data['stats'][path]['total'] += 1
+
+
+def add_dashboard_variables(data: Dict[str, Any], dashboard_data: Dict[str, Any]) -> None:
+ if 'templating' not in dashboard_data or 'list' not in dashboard_data['templating']:
+ return
+ for variable in dashboard_data['templating']['list']:
+ if 'name' in variable:
+ data['variables'][variable['name']] = 'UNSET VARIABLE'
--- /dev/null
+[tox]
+envlist = lint,jsonnet-{check,lint,fix},promql-query-{test,lint},alerts-check
+skipsdist = true
+
+[testenv:jsonnet-bundler-{install,update}]
+whitelist_externals =
+ jb
+description =
+ install: Install the jsonnet dependencies
+ update: Update the jsonnet dependencies
+commands =
+ install: jb install
+ update: jb update
+
+[testenv:jsonnet-{check,fix,lint}]
+basepython = python3
+whitelist_externals =
+ find
+ jb
+ jsonnet
+ jsonnetfm
+ sh
+description =
+ check: Ensure that auto-generated files matches the current version
+ fix: Update generated files from jsonnet filse with latest changes
+ lint: Test if jsonnet files are linted (without any update)
+deps =
+ -rrequirements-grafonnet.txt
+depends = jsonnet-bundler-install
+commands =
+ check: sh test-jsonnet.sh
+ lint: ./lint-jsonnet.sh --test
+ fix: jsonnet -J vendor -m dashboards_out dashboards.jsonnet
+
+[testenv:lint]
+description =
+ Run python linters
+deps =
+ -rrequirements-lint.txt
+setenv =
+commands =
+ pylint --rcfile=.pylintrc tests_dashboards
+ mypy tests_dashboards
+ isort tests_dashboards
+
+[testenv:promql-query-test]
+description =
+ lint: Run promtool check on grafana queries
+ test: Run promtool unit testing on grafana queries.
+deps =
+ -rrequirements-lint.txt
+depends = grafonnet-check
+setenv =
+whitelist_externals =
+ promtool
+commands =
+ behave tests_dashboards/features
+
+[testenv:alerts-{check,lint}]
+deps =
+ -rrequirements-alerts.txt
+ pytest
+depends = grafonnet-check
+whitelist_externals =
+ promtool
+commands =
+ lint: promtool check rules prometheus_alerts.yaml
+ test: pytest -rA tests_alerts/test_syntax.py tests_alerts/test_unittests.py
+ python3 ./tests_alerts/validate_rules.py
+++ /dev/null
-## Grafana dashboards for Ceph
-
-Here you can find a collection of [Grafana](https://grafana.com/grafana)
-dashboards for Ceph Monitoring. These dashboards are based on metrics collected
-from [prometheus](https://prometheus.io/) scraping the [prometheus mgr
-plugin](http://docs.ceph.com/en/latest/mgr/prometheus/) and the
-[node_exporter](https://github.com/prometheus/node_exporter).
-
-### Other requirements
-
-- Luminous 12.2.5 or newer
-- [Status Panel](https://grafana.com/plugins/vonage-status-panel) installed
-- node_exporter 0.15.x and 0.16.x are supported (host details and hosts
-overview dashboards)
GRAFANA_VERSION ?= 8.3.5-1
PIECHART_VERSION ?= "1.6.2"
STATUS_PANEL_VERSION ?= "1.0.11"
-DASHBOARD_DIR := "../dashboards"
+DASHBOARD_DIR := "../../ceph-mixin/dashboards_out"
DASHBOARD_PROVISIONING := "ceph-dashboard.yml"
IMAGE := "docker.io/redhat/ubi8:8.5"
PKGMGR := "dnf"
+++ /dev/null
-../../../src/pybind/mgr/dashboard/.pylintrc
\ No newline at end of file
+++ /dev/null
-set(CEPH_GRAFANA_DASHBOARDS_DIR "${CMAKE_INSTALL_SYSCONFDIR}/grafana/dashboards/ceph-dashboard"
- CACHE PATH "Location for grafana dashboards")
-file(GLOB CEPH_GRAFANA_DASHBOARDS "*.json")
-install(FILES
- ${CEPH_GRAFANA_DASHBOARDS}
- DESTINATION ${CEPH_GRAFANA_DASHBOARDS_DIR})
-
-set(CEPH_BUILD_VIRTUALENV $ENV{TMPDIR})
-if(NOT CEPH_BUILD_VIRTUALENV)
- set(CEPH_BUILD_VIRTUALENV ${CMAKE_BINARY_DIR})
-endif()
-
-if(WITH_GRAFANA)
- if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm|ARM")
- include(AddCephTest)
- add_tox_test(grafana-check TOX_ENVS grafonnet-check)
- add_tox_test(grafana-query-test TOX_ENVS promql-query-test)
- add_tox_test(grafana-lint TOX_ENVS lint)
- set(ver 0.1.0)
- set(name grafonnet-lib)
- include(ExternalProject)
- ExternalProject_Add(${name}
- URL https://github.com/grafana/${name}/archive/v${ver}/${name}-${ver}.tar.gz
- URL_MD5 0798752ed40864fa8b3db40a3c970642
- BUILD_COMMAND ""
- CONFIGURE_COMMAND ""
- INSTALL_COMMAND ""
- EXCLUDE_FROM_ALL ON)
- add_dependencies(tests
- ${name})
- ExternalProject_Get_Property(${name} SOURCE_DIR)
- set_property(
- TEST run-tox-grafana-check run-tox-grafana-query-test run-tox-grafana-lint
- APPEND
- PROPERTY ENVIRONMENT
- GRAFONNET_PATH=${SOURCE_DIR}/grafonnet)
- endif(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm|ARM")
-endif()
+++ /dev/null
-Context
-These dashboards should be enough to get started on the integration. It's not a complete set, so more will be added in the next week.
-
-Bare in mind that the osd device details dashboard needs node_exporter active - all the other dashboards pick data out of ceph-mgr based metrics.
-
-
-The cephfs dashboard only has 2 panels currently. The counter available are
-a little light at the moment. Patrick/Venky have been addressing this with
-https://bugzilla.redhat.com/show_bug.cgi?id=1618523
-cephfs-overview.json
-
-Host Information
-host-details.json combines generic server metrics that show cpu/memory/network stats (including network errors/drops),
-with disk level stats for OSD hosts. OSD charts show the physical device name together with it's corresponding osd id for correlation.
-
-Ceph Pools
-two dashboards. Overview gives the high level combined view, pool-detail needs a pool_name variable passed to it (currently uses a templating var which is visible)
-pool-overview.json
-pool-detail.json
-
-OSD Device Details. This dashboard needs some further work. It currently shows
-OSD level stats with physical device stats but leaves out some of the counters
-that cephmetrics provides for trouble shooting.
-osd-device-details.json
-
-Object gateway dashboards, again split into overview and detail. The detail dashboard needs the relevant ceph-deamon name for the rgw instance.
-radosgw-overview.json
-radosgw-detail.json
+++ /dev/null
-{
- "__requires": [
- {
- "type": "grafana",
- "id": "grafana",
- "name": "Grafana",
- "version": "5.0.0"
- },
- {
- "type": "panel",
- "id": "graph",
- "name": "Graph",
- "version": "5.0.0"
- },
- {
- "type": "panel",
- "id": "heatmap",
- "name": "Heatmap",
- "version": "5.0.0"
- },
- {
- "type": "panel",
- "id": "singlestat",
- "name": "Singlestat",
- "version": "5.0.0"
- },
- {
- "type": "panel",
- "id": "vonage-status-panel",
- "name": "Status Panel",
- "version": "1.0.8"
- }
- ],
- "annotations": {
- "list": []
- },
- "description": "Ceph cluster overview",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "id": null,
- "iteration": 1525415495309,
- "links": [],
- "panels": [
- {
- "cacheTimeout": null,
- "colorBackground": true,
- "colorValue": false,
- "colors": [
- "rgba(50, 128, 45, 0.9)",
- "rgba(237, 129, 40, 0.9)",
- "rgb(255, 0, 0)"
- ],
- "datasource": "$datasource",
- "editable": false,
- "error": false,
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 2,
- "x": 0,
- "y": 0
- },
- "hideTimeOverride": true,
- "id": 21,
- "interval": "1m",
- "links": [],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "ceph_health_status",
- "format": "time_series",
- "instant": true,
- "interval": "$interval",
- "intervalFactor": 1,
- "refId": "A",
- "step": 60
- }
- ],
- "thresholds": "1,2",
- "timeFrom": null,
- "title": "Health Status",
- "transparent": false,
- "type": "singlestat",
- "valueFontSize": "50%",
- "valueMaps": [
- {
- "op": "=",
- "text": "OK",
- "value": "0"
- },
- {
- "op": "=",
- "text": "WARN",
- "value": "1"
- },
- {
- "op": "=",
- "text": "ERR",
- "value": "2"
- }
- ],
- "valueName": "current"
- },
- {
- "colorMode": "Panel",
- "colors": {
- "crit": "rgb(255, 0, 0)",
- "disable": "rgba(128, 128, 128, 0.9)",
- "ok": "rgba(50, 128, 45, 0.9)",
- "warn": "rgba(237, 129, 40, 0.9)"
- },
- "cornerRadius": 0,
- "datasource": "$datasource",
- "displayName": "",
- "flipCard": false,
- "flipTime": 5,
- "fontFormat": "Regular",
- "gridPos": {
- "h": 3,
- "w": 2,
- "x": 2,
- "y": 0
- },
- "id": 43,
- "isAutoScrollOnOverflow": false,
- "isGrayOnNoData": false,
- "isHideAlertsOnDisable": false,
- "isIgnoreOKColors": false,
- "links": [],
- "targets": [
- {
- "aggregation": "Last",
- "alias": "All",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "count(ceph_osd_metadata)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "All",
- "refId": "A",
- "units": "none",
- "valueHandler": "Number Threshold"
- },
- {
- "aggregation": "Last",
- "alias": "In",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "sum(ceph_osd_in)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "In",
- "refId": "B",
- "units": "none",
- "valueHandler": "Number Threshold"
- },
- {
- "aggregation": "Last",
- "alias": "Out",
- "decimals": 2,
- "displayAliasType": "Warning / Critical",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "sum(ceph_osd_in == bool 0)",
- "format": "time_series",
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "Out",
- "refId": "C",
- "units": "none",
- "valueHandler": "Number Threshold",
- "warn": 1
- },
- {
- "aggregation": "Last",
- "alias": "Up",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "sum(ceph_osd_up)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Up",
- "refId": "D",
- "units": "none",
- "valueHandler": "Number Threshold"
- },
- {
- "aggregation": "Last",
- "alias": "Down",
- "crit": 2,
- "decimals": 2,
- "displayAliasType": "Warning / Critical",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "sum(ceph_osd_up == bool 0)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Down",
- "refId": "E",
- "units": "none",
- "valueHandler": "Number Threshold",
- "warn": 1
- }
- ],
- "title": "OSDs",
- "type": "vonage-status-panel"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "decimals": 2,
- "format": "percentunit",
- "gauge": {
- "maxValue": 1,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 6,
- "w": 4,
- "x": 4,
- "y": 0
- },
- "id": 47,
- "interval": null,
- "links": [],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": true
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_osd_stat_bytes_used)/sum(ceph_osd_stat_bytes)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Used",
- "refId": "A"
- }
- ],
- "thresholds": "0.7,0.8",
- "title": "Capacity used",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
- "h": 6,
- "w": 8,
- "x": 8,
- "y": 0
- },
- "id": 53,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "Active",
- "color": "#508642",
- "fill": 1,
- "stack": "A"
- },
- {
- "alias": "Total",
- "color": "#f9e2d2"
- },
- {
- "alias": "Degraded",
- "color": "#eab839"
- },
- {
- "alias": "Undersized",
- "color": "#f9934e"
- },
- {
- "alias": "Inconsistent",
- "color": "#e24d42"
- },
- {
- "alias": "Down",
- "color": "#bf1b00"
- },
- {
- "alias": "Inactive",
- "color": "#bf1b00",
- "fill": 4,
- "linewidth": 0,
- "stack": "A"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(ceph_pg_total)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Total",
- "refId": "A"
- },
- {
- "expr": "sum(ceph_pg_active)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Active",
- "refId": "B"
- },
- {
- "expr": "sum(ceph_pg_total - ceph_pg_active)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Inactive",
- "refId": "G"
- },
- {
- "expr": "sum(ceph_pg_undersized)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Undersized",
- "refId": "F"
- },
- {
- "expr": "sum(ceph_pg_degraded)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Degraded",
- "refId": "C"
- },
- {
- "expr": "sum(ceph_pg_inconsistent)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Inconsistent",
- "refId": "D"
- },
- {
- "expr": "sum(ceph_pg_down)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Down",
- "refId": "E"
- }
- ],
- "thresholds": [],
- "timeFrom": null,
- "timeShift": null,
- "title": "PG States",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
- "h": 6,
- "w": 8,
- "x": 16,
- "y": 0
- },
- "id": 66,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "Avg Apply Latency",
- "color": "#7eb26d"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "quantile(0.95, ceph_osd_apply_latency_ms)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Apply Latency P_95",
- "refId": "A"
- },
- {
- "expr": "quantile(0.95, ceph_osd_commit_latency_ms)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Commit Latency P_95",
- "refId": "B"
- },
- {
- "expr": "avg(ceph_osd_apply_latency_ms)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Avg Apply Latency",
- "refId": "C"
- },
- {
- "expr": "avg(ceph_osd_commit_latency_ms)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Avg Commit Latency",
- "refId": "D"
- }
- ],
- "thresholds": [],
- "timeFrom": null,
- "timeShift": null,
- "title": "OSD Latencies",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "ms",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "clusterName": "",
- "colorMode": "Panel",
- "colors": {
- "crit": "rgba(245, 54, 54, 0.9)",
- "disable": "rgba(128, 128, 128, 0.9)",
- "ok": "rgba(50, 128, 45, 0.9)",
- "warn": "rgba(237, 129, 40, 0.9)"
- },
- "cornerRadius": 1,
- "datasource": "$datasource",
- "displayName": "",
- "flipCard": false,
- "flipTime": 5,
- "fontFormat": "Regular",
- "gridPos": {
- "h": 3,
- "w": 2,
- "x": 0,
- "y": 3
- },
- "id": 41,
- "isAutoScrollOnOverflow": false,
- "isGrayOnNoData": false,
- "isHideAlertsOnDisable": false,
- "isIgnoreOKColors": false,
- "links": [],
- "targets": [
- {
- "aggregation": "Last",
- "alias": "In Quorum",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "sum(ceph_mon_quorum_status)",
- "format": "time_series",
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "In Quorum",
- "refId": "A",
- "units": "none",
- "valueHandler": "Text Only"
- },
- {
- "aggregation": "Last",
- "alias": "Total",
- "crit": 1,
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "count(ceph_mon_quorum_status)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Total",
- "refId": "B",
- "units": "none",
- "valueHandler": "Text Only",
- "warn": 2
- },
- {
- "aggregation": "Last",
- "alias": "MONs out of Quorum",
- "crit": 1.6,
- "decimals": 2,
- "displayAliasType": "Warning / Critical",
- "displayType": "Annotation",
- "displayValueWithAlias": "Never",
- "expr": "count(ceph_mon_quorum_status) / sum(ceph_mon_quorum_status)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "MONs out of Quorum",
- "refId": "C",
- "units": "none",
- "valueHandler": "Number Threshold",
- "warn": 1.1
- }
- ],
- "title": "Monitors",
- "type": "vonage-status-panel"
- },
- {
- "colorMode": "Panel",
- "colors": {
- "crit": "rgba(245, 54, 54, 0.9)",
- "disable": "rgba(128, 128, 128, 0.9)",
- "ok": "rgba(50, 128, 45, 0.9)",
- "warn": "rgba(237, 129, 40, 0.9)"
- },
- "cornerRadius": 0,
- "datasource": "$datasource",
- "displayName": "",
- "flipCard": false,
- "flipTime": 5,
- "fontFormat": "Regular",
- "gridPos": {
- "h": 3,
- "w": 2,
- "x": 2,
- "y": 3
- },
- "id": 68,
- "isAutoScrollOnOverflow": false,
- "isGrayOnNoData": false,
- "isHideAlertsOnDisable": false,
- "isIgnoreOKColors": false,
- "links": [],
- "targets": [
- {
- "aggregation": "Last",
- "alias": "Active",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "count(ceph_mgr_status == 1) or vector(0)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Active",
- "refId": "A",
- "units": "none",
- "valueHandler": "Number Threshold"
- },
- {
- "aggregation": "Last",
- "alias": "Standby",
- "decimals": 2,
- "displayAliasType": "Always",
- "displayType": "Regular",
- "displayValueWithAlias": "When Alias Displayed",
- "expr": "count(ceph_mgr_status == 0) or vector(0)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Standby",
- "refId": "B",
- "units": "none",
- "valueHandler": "Number Threshold"
- }
- ],
- "title": "MGRs",
- "type": "vonage-status-panel"
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 6
- },
- "id": 45,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 0.5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "Reads",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(ceph_osd_op_w_in_bytes[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Writes",
- "refId": "A"
- },
- {
- "expr": "sum(irate(ceph_osd_op_r_out_bytes[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Reads",
- "refId": "B"
- }
- ],
- "thresholds": [],
- "timeFrom": null,
- "timeShift": null,
- "title": "Cluster I/O",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 6
- },
- "id": 62,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(deriv(ceph_pool_stored[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "refId": "A"
- }
- ],
- "thresholds": [],
- "timeFrom": null,
- "timeShift": null,
- "title": "In-/Egress",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": " Egress (-) / Ingress (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "cards": {
- "cardPadding": null,
- "cardRound": 1
- },
- "color": {
- "cardColor": "rgb(0, 254, 255)",
- "colorScale": "sqrt",
- "colorScheme": "interpolateBlues",
- "exponent": 0.5,
- "min": null,
- "mode": "spectrum"
- },
- "dataFormat": "timeseries",
- "datasource": "$datasource",
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 0,
- "y": 15
- },
- "heatmap": {},
- "highlightCards": true,
- "id": 55,
- "legend": {
- "show": true
- },
- "links": [],
- "span": 12,
- "targets": [
- {
- "expr": "ceph_osd_stat_bytes_used / ceph_osd_stat_bytes",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 1,
- "legendFormat": "Util (%)",
- "refId": "A",
- "step": 60
- }
- ],
- "timeFrom": null,
- "title": "OSD Capacity Utilization",
- "tooltip": {
- "show": true,
- "showHistogram": false
- },
- "type": "heatmap",
- "xAxis": {
- "show": true
- },
- "xBucketNumber": null,
- "xBucketSize": "",
- "yAxis": {
- "decimals": 2,
- "format": "percentunit",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true,
- "splitFactor": null
- },
- "yBucketNumber": null,
- "yBucketSize": null
- },
- {
- "cards": {
- "cardPadding": null,
- "cardRound": 1
- },
- "color": {
- "cardColor": "#b4ff00",
- "colorScale": "sqrt",
- "colorScheme": "interpolateBlues",
- "exponent": 0.5,
- "mode": "spectrum"
- },
- "dataFormat": "timeseries",
- "datasource": "$datasource",
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 6,
- "y": 15
- },
- "heatmap": {},
- "highlightCards": true,
- "id": 59,
- "legend": {
- "show": true
- },
- "links": [],
- "targets": [
- {
- "expr": "ceph_osd_numpg",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "#PGs",
- "refId": "A"
- }
- ],
- "title": "PGs per OSD",
- "tooltip": {
- "show": true,
- "showHistogram": false
- },
- "type": "heatmap",
- "xAxis": {
- "show": true
- },
- "xBucketNumber": null,
- "xBucketSize": "",
- "yAxis": {
- "decimals": null,
- "format": "none",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true,
- "splitFactor": null
- },
- "yBucketNumber": null,
- "yBucketSize": null
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 15
- },
- "id": 64,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(ceph_osd_recovery_ops[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Op/s",
- "refId": "A"
- }
- ],
- "thresholds": [],
- "timeFrom": null,
- "timeShift": null,
- "title": "Recovery Rate",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "ops",
- "label": "Recovery Ops/s",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "refresh": "30s",
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "ceph",
- "cluster"
- ],
- "templating": {
- "list": [
- {
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "auto": true,
- "auto_count": 10,
- "auto_min": "1m",
- "current": {
- "text": "auto",
- "value": "$__auto_interval_interval"
- },
- "datasource": null,
- "hide": 0,
- "includeAll": false,
- "label": "Interval",
- "multi": false,
- "name": "interval",
- "options": [
- {
- "selected": true,
- "text": "auto",
- "value": "$__auto_interval_interval"
- },
- {
- "selected": false,
- "text": "1m",
- "value": "1m"
- },
- {
- "selected": false,
- "text": "10m",
- "value": "10m"
- },
- {
- "selected": false,
- "text": "30m",
- "value": "30m"
- },
- {
- "selected": false,
- "text": "1h",
- "value": "1h"
- },
- {
- "selected": false,
- "text": "6h",
- "value": "6h"
- },
- {
- "selected": false,
- "text": "12h",
- "value": "12h"
- },
- {
- "selected": false,
- "text": "1d",
- "value": "1d"
- },
- {
- "selected": false,
- "text": "7d",
- "value": "7d"
- },
- {
- "selected": false,
- "text": "14d",
- "value": "14d"
- },
- {
- "selected": false,
- "text": "30d",
- "value": "30d"
- }
- ],
- "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
- "refresh": 2,
- "type": "interval"
- }
- ]
- },
- "time": {
- "from": "now-6h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "Ceph - Cluster",
- "version": 13
- }
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "MDS Performance",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*Reads/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(rate(ceph_objecter_op_r{ceph_daemon=~\"($mds_servers).*\"}[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read Ops",
- "refId": "A"
- },
- {
- "expr": "sum(rate(ceph_objecter_op_w{ceph_daemon=~\"($mds_servers).*\"}[1m]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write Ops",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "MDS Workload - $mds_servers",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "none",
- "label": "Reads(-) / Writes (+)",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "ceph_mds_server_handle_client_request{ceph_daemon=~\"($mds_servers).*\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{ceph_daemon}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Client Request Load - $mds_servers",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "none",
- "label": "Client Requests",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "MDS Server",
- "multi": false,
- "name": "mds_servers",
- "options": [ ],
- "query": "label_values(ceph_mds_inodes, ceph_daemon)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "MDS Performance",
- "uid": "tbO9LAiZz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- },
- {
- "id": "singlestat",
- "name": "Singlestat",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "$ceph_hosts System Overview",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 3,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "count(sum by (ceph_daemon) (ceph_osd_metadata{hostname='$ceph_hosts'}))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "OSDs",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "aliasColors": {
- "interrupt": "#447EBC",
- "steal": "#6D1F62",
- "system": "#890F02",
- "user": "#3F6833",
- "wait": "#C15C17"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Shows the CPU breakdown. When multiple servers are selected, only the first host's cpu data is shown",
- "fill": 1,
- "gridPos": {
- "h": 10,
- "w": 6,
- "x": 3,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (mode) (\n irate(node_cpu{instance=~\"($ceph_hosts)([\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[1m]) or\n irate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[1m])\n) / scalar(\n sum(irate(node_cpu{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[1m]) or\n irate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[1m]))\n) * 100",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{mode}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Utilization",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "percent",
- "label": "% Utilization",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "Available": "#508642",
- "Free": "#508642",
- "Total": "#bf1b00",
- "Used": "#bf1b00",
- "total": "#bf1b00",
- "used": "#0a50a1"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 10,
- "w": 6,
- "x": 9,
- "y": 1
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "total",
- "color": "#bf1b00",
- "fill": 0,
- "linewidth": 2,
- "stack": false
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "node_memory_MemFree{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"} ",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Free",
- "refId": "A"
- },
- {
- "expr": "node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"} ",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "total",
- "refId": "B"
- },
- {
- "expr": "(node_memory_Cached{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n(node_memory_Buffers{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) +\n(node_memory_Slab{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) \n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "buffers/cache",
- "refId": "C"
- },
- {
- "expr": "(node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"})- (\n (node_memory_MemFree{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n (node_memory_Cached{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) + \n (node_memory_Buffers{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"}) +\n (node_memory_Slab{instance=~\"$ceph_hosts([\\\\.:].*)?\"} or node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\.:].*)?\"})\n )\n \n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "used",
- "refId": "D"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "RAM Usage",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": "RAM used",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Show the network load (rx,tx) across all interfaces (excluding loopback 'lo')",
- "fill": 1,
- "gridPos": {
- "h": 10,
- "w": 6,
- "x": 15,
- "y": 1
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*tx/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (device) (\n irate(node_network_receive_bytes{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m]) or \n irate(node_network_receive_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m])\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.rx",
- "refId": "A"
- },
- {
- "expr": "sum by (device) (\n irate(node_network_transmit_bytes{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\",device!=\"lo\"}[1m])\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.tx",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network Load",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "decbytes",
- "label": "Send (-) / Receive (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 5,
- "w": 3,
- "x": 21,
- "y": 1
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*tx/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(node_network_receive_drop{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_receive_drop_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.rx",
- "refId": "A"
- },
- {
- "expr": "irate(node_network_transmit_drop{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_transmit_drop_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.tx",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network drop rate",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "pps",
- "label": "Send (-) / Receive (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 3,
- "x": 0,
- "y": 6
- },
- "id": 8,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_osd_stat_bytes and on (ceph_daemon) ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"})",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Raw Capacity",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 5,
- "w": 3,
- "x": 21,
- "y": 6
- },
- "id": 9,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*tx/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(node_network_receive_errs{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_receive_errs_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.rx",
- "refId": "A"
- },
- {
- "expr": "irate(node_network_transmit_errs{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m]) or irate(node_network_transmit_errs_total{instance=~\"$ceph_hosts([\\\\.:].*)?\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}.tx",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network error rate",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "pps",
- "label": "Send (-) / Receive (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 11
- },
- "id": 10,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "OSD Disk Performance Statistics",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it's name and corresponding OSD id value",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 11,
- "x": 0,
- "y": 12
- },
- "id": 11,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "connected",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*reads/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(\n (\n irate(node_disk_writes_completed{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or\n irate(node_disk_writes_completed_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n )",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}}) writes",
- "refId": "A"
- },
- {
- "expr": "label_replace(\n (irate(node_disk_reads_completed{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_reads_completed_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ),\n \"instance\",\n \"$1\",\n \"instance\",\n \"([^:.]*).*\"\n )",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}}) reads",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$ceph_hosts Disk IOPS",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ops",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 11,
- "x": 12,
- "y": 12
- },
- "id": 12,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "connected",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*read/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace((irate(node_disk_bytes_written{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_written_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}}) write",
- "refId": "A"
- },
- {
- "expr": "label_replace((irate(node_disk_bytes_read{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_read_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}}) read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$ceph_hosts Throughput by Disk",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it's corresponding OSD id",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 11,
- "x": 0,
- "y": 21
- },
- "id": 13,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) ) / clamp_min(irate(node_disk_writes_completed_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]), 0.001) or (irate(node_disk_read_time_seconds_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) ) / clamp_min(irate(node_disk_reads_completed_total{ instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]), 0.001), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")) * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}})",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$ceph_hosts Disk Latency",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": "",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 11,
- "x": 12,
- "y": 21
- },
- "id": 14,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "connected",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(((irate(node_disk_io_time_ms{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) / 10 ) or irate(node_disk_io_time_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}}({{ceph_daemon}})",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$ceph_hosts Disk utilization",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "percent",
- "label": "%Util",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "refresh": "10s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "overview"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "Hostname",
- "multi": false,
- "name": "ceph_hosts",
- "options": [ ],
- "query": "label_values(node_scrape_collector_success, instance) ",
- "refresh": 1,
- "regex": "([^.:]*).*",
- "sort": 3,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "Host Details",
- "uid": "rtOg0AiWz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- },
- {
- "id": "singlestat",
- "name": "Singlestat",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "count(sum by (hostname) (ceph_osd_metadata))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "OSD Hosts",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster",
- "format": "percentunit",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 4,
- "y": 0
- },
- "id": 3,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "avg(\n 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "AVG CPU Busy",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)",
- "format": "percentunit",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 8,
- "y": 0
- },
- "id": 4,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "avg (((node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"})- (\n (node_memory_MemFree{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemFree_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) + \n (node_memory_Cached{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Cached_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) + \n (node_memory_Buffers{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Buffers_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) +\n (node_memory_Slab{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_Slab_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"})\n )) /\n (node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*\"} ))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "AVG RAM Utilization",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "IOPS Load at the device as reported by the OS on all OSD hosts",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 12,
- "y": 0
- },
- "id": 5,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum ((irate(node_disk_reads_completed{instance=~\"($osd_hosts).*\"}[5m]) or irate(node_disk_reads_completed_total{instance=~\"($osd_hosts).*\"}[5m]) ) + \n(irate(node_disk_writes_completed{instance=~\"($osd_hosts).*\"}[5m]) or irate(node_disk_writes_completed_total{instance=~\"($osd_hosts).*\"}[5m])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Physical IOPS",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 16,
- "y": 0
- },
- "id": 6,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "avg (\n label_replace((irate(node_disk_io_time_ms[5m]) / 10 ) or\n (irate(node_disk_io_time_seconds_total[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\"\n ) *\n on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~\"($osd_hosts).*\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\")\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "AVG Disk Utilization",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Total send/receive network load across all hosts in the ceph cluster",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 5,
- "w": 4,
- "x": 20,
- "y": 0
- },
- "id": 7,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum (\n\t(\n\t\tirate(node_network_receive_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m]) or\n\t\tirate(node_network_receive_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n\t) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n) +\nsum (\n\t(\n\t\tirate(node_network_transmit_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m]) or\n\t\tirate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n\t) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n\t)\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Network Load",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Show the top 10 busiest hosts by cpu",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 5
- },
- "id": 8,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "topk(10,100 * ( 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]) or\n irate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[1m]))\n )\n )\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Busy - Top 10 Hosts",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "percent",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Top 10 hosts by network load",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 5
- },
- "id": 9,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "topk(10, (sum by(instance) (\n(\n\tirate(node_network_receive_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m]) or\n\tirate(node_network_receive_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m])\n) +\n(\n\tirate(node_network_transmit_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m]) or\n\tirate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[1m])\n) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\"))\n))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network Load - Top 10 Hosts",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": "10s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "osd_hosts",
- "options": [ ],
- "query": "label_values(ceph_disk_occupation, exported_instance)",
- "refresh": 1,
- "regex": "([^.]*).*",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "mon_hosts",
- "options": [ ],
- "query": "label_values(ceph_mon_metadata, ceph_daemon)",
- "refresh": 1,
- "regex": "mon.(.*)",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "mds_hosts",
- "options": [ ],
- "query": "label_values(ceph_mds_inodes, ceph_daemon)",
- "refresh": 1,
- "regex": "mds.(.*)",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "rgw_hosts",
- "options": [ ],
- "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
- "refresh": 1,
- "regex": "rgw.(.*)",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "Host Overview",
- "uid": "y0KGL0iZz",
- "version": 0
-}
+++ /dev/null
-local g = import 'grafana.libsonnet';
-
-local dashboardSchema(title, description, uid, time_from, refresh, schemaVersion, tags, timezone, timepicker) =
- g.dashboard.new(title=title, description=description, uid=uid, time_from=time_from, refresh=refresh, schemaVersion=schemaVersion, tags=tags, timezone=timezone, timepicker=timepicker);
-
-local graphPanelSchema(aliasColors, title, description, nullPointMode, stack, formatY1, formatY2, labelY1, labelY2, min, fill, datasource, legend_alignAsTable=false, legend_avg=false, legend_min=false, legend_max=false, legend_current=false, legend_values=false) =
- g.graphPanel.new(aliasColors=aliasColors, title=title, description=description, nullPointMode=nullPointMode, stack=stack, formatY1=formatY1, formatY2=formatY2, labelY1=labelY1, labelY2=labelY2, min=min, fill=fill, datasource=datasource, legend_alignAsTable=legend_alignAsTable, legend_avg=legend_avg, legend_min=legend_min, legend_max=legend_max, legend_current=legend_current, legend_values=legend_values);
-
-local addTargetSchema(expr, intervalFactor, format, legendFormat) =
- g.prometheus.target(expr=expr, intervalFactor=intervalFactor, format=format, legendFormat=legendFormat);
-
-local addTemplateSchema(name, datasource, query, refresh, includeAll, sort, label, regex) =
- g.template.new(name=name, datasource=datasource, query=query, refresh=refresh, includeAll=includeAll, sort=sort, label=label, regex=regex);
-
-local addAnnotationSchema(builtIn, datasource, enable, hide, iconColor, name, type) =
- g.annotation.datasource(builtIn=builtIn, datasource=datasource, enable=enable, hide=hide, iconColor=iconColor, name=name, type=type);
-
-local addRowSchema(collapse, showTitle, title) =
- g.row.new(collapse=collapse, showTitle=showTitle, title=title);
-
-local addSingelStatSchema(colors, datasource, format, title, description, valueName, colorValue, gaugeMaxValue, gaugeShow, sparklineShow, thresholds) =
- g.singlestat.new(colors=colors, datasource=datasource, format=format, title=title, description=description, valueName=valueName, colorValue=colorValue, gaugeMaxValue=gaugeMaxValue, gaugeShow=gaugeShow, sparklineShow=sparklineShow, thresholds=thresholds);
-
-local addPieChartSchema(aliasColors, datasource, description, legendType, pieType, title, valueName) =
- g.pieChartPanel.new(aliasColors=aliasColors, datasource=datasource, description=description, legendType=legendType, pieType=pieType, title=title, valueName=valueName);
-
-local addTableSchema(datasource, description, sort, styles, title, transform) =
- g.tablePanel.new(datasource=datasource, description=description, sort=sort, styles=styles, title=title, transform=transform);
-
-local addStyle(alias, colorMode, colors, dateFormat, decimals, mappingType, pattern, thresholds, type, unit, valueMaps) =
- {'alias': alias, 'colorMode': colorMode, 'colors':colors, 'dateFormat':dateFormat, 'decimals':decimals, 'mappingType':mappingType, 'pattern':pattern, 'thresholds':thresholds, 'type':type, 'unit':unit, 'valueMaps':valueMaps};
-
-{
- "hosts-overview.json":
- local HostsOverviewSingleStatPanel(format, title, description, valueName, expr, targetFormat, x, y, w, h) =
- addSingelStatSchema(['#299c46','rgba(237, 129, 40, 0.89)','#d44a3a'], '$datasource', format, title, description, valueName, false, 100, false, false, '')
- .addTarget(addTargetSchema(expr, 1, targetFormat, '')) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- local HostsOverviewGraphPanel(title, description, formatY1, expr, legendFormat, x, y, w, h) =
- graphPanelSchema({}, title, description, 'null', false, formatY1, 'short', null, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'Host Overview', '', 'y0KGL0iZz', 'now-1h', '10s', 16, [], '', {refresh_intervals:['5s','10s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addRequired(
- type='panel', id='singlestat', name='Singlestat', version='5.0.0'
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('osd_hosts', '$datasource', 'label_values(ceph_disk_occupation, exported_instance)', 1, true, 1, null, '([^.]*).*')
- )
- .addTemplate(
- addTemplateSchema('mon_hosts', '$datasource', 'label_values(ceph_mon_metadata, ceph_daemon)', 1, true, 1, null, 'mon.(.*)')
- )
- .addTemplate(
- addTemplateSchema('mds_hosts', '$datasource', 'label_values(ceph_mds_inodes, ceph_daemon)', 1, true, 1, null, 'mds.(.*)')
- )
- .addTemplate(
- addTemplateSchema('rgw_hosts', '$datasource', 'label_values(ceph_rgw_metadata, ceph_daemon)', 1, true, 1, null, 'rgw.(.*)')
- )
- .addPanels([
- HostsOverviewSingleStatPanel(
- 'none',
- 'OSD Hosts',
- '',
- 'current',
- 'count(sum by (hostname) (ceph_osd_metadata))',
- 'time_series',
- 0, 0, 4, 5
- ),
- HostsOverviewSingleStatPanel(
- 'percentunit',
- 'AVG CPU Busy',
- 'Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster',
- 'current',
- 'avg(\n 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode=\'idle\',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[1m]) or\n irate(node_cpu{mode=\'idle\',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[1m]))\n )\n )',
- 'time_series',
- 4, 0, 4, 5
- ),
- HostsOverviewSingleStatPanel(
- 'percentunit',
- 'AVG RAM Utilization',
- 'Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)',
- 'current',
- 'avg (((node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemTotal_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"})- (\n (node_memory_MemFree{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemFree_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) + \n (node_memory_Cached{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Cached_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) + \n (node_memory_Buffers{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Buffers_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) +\n (node_memory_Slab{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_Slab_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"})\n )) /\n (node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or node_memory_MemTotal_bytes{instance=~"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*"} ))',
- 'time_series',
- 8, 0, 4, 5
- ),
- HostsOverviewSingleStatPanel(
- 'none',
- 'Physical IOPS',
- 'IOPS Load at the device as reported by the OS on all OSD hosts',
- 'current',
- 'sum ((irate(node_disk_reads_completed{instance=~"($osd_hosts).*"}[5m]) or irate(node_disk_reads_completed_total{instance=~"($osd_hosts).*"}[5m]) ) + \n(irate(node_disk_writes_completed{instance=~"($osd_hosts).*"}[5m]) or irate(node_disk_writes_completed_total{instance=~"($osd_hosts).*"}[5m])))',
- 'time_series',
- 12, 0, 4, 5
- ),
- HostsOverviewSingleStatPanel(
- 'percent',
- 'AVG Disk Utilization',
- 'Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)',
- 'current',
- 'avg (\n label_replace((irate(node_disk_io_time_ms[5m]) / 10 ) or\n (irate(node_disk_io_time_seconds_total[5m]) * 100), "instance", "$1", "instance", "([^.:]*).*"\n ) *\n on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($osd_hosts).*"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^.:]*).*")\n)',
- 'time_series',
- 16, 0, 4, 5
- ),
- HostsOverviewSingleStatPanel(
- 'bytes',
- 'Network Load',
- 'Total send/receive network load across all hosts in the ceph cluster',
- 'current',
- 'sum (\n\t(\n\t\tirate(node_network_receive_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m]) or\n\t\tirate(node_network_receive_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m])\n\t) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)")\n) +\nsum (\n\t(\n\t\tirate(node_network_transmit_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m]) or\n\t\tirate(node_network_transmit_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[1m])\n\t) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)")\n\t)\n'
- , 'time_series',
- 20, 0, 4, 5
- ),
- HostsOverviewGraphPanel(
- 'CPU Busy - Top 10 Hosts',
- 'Show the top 10 busiest hosts by cpu',
- 'percent',
- 'topk(10,100 * ( 1 - (\n avg by(instance) \n (irate(node_cpu_seconds_total{mode=\'idle\',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[1m]) or\n irate(node_cpu{mode=\'idle\',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[1m]))\n )\n )\n)',
- '{{instance}}',
- 0, 5, 12, 9
- ),
- HostsOverviewGraphPanel(
- 'Network Load - Top 10 Hosts',
- 'Top 10 hosts by network load',
- 'Bps',
- 'topk(10, (sum by(instance) (\n(\n\tirate(node_network_receive_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m]) or\n\tirate(node_network_receive_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m])\n) +\n(\n\tirate(node_network_transmit_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m]) or\n\tirate(node_network_transmit_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[1m])\n) unless on (device, instance)\n\tlabel_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)"))\n))\n'
- ,
- '{{instance}}',
- 12, 5, 12, 9
- ),
- ])
-}
-{
- "host-details.json":
- local HostDetailsSingleStatPanel(format, title, description, valueName, expr, targetFormat, x, y, w, h) =
- addSingelStatSchema(['#299c46','rgba(237, 129, 40, 0.89)','#d44a3a'], '$datasource', format, title, description, valueName, false, 100, false, false, '')
- .addTarget(addTargetSchema(expr, 1, targetFormat, '')) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- local HostDetailsGraphPanel(alias, title, description, nullPointMode, formatY1, labelY1, expr, legendFormat, x, y, w, h) =
- graphPanelSchema(alias, title, description, nullPointMode, false, formatY1, 'short', labelY1, null, null, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'Host Details', '', 'rtOg0AiWz', 'now-1h', '10s', 16, ['overview'], '', {refresh_intervals:['5s','10s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addRequired(
- type='panel', id='singlestat', name='Singlestat', version='5.0.0'
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('ceph_hosts', '$datasource', 'label_values(node_scrape_collector_success, instance) ', 1, false, 3, 'Hostname', '([^.:]*).*')
- )
- .addPanels([
- addRowSchema(false, true, '$ceph_hosts System Overview') + {gridPos: {x: 0, y: 0, w: 24, h: 1}},
- HostDetailsSingleStatPanel(
- 'none',
- 'OSDs',
- '',
- 'current',
- 'count(sum by (ceph_daemon) (ceph_osd_metadata{hostname=\'$ceph_hosts\'}))',
- 'time_series',
- 0, 1, 3, 5
- ),
- HostDetailsGraphPanel(
- {"interrupt": "#447EBC","steal": "#6D1F62","system": "#890F02","user": "#3F6833","wait": "#C15C17"},
- 'CPU Utilization',
- 'Shows the CPU breakdown. When multiple servers are selected, only the first host\'s cpu data is shown',
- 'null',
- 'percent',
- '% Utilization',
- 'sum by (mode) (\n irate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[1m]) or\n irate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[1m])\n) / scalar(\n sum(irate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?"}[1m]) or\n irate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[1m]))\n) * 100',
- '{{mode}}',
- 3, 1, 6, 10
- ),
- HostDetailsGraphPanel(
- {"Available": "#508642","Free": "#508642","Total": "#bf1b00","Used": "#bf1b00","total": "#bf1b00","used": "#0a50a1"},
- 'RAM Usage',
- '',
- 'null',
- 'bytes',
- 'RAM used',
- 'node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} ',
- 'Free',
- 9, 1, 6, 10)
- .addTargets(
- [
- addTargetSchema(
- 'node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} ',
- 1,
- 'time_series',
- 'total'
- ),
- addTargetSchema(
- '(node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n(node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) +\n(node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) \n',
- 1,
- 'time_series',
- 'buffers/cache'
- ),
- addTargetSchema(
- '(node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"})- (\n (node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n (node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) + \n (node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"}) +\n (node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"})\n )\n \n',
- 1,
- 'time_series',
- 'used'
- )])
- .addSeriesOverride({"alias": "total","color": "#bf1b00","fill": 0,"linewidth": 2,"stack": false}
- ),
- HostDetailsGraphPanel(
- {},
- 'Network Load',
- 'Show the network load (rx,tx) across all interfaces (excluding loopback \'lo\')',
- 'null',
- 'decbytes',
- 'Send (-) / Receive (+)',
- 'sum by (device) (\n irate(node_network_receive_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m]) or \n irate(node_network_receive_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m])\n)',
- '{{device}}.rx',
- 15, 1, 6, 10
- )
- .addTargets(
- [
- addTargetSchema(
- 'sum by (device) (\n irate(node_network_transmit_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m]) or\n irate(node_network_transmit_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[1m])\n)',
- 1,
- 'time_series',
- '{{device}}.tx'
- )])
- .addSeriesOverride({"alias": "/.*tx/","transform": "negative-Y"}
- ),
- HostDetailsGraphPanel(
- {},
- 'Network drop rate',
- '',
- 'null',
- 'pps',
- 'Send (-) / Receive (+)',
- 'irate(node_network_receive_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_receive_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
- '{{device}}.rx',
- 21, 1, 3, 5
- )
- .addTargets(
- [
- addTargetSchema(
- 'irate(node_network_transmit_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_transmit_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
- 1,
- 'time_series',
- '{{device}}.tx'
- )])
- .addSeriesOverride({"alias": "/.*tx/","transform": "negative-Y"}
- ),
- HostDetailsSingleStatPanel(
- 'bytes',
- 'Raw Capacity',
- 'Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.',
- 'current',
- 'sum(ceph_osd_stat_bytes and on (ceph_daemon) ceph_disk_occupation{instance=~"($ceph_hosts)([\\\\.:].*)?"})',
- 'time_series',
- 0, 6, 3, 5
- ),
- HostDetailsGraphPanel(
- {},
- 'Network error rate',
- '',
- 'null',
- 'pps',
- 'Send (-) / Receive (+)',
- 'irate(node_network_receive_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_receive_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
- '{{device}}.rx',
- 21, 6, 3, 5
- )
- .addTargets(
- [
- addTargetSchema(
- 'irate(node_network_transmit_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m]) or irate(node_network_transmit_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[1m])',
- 1,
- 'time_series',
- '{{device}}.tx'
- )])
- .addSeriesOverride({"alias": "/.*tx/","transform": "negative-Y"}
- ),
- addRowSchema(false, true, 'OSD Disk Performance Statistics') + {gridPos: {x: 0, y: 11, w: 24, h: 1}},
- HostDetailsGraphPanel(
- {},
- '$ceph_hosts Disk IOPS',
- 'For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it\'s name and corresponding OSD id value',
- 'connected',
- 'ops',
- 'Read (-) / Write (+)',
- 'label_replace(\n (\n irate(node_disk_writes_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or\n irate(node_disk_writes_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n "device",\n "$1",\n "device",\n "/dev/(.*)"\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n )',
- '{{device}}({{ceph_daemon}}) writes',
- 0, 12, 11, 9
- )
- .addTargets(
- [
- addTargetSchema(
- 'label_replace(\n (irate(node_disk_reads_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_reads_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n)\n* on(instance, device) group_left(ceph_daemon)\n label_replace(\n label_replace(\n ceph_disk_occupation_human,\n "device",\n "$1",\n "device",\n "/dev/(.*)"\n ),\n "instance",\n "$1",\n "instance",\n "([^:.]*).*"\n )',
- 1,
- 'time_series',
- '{{device}}({{ceph_daemon}}) reads'
- )])
- .addSeriesOverride({"alias": "/.*reads/","transform": "negative-Y"}
- ),
- HostDetailsGraphPanel(
- {},
- '$ceph_hosts Throughput by Disk',
- 'For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id',
- 'connected',
- 'Bps',
- 'Read (-) / Write (+)',
- 'label_replace((irate(node_disk_bytes_written{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_written_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- '{{device}}({{ceph_daemon}}) write',
- 12, 12, 11, 9
- )
- .addTargets(
- [
- addTargetSchema(
- 'label_replace((irate(node_disk_bytes_read{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) or irate(node_disk_read_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m])), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- 1,
- 'time_series',
- '{{device}}({{ceph_daemon}}) read'
- )])
- .addSeriesOverride({"alias": "/.*read/","transform": "negative-Y"}
- ),
- HostDetailsGraphPanel(
- {},
- '$ceph_hosts Disk Latency',
- 'For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it\'s corresponding OSD id',
- 'null as zero',
- 's',
- '',
- 'max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) ) / clamp_min(irate(node_disk_writes_completed_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]), 0.001) or (irate(node_disk_read_time_seconds_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) ) / clamp_min(irate(node_disk_reads_completed_total{ instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]), 0.001), "instance", "$1", "instance", "([^:.]*).*")) * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($ceph_hosts)([\\\\.:].*)?"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- '{{device}}({{ceph_daemon}})',
- 0, 21, 11, 9
- ),
- HostDetailsGraphPanel(
- {},
- '$ceph_hosts Disk utilization',
- 'Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.',
- 'connected',
- 'percent',
- '%Util',
- 'label_replace(((irate(node_disk_io_time_ms{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) / 10 ) or irate(node_disk_io_time_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[5m]) * 100), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation_human{instance=~"($ceph_hosts)([\\\\.:].*)?"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- '{{device}}({{ceph_daemon}})',
- 12, 21, 11, 9
- )
- ])
-}
-{
- "radosgw-sync-overview.json":
- local RgwSyncOverviewPanel(title, formatY1, labelY1, rgwMetric, x, y, w, h) =
- graphPanelSchema({}, title, '', 'null as zero', true, formatY1, 'short', labelY1, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema('sum by (source_zone) (rate(%s[30s]))' % rgwMetric, 1, 'time_series', '{{source_zone}}')]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'RGW Sync Overview', '', 'rgw-sync-overview', 'now-1h', '15s', 16, ["overview"], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.0.0'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- addTemplateSchema('rgw_servers', '$datasource', 'prometehus', 1, true, 1, '', '')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addPanels([
- RgwSyncOverviewPanel(
- 'Replication (throughput) from Source Zone',
- 'Bps',
- null,
- 'ceph_data_sync_from_zone_fetch_bytes_sum',
- 0, 0, 8, 7
- ),
- RgwSyncOverviewPanel(
- 'Replication (objects) from Source Zone',
- 'short',
- 'Objects/s',
- 'ceph_data_sync_from_zone_fetch_bytes_count',
- 8, 0, 8, 7
- ),
- RgwSyncOverviewPanel(
- 'Polling Request Latency from Source Zone',
- 'ms',
- null,
- 'ceph_data_sync_from_zone_poll_latency_sum',
- 16, 0, 8, 7
- ),
- RgwSyncOverviewPanel(
- 'Unsuccessful Object Replications from Source Zone',
- 'short',
- 'Count/s',
- 'ceph_data_sync_from_zone_fetch_errors',
- 0, 7, 8, 7
- )
- ])
-}
-{
- "radosgw-overview.json":
- local RgwOverviewPanel(title, description, formatY1, formatY2, expr1, legendFormat1, x, y, w, h, datasource='$datasource', legend_alignAsTable=false, legend_avg=false, legend_min=false, legend_max=false, legend_current=false, legend_values=false) =
- graphPanelSchema({}, title, description, 'null', false, formatY1, formatY2, null, null, 0, 1, datasource, legend_alignAsTable, legend_avg, legend_min, legend_max, legend_current, legend_values)
- .addTargets(
- [addTargetSchema(expr1, 1, 'time_series', legendFormat1)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'RGW Overview', '', 'WAkugZpiz', 'now-1h', '15s', 16, ['overview'], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.0.0'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- addTemplateSchema('rgw_servers', '$datasource', 'label_values(ceph_rgw_metadata, ceph_daemon)', 1, true, 1, '', '')
- )
- .addTemplate(
- addTemplateSchema('code', '$datasource', 'label_values(haproxy_server_http_responses_total{instance=~"$ingress_service"}, code)', 1, true, 1, 'HTTP Code', '')
- )
- .addTemplate(
- addTemplateSchema('ingress_service', '$datasource', 'label_values(haproxy_server_status, instance)', 1, true, 1, 'Ingress Service', '')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addPanels([
- addRowSchema(false, true, 'RGW Overview - All Gateways') + {gridPos: {x: 0, y: 0, w: 24, h: 1}},
- RgwOverviewPanel(
- 'Average GET/PUT Latencies',
- '',
- 's',
- 'short',
- 'rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata',
- 'GET AVG',
- 0, 1, 8, 7
- )
- .addTargets(
- [
- addTargetSchema(
- 'rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata',
- 1,
- 'time_series',
- 'PUT AVG'
- )]),
- RgwOverviewPanel(
- 'Total Requests/sec by RGW Instance',
- '',
- 'none',
- 'short',
- 'sum by (rgw_host) (label_replace(rate(ceph_rgw_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, "rgw_host", "$1", "ceph_daemon", "rgw.(.*)"))',
- '{{rgw_host}}',
- 8, 1, 7, 7
- ),
- RgwOverviewPanel(
- 'GET Latencies by RGW Instance',
- 'Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts',
- 's',
- 'short',
- 'label_replace(\n rate(ceph_rgw_get_initial_lat_sum[30s]) /\n rate(ceph_rgw_get_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n"rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
- '{{rgw_host}}',
- 15, 1, 6, 7
- ),
- RgwOverviewPanel(
- 'Bandwidth Consumed by Type',
- 'Total bytes transferred in/out of all radosgw instances within the cluster',
- 'bytes',
- 'short',
- 'sum(rate(ceph_rgw_get_b[30s]))',
- 'GETs',
- 0, 8, 8, 6
- )
- .addTargets(
- [
- addTargetSchema(
- 'sum(rate(ceph_rgw_put_b[30s]))',
- 1,
- 'time_series',
- 'PUTs'
- )]),
- RgwOverviewPanel(
- 'Bandwidth by RGW Instance',
- 'Total bytes transferred in/out through get/put operations, by radosgw instance',
- 'bytes',
- 'short',
- 'label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b[30s]) + \n rate(ceph_rgw_put_b[30s])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, "rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
- '{{rgw_host}}',
- 8, 8, 7, 6
- ),
- RgwOverviewPanel(
- 'PUT Latencies by RGW Instance',
- 'Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts',
- 's',
- 'short',
- 'label_replace(\n rate(ceph_rgw_put_initial_lat_sum[30s]) /\n rate(ceph_rgw_put_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n"rgw_host", "$1", "ceph_daemon", "rgw.(.*)")',
- '{{rgw_host}}',
- 15, 8, 6, 6
- ),
- addRowSchema(false, true, 'RGW Overview - HAProxy Metrics') + {gridPos: {x: 0, y: 12, w: 9, h: 12}},
- RgwOverviewPanel(
- 'Total responses by HTTP code',
- '',
- 'short',
- 'short',
- 'sum(irate(haproxy_frontend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"frontend"}[5m])) by (code)',
- 'Frontend {{ code }}',
- 0, 12, 5, 12,
- '$datasource',
- true, true, true, true, true, true)
- .addTargets(
- [
- addTargetSchema(
- 'sum(irate(haproxy_backend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"backend"}[5m])) by (code)',
- 1,
- 'time_series',
- 'Backend {{ code }}'
- )])
- .addSeriesOverride([
- { "alias": "/.*Back.*/",
- "transform": "negative-Y" },
- { "alias": "/.*1.*/" },
- { "alias": "/.*2.*/" },
- { "alias": "/.*3.*/" },
- { "alias": "/.*4.*/" },
- { "alias": "/.*5.*/" },
- { "alias": "/.*other.*/" }
- ]),
- RgwOverviewPanel(
- 'Total requests / responses',
- '',
- 'short',
- 'short',
- 'sum(irate(haproxy_frontend_http_requests_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)',
- 'Requests',
- 5, 12, 5, 12,
- '$datasource',
- true, true, true, true, true, true)
- .addTargets(
- [
- addTargetSchema('sum(irate(haproxy_backend_response_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Response errors'),
- addTargetSchema('sum(irate(haproxy_frontend_request_errors_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Requests errors'),
- addTargetSchema('sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend redispatch'),
- addTargetSchema('sum(irate(haproxy_backend_retry_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend retry'),
- addTargetSchema('sum(irate(haproxy_frontend_requests_denied_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Request denied'),
- addTargetSchema('sum(haproxy_backend_current_queue{proxy=~"backend",instance=~"$ingress_service"}) by (instance)', 2, 'time_series', 'Backend Queued'),
- ])
- .addSeriesOverride([
- {
- "alias": "/.*Response.*/",
- "transform": "negative-Y"
- },
- {
- "alias": "/.*Backend.*/",
- "transform": "negative-Y"
- }
- ]),
- RgwOverviewPanel(
- 'Total number of connections',
- '',
- 'short',
- 'short',
- 'sum(irate(haproxy_frontend_connections_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)',
- 'Front',
- 10, 12, 5, 12,
- '$datasource',
- true, true, true, true, true, true)
- .addTargets(
- [
- addTargetSchema('sum(irate(haproxy_backend_connection_attempts_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back'),
- addTargetSchema('sum(irate(haproxy_backend_connection_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back errors'),
- ])
- .addSeriesOverride([
- {
- "alias": "/.*Back.*/",
- "transform": "negative-Y"
- }
- ]),
- RgwOverviewPanel(
- 'Current total of incoming / outgoing bytes',
- '',
- 'short',
- 'short',
- 'sum(irate(haproxy_frontend_bytes_in_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)', 'IN Front', 15, 12, 6, 12, '$datasource', true, true, true, true, true, true)
- .addTargets(
- [
- addTargetSchema('sum(irate(haproxy_frontend_bytes_out_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Front'),
- addTargetSchema('sum(irate(haproxy_backend_bytes_in_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'IN Back'),
- addTargetSchema('sum(irate(haproxy_backend_bytes_out_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Back')
- ])
- .addSeriesOverride([
- {
- "alias": "/.*OUT.*/",
- "transform": "negative-Y"
- }
- ])
- ])
-}
-{
- "radosgw-detail.json":
- local RgwDetailsPanel(aliasColors, title, description, formatY1, formatY2, expr1, expr2, legendFormat1, legendFormat2, x, y, w, h) =
- graphPanelSchema(aliasColors, title, description, 'null', false, formatY1, formatY2, null, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr1, 1, 'time_series', legendFormat1),addTargetSchema(expr2, 1, 'time_series', legendFormat2)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'RGW Instance Detail', '', 'x5ARzZtmk', 'now-1h', '15s', 16, ['overview'], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.0.0'
- )
- .addRequired(
- type='panel', id='grafana-piechart-panel', name='Pie Chart', version='1.3.3'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('rgw_servers', '$datasource', 'label_values(ceph_rgw_metadata, ceph_daemon)', 1, true, 1, '', '')
- )
- .addPanels([
- addRowSchema(false, true, 'RGW Host Detail : $rgw_servers') + {gridPos: {x: 0, y: 0, w: 24, h: 1}},
- RgwDetailsPanel(
- {},
- '$rgw_servers GET/PUT Latencies',
- '',
- 's',
- 'short',
- 'sum by (instance_id) (rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'sum by (instance_id) (rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'GET {{ceph_daemon}}',
- 'PUT {{ceph_daemon}}',
- 0, 1, 6, 8
- ),
- RgwDetailsPanel(
- {},
- 'Bandwidth by HTTP Operation',
- '',
- 'bytes',
- 'short',
- 'rate(ceph_rgw_get_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'rate(ceph_rgw_put_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'GETs {{ceph_daemon}}',
- 'PUTs {{ceph_daemon}}',
- 6, 1, 7, 8
- ),
- RgwDetailsPanel(
- {"GETs": "#7eb26d","Other": "#447ebc","PUTs": "#eab839","Requests": "#3f2b5b","Requests Failed": "#bf1b00"},
- 'HTTP Request Breakdown',
- '',
- 'short',
- 'short',
- 'rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 'Requests Failed {{ceph_daemon}}',
- 'GETs {{ceph_daemon}}',
- 13, 1, 7, 8
- )
- .addTargets(
- [
- addTargetSchema(
- 'rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 1,
- 'time_series',
- 'PUTs {{ceph_daemon}}'
- ),
- addTargetSchema(
- '(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}',
- 1,
- 'time_series',
- 'Other {{ceph_daemon}}'
- )]),
- addPieChartSchema(
- {"GETs": "#7eb26d","Other (HEAD,POST,DELETE)": "#447ebc","PUTs": "#eab839","Requests": "#3f2b5b","Failures": "#bf1b00"},
- '$datasource',
- '',
- 'Under graph',
- 'pie',
- 'Workload Breakdown',
- 'current'
- )
- .addTarget(addTargetSchema('rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}', 1, 'time_series', 'Failures {{ceph_daemon}}'))
- .addTarget(addTargetSchema('rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}', 1, 'time_series', 'GETs {{ceph_daemon}}'))
- .addTarget(addTargetSchema('rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}', 1, 'time_series', 'PUTs {{ceph_daemon}}'))
- .addTarget(addTargetSchema('(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~"$rgw_servers"}', 1, 'time_series', 'Other (DELETE,LIST) {{ceph_daemon}}')) + {gridPos: {x: 20, y: 1, w: 4, h: 8}}
- ])
-}
-{
- "rbd-details.json":
- local RbdDetailsPanel(title, formatY1, expr1, expr2, x, y, w, h) =
- graphPanelSchema({}, title, '', 'null as zero', false, formatY1, formatY1, null, null, 0, 1, '$Datasource')
- .addTargets(
- [addTargetSchema(expr1, 1, 'time_series', 'Write'),addTargetSchema(expr2, 1, 'time_series', 'Read')]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'RBD Details', 'Detailed Performance of RBD Images (IOPS/Throughput/Latency)', 'YhCYGcuZz', 'now-1h', false, 16, [], '', {refresh_intervals:['5s','10s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.3'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('Datasource', 'prometheus', 'default', label=null)
- )
- .addTemplate(
- addTemplateSchema('Pool', '$Datasource', 'label_values(pool)', 1, false, 0, '', '')
- )
- .addTemplate(
- addTemplateSchema('Image', '$Datasource', 'label_values(image)', 1, false, 0, '', '')
- )
- .addPanels([
- RbdDetailsPanel(
- 'IOPS',
- 'iops',
- 'irate(ceph_rbd_write_ops{pool="$Pool", image="$Image"}[30s])',
- 'irate(ceph_rbd_read_ops{pool="$Pool", image="$Image"}[30s])',
- 0, 0, 8, 9
- ),
- RbdDetailsPanel(
- 'Throughput',
- 'Bps',
- 'irate(ceph_rbd_write_bytes{pool="$Pool", image="$Image"}[30s])',
- 'irate(ceph_rbd_read_bytes{pool="$Pool", image="$Image"}[30s])',
- 8, 0, 8, 9
- ),
- RbdDetailsPanel(
- 'Average Latency',
- 'ns',
- 'irate(ceph_rbd_write_latency_sum{pool="$Pool", image="$Image"}[30s]) / irate(ceph_rbd_write_latency_count{pool="$Pool", image="$Image"}[30s])',
- 'irate(ceph_rbd_read_latency_sum{pool="$Pool", image="$Image"}[30s]) / irate(ceph_rbd_read_latency_count{pool="$Pool", image="$Image"}[30s])',
- 16, 0, 8, 9
- )
- ])
-}
-{
- "rbd-overview.json":
- local RgwOverviewStyle(alias, pattern, type, unit) =
- addStyle(alias, null, ["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"], 'YYYY-MM-DD HH:mm:ss', 2, 1, pattern, [], type, unit, []);
- local RbdOverviewPanel(title, formatY1, expr1, expr2, legendFormat1, legendFormat2, x, y, w, h) =
- graphPanelSchema({}, title, '', 'null', false, formatY1, 'short', null, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr1, 1, 'time_series', legendFormat1),addTargetSchema(expr2, 1, 'time_series', legendFormat2)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'RBD Overview', '', '41FrpeUiz', 'now-1h', '30s', 16, ["overview"], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.4.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addRequired(
- type='datasource', id='prometheus', name='Prometheus', version='5.0.0'
- )
- .addRequired(
- type='panel', id='table', name='Table', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addPanels([
- RbdOverviewPanel(
- 'IOPS',
- 'short',
- 'round(sum(irate(ceph_rbd_write_ops[30s])))',
- 'round(sum(irate(ceph_rbd_read_ops[30s])))',
- 'Writes',
- 'Reads',
- 0, 0, 8, 7
- ),
- RbdOverviewPanel(
- 'Throughput',
- 'Bps',
- 'round(sum(irate(ceph_rbd_write_bytes[30s])))',
- 'round(sum(irate(ceph_rbd_read_bytes[30s])))',
- 'Write',
- 'Read',
- 8, 0, 8, 7
- ),
- RbdOverviewPanel(
- 'Average Latency',
- 'ns',
- 'round(sum(irate(ceph_rbd_write_latency_sum[30s])) / sum(irate(ceph_rbd_write_latency_count[30s])))',
- 'round(sum(irate(ceph_rbd_read_latency_sum[30s])) / sum(irate(ceph_rbd_read_latency_count[30s])))',
- 'Write',
- 'Read',
- 16, 0, 8, 7
- ),
- addTableSchema(
- '$datasource',
- '',
- {"col": 3,"desc": true},
- [
- RgwOverviewStyle('Pool', 'pool', 'string', 'short'),RgwOverviewStyle('Image', 'image', 'string', 'short'),RgwOverviewStyle('IOPS', 'Value', 'number', 'iops'), RgwOverviewStyle('', '/.*/', 'hidden', 'short')], 'Highest IOPS', 'table'
- )
- .addTarget(
- addTargetSchema(
- 'topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on (image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))',
- 1,
- 'table',
- '')
- ) + {gridPos: {x: 0, y: 7, w: 8, h: 7}},
- addTableSchema(
- '$datasource',
- '',
- {"col": 3,"desc": true},
- [
- RgwOverviewStyle('Pool', 'pool', 'string', 'short'),RgwOverviewStyle('Image', 'image', 'string', 'short'),RgwOverviewStyle('Throughput', 'Value', 'number', 'Bps'), RgwOverviewStyle('', '/.*/', 'hidden', 'short')], 'Highest Throughput', 'table'
- )
- .addTarget(
- addTargetSchema(
- 'topk(10, sort(sum(irate(ceph_rbd_read_bytes[30s]) + irate(ceph_rbd_write_bytes[30s])) by (pool, image, namespace)))',
- 1,
- 'table',
- ''
- )
- ) + {gridPos: {x: 8, y: 7, w: 8, h: 7}},
- addTableSchema(
- '$datasource',
- '',
- {"col": 3,"desc": true},
- [
- RgwOverviewStyle('Pool', 'pool', 'string', 'short'),RgwOverviewStyle('Image', 'image', 'string', 'short'),RgwOverviewStyle('Latency', 'Value', 'number', 'ns'), RgwOverviewStyle('', '/.*/', 'hidden', 'short')], 'Highest Latency', 'table'
- )
- .addTarget(
- addTargetSchema(
- 'topk(10,\n sum(\n irate(ceph_rbd_write_latency_sum[30s]) / clamp_min(irate(ceph_rbd_write_latency_count[30s]), 1) +\n irate(ceph_rbd_read_latency_sum[30s]) / clamp_min(irate(ceph_rbd_read_latency_count[30s]), 1)\n ) by (pool, image, namespace)\n)',
- 1,
- 'table',
- ''
- )
- ) + {gridPos: {x: 16, y: 7, w: 8, h: 7}}
- ])
-}
-{
- "pool-overview.json":
- local PoolOverviewSingleStatPanel(format, title, description, valueName, expr, targetFormat, x, y, w, h) =
- addSingelStatSchema(['#299c46','rgba(237, 129, 40, 0.89)','#d44a3a'], '$datasource', format, title, description, valueName, false, 100, false, false, '')
- .addTarget(addTargetSchema(expr, 1, targetFormat, '')) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- local PoolOverviewStyle(alias, pattern, type, unit, colorMode, thresholds, valueMaps) =
- addStyle(alias, colorMode, ["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"], 'YYYY-MM-DD HH:mm:ss', 2, 1, pattern, thresholds, type, unit, valueMaps);
-
- local PoolOverviewGraphPanel(title, description, formatY1, labelY1, expr, targetFormat, legendFormat, x, y, w, h) =
- graphPanelSchema({}, title, description, 'null as zero', false, formatY1, 'short', labelY1, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'Ceph Pools Overview', '', 'z99hzWtmk', 'now-1h', '15s', 22, [], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'Dashboard1', label='Data Source')
- )
- .addTemplate(
- g.template.custom(label='TopK', name='topk', current='15', query='15')
- )
- .addPanels([
- PoolOverviewSingleStatPanel(
- 'none',
- 'Pools',
- '',
- 'avg',
- 'count(ceph_pool_metadata)',
- 'table',
- 0, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'none',
- 'Pools with Compression',
- 'Count of the pools that have compression enabled', 'current', 'count(ceph_pool_metadata{compression_mode!="none"})',
- '',
- 3, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'bytes',
- 'Total Raw Capacity',
- 'Total raw capacity available to the cluster',
- 'current',
- 'sum(ceph_osd_stat_bytes)',
- '',
- 6, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'bytes',
- 'Raw Capacity Consumed',
- 'Total raw capacity consumed by user data and associated overheads (metadata + redundancy)',
- 'current',
- 'sum(ceph_pool_bytes_used)',
- '',
- 9, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'bytes',
- 'Logical Stored ',
- 'Total of client data stored in the cluster',
- 'current',
- 'sum(ceph_pool_stored)',
- '',
- 12, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'bytes',
- 'Compression Savings',
- 'A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression',
- 'current',
- 'sum(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used)',
- '',
- 15, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'percent',
- 'Compression Eligibility',
- 'Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data\n',
- 'current',
- '(sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_stored_raw and ceph_pool_compress_under_bytes > 0)) * 100',
- 'table',
- 18, 0, 3, 3
- ),
- PoolOverviewSingleStatPanel(
- 'none',
- 'Compression Factor',
- 'This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)',
- 'current',
- 'sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_compress_bytes_used > 0)',
- '',
- 21, 0, 3, 3
- ),
- addTableSchema(
- '$datasource', '', {"col": 5,"desc": true}, [PoolOverviewStyle('', 'Time', 'hidden', 'short', null, [], []),PoolOverviewStyle('', 'instance', 'hidden', 'short', null, [], []),PoolOverviewStyle('', 'job', 'hidden', 'short', null, [], []),PoolOverviewStyle('Pool Name', 'name', 'string', 'short', null, [], []),PoolOverviewStyle('Pool ID', 'pool_id', 'hidden', 'none', null, [], []),PoolOverviewStyle('Compression Factor', 'Value #A', 'number', 'none', null, [], []),PoolOverviewStyle('% Used', 'Value #D', 'number', 'percentunit', 'value', ['70','85'], []),PoolOverviewStyle('Usable Free', 'Value #B', 'number', 'bytes', null, [], []),PoolOverviewStyle('Compression Eligibility', 'Value #C', 'number', 'percent', null, [], []),PoolOverviewStyle('Compression Savings', 'Value #E', 'number', 'bytes', null, [], []),PoolOverviewStyle('Growth (5d)', 'Value #F', 'number', 'bytes', 'value', ['0', '0'], []),PoolOverviewStyle('IOPS', 'Value #G', 'number', 'none', null, [], []),PoolOverviewStyle('Bandwidth', 'Value #H', 'number', 'Bps', null, [], []),PoolOverviewStyle('', '__name__', 'hidden', 'short', null, [], []),PoolOverviewStyle('', 'type', 'hidden', 'short', null, [], []),PoolOverviewStyle('', 'compression_mode', 'hidden', 'short', null, [], []),PoolOverviewStyle('Type', 'description', 'string', 'short', null, [], []),PoolOverviewStyle('Stored', 'Value #J', 'number', 'bytes', null, [], []),PoolOverviewStyle('', 'Value #I', 'hidden', 'short', null, [], []),PoolOverviewStyle('Compression', 'Value #K', 'string', 'short', null, [], [{"text": "ON","value": "1"}])], 'Pool Overview', 'table'
- )
- .addTargets(
- [addTargetSchema('(ceph_pool_compress_under_bytes / ceph_pool_compress_bytes_used > 0) and on(pool_id) (((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100 > 0.5)', 1, 'table', ''),
- addTargetSchema('ceph_pool_max_avail * on(pool_id) group_left(name) ceph_pool_metadata', 1, 'table', ''),
- addTargetSchema('((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100', 1, 'table', ''),
- addTargetSchema('(ceph_pool_percent_used * on(pool_id) group_left(name) ceph_pool_metadata)', 1, 'table', ''),
- addTargetSchema('(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used > 0)', 1, 'table', ''),
- addTargetSchema('delta(ceph_pool_stored[5d])', 1, 'table', ''),
- addTargetSchema('rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])', 1, 'table', ''),
- addTargetSchema('rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])', 1, 'table', ''),
- addTargetSchema('ceph_pool_metadata', 1, 'table', ''),
- addTargetSchema('ceph_pool_stored * on(pool_id) group_left ceph_pool_metadata', 1, 'table', ''),
- addTargetSchema('ceph_pool_metadata{compression_mode!="none"}', 1, 'table', ''),
- addTargetSchema('', '', '', '')]
- ) + {gridPos: {x: 0, y: 3, w: 24, h: 6}},
- PoolOverviewGraphPanel(
- 'Top $topk Client IOPS by Pool',
- 'This chart shows the sum of read and write IOPS from all clients by pool',
- 'short',
- 'IOPS',
- 'topk($topk,round((rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])),1) * on(pool_id) group_left(instance,name) ceph_pool_metadata) ',
- 'time_series',
- '{{name}} ',
- 0, 9, 12, 8
- )
- .addTarget(
- addTargetSchema(
- 'topk($topk,rate(ceph_pool_wr[30s]) + on(pool_id) group_left(instance,name) ceph_pool_metadata) ',
- 1,
- 'time_series',
- '{{name}} - write')
- ),
- PoolOverviewGraphPanel(
- 'Top $topk Client Bandwidth by Pool',
- 'The chart shows the sum of read and write bytes from all clients, by pool',
- 'Bps',
- 'Throughput',
- 'topk($topk,(rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])) * on(pool_id) group_left(instance,name) ceph_pool_metadata)',
- 'time_series',
- '{{name}}',
- 12, 9, 12, 8
- ),
- PoolOverviewGraphPanel(
- 'Pool Capacity Usage (RAW)',
- 'Historical view of capacity usage, to help identify growth and trends in pool consumption',
- 'bytes',
- 'Capacity Used',
- 'ceph_pool_bytes_used * on(pool_id) group_right ceph_pool_metadata',
- '',
- '{{name}}',
- 0, 17, 24, 7
- )
- ])
-}
-{
- "pool-detail.json":
- local PoolDetailSingleStatPanel(format, title, description, valueName, colorValue, gaugeMaxValue, gaugeShow, sparkLineShow, thresholds, expr, targetFormat, x, y, w, h) =
- addSingelStatSchema(['#299c46','rgba(237, 129, 40, 0.89)','#d44a3a'], '$datasource', format, title, description, valueName, colorValue, gaugeMaxValue, gaugeShow, sparkLineShow, thresholds)
- .addTarget(addTargetSchema(expr, 1, targetFormat, '')) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- local PoolDetailGraphPanel(alias, title, description, formatY1, labelY1, expr, targetFormat, legendFormat, x, y, w, h) =
- graphPanelSchema(alias, title, description, 'null as zero', false, formatY1, 'short', labelY1, null, null, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'Ceph Pool Details', '', '-xyV8KCiz', 'now-1h', '15s', 22, [], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addRequired(
- type='panel', id='singlestat', name='Singlestat', version='5.0.0'
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'Prometheus admin.virt1.home.fajerski.name:9090', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('pool_name', '$datasource', 'label_values(ceph_pool_metadata,name)', 1, false, 1, 'Pool Name', '')
- )
- .addPanels([
- PoolDetailSingleStatPanel(
- 'percentunit',
- 'Capacity used',
- '',
- 'current',
- true, 1, true, true,
- '.7,.8',
- '(ceph_pool_stored / (ceph_pool_stored + ceph_pool_max_avail)) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 'time_series',
- 0, 0, 7, 7
- ),
- PoolDetailSingleStatPanel(
- 's',
- 'Time till full',
- 'Time till pool is full assuming the average fill rate of the last 6 hours',
- false, 100, false, false,
- '',
- 'current',
- '(ceph_pool_max_avail / deriv(ceph_pool_stored[6h])) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"} > 0',
- 'time_series',
- 7, 0, 5, 7
- ),
- PoolDetailGraphPanel(
- {"read_op_per_sec": "#3F6833","write_op_per_sec": "#E5AC0E"},
- '$pool_name Object Ingress/Egress',
- '',
- 'ops',
- 'Objects out(-) / in(+) ',
- 'deriv(ceph_pool_objects[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 'time_series',
- 'Objects per second',
- 12, 0, 12, 7
- ),
- PoolDetailGraphPanel(
- {"read_op_per_sec": "#3F6833","write_op_per_sec": "#E5AC0E"},
- '$pool_name Client IOPS',
- '',
- 'iops',
- 'Read (-) / Write (+)',
- 'irate(ceph_pool_rd[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 'time_series',
- 'reads',
- 0, 7, 12, 7
- )
- .addSeriesOverride({"alias": "reads","transform": "negative-Y"})
- .addTarget(
- addTargetSchema(
- 'irate(ceph_pool_wr[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 1,
- 'time_series',
- 'writes'
- )
- ),
- PoolDetailGraphPanel(
- {"read_op_per_sec": "#3F6833","write_op_per_sec": "#E5AC0E"},
- '$pool_name Client Throughput',
- '',
- 'Bps', 'Read (-) / Write (+)',
- 'irate(ceph_pool_rd_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 'time_series',
- 'reads',
- 12, 7, 12, 7
- )
- .addSeriesOverride({"alias": "reads","transform": "negative-Y"})
- .addTarget(
- addTargetSchema(
- 'irate(ceph_pool_wr_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 1,
- 'time_series',
- 'writes'
- )
- ),
- PoolDetailGraphPanel(
- {"read_op_per_sec": "#3F6833","write_op_per_sec": "#E5AC0E"},
- '$pool_name Objects',
- '',
- 'short',
- 'Objects',
- 'ceph_pool_objects * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~"$pool_name"}',
- 'time_series',
- 'Number of Objects',
- 0, 14, 12, 7
- )
- ])
-}
-{
- "osds-overview.json":
- local OsdOverviewStyle(alias, pattern, type, unit) =
- addStyle(alias, null, ["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"], 'YYYY-MM-DD HH:mm:ss', 2, 1, pattern, [], type, unit, []);
- local OsdOverviewGraphPanel(alias, title, description, formatY1, labelY1, min, expr, legendFormat1, x, y, w, h) =
- graphPanelSchema(alias, title, description, 'null', false, formatY1, 'short', labelY1, null, min, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat1)]) + {gridPos: {x: x, y: y, w: w, h: h}};
- local OsdOverviewPieChartPanel(alias, description, title) =
- addPieChartSchema(alias, '$datasource', description, 'Under graph', 'pie', title, 'current');
- local OsdOverviewSingleStatPanel(colors, format, title, description, valueName, colorValue, gaugeMaxValue, gaugeShow, sparkLineShow, thresholds, expr, targetFormat, x, y, w, h) =
- addSingelStatSchema(colors, '$datasource', format, title, description, valueName, colorValue, gaugeMaxValue, gaugeShow, sparkLineShow, thresholds)
- .addTarget(addTargetSchema(expr, 1, targetFormat, '')) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'OSD Overview', '', 'lo02I1Aiz', 'now-1h', '10s', 16, [], '', {refresh_intervals:['5s','10s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.0.0'
- )
- .addRequired(
- type='panel', id='grafana-piechart-panel', name='Pie Chart', version='1.3.3'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addRequired(
- type='panel', id='table', name='Table', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addPanels([
- OsdOverviewGraphPanel(
- {"@95%ile": "#e0752d"},
- 'OSD Read Latencies',
- '',
- 'ms',
- null,
- '0',
- 'avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)',
- 'AVG read',
- 0, 0, 8, 8
- )
- .addTargets(
- [
- addTargetSchema(
- 'max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)',
- 1,
- 'time_series',
- 'MAX read'),
- addTargetSchema(
- 'quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)',
- 1,
- 'time_series',
- '@95%ile'
- )],
- ),
- addTableSchema(
- '$datasource',
- 'This table shows the osd\'s that are delivering the 10 highest read latencies within the cluster',
- {"col": 2,"desc": true},
- [OsdOverviewStyle('OSD ID', 'ceph_daemon', 'string', 'short'),OsdOverviewStyle('Latency (ms)', 'Value', 'number', 'none'),OsdOverviewStyle('', '/.*/', 'hidden', 'short')], 'Highest READ Latencies', 'table'
- )
- .addTarget(
- addTargetSchema(
- 'topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n ))\n)\n\n',
- 1,
- 'table',
- ''
- )
- ) + {gridPos: {x: 8, y: 0, w: 4, h: 8}},
- OsdOverviewGraphPanel(
- {"@95%ile write": "#e0752d"},
- 'OSD Write Latencies',
- '',
- 'ms',
- null,
- '0',
- 'avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)',
- 'AVG write',
- 12, 0, 8, 8
- )
- .addTargets(
- [
- addTargetSchema(
- 'max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)',
- 1,
- 'time_series',
- 'MAX write'
- ),
- addTargetSchema(
- 'quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)',
- 1,
- 'time_series',
- '@95%ile write'
- )],
- ),
- addTableSchema(
- '$datasource',
- 'This table shows the osd\'s that are delivering the 10 highest write latencies within the cluster',
- {"col": 2,"desc": true},
- [OsdOverviewStyle('OSD ID', 'ceph_daemon', 'string', 'short'),OsdOverviewStyle('Latency (ms)', 'Value', 'number', 'none'),OsdOverviewStyle('', '/.*/', 'hidden', 'short')], 'Highest WRITE Latencies', 'table'
- )
- .addTarget(
- addTargetSchema(
- 'topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n',
- 1,
- 'table',
- ''
- )
- ) + {gridPos: {x: 20, y: 0, w: 4, h: 8}},
- OsdOverviewPieChartPanel(
- {},
- '',
- 'OSD Types Summary'
- )
- .addTarget(addTargetSchema('count by (device_class) (ceph_osd_metadata)', 1, 'time_series', '{{device_class}}')) + {gridPos: {x: 0, y: 8, w: 4, h: 8}},
- OsdOverviewPieChartPanel(
- {"Non-Encrypted": "#E5AC0E"},
- '',
- 'OSD Objectstore Types'
- )
- .addTarget(addTargetSchema('count(ceph_bluefs_wal_total_bytes)', 1, 'time_series', 'bluestore'))
- .addTarget(addTargetSchema('count(ceph_osd_metadata) - count(ceph_bluefs_wal_total_bytes)', 1, 'time_series', 'filestore'))
- .addTarget(addTargetSchema('absent(ceph_bluefs_wal_total_bytes)*count(ceph_osd_metadata)', 1, 'time_series', 'filestore')) + {gridPos: {x: 4, y: 8, w: 4, h: 8}},
- OsdOverviewPieChartPanel(
- {},
- 'The pie chart shows the various OSD sizes used within the cluster',
- 'OSD Size Summary'
- )
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes < 1099511627776)', 1, 'time_series', '<1TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 1099511627776 < 2199023255552)', 1, 'time_series', '<2TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 2199023255552 < 3298534883328)', 1, 'time_series', '<3TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 3298534883328 < 4398046511104)', 1, 'time_series', '<4TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 4398046511104 < 6597069766656)', 1, 'time_series', '<6TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 6597069766656 < 8796093022208)', 1, 'time_series', '<8TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 8796093022208 < 10995116277760)', 1, 'time_series', '<10TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 10995116277760 < 13194139533312)', 1, 'time_series', '<12TB'))
- .addTarget(addTargetSchema('count(ceph_osd_stat_bytes >= 13194139533312)', 1, 'time_series', '<12TB+')) + {gridPos: {x: 8, y: 8, w: 4, h: 8}},
- g.graphPanel.new(bars=true, datasource='$datasource', title='Distribution of PGs per OSD', x_axis_buckets=20, x_axis_mode='histogram', x_axis_values=['total'], formatY1='short', formatY2='short', labelY1='# of OSDs', min='0', nullPointMode='null')
- .addTarget(addTargetSchema('ceph_osd_numpg\n', 1, 'time_series', 'PGs per OSD')) + {gridPos: {x: 12, y: 8, w: 8, h: 8}},
- OsdOverviewSingleStatPanel(
- ['#d44a3a', '#299c46'],
- 'percentunit',
- 'OSD onode Hits Ratio',
- 'This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster',
- 'current',
- true, 1, true, false,
- '.75',
- 'sum(ceph_bluestore_onode_hits)/(sum(ceph_bluestore_onode_hits) + sum(ceph_bluestore_onode_misses))',
- 'time_series',
- 20, 8, 4, 8
- ),
- addRowSchema(false, true, 'R/W Profile') + {gridPos: {x: 0, y: 16, w: 24, h: 1}},
- OsdOverviewGraphPanel(
- {},
- 'Read/Write Profile',
- 'Show the read/write workload profile overtime',
- 'short',
- null,
- null,
- 'round(sum(irate(ceph_pool_rd[30s])))',
- 'Reads',
- 0, 17, 24, 8
- )
- .addTargets([addTargetSchema('round(sum(irate(ceph_pool_wr[30s])))', 1, 'time_series', 'Writes')])
- ])
-}
-{
- "osd-device-details.json":
- local OsdDeviceDetailsPanel(title, description, formatY1, labelY1, expr1, expr2, legendFormat1, legendFormat2, x, y, w, h) =
- graphPanelSchema({}, title, description, 'null', false, formatY1, 'short', labelY1, null, null, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr1, 1, 'time_series', legendFormat1),addTargetSchema(expr2, 1, 'time_series', legendFormat2)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'OSD device details', '', 'CrAHE0iZz', 'now-3h', '', 16, [], '', {refresh_intervals:['5s','10s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('osd', '$datasource', 'label_values(ceph_osd_metadata,ceph_daemon)', 1, false, 1, 'OSD', '(.*)')
- )
- .addPanels([
- addRowSchema(false, true, 'OSD Performance') + {gridPos: {x: 0, y: 0, w: 24, h: 1}},
- OsdDeviceDetailsPanel(
- '$osd Latency',
- '',
- 's',
- 'Read (-) / Write (+)',
- 'irate(ceph_osd_op_r_latency_sum{ceph_daemon=~"$osd"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m])',
- 'irate(ceph_osd_op_w_latency_sum{ceph_daemon=~"$osd"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m])',
- 'read',
- 'write',
- 0, 1, 6, 9
- )
- .addSeriesOverride({"alias": "read","transform": "negative-Y"}
- ),
- OsdDeviceDetailsPanel(
- '$osd R/W IOPS',
- '',
- 'short',
- 'Read (-) / Write (+)',
- 'irate(ceph_osd_op_r{ceph_daemon=~"$osd"}[1m])',
- 'irate(ceph_osd_op_w{ceph_daemon=~"$osd"}[1m])',
- 'Reads',
- 'Writes',
- 6, 1, 6, 9
- )
- .addSeriesOverride({"alias": "Reads","transform": "negative-Y"}
- ),
- OsdDeviceDetailsPanel(
- '$osd R/W Bytes',
- '',
- 'bytes',
- 'Read (-) / Write (+)',
- 'irate(ceph_osd_op_r_out_bytes{ceph_daemon=~"$osd"}[1m])',
- 'irate(ceph_osd_op_w_in_bytes{ceph_daemon=~"$osd"}[1m])',
- 'Read Bytes',
- 'Write Bytes',
- 12, 1, 6, 9
- )
- .addSeriesOverride({"alias": "Read Bytes","transform": "negative-Y"}),
- addRowSchema(false, true, 'Physical Device Performance') + {gridPos: {x: 0, y: 10, w: 24, h: 1}},
- OsdDeviceDetailsPanel(
- 'Physical Device Latency for $osd',
- '',
- 's',
- 'Read (-) / Write (+)',
- '(label_replace(irate(node_disk_read_time_seconds_total[1m]) / irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*"))',
- '(label_replace(irate(node_disk_write_time_seconds_total[1m]) / irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*"))',
- '{{instance}}/{{device}} Reads',
- '{{instance}}/{{device}} Writes',
- 0, 11, 6, 9
- )
- .addSeriesOverride({"alias": "/.*Reads/","transform": "negative-Y"}
- ),
- OsdDeviceDetailsPanel(
- 'Physical Device R/W IOPS for $osd',
- '',
- 'short',
- 'Read (-) / Write (+)',
- 'label_replace(irate(node_disk_writes_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- 'label_replace(irate(node_disk_reads_completed_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- '{{device}} on {{instance}} Writes',
- '{{device}} on {{instance}} Reads',
- 6, 11, 6, 9
- )
- .addSeriesOverride({"alias": "/.*Reads/","transform": "negative-Y"}
- ),
- OsdDeviceDetailsPanel(
- 'Physical Device R/W Bytes for $osd',
- '',
- 'Bps',
- 'Read (-) / Write (+)',
- 'label_replace(irate(node_disk_read_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- 'label_replace(irate(node_disk_written_bytes_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- '{{instance}} {{device}} Reads',
- '{{instance}} {{device}} Writes',
- 12, 11, 6, 9
- )
- .addSeriesOverride({"alias": "/.*Reads/","transform": "negative-Y"}
- ),
- graphPanelSchema(
- {},
- 'Physical Device Util% for $osd',
- '',
- 'null',
- false,
- 'percentunit',
- 'short',
- null, null, null,
- 1,
- '$datasource'
- )
- .addTarget(
- addTargetSchema(
- 'label_replace(irate(node_disk_io_time_seconds_total[1m]), "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*")',
- 1,
- 'time_series',
- '{{device}} on {{instance}}'
- )) + {gridPos: {x: 18, y: 11, w: 6, h: 9}},
- ])
-}
-{
- "cephfs-overview.json":
- local CephfsOverviewGraphPanel(title, formatY1, labelY1, expr, legendFormat, x, y, w, h) =
- graphPanelSchema({}, title, '', 'null', false, formatY1, 'short', labelY1, null, 0, 1, '$datasource')
- .addTargets(
- [addTargetSchema(expr, 1, 'time_series', legendFormat)]) + {gridPos: {x: x, y: y, w: w, h: h}};
-
- dashboardSchema(
- 'MDS Performance', '', 'tbO9LAiZz', 'now-1h', '15s', 16, [], '', {refresh_intervals:['5s','10s','15s','30s','1m','5m','15m','30m','1h','2h','1d'],time_options:['5m','15m','1h','6h','12h','24h','2d','7d','30d']}
- )
- .addAnnotation(
- addAnnotationSchema(
- 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard')
- )
- .addRequired(
- type='grafana', id='grafana', name='Grafana', version='5.3.2'
- )
- .addRequired(
- type='panel', id='graph', name='Graph', version='5.0.0'
- )
- .addTemplate(
- g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
- )
- .addTemplate(
- addTemplateSchema('mds_servers', '$datasource', 'label_values(ceph_mds_inodes, ceph_daemon)', 1, true, 1, 'MDS Server', '')
- )
- .addPanels([
- addRowSchema(false, true, 'MDS Performance') + {gridPos: {x: 0, y: 0, w: 24, h: 1}},
- CephfsOverviewGraphPanel(
- 'MDS Workload - $mds_servers',
- 'none',
- 'Reads(-) / Writes (+)',
- 'sum(rate(ceph_objecter_op_r{ceph_daemon=~"($mds_servers).*"}[1m]))',
- 'Read Ops',
- 0, 1, 12, 9
- )
- .addTarget(addTargetSchema('sum(rate(ceph_objecter_op_w{ceph_daemon=~"($mds_servers).*"}[1m]))', 1, 'time_series', 'Write Ops'))
- .addSeriesOverride({"alias": "/.*Reads/","transform": "negative-Y"}
- ),
- CephfsOverviewGraphPanel(
- 'Client Request Load - $mds_servers',
- 'none',
- 'Client Requests',
- 'ceph_mds_server_handle_client_request{ceph_daemon=~"($mds_servers).*"}',
- '{{ceph_daemon}}',
- 12, 1, 12, 9
- )
- ])
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "OSD Performance",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "read",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_osd_op_r_latency_sum{ceph_daemon=~\"$osd\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "read",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_osd_op_w_latency_sum{ceph_daemon=~\"$osd\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "write",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$osd Latency",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 6,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "Reads",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_osd_op_r{ceph_daemon=~\"$osd\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Reads",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_osd_op_w{ceph_daemon=~\"$osd\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$osd R/W IOPS",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 12,
- "y": 1
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "Read Bytes",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_osd_op_r_out_bytes{ceph_daemon=~\"$osd\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read Bytes",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_osd_op_w_in_bytes{ceph_daemon=~\"$osd\"}[1m])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write Bytes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$osd R/W Bytes",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 10
- },
- "id": 6,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Physical Device Performance",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 0,
- "y": 11
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*Reads/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "(label_replace(irate(node_disk_read_time_seconds_total[1m]) / irate(node_disk_reads_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}}/{{device}} Reads",
- "refId": "A"
- },
- {
- "expr": "(label_replace(irate(node_disk_write_time_seconds_total[1m]) / irate(node_disk_writes_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}}/{{device}} Writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Physical Device Latency for $osd",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 6,
- "y": 11
- },
- "id": 8,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*Reads/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(irate(node_disk_writes_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}} on {{instance}} Writes",
- "refId": "A"
- },
- {
- "expr": "label_replace(irate(node_disk_reads_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}} on {{instance}} Reads",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Physical Device R/W IOPS for $osd",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 12,
- "y": 11
- },
- "id": 9,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/.*Reads/",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(irate(node_disk_read_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}} {{device}} Reads",
- "refId": "A"
- },
- {
- "expr": "label_replace(irate(node_disk_written_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{instance}} {{device}} Writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Physical Device R/W Bytes for $osd",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 18,
- "y": 11
- },
- "id": 10,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(irate(node_disk_io_time_seconds_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation_human{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device}} on {{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Physical Device Util% for $osd",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "refresh": "",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "OSD",
- "multi": false,
- "name": "osd",
- "options": [ ],
- "query": "label_values(ceph_osd_metadata,ceph_daemon)",
- "refresh": 1,
- "regex": "(.*)",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-3h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "OSD device details",
- "uid": "CrAHE0iZz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.0.0"
- },
- {
- "id": "grafana-piechart-panel",
- "name": "Pie Chart",
- "type": "panel",
- "version": "1.3.3"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- },
- {
- "id": "table",
- "name": "Table",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "aliasColors": {
- "@95%ile": "#e0752d"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 8,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "AVG read",
- "refId": "A"
- },
- {
- "expr": "max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "MAX read",
- "refId": "B"
- },
- {
- "expr": "quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "@95%ile",
- "refId": "C"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "OSD Read Latencies",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ms",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- }
- ]
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "This table shows the osd's that are delivering the 10 highest read latencies within the cluster",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 8,
- "y": 0
- },
- "id": 3,
- "sort": {
- "col": 2,
- "desc": true
- },
- "styles": [
- {
- "alias": "OSD ID",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "ceph_daemon",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Latency (ms)",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value",
- "thresholds": [ ],
- "type": "number",
- "unit": "none",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "/.*/",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- }
- ],
- "targets": [
- {
- "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n ))\n)\n\n",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Highest READ Latencies",
- "transform": "table",
- "type": "table"
- },
- {
- "aliasColors": {
- "@95%ile write": "#e0752d"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 8,
- "x": 12,
- "y": 0
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "AVG write",
- "refId": "A"
- },
- {
- "expr": "max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "MAX write",
- "refId": "B"
- },
- {
- "expr": "quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "@95%ile write",
- "refId": "C"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "OSD Write Latencies",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ms",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- }
- ]
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 20,
- "y": 0
- },
- "id": 5,
- "sort": {
- "col": 2,
- "desc": true
- },
- "styles": [
- {
- "alias": "OSD ID",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "ceph_daemon",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Latency (ms)",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value",
- "thresholds": [ ],
- "type": "number",
- "unit": "none",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "/.*/",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- }
- ],
- "targets": [
- {
- "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Highest WRITE Latencies",
- "transform": "table",
- "type": "table"
- },
- {
- "aliasColors": { },
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 0,
- "y": 8
- },
- "id": 6,
- "legend": {
- "percentage": true,
- "show": true,
- "values": true
- },
- "legendType": "Under graph",
- "pieType": "pie",
- "targets": [
- {
- "expr": "count by (device_class) (ceph_osd_metadata)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{device_class}}",
- "refId": "A"
- }
- ],
- "title": "OSD Types Summary",
- "type": "grafana-piechart-panel",
- "valueName": "current"
- },
- {
- "aliasColors": {
- "Non-Encrypted": "#E5AC0E"
- },
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 4,
- "y": 8
- },
- "id": 7,
- "legend": {
- "percentage": true,
- "show": true,
- "values": true
- },
- "legendType": "Under graph",
- "pieType": "pie",
- "targets": [
- {
- "expr": "count(ceph_bluefs_wal_total_bytes)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "bluestore",
- "refId": "A"
- },
- {
- "expr": "count(ceph_osd_metadata) - count(ceph_bluefs_wal_total_bytes)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "filestore",
- "refId": "B"
- },
- {
- "expr": "absent(ceph_bluefs_wal_total_bytes)*count(ceph_osd_metadata)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "filestore",
- "refId": "C"
- }
- ],
- "title": "OSD Objectstore Types",
- "type": "grafana-piechart-panel",
- "valueName": "current"
- },
- {
- "aliasColors": { },
- "datasource": "$datasource",
- "description": "The pie chart shows the various OSD sizes used within the cluster",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 8,
- "y": 8
- },
- "id": 8,
- "legend": {
- "percentage": true,
- "show": true,
- "values": true
- },
- "legendType": "Under graph",
- "pieType": "pie",
- "targets": [
- {
- "expr": "count(ceph_osd_stat_bytes < 1099511627776)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<1TB",
- "refId": "A"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 1099511627776 < 2199023255552)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<2TB",
- "refId": "B"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 2199023255552 < 3298534883328)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<3TB",
- "refId": "C"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 3298534883328 < 4398046511104)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<4TB",
- "refId": "D"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 4398046511104 < 6597069766656)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<6TB",
- "refId": "E"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 6597069766656 < 8796093022208)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<8TB",
- "refId": "F"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 8796093022208 < 10995116277760)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<10TB",
- "refId": "G"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 10995116277760 < 13194139533312)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<12TB",
- "refId": "H"
- },
- {
- "expr": "count(ceph_osd_stat_bytes >= 13194139533312)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "<12TB+",
- "refId": "I"
- }
- ],
- "title": "OSD Size Summary",
- "type": "grafana-piechart-panel",
- "valueName": "current"
- },
- {
- "aliasColors": { },
- "bars": true,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 8,
- "x": 12,
- "y": 8
- },
- "id": 9,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "ceph_osd_numpg\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PGs per OSD",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Distribution of PGs per OSD",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": 20,
- "mode": "histogram",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "# of OSDs",
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": "0",
- "show": true
- }
- ]
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": true,
- "colors": [
- "#d44a3a",
- "#299c46"
- ],
- "datasource": "$datasource",
- "description": "This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster",
- "format": "percentunit",
- "gauge": {
- "maxValue": 1,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 20,
- "y": 8
- },
- "id": 10,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_bluestore_onode_hits)/(sum(ceph_bluestore_onode_hits) + sum(ceph_bluestore_onode_misses))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": ".75",
- "title": "OSD onode Hits Ratio",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 16
- },
- "id": 11,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "R/W Profile",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Show the read/write workload profile overtime",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 24,
- "x": 0,
- "y": 17
- },
- "id": 12,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "round(sum(irate(ceph_pool_rd[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Reads",
- "refId": "A"
- },
- {
- "expr": "round(sum(irate(ceph_pool_wr[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Read/Write Profile",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "refresh": "10s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "OSD Overview",
- "uid": "lo02I1Aiz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- },
- {
- "id": "singlestat",
- "name": "Singlestat",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": true,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "percentunit",
- "gauge": {
- "maxValue": 1,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 7,
- "w": 7,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": true
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "(ceph_pool_stored / (ceph_pool_stored + ceph_pool_max_avail)) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": ".7,.8",
- "title": "Capacity used",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": 100,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Time till pool is full assuming the average fill rate of the last 6 hours",
- "format": "s",
- "gauge": {
- "maxValue": false,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 7,
- "w": 5,
- "x": 7,
- "y": 0
- },
- "id": 3,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": ""
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "(ceph_pool_max_avail / deriv(ceph_pool_stored[6h])) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"} > 0",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "current",
- "title": "Time till full",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": false
- },
- {
- "aliasColors": {
- "read_op_per_sec": "#3F6833",
- "write_op_per_sec": "#E5AC0E"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 12,
- "x": 12,
- "y": 0
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "deriv(ceph_pool_objects[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Objects per second",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$pool_name Object Ingress/Egress",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ops",
- "label": "Objects out(-) / in(+) ",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "read_op_per_sec": "#3F6833",
- "write_op_per_sec": "#E5AC0E"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 12,
- "x": 0,
- "y": 7
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "reads",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_pool_rd[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "reads",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_pool_wr[1m]) * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$pool_name Client IOPS",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "iops",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "read_op_per_sec": "#3F6833",
- "write_op_per_sec": "#E5AC0E"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 12,
- "x": 12,
- "y": 7
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "reads",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_pool_rd_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "reads",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_pool_wr_bytes[1m]) + on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "writes",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$pool_name Client Throughput",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": "Read (-) / Write (+)",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "read_op_per_sec": "#3F6833",
- "write_op_per_sec": "#E5AC0E"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 12,
- "x": 0,
- "y": 14
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "ceph_pool_objects * on(pool_id) group_left(instance,name) ceph_pool_metadata{name=~\"$pool_name\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Number of Objects",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$pool_name Objects",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "Objects",
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 22,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "Prometheus admin.virt1.home.fajerski.name:9090",
- "value": "Prometheus admin.virt1.home.fajerski.name:9090"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "Pool Name",
- "multi": false,
- "name": "pool_name",
- "options": [ ],
- "query": "label_values(ceph_pool_metadata,name)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "Ceph Pool Details",
- "uid": "-xyV8KCiz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [ ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "count(ceph_pool_metadata)",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Pools",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "avg"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Count of the pools that have compression enabled",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 3,
- "y": 0
- },
- "id": 3,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "count(ceph_pool_metadata{compression_mode!=\"none\"})",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Pools with Compression",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Total raw capacity available to the cluster",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 6,
- "y": 0
- },
- "id": 4,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_osd_stat_bytes)",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Total Raw Capacity",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Total raw capacity consumed by user data and associated overheads (metadata + redundancy)",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 9,
- "y": 0
- },
- "id": 5,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_pool_bytes_used)",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Raw Capacity Consumed",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Total of client data stored in the cluster",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 12,
- "y": 0
- },
- "id": 6,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_pool_stored)",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Logical Stored ",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression",
- "format": "bytes",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 15,
- "y": 0
- },
- "id": 7,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used)",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Compression Savings",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data\n",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 18,
- "y": 0
- },
- "id": 8,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "(sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_stored_raw and ceph_pool_compress_under_bytes > 0)) * 100",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Compression Eligibility",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "description": "This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 3,
- "w": 3,
- "x": 21,
- "y": 0
- },
- "id": 9,
- "interval": null,
- "links": [ ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(ceph_pool_compress_under_bytes > 0) / sum(ceph_pool_compress_bytes_used > 0)",
- "format": "",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Compression Factor",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 6,
- "w": 24,
- "x": 0,
- "y": 3
- },
- "id": 10,
- "sort": {
- "col": 5,
- "desc": true
- },
- "styles": [
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Time",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "instance",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "job",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Pool Name",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "name",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Pool ID",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "pool_id",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "none",
- "valueMaps": [ ]
- },
- {
- "alias": "Compression Factor",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #A",
- "thresholds": [ ],
- "type": "number",
- "unit": "none",
- "valueMaps": [ ]
- },
- {
- "alias": "% Used",
- "colorMode": "value",
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #D",
- "thresholds": [
- "70",
- "85"
- ],
- "type": "number",
- "unit": "percentunit",
- "valueMaps": [ ]
- },
- {
- "alias": "Usable Free",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #B",
- "thresholds": [ ],
- "type": "number",
- "unit": "bytes",
- "valueMaps": [ ]
- },
- {
- "alias": "Compression Eligibility",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #C",
- "thresholds": [ ],
- "type": "number",
- "unit": "percent",
- "valueMaps": [ ]
- },
- {
- "alias": "Compression Savings",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #E",
- "thresholds": [ ],
- "type": "number",
- "unit": "bytes",
- "valueMaps": [ ]
- },
- {
- "alias": "Growth (5d)",
- "colorMode": "value",
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #F",
- "thresholds": [
- "0",
- "0"
- ],
- "type": "number",
- "unit": "bytes",
- "valueMaps": [ ]
- },
- {
- "alias": "IOPS",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #G",
- "thresholds": [ ],
- "type": "number",
- "unit": "none",
- "valueMaps": [ ]
- },
- {
- "alias": "Bandwidth",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #H",
- "thresholds": [ ],
- "type": "number",
- "unit": "Bps",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "__name__",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "type",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "compression_mode",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Type",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "description",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Stored",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #J",
- "thresholds": [ ],
- "type": "number",
- "unit": "bytes",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #I",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Compression",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value #K",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [
- {
- "text": "ON",
- "value": "1"
- }
- ]
- }
- ],
- "targets": [
- {
- "expr": "(ceph_pool_compress_under_bytes / ceph_pool_compress_bytes_used > 0) and on(pool_id) (((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100 > 0.5)",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- },
- {
- "expr": "ceph_pool_max_avail * on(pool_id) group_left(name) ceph_pool_metadata",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "B"
- },
- {
- "expr": "((ceph_pool_compress_under_bytes > 0) / ceph_pool_stored_raw) * 100",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "C"
- },
- {
- "expr": "(ceph_pool_percent_used * on(pool_id) group_left(name) ceph_pool_metadata)",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "D"
- },
- {
- "expr": "(ceph_pool_compress_under_bytes - ceph_pool_compress_bytes_used > 0)",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "E"
- },
- {
- "expr": "delta(ceph_pool_stored[5d])",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "F"
- },
- {
- "expr": "rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "G"
- },
- {
- "expr": "rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "H"
- },
- {
- "expr": "ceph_pool_metadata",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "I"
- },
- {
- "expr": "ceph_pool_stored * on(pool_id) group_left ceph_pool_metadata",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "J"
- },
- {
- "expr": "ceph_pool_metadata{compression_mode!=\"none\"}",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "K"
- },
- {
- "expr": "",
- "format": "",
- "intervalFactor": "",
- "legendFormat": "",
- "refId": "L"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Pool Overview",
- "transform": "table",
- "type": "table"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "This chart shows the sum of read and write IOPS from all clients by pool",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 0,
- "y": 9
- },
- "id": 11,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "topk($topk,round((rate(ceph_pool_rd[30s]) + rate(ceph_pool_wr[30s])),1) * on(pool_id) group_left(instance,name) ceph_pool_metadata) ",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{name}} ",
- "refId": "A"
- },
- {
- "expr": "topk($topk,rate(ceph_pool_wr[30s]) + on(pool_id) group_left(instance,name) ceph_pool_metadata) ",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{name}} - write",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Top $topk Client IOPS by Pool",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "IOPS",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "The chart shows the sum of read and write bytes from all clients, by pool",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 9
- },
- "id": 12,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "topk($topk,(rate(ceph_pool_rd_bytes[30s]) + rate(ceph_pool_wr_bytes[30s])) * on(pool_id) group_left(instance,name) ceph_pool_metadata)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{name}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Top $topk Client Bandwidth by Pool",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": "Throughput",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Historical view of capacity usage, to help identify growth and trends in pool consumption",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 24,
- "x": 0,
- "y": 17
- },
- "id": 13,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "ceph_pool_bytes_used * on(pool_id) group_right ceph_pool_metadata",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{name}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Pool Capacity Usage (RAW)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": "Capacity Used",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 22,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "Dashboard1",
- "value": "Dashboard1"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "15",
- "value": "15"
- },
- "hide": 0,
- "includeAll": false,
- "label": "TopK",
- "multi": false,
- "name": "topk",
- "options": [
- {
- "text": "15",
- "value": "15"
- }
- ],
- "query": "15",
- "refresh": 0,
- "type": "custom"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "Ceph Pools Overview",
- "uid": "z99hzWtmk",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.0.0"
- },
- {
- "id": "grafana-piechart-panel",
- "name": "Pie Chart",
- "type": "panel",
- "version": "1.3.3"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "RGW Host Detail : $rgw_servers",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 6,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (instance_id) (rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GET {{ceph_daemon}}",
- "refId": "A"
- },
- {
- "expr": "sum by (instance_id) (rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s])) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUT {{ceph_daemon}}",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "$rgw_servers GET/PUT Latencies",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 7,
- "x": 6,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(ceph_rgw_get_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GETs {{ceph_daemon}}",
- "refId": "A"
- },
- {
- "expr": "rate(ceph_rgw_put_b[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs {{ceph_daemon}}",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Bandwidth by HTTP Operation",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "GETs": "#7eb26d",
- "Other": "#447ebc",
- "PUTs": "#eab839",
- "Requests": "#3f2b5b",
- "Requests Failed": "#bf1b00"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 8,
- "w": 7,
- "x": 13,
- "y": 1
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Requests Failed {{ceph_daemon}}",
- "refId": "A"
- },
- {
- "expr": "rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GETs {{ceph_daemon}}",
- "refId": "B"
- },
- {
- "expr": "rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs {{ceph_daemon}}",
- "refId": "C"
- },
- {
- "expr": "(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Other {{ceph_daemon}}",
- "refId": "D"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "HTTP Request Breakdown",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
- "Failures": "#bf1b00",
- "GETs": "#7eb26d",
- "Other (HEAD,POST,DELETE)": "#447ebc",
- "PUTs": "#eab839",
- "Requests": "#3f2b5b"
- },
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 8,
- "w": 4,
- "x": 20,
- "y": 1
- },
- "id": 6,
- "legend": {
- "percentage": true,
- "show": true,
- "values": true
- },
- "legendType": "Under graph",
- "pieType": "pie",
- "targets": [
- {
- "expr": "rate(ceph_rgw_failed_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Failures {{ceph_daemon}}",
- "refId": "A"
- },
- {
- "expr": "rate(ceph_rgw_get[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GETs {{ceph_daemon}}",
- "refId": "B"
- },
- {
- "expr": "rate(ceph_rgw_put[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs {{ceph_daemon}}",
- "refId": "C"
- },
- {
- "expr": "(\n rate(ceph_rgw_req[30s]) -\n (rate(ceph_rgw_get[30s]) + rate(ceph_rgw_put[30s]))\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\"}",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Other (DELETE,LIST) {{ceph_daemon}}",
- "refId": "D"
- }
- ],
- "title": "Workload Breakdown",
- "type": "grafana-piechart-panel",
- "valueName": "current"
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "overview"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "",
- "multi": false,
- "name": "rgw_servers",
- "options": [ ],
- "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "RGW Instance Detail",
- "uid": "x5ARzZtmk",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.0.0"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "RGW Overview - All Gateways",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GET AVG",
- "refId": "A"
- },
- {
- "expr": "rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUT AVG",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Average GET/PUT Latencies",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 7,
- "x": 8,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (rgw_host) (label_replace(rate(ceph_rgw_req[30s]) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{rgw_host}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Total Requests/sec by RGW Instance",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "none",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 6,
- "x": 15,
- "y": 1
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum[30s]) /\n rate(ceph_rgw_get_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n\"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{rgw_host}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "GET Latencies by RGW Instance",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Total bytes transferred in/out of all radosgw instances within the cluster",
- "fill": 1,
- "gridPos": {
- "h": 6,
- "w": 8,
- "x": 0,
- "y": 8
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(rate(ceph_rgw_get_b[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GETs",
- "refId": "A"
- },
- {
- "expr": "sum(rate(ceph_rgw_put_b[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Bandwidth Consumed by Type",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Total bytes transferred in/out through get/put operations, by radosgw instance",
- "fill": 1,
- "gridPos": {
- "h": 6,
- "w": 7,
- "x": 8,
- "y": 8
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b[30s]) + \n rate(ceph_rgw_put_b[30s])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata, \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{rgw_host}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Bandwidth by RGW Instance",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts",
- "fill": 1,
- "gridPos": {
- "h": 6,
- "w": 6,
- "x": 15,
- "y": 8
- },
- "id": 8,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum[30s]) /\n rate(ceph_rgw_put_initial_lat_count[30s]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata,\n\"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\")",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{rgw_host}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "PUT Latencies by RGW Instance",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 12,
- "w": 9,
- "x": 0,
- "y": 12
- },
- "id": 9,
- "panels": [ ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "RGW Overview - HAProxy Metrics",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 12,
- "w": 5,
- "x": 0,
- "y": 12
- },
- "id": 10,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- [
- {
- "alias": "/.*Back.*/",
- "transform": "negative-Y"
- },
- {
- "alias": "/.*1.*/"
- },
- {
- "alias": "/.*2.*/"
- },
- {
- "alias": "/.*3.*/"
- },
- {
- "alias": "/.*4.*/"
- },
- {
- "alias": "/.*5.*/"
- },
- {
- "alias": "/.*other.*/"
- }
- ]
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(haproxy_frontend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"frontend\"}[5m])) by (code)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Frontend {{ code }}",
- "refId": "A"
- },
- {
- "expr": "sum(irate(haproxy_backend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"backend\"}[5m])) by (code)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Backend {{ code }}",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Total responses by HTTP code",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 12,
- "w": 5,
- "x": 5,
- "y": 12
- },
- "id": 11,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- [
- {
- "alias": "/.*Response.*/",
- "transform": "negative-Y"
- },
- {
- "alias": "/.*Backend.*/",
- "transform": "negative-Y"
- }
- ]
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(haproxy_frontend_http_requests_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Requests",
- "refId": "A"
- },
- {
- "expr": "sum(irate(haproxy_backend_response_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Response errors",
- "refId": "B"
- },
- {
- "expr": "sum(irate(haproxy_frontend_request_errors_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Requests errors",
- "refId": "C"
- },
- {
- "expr": "sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Backend redispatch",
- "refId": "D"
- },
- {
- "expr": "sum(irate(haproxy_backend_retry_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Backend retry",
- "refId": "E"
- },
- {
- "expr": "sum(irate(haproxy_frontend_requests_denied_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Request denied",
- "refId": "F"
- },
- {
- "expr": "sum(haproxy_backend_current_queue{proxy=~\"backend\",instance=~\"$ingress_service\"}) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Backend Queued",
- "refId": "G"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Total requests / responses",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 12,
- "w": 5,
- "x": 10,
- "y": 12
- },
- "id": 12,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- [
- {
- "alias": "/.*Back.*/",
- "transform": "negative-Y"
- }
- ]
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(haproxy_frontend_connections_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Front",
- "refId": "A"
- },
- {
- "expr": "sum(irate(haproxy_backend_connection_attempts_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Back",
- "refId": "B"
- },
- {
- "expr": "sum(irate(haproxy_backend_connection_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Back errors",
- "refId": "C"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Total number of connections",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 12,
- "w": 6,
- "x": 15,
- "y": 12
- },
- "id": 13,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- [
- {
- "alias": "/.*OUT.*/",
- "transform": "negative-Y"
- }
- ]
- ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(haproxy_frontend_bytes_in_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "IN Front",
- "refId": "A"
- },
- {
- "expr": "sum(irate(haproxy_frontend_bytes_out_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "OUT Front",
- "refId": "B"
- },
- {
- "expr": "sum(irate(haproxy_backend_bytes_in_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "IN Back",
- "refId": "C"
- },
- {
- "expr": "sum(irate(haproxy_backend_bytes_out_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "OUT Back",
- "refId": "D"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current total of incoming / outgoing bytes",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "overview"
- ],
- "templating": {
- "list": [
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "",
- "multi": false,
- "name": "rgw_servers",
- "options": [ ],
- "query": "label_values(ceph_rgw_metadata, ceph_daemon)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "HTTP Code",
- "multi": false,
- "name": "code",
- "options": [ ],
- "query": "label_values(haproxy_server_http_responses_total{instance=~\"$ingress_service\"}, code)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "Ingress Service",
- "multi": false,
- "name": "ingress_service",
- "options": [ ],
- "query": "label_values(haproxy_server_status, instance)",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "RGW Overview",
- "uid": "WAkugZpiz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.0.0"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_sum[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{source_zone}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Replication (throughput) from Source Zone",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 8,
- "y": 0
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_count[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{source_zone}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Replication (objects) from Source Zone",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "Objects/s",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 16,
- "y": 0
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_poll_latency_sum[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{source_zone}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Polling Request Latency from Source Zone",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ms",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 0,
- "y": 7
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_errors[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{source_zone}}",
- "refId": "A"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Unsuccessful Object Replications from Source Zone",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": "Count/s",
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": "15s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "overview"
- ],
- "templating": {
- "list": [
- {
- "allValue": null,
- "current": { },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": "",
- "multi": false,
- "name": "rgw_servers",
- "options": [ ],
- "query": "prometehus",
- "refresh": 1,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "RGW Sync Overview",
- "uid": "rgw-sync-overview",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.3.3"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "Detailed Performance of RBD Images (IOPS/Throughput/Latency)",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$Datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 8,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_rbd_write_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_rbd_read_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "IOPS",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "iops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "iops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$Datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 8,
- "x": 8,
- "y": 0
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_rbd_write_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_rbd_read_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Throughput",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$Datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 9,
- "w": 8,
- "x": 16,
- "y": 0
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "irate(ceph_rbd_write_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_write_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write",
- "refId": "A"
- },
- {
- "expr": "irate(ceph_rbd_read_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_read_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Average Latency",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ns",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "ns",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "refresh": false,
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [ ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "Datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$Datasource",
- "hide": 0,
- "includeAll": false,
- "label": "",
- "multi": false,
- "name": "Pool",
- "options": [ ],
- "query": "label_values(pool)",
- "refresh": 1,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": { },
- "datasource": "$Datasource",
- "hide": 0,
- "includeAll": false,
- "label": "",
- "multi": false,
- "name": "Image",
- "options": [ ],
- "query": "label_values(image)",
- "refresh": 1,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [ ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "RBD Details",
- "uid": "YhCYGcuZz",
- "version": 0
-}
+++ /dev/null
-{
- "__inputs": [ ],
- "__requires": [
- {
- "id": "grafana",
- "name": "Grafana",
- "type": "grafana",
- "version": "5.4.2"
- },
- {
- "id": "graph",
- "name": "Graph",
- "type": "panel",
- "version": "5.0.0"
- },
- {
- "id": "prometheus",
- "name": "Prometheus",
- "type": "datasource",
- "version": "5.0.0"
- },
- {
- "id": "table",
- "name": "Table",
- "type": "panel",
- "version": "5.0.0"
- }
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "showIn": 0,
- "tags": [ ],
- "type": "dashboard"
- }
- ]
- },
- "description": "",
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [ ],
- "panels": [
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "round(sum(irate(ceph_rbd_write_ops[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Writes",
- "refId": "A"
- },
- {
- "expr": "round(sum(irate(ceph_rbd_read_ops[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Reads",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "IOPS",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 8,
- "y": 0
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "round(sum(irate(ceph_rbd_write_bytes[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write",
- "refId": "A"
- },
- {
- "expr": "round(sum(irate(ceph_rbd_read_bytes[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Throughput",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": { },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "description": "",
- "fill": 1,
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 16,
- "y": 0
- },
- "id": 4,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [ ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [ ],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "round(sum(irate(ceph_rbd_write_latency_sum[30s])) / sum(irate(ceph_rbd_write_latency_count[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Write",
- "refId": "A"
- },
- {
- "expr": "round(sum(irate(ceph_rbd_read_latency_sum[30s])) / sum(irate(ceph_rbd_read_latency_count[30s])))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Read",
- "refId": "B"
- }
- ],
- "thresholds": [ ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Average Latency",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [ ]
- },
- "yaxes": [
- {
- "format": "ns",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 0,
- "y": 7
- },
- "id": 5,
- "sort": {
- "col": 3,
- "desc": true
- },
- "styles": [
- {
- "alias": "Pool",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "pool",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Image",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "image",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "IOPS",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value",
- "thresholds": [ ],
- "type": "number",
- "unit": "iops",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "/.*/",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- }
- ],
- "targets": [
- {
- "expr": "topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on (image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Highest IOPS",
- "transform": "table",
- "type": "table"
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 8,
- "y": 7
- },
- "id": 6,
- "sort": {
- "col": 3,
- "desc": true
- },
- "styles": [
- {
- "alias": "Pool",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "pool",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Image",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "image",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Throughput",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value",
- "thresholds": [ ],
- "type": "number",
- "unit": "Bps",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "/.*/",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- }
- ],
- "targets": [
- {
- "expr": "topk(10, sort(sum(irate(ceph_rbd_read_bytes[30s]) + irate(ceph_rbd_write_bytes[30s])) by (pool, image, namespace)))",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Highest Throughput",
- "transform": "table",
- "type": "table"
- },
- {
- "columns": [ ],
- "datasource": "$datasource",
- "description": "",
- "gridPos": {
- "h": 7,
- "w": 8,
- "x": 16,
- "y": 7
- },
- "id": 7,
- "sort": {
- "col": 3,
- "desc": true
- },
- "styles": [
- {
- "alias": "Pool",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "pool",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Image",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "image",
- "thresholds": [ ],
- "type": "string",
- "unit": "short",
- "valueMaps": [ ]
- },
- {
- "alias": "Latency",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "Value",
- "thresholds": [ ],
- "type": "number",
- "unit": "ns",
- "valueMaps": [ ]
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
- "rgba(245, 54, 54, 0.9)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(50, 172, 45, 0.97)"
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "mappingType": 1,
- "pattern": "/.*/",
- "thresholds": [ ],
- "type": "hidden",
- "unit": "short",
- "valueMaps": [ ]
- }
- ],
- "targets": [
- {
- "expr": "topk(10,\n sum(\n irate(ceph_rbd_write_latency_sum[30s]) / clamp_min(irate(ceph_rbd_write_latency_count[30s]), 1) +\n irate(ceph_rbd_read_latency_sum[30s]) / clamp_min(irate(ceph_rbd_read_latency_count[30s]), 1)\n ) by (pool, image, namespace)\n)",
- "format": "table",
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Highest Latency",
- "transform": "table",
- "type": "table"
- }
- ],
- "refresh": "30s",
- "rows": [ ],
- "schemaVersion": 16,
- "style": "dark",
- "tags": [
- "overview"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": "Data Source",
- "name": "datasource",
- "options": [ ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "15s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "",
- "title": "RBD Overview",
- "uid": "41FrpeUiz",
- "version": 0
-}
+++ /dev/null
-attrs==21.2.0
-behave==1.2.6
-py==1.10.0
-pyparsing==2.4.7
-PyYAML==6.0
-types-PyYAML==6.0.0
-typing-extensions==3.10.0.2
-termcolor==1.1.0
-types-termcolor==1.1.2
-dataclasses==0.6
-types-dataclasses==0.6.1
-six==1.16.0
-toml==0.10.2
-pylint==2.6.0
-isort==5.10.0
-mypy==0.910
-mypy-extensions==0.4.3
-prettytable==2.4.0
+++ /dev/null
-#!/usr/bin/env bash
-
-set -e
-TEMPDIR=`mktemp -d`
-BASEDIR=$(dirname "$0")
-
-JSONNET_PATH="${GRAFONNET_PATH}" jsonnet -m ${TEMPDIR} $BASEDIR/jsonnet/grafana_dashboards.jsonnet
-
-truncate -s 0 ${TEMPDIR}/json_difference.log
-for json_files in $BASEDIR/*.json
-do
- JSON_FILE_NAME=$(basename $json_files)
- for generated_files in ${TEMPDIR}/*.json
- do
- GENERATED_FILE_NAME=$(basename $generated_files)
- if [ $JSON_FILE_NAME == $GENERATED_FILE_NAME ]; then
- jsondiff --indent 2 $generated_files $json_files | tee -a ${TEMPDIR}/json_difference.log
- fi
- done
-done
-
-if [[ $(wc -l < ${TEMPDIR}/json_difference.log) -eq 0 ]]
-then
- rm -rf ${TEMPDIR}
- echo "Congratulations! Grafonnet Check Passed"
-else
- rm -rf ${TEMPDIR}
- echo "Grafonnet Check Failed, failed comparing generated file with existing"
- exit 1
-fi
+++ /dev/null
-import re
-import subprocess
-import sys
-import tempfile
-from dataclasses import asdict, dataclass, field
-from typing import Any, List
-
-import yaml
-
-
-@dataclass
-class InputSeries:
- series: str = ''
- values: str = ''
-
-@dataclass
-class ExprSample:
- labels: str = ''
- value: float = -1
-
-@dataclass
-class PromqlExprTest:
- expr: str = ''
- eval_time: str = '1m'
- exp_samples: List[ExprSample] = field(default_factory=list)
-
-@dataclass
-class Test:
- interval: str = '1m'
- input_series: List[InputSeries] = field(default_factory=list)
- promql_expr_test: List[PromqlExprTest] = field(default_factory=list)
-
-
-@dataclass
-class TestFile:
- evaluation_interval: str = '1m'
- tests: List[Test] = field(default_factory=list)
-
-
-class PromqlTest:
- """
- Base class to provide prometheus query test capabilities. After setting up
- the query test with its input and expected output it's expected to run promtool.
-
- https://prometheus.io/docs/prometheus/latest/configuration/unit_testing_rules/#test-yml
-
- The workflow of testing would be something like:
-
- # add prometheus query to test
- self.set_expression('bonding_slaves > 0')
-
- # add some prometheus input series
- self.add_series('bonding_slaves{master="bond0"}', '2')
- self.add_series('bonding_slaves{master="bond1"}', '3')
- self.add_series('node_network_receive_bytes{instance="127.0.0.1",
- device="eth1"}', "10 100 230 22")
-
- # expected output of the query
- self.add_exp_samples('bonding_slaves{master="bond0"}', 2)
- self.add_exp_samples('bonding_slaves{master="bond1"}', 3)
-
- # at last, always call promtool with:
- self.assertTrue(self.run_promtool())
- # assertTrue means it expect promtool to succeed
- """
-
- def __init__(self):
- self.test_output_file = tempfile.NamedTemporaryFile('w+')
-
- self.test_file = TestFile()
- self.test = Test()
- self.promql_expr_test = PromqlExprTest()
- self.test.promql_expr_test.append(self.promql_expr_test)
- self.test_file.tests.append(self.test)
-
- self.variables = {}
-
- def __del__(self):
- self.test_output_file.close()
-
-
- def set_evaluation_interval(self, interval: int, unit: str = 'm') -> None:
- """
- Set the evaluation interval of the time series
-
- Args:
- interval (int): number of units.
- unit (str): unit type: 'ms', 's', 'm', etc...
- """
- self.test_file.evaluation_interval = f'{interval}{unit}'
-
- def set_interval(self, interval: int, unit: str = 'm') -> None:
- """
- Set the duration of the time series
-
- Args:
- interval (int): number of units.
- unit (str): unit type: 'ms', 's', 'm', etc...
- """
- self.test.interval = f'{interval}{unit}'
-
- def set_expression(self, expr: str) -> None:
- """
- Set the prometheus expression/query used to filter data.
-
- Args:
- expr(str): expression/query.
- """
- self.promql_expr_test.expr = expr
-
- def add_series(self, series: str, values: str) -> None:
- """
- Add a series to the input.
-
- Args:
- series(str): Prometheus series.
- Notation: '<metric name>{<label name>=<label value>, ...}'
- values(str): Value of the series.
- """
- input_series = InputSeries(series=series, values=values)
- self.test.input_series.append(input_series)
-
- def set_eval_time(self, eval_time: int, unit: str = 'm') -> None:
- """
- Set the time when the expression will be evaluated
-
- Args:
- interval (int): number of units.
- unit (str): unit type: 'ms', 's', 'm', etc...
- """
- self.promql_expr_test.eval_time = f'{eval_time}{unit}'
-
- def add_exp_samples(self, sample: str, values: Any) -> None:
- """
- Add an expected sample/output of the query given the series/input
-
- Args:
- sample(str): Expected sample.
- Notation: '<metric name>{<label name>=<label value>, ...}'
- values(Any): Value of the sample.
- """
- expr_sample = ExprSample(labels=sample, value=values)
- self.promql_expr_test.exp_samples.append(expr_sample)
-
- def set_variable(self, variable: str, value: str):
- """
- If a query makes use of grafonnet variables, for example
- '$osd_hosts', you should change this to a real value. Example:
-
-
- > self.set_expression('bonding_slaves{master="$osd_hosts"} > 0')
- > self.set_variable('osd_hosts', '127.0.0.1')
- > print(self.query)
- > bonding_slaves{master="127.0.0.1"} > 0
-
- Args:
- variable(str): Variable name
- value(str): Value to replace variable with
-
- """
- self.variables[variable] = value
-
- def run_promtool(self):
- """
- Run promtool to test the query after setting up the input, output
- and extra parameters.
-
- Returns:
- bool: True if successful, False otherwise.
- """
-
- for variable, value in self.variables.items():
- expr = self.promql_expr_test.expr
- new_expr = re.sub(r'\${0}'.format(variable), str(value), expr)
- self.set_expression(new_expr)
-
- test_as_dict = asdict(self.test_file)
- yaml.dump(test_as_dict, self.test_output_file)
-
- args = f'promtool test rules {self.test_output_file.name}'.split()
- try:
- subprocess.run(args, check=True)
- return True
- except subprocess.CalledProcessError as process_error:
- print(yaml.dump(test_as_dict))
- print(process_error.stderr)
- return False
+++ /dev/null
-Feature: Ceph Cluster Dashboard
-
-Scenario: "Test total PG States"
- Given the following series:
- | metrics | values |
- | ceph_pg_total{foo="var"} | 10 100 |
- | ceph_pg_total{foo="bar"} | 20 200 |
- Then Grafana panel `PG States` with legend `Total` shows:
- | metrics | values |
- | {} | 300 |
-
-Scenario: "Test OSDs in"
- Given the following series:
- | metrics | values |
- | ceph_osd_in{ceph_daemon="osd.0"} | 1.0 |
- | ceph_osd_in{ceph_daemon="osd.1"} | 0.0 |
- | ceph_osd_in{ceph_daemon="osd.2"} | 1.0 |
- When variable `instance` is `.*`
- Then Grafana panel `OSDs` with legend `In` shows:
- | metrics | values |
- | {} | 2 |
-
-Scenario: "Test OSDs down"
- Given the following series:
- | metrics | values |
- | ceph_osd_up{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
- | ceph_osd_up{ceph_daemon="osd.1", instance="127.0.0.1"} | 0.0 |
- | ceph_osd_up{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
- When variable `instance` is `127.0.0.1`
- Then Grafana panel `OSDs` with legend `Down` shows:
- | metrics | values |
- | {} | 3 |
-
-Scenario: "Test OSDs out"
- Given the following series:
- | metrics | values |
- | ceph_osd_in{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
- | ceph_osd_in{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
- | ceph_osd_in{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
- When variable `instance` is `127.0.0.1`
- Then Grafana panel `OSDs` with legend `Out` shows:
- | metrics | values |
- | {} | 2 |
-
-Scenario: "Test OSDs all"
- Given the following series:
- | metrics | values |
- | ceph_osd_metadata{ceph_daemon="osd.0", instance="127.0.0.1"} | 1.0 |
- | ceph_osd_metadata{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
- | ceph_osd_metadata{ceph_daemon="osd.2", instance="127.0.0.1"} | 1.0 |
- When variable `instance` is `127.0.0.1`
- Then Grafana panel `OSDs` with legend `All` shows:
- | metrics | values |
- | {} | 3 |
+++ /dev/null
-# type: ignore[no-redef]
-# pylint: disable=E0611,W0613,E0102
-import copy
-
-from behave import given, then, when
-from prettytable import PrettyTable
-
-from tests import PromqlTest
-from tests.util import get_dashboards_data, resolve_time_and_unit
-
-
-class GlobalContext:
- def __init__(self):
- self.tested_queries_count = 0
- self.promql_expr_test = None
- self.data = get_dashboards_data()
- self.query_map = self.data['queries']
-
- def reset_promql_test(self):
- self.promql_expr_test = PromqlTest()
- self.promql_expr_test.variables = copy.copy(self.data['variables'])
-
- def print_query_stats(self):
- total = len(self.query_map)
- table = PrettyTable()
- table.field_names = ['Name', 'Queries', 'Tested', 'Cover']
-
- def percent(tested, total):
- return str(round((tested / total) * 100, 2)) + '%'
-
- def file_name(path):
- return path.split('/')[-1]
-
- total = 0
- tested = 0
- for path, stat in self.data['stats'].items():
- assert stat['total']
- table.add_row([file_name(path), stat['total'], stat['tested'],
- percent(stat['tested'], stat['total'])])
- total += stat['total']
- tested += stat['tested']
-
- assert total
- table.add_row(['Total', total, tested, percent(tested, total)])
- print(table)
-
-
-global_context = GlobalContext()
-
-# Behave function overloading
-# ===========================
-
-
-def before_scenario(context, scenario):
- global_context.reset_promql_test()
-
-
-def after_scenario(context, scenario):
- assert global_context.promql_expr_test.run_promtool()
-
-
-def after_all(context):
- global_context.print_query_stats()
-
-
-@given("the following series")
-def step_impl(context):
- for row in context.table:
- metric = row['metrics']
- value = row['values']
- global_context.promql_expr_test.add_series(metric, value)
-
-
-@when('evaluation interval is `{interval}`')
-def step_impl(context, interval):
- interval_without_unit, unit = resolve_time_and_unit(interval)
- if interval_without_unit is None:
- raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
- 'A valid time looks like "1m" where you have a number plus a unit')
- global_context.promql_expr_test.set_evaluation_interval(interval_without_unit, unit)
-
-
-@when('interval is `{interval}`')
-def step_impl(context, interval):
- interval_without_unit, unit = resolve_time_and_unit(interval)
- if interval_without_unit is None:
- raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
- 'A valid time looks like "1m" where you have a number plus a unit')
- global_context.promql_expr_test.set_interval(interval_without_unit, unit)
-
-
-@when('evaluation time is `{eval_time}`')
-def step_impl(context, eval_time):
- eval_time_without_unit, unit = resolve_time_and_unit(eval_time)
- if eval_time_without_unit is None:
- raise ValueError(f'Invalid evalution time: {eval_time}. ' +
- 'A valid time looks like "1m" where you have a number plus a unit')
- global_context.promql_expr_test.set_eval_time(eval_time_without_unit, unit)
-
-
-@when('variable `{variable}` is `{value}`')
-def step_impl(context, variable, value):
- global_context.promql_expr_test.set_variable(variable, value)
-
-
-@then('Grafana panel `{panel_name}` with legend `{legend}` shows')
-def step_impl(context, panel_name, legend):
- """
- This step can have an empty legend. As 'behave' doesn't provide a way
- to say it's empty we use EMPTY to mark as empty.
- """
- if legend == "EMPTY":
- legend = ''
- query_id = panel_name + '-' + legend
- if query_id not in global_context.query_map:
- raise KeyError((f'Query with legend {legend} in panel "{panel_name}"'
- 'couldn\'t be found'))
-
- expr = global_context.query_map[query_id]['query']
- global_context.promql_expr_test.set_expression(expr)
- for row in context.table:
- metric = row['metrics']
- value = row['values']
- global_context.promql_expr_test.add_exp_samples(metric, float(value))
- path = global_context.query_map[query_id]['path']
- global_context.data['stats'][path]['tested'] += 1
-
-
-@then('query `{query}` produces')
-def step_impl(context, query):
- global_context.promql_expr_test.set_expression(query)
- for row in context.table:
- metric = row['metrics']
- value = row['values']
- global_context.promql_expr_test.add_exp_samples(metric, float(value))
+++ /dev/null
-Feature: Host Details Dashboard
-
-Scenario: "Test OSD"
- Given the following series:
- | metrics | values |
- | ceph_osd_metadata{back_iface="",ceph_daemon="osd.0",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
- | ceph_osd_metadata{back_iface="",ceph_daemon="osd.1",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
- | ceph_osd_metadata{back_iface="",ceph_daemon="osd.2",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
- When variable `ceph_hosts` is `127.0.0.1`
- Then Grafana panel `OSDs` with legend `EMPTY` shows:
- | metrics | values |
- | {} | 3 |
-
-# IOPS Panel - begin
-
-Scenario: "Test Disk IOPS - Writes - Several OSDs per device"
- Given the following series:
- | metrics | values |
- | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
- | metrics | values |
- | {ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
-
-Scenario: "Test Disk IOPS - Writes - Single OSD per device"
- Given the following series:
- | metrics | values |
- | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
-
-Scenario: "Test Disk IOPS - Reads - Several OSDs per device"
- Given the following series:
- | metrics | values |
- | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
- | metrics | values |
- | {ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
-
-Scenario: "Test Disk IOPS - Reads - Single OSD per device"
- Given the following series:
- | metrics | values |
- | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
-
-# IOPS Panel - end
-
-# Node disk bytes written/read panel - begin
-
-Scenario: "Test disk throughput - read"
- Given the following series:
- | metrics | values |
- | node_disk_read_bytes_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_read_bytes_total{device="sdb",instance="localhost:9100"} | 100+600x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) read` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
-
-Scenario: "Test disk throughput - write"
- Given the following series:
- | metrics | values |
- | node_disk_written_bytes_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_written_bytes_total{device="sdb",instance="localhost:9100"} | 100+600x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) write` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
-
-# Node disk bytes written/read panel - end
-
-Scenario: "Test $ceph_hosts Disk Latency panel"
- Given the following series:
- | metrics | values |
- | node_disk_write_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_write_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | node_disk_writes_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | node_disk_read_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_read_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | node_disk_reads_completed_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk Latency` with legend `{{device}}({{ceph_daemon}})` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
-
-Scenario: "Test $ceph_hosts Disk utilization"
- Given the following series:
- | metrics | values |
- | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `ceph_hosts` is `localhost`
- Then Grafana panel `$ceph_hosts Disk utilization` with legend `{{device}}({{ceph_daemon}})` shows:
- | metrics | values |
- | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 100 |
- | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 100 |
-
+++ /dev/null
-Feature: Hosts Overview Dashboard
-
-Scenario: "Test network load succeeds"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- When variable `osd_hosts` is `127.0.0.1`
- Then Grafana panel `Network Load` with legend `EMPTY` shows:
- | metrics | values |
- | {} | 6 |
-
-Scenario: "Test network load with bonding succeeds"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
- | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
- When variable `osd_hosts` is `127.0.0.1`
- Then Grafana panel `Network Load` with legend `EMPTY` shows:
- | metrics | values |
- | {} | 6 |
-
-Scenario: "Test AVG Disk Utilization"
- Given the following series:
- | metrics | values |
- | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
- | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
- | node_disk_io_time_seconds_total{device="sdc",instance="localhost:9100"} | 10 2000 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd_hosts` is `localhost`
- Then Grafana panel `AVG Disk Utilization` with legend `EMPTY` shows:
- | metrics | values |
- | {} | 100 |
+++ /dev/null
-Feature: OSD device details
-
-Scenario: "Test Physical Device Latency for $osd - Reads"
- Given the following series:
- | metrics | values |
- | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 60 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 60 |
- | node_disk_read_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
- | node_disk_read_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Reads` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 10 |
-
-Scenario: "Test Physical Device Latency for $osd - Writes"
- Given the following series:
- | metrics | values |
- | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 60 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 60 |
- | node_disk_write_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
- | node_disk_write_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Writes` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 10 |
-
-Scenario: "Test Physical Device R/W IOPS for $osd - Writes"
- Given the following series:
- | metrics | values |
- | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 1.5 |
-
-Scenario: "Test Physical Device R/W IOPS for $osd - Reads"
- Given the following series:
- | metrics | values |
- | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 1.5 |
-
-Scenario: "Test Physical Device R/W Bytes for $osd - Reads"
- Given the following series:
- | metrics | values |
- | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
- | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 1.5 |
-
-Scenario: "Test Physical Device R/W Bytes for $osd - Writes"
- Given the following series:
- | metrics | values |
- | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
- | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 1.5 |
-
-Scenario: "Test Physical Device Util% for $osd"
- Given the following series:
- | metrics | values |
- | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10 100 |
- | ceph_disk_occupation_human{ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
- | ceph_disk_occupation_human{ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
- When variable `osd` is `osd.0`
- Then Grafana panel `Physical Device Util% for $osd` with legend `{{device}} on {{instance}}` shows:
- | metrics | values |
- | {device="sda",instance="localhost"} | 1.5 |
+++ /dev/null
-Feature: OSD Overview
-
-Scenario: "Test OSD onode Hits Ratio"
- Given the following series:
- | metrics | values |
- | ceph_bluestore_onode_hits{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 5255 |
- | ceph_bluestore_onode_hits{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 5419 |
- | ceph_bluestore_onode_hits{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 5242 |
- | ceph_bluestore_onode_misses{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 202 |
- | ceph_bluestore_onode_misses{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 247 |
- | ceph_bluestore_onode_misses{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 234 |
- Then Grafana panel `OSD onode Hits Ratio` with legend `EMPTY` shows:
- | metrics | values |
- | {} | 9.588529429483704E-01 |
-
+++ /dev/null
-Feature: RGW Host Detail Dashboard
-
-Scenario: "Test $rgw_servers GET/PUT Latencies - GET"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
- | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `GET {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance_id="58892247"} | 2.5000000000000004 |
-
-Scenario: "Test $rgw_servers GET/PUT Latencies - PUT"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
- | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `PUT {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1 |
-
-Scenario: "Test Bandwidth by HTTP Operation - GET"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
- | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.1`
- Then Grafana panel `Bandwidth by HTTP Operation` with legend `GETs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1.6666666666666667 |
-
-Scenario: "Test Bandwidth by HTTP Operation - PUT"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
- | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.1`
- Then Grafana panel `Bandwidth by HTTP Operation` with legend `PUTs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 |
-
-Scenario: "Test HTTP Request Breakdown - Requests Failed"
- Given the following series:
- | metrics | values |
- | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `HTTP Request Breakdown` with legend `Requests Failed {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 6.666666666666667e-02 |
-
-Scenario: "Test HTTP Request Breakdown - GET"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `HTTP Request Breakdown` with legend `GETs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .6666666666666666 |
-
-Scenario: "Test HTTP Request Breakdown - PUT"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `HTTP Request Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.3333333333333335 |
-
-Scenario: "Test HTTP Request Breakdown - Other"
- Given the following series:
- | metrics | values |
- | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
- | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
- | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `HTTP Request Breakdown` with legend `Other {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
-
-Scenario: "Test Workload Breakdown - Failures"
- Given the following series:
- | metrics | values |
- | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `Workload Breakdown` with legend `Failures {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 6.666666666666667e-02 |
-
-Scenario: "Test Workload Breakdown - GETs"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `Workload Breakdown` with legend `GETs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .6666666666666666 |
-
-Scenario: "Test Workload Breakdown - PUTs"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `Workload Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.3333333333333335 |
-
-Scenario: "Test Workload Breakdown - Other"
- Given the following series:
- | metrics | values |
- | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
- | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
- | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- And variable `rgw_servers` is `rgw.foo`
- Then Grafana panel `Workload Breakdown` with legend `Other (DELETE,LIST) {{ceph_daemon}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
+++ /dev/null
-Feature: RGW Overview Dashboard
-
-Scenario: "Test Average GET Latencies"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
- | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- Then Grafana panel `Average GET/PUT Latencies` with legend `GET AVG` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo",instance="127.0.0.1", instance_id="58892247", job="ceph"} | 2.5000000000000004 |
-
-Scenario: "Test Average PUT Latencies"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
- | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- Then Grafana panel `Average GET/PUT Latencies` with legend `PUT AVG` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo",instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 |
-
-Scenario: "Test Total Requests/sec by RGW Instance"
- Given the following series:
- | metrics | values |
- | ceph_rgw_req{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
- | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
- When interval is `30s`
- Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows:
- | metrics | values |
- | {rgw_host="1"} | 1.6666666666666667 |
-
-Scenario: "Test GET Latencies by RGW Instance"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
- | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When interval is `30s`
- Then Grafana panel `GET Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 2.5000000000000004 |
-
-Scenario: "Test Bandwidth Consumed by Type- GET"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
- When evaluation time is `1m`
- And interval is `30s`
- Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows:
- | metrics | values |
- | {} | 1.6666666666666667 |
-
-Scenario: "Test Bandwidth Consumed by Type- PUT"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
- When evaluation time is `1m`
- And interval is `30s`
- Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows:
- | metrics | values |
- | {} | 1 |
-
-Scenario: "Test Bandwidth by RGW Instance"
- Given the following series:
- | metrics | values |
- | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
- | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
- | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
- When evaluation time is `1m`
- And interval is `30s`
- Then Grafana panel `Bandwidth by RGW Instance` with legend `{{rgw_host}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.1", instance_id="92806566", rgw_host="1"} | 2.666666666666667 |
-
-Scenario: "Test PUT Latencies by RGW Instance"
- Given the following series:
- | metrics | values |
- | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
- | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
- | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
- When evaluation time is `1m`
- And interval is `30s`
- Then Grafana panel `PUT Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
- | metrics | values |
- | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |
-
-Scenario: "Test Total backend responses by HTTP code"
- Given the following series:
- | metrics | values |
- | haproxy_backend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 |
- | haproxy_backend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- When variable `code` is `200`
- Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows:
- | metrics | values |
- | {code="200"} | 1.5 |
-
-Scenario: "Test Total frontend responses by HTTP code"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 |
- | haproxy_frontend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- When variable `code` is `200`
- Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows:
- | metrics | values |
- | {code="200"} | 1.5 |
-
-Scenario: "Test Total http frontend requests by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Requests` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend response errors by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Response errors` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total frontend requests errors by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Requests errors` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend redispatch warnings by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend retry warnings by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Backend retry` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total frontend requests denied by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Request denied` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend current queue by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 200 |
-
-Scenario: "Test Total frontend connections by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total number of connections` with legend `Front` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend connections attempts by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total number of connections` with legend `Back` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total backend connections error by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Total number of connections` with legend `Back errors` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 3 |
-
-Scenario: "Test Total frontend bytes incoming by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 24 |
-
-Scenario: "Test Total frontend bytes outgoing by instance"
- Given the following series:
- | metrics | values |
- | haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 24 |
-
-Scenario: "Test Total backend bytes incoming by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 24 |
-
-Scenario: "Test Total backend bytes outgoing by instance"
- Given the following series:
- | metrics | values |
- | haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
- | haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
- When variable `ingress_service` is `ingress.rgw.1`
- Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows:
- | metrics | values |
- | {instance="ingress.rgw.1"} | 24 |
+++ /dev/null
-Feature: Test tester
-
-Scenario: "Simple query works"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
- | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
- | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
- Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
- | metrics | values |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 100 |
-
-Scenario: "Query with evaluation time"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
- | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
- | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
- When evaluation time is `0m`
- Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
- | metrics | values |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
-
-Scenario: "Query with evaluation time and variable value"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
- | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
- | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
- | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
- When evaluation time is `0m`
- And variable `osd_hosts` is `127.0.0.1`
- Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
- | metrics | values |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
-
-Scenario: "Query with interval time"
- Given the following series:
- | metrics | values |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
- | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
- | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 300 |
- | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 300 |
- | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
- When evaluation time is `2h`
- And evaluation interval is `1h`
- And interval is `1h`
- And variable `osd_hosts` is `127.0.0.1`
- Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
- | metrics | values |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 200 |
- | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 200 |
\ No newline at end of file
+++ /dev/null
-# This file and steps files is needed even if its empty because of 'behave' :(
+++ /dev/null
-attrs==21.2.0
-behave==1.2.6
-py==1.10.0
-pyparsing==2.4.7
-PyYAML==6.0
-types-PyYAML==6.0.0
-typing-extensions==3.10.0.2
-termcolor==1.1.0
-types-termcolor==1.1.2
-dataclasses==0.6
-types-dataclasses==0.6.1
-prettytable==2.4.0
+++ /dev/null
-import json
-from pathlib import Path
-from typing import Any, Dict, Tuple, Union
-
-from termcolor import cprint
-
-UNITS = ['ms', 's', 'm', 'h', 'd', 'w', 'y']
-
-
-def resolve_time_and_unit(time: str) -> Union[Tuple[int, str], Tuple[None, None]]:
- """
- Divide time with its unit and return a tuple like (10, 'm')
- Return None if its and invalid prometheus time
- Valid units are inside UNITS.
- """
- if time[-1] in UNITS:
- return int(time[:-1]), time[-1]
- if time[-2:] in UNITS:
- return int(time[:-2]), time[-2:]
- return None, None
-
-
-def get_dashboards_data() -> Dict[str, Any]:
- data: Dict[str, Any] = {'queries': {}, 'variables': {}, 'stats': {}}
- for file in Path(__file__).parent.parent.glob('*.json'):
- with open(file, 'r') as f:
- dashboard_data = json.load(f)
- data['stats'][str(file)] = {'total': 0, 'tested': 0}
- add_dashboard_queries(data, dashboard_data, str(file))
- add_dashboard_variables(data, dashboard_data)
- return data
-
-
-def add_dashboard_queries(data: Dict[str, Any], dashboard_data: Dict[str, Any], path: str) -> None:
- """
- Grafana panels can have more than one target/query, in order to identify each
- query in the panel we append the "legendFormat" of the target to the panel name.
- format: panel_name-legendFormat
- """
- if 'panels' not in dashboard_data:
- return
- for panel in dashboard_data['panels']:
- if (
- 'title' in panel
- and 'targets' in panel
- and len(panel['targets']) > 0
- and 'expr' in panel['targets'][0]
- ):
- for target in panel['targets']:
- title = panel['title']
- legend_format = target['legendFormat'] if 'legendFormat' in target else ""
- query_id = title + '-' + legend_format
- if query_id in data['queries']:
- # NOTE: If two or more panels have the same name and legend it
- # might suggest a refactoring is needed or add something else
- # to identify each query.
- cprint((f'WARNING: Query in panel "{title}" with legend "{legend_format}"'
- ' already exists'), 'yellow')
- data['queries'][query_id] = {'query': target['expr'], 'path': path}
- data['stats'][path]['total'] += 1
-
-
-def add_dashboard_variables(data: Dict[str, Any], dashboard_data: Dict[str, Any]) -> None:
- if 'templating' not in dashboard_data or 'list' not in dashboard_data['templating']:
- return
- for variable in dashboard_data['templating']['list']:
- if 'name' in variable:
- data['variables'][variable['name']] = 'UNSET VARIABLE'
+++ /dev/null
-[tox]
-envlist = grafonnet-{check,fix},lint,promql-query-test
-skipsdist = true
-
-[grafonnet]
-deps =
- -rrequirements-grafonnet.txt
-
-[testenv:grafonnet-{check,fix}]
-basepython = python3
-whitelist_externals =
- jsonnet
- bash
-description =
- check: Ensure that auto-generated grafana dashboard files matches the current version
- fix: generate dashboard json files from jsonnet file with latest changes
-deps =
- {[grafonnet]deps}
-passenv = GRAFONNET_PATH
-commands =
- check: bash test-jsonnet.sh
- fix: jsonnet -m . jsonnet/grafana_dashboards.jsonnet
-
-
-[testenv:lint]
-description =
- Run linters
-deps =
- -rrequirements-lint.txt
-setenv =
-commands =
- pylint --rcfile=.pylintrc tests
- mypy tests
- isort tests
-
-[testenv:promql-query-test]
-description =
- Run promtool unit testing on grafana queries.
-deps =
- -rtests/requirements.txt
-depends = grafonnet-check
-setenv =
-commands =
- behave tests/features
+++ /dev/null
-add_subdirectory(tests)
+++ /dev/null
-## Prometheus related bits
-
-### Alerts
-In monitoring/prometheus/alerts you'll find a set of Prometheus alert rules that
-should provide a decent set of default alerts for a Ceph cluster. Just put this
-file in a place according to your Prometheus configuration (wherever the `rules`
-configuration stanza points).
+++ /dev/null
-groups:
- - name: cluster health
- rules:
- - alert: CephHealthError
- expr: ceph_health_status == 2
- for: 5m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.2.1
- annotations:
- summary: Cluster is in an ERROR state
- description: >
- Ceph in HEALTH_ERROR state for more than 5 minutes.
- Please check "ceph health detail" for more information.
-
- - alert: CephHealthWarning
- expr: ceph_health_status == 1
- for: 15m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: Cluster is in a WARNING state
- description: >
- Ceph has been in HEALTH_WARN for more than 15 minutes.
- Please check "ceph health detail" for more information.
-
- - name: mon
- rules:
- - alert: CephMonDownQuorumAtRisk
- expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1
- for: 30s
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.3.1
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
- summary: Monitor quorum is at risk
- description: |
- {{ $min := query "floor(count(ceph_mon_metadata) / 2) +1" | first | value }}Quorum requires a majority of monitors (x {{ $min }}) to be active
- Without quorum the cluster will become inoperable, affecting all connected clients and services.
-
- The following monitors are down:
- {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }}
- - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
- {{- end }}
- - alert: CephMonDown
- expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1))
- for: 30s
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
- summary: One of more ceph monitors are down
- description: |
- {{ $down := query "count(ceph_mon_quorum_status == 0)" | first | value }}{{ $s := "" }}{{ if gt $down 1.0 }}{{ $s = "s" }}{{ end }}You have {{ $down }} monitor{{ $s }} down.
- Quorum is still intact, but the loss of further monitors will make your cluster inoperable.
-
- The following monitors are down:
- {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }}
- - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
- {{- end }}
- - alert: CephMonDiskspaceCritical
- expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.3.2
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit
- summary: Disk space on at least one monitor is critically low
- description: |
- The free space available to a monitor's store is critically low (<5% by default).
- You should increase the space available to the monitor(s). The
- default location for the store sits under /var/lib/ceph. Your monitor hosts are;
- {{- range query "ceph_mon_metadata"}}
- - {{ .Labels.hostname }}
- {{- end }}
-
- - alert: CephMonDiskspaceLow
- expr: ceph_health_detail{name="MON_DISK_LOW"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low
- summary: Disk space on at least one monitor is approaching full
- description: |
- The space available to a monitor's store is approaching full (>70% is the default).
- You should increase the space available to the monitor store. The
- default location for the store sits under /var/lib/ceph. Your monitor hosts are;
- {{- range query "ceph_mon_metadata"}}
- - {{ .Labels.hostname }}
- {{- end }}
-
- - alert: CephMonClockSkew
- expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew
- summary: Clock skew across the Monitor hosts detected
- description: |
- The ceph monitors rely on a consistent time reference to maintain
- quorum and cluster consistency. This event indicates that at least
- one of your mons is not sync'd correctly.
-
- Review the cluster status with ceph -s. This will show which monitors
- are affected. Check the time sync status on each monitor host.
-
- - name: osd
- rules:
- - alert: CephOSDDownHigh
- expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.1
- annotations:
- summary: More than 10% of OSDs are down
- description: |
- {{ $value | humanize }}% or {{ with query "count(ceph_osd_up == 0)" }}{{ . | first | value }}{{ end }} of {{ with query "count(ceph_osd_up)" }}{{ . | first | value }}{{ end }} OSDs are down (>= 10%).
-
- The following OSDs are down:
- {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }}
- - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
- {{- end }}
- - alert: CephOSDHostDown
- expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.8
- annotations:
- summary: An OSD host is offline
- description: |
- The following OSDs are down:
- {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }}
- - {{ .Labels.hostname }} : {{ .Labels.ceph_daemon }}
- {{- end }}
- - alert: CephOSDDown
- expr: ceph_health_detail{name="OSD_DOWN"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.2
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down
- summary: An OSD has been marked down/unavailable
- description: |
- {{ $num := query "count(ceph_osd_up == 0)" | first | value }}{{ $s := "" }}{{ if gt $num 1.0 }}{{ $s = "s" }}{{ end }}{{ $num }} OSD{{ $s }} down for over 5mins.
-
- The following OSD{{ $s }} {{ if eq $s "" }}is{{ else }}are{{ end }} down:
- {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0"}}
- - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }}
- {{- end }}
-
- - alert: CephOSDNearFull
- expr: ceph_health_detail{name="OSD_NEARFULL"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.3
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull
- summary: OSD(s) running low on free space (NEARFULL)
- description: |
- One or more OSDs have reached their NEARFULL threshold
-
- Use 'ceph health detail' to identify which OSDs have reached this threshold.
- To resolve, either add capacity to the cluster, or delete unwanted data
- - alert: CephOSDFull
- expr: ceph_health_detail{name="OSD_FULL"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.6
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full
- summary: OSD(s) is full, writes blocked
- description: |
- An OSD has reached it's full threshold. Writes from all pools that share the
- affected OSD will be blocked.
-
- To resolve, either add capacity to the cluster, or delete unwanted data
- - alert: CephOSDBackfillFull
- expr: ceph_health_detail{name="OSD_BACKFILLFULL"} > 0
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull
- summary: OSD(s) too full for backfill operations
- description: |
- An OSD has reached it's BACKFILL FULL threshold. This will prevent rebalance operations
- completing for some pools. Check the current capacity utilisation with 'ceph df'
-
- To resolve, either add capacity to the cluster, or delete unwanted data
- - alert: CephOSDTooManyRepairs
- expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 1
- for: 30s
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs
- summary: OSD has hit a high number of read errors
- description: |
- Reads from an OSD have used a secondary PG to return data to the client, indicating
- a potential failing disk.
- - alert: CephOSDTimeoutsPublicNetwork
- expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: Network issues delaying OSD heartbeats (public network)
- description: |
- OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network
- for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
- - alert: CephOSDTimeoutsClusterNetwork
- expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: Network issues delaying OSD heartbeats (cluster network)
- description: |
- OSD heartbeats on the cluster's 'cluster' network (backend) are running slow. Investigate the network
- for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
- - alert: CephOSDInternalDiskSizeMismatch
- expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch
- summary: OSD size inconsistency error
- description: |
- One or more OSDs have an internal inconsistency between the size of the physical device and it's metadata.
- This could lead to the OSD(s) crashing in future. You should redeploy the effected OSDs.
- - alert: CephDeviceFailurePredicted
- expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2
- summary: Device(s) have been predicted to fail soon
- description: |
- The device health module has determined that one or more devices will fail
- soon. To review the device states use 'ceph device ls'. To show a specific
- device use 'ceph device info <dev id>'.
-
- Mark the OSD as out (so data may migrate to other OSDs in the cluster). Once
- the osd is empty remove and replace the OSD.
- - alert: CephDeviceFailurePredictionTooHigh
- expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.7
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany
- summary: Too many devices have been predicted to fail, unable to resolve
- description: |
- The device health module has determined that the number of devices predicted to
- fail can not be remediated automatically, since it would take too many osd's out of
- the cluster, impacting performance and potentially availabililty. You should add new
- OSDs to the cluster to allow data to be relocated to avoid the data integrity issues.
- - alert: CephDeviceFailureRelocationIncomplete
- expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use
- summary: A device failure is predicted, but unable to relocate data
- description: |
- The device health module has determined that one or more devices will fail
- soon, but the normal process of relocating the data on the device to other
- OSDs in the cluster is blocked.
-
- Check the the cluster has available freespace. It may be necessary to add
- more disks to the cluster to allow the data from the failing device to
- successfully migrate.
-
- - alert: CephOSDFlapping
- expr: |
- (
- rate(ceph_osd_up[5m])
- * on(ceph_daemon) group_left(hostname) ceph_osd_metadata
- ) * 60 > 1
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.4
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds
- summary: Network issues are causing OSD's to flap (mark each other out)
- description: >
- OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} was
- marked down and back up at {{ $value | humanize }} times once a
- minute for 5 minutes. This could indicate a network issue (latency,
- packet drop, disruption) on the clusters "cluster network". Check the
- network environment on the listed host(s).
-
- - alert: CephOSDReadErrors
- expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1
- for: 30s
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors
- summary: Device read errors detected
- description: >
- An OSD has encountered read errors, but the OSD has recovered by retrying
- the reads. This may indicate an issue with the Hardware or Kernel.
- # alert on high deviation from average PG count
- - alert: CephPGImbalance
- expr: |
- abs(
- (
- (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0) by (job)
- ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)
- ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.5
- annotations:
- summary: PG allocations are not balanced across devices
- description: >
- OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} deviates
- by more than 30% from average PG count.
- # alert on high commit latency...but how high is too high
-
- - name: mds
- rules:
- - alert: CephFilesystemDamaged
- expr: ceph_health_detail{name="MDS_DAMAGE"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.1
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
- summary: Ceph filesystem is damaged.
- description: >
- The filesystems metadata has been corrupted. Data access
- may be blocked.
-
- Either analyse the output from the mds daemon admin socket, or
- escalate to support
- - alert: CephFilesystemOffline
- expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.3
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down
- summary: Ceph filesystem is offline
- description: >
- All MDS ranks are unavailable. The ceph daemons providing the metadata
- for the Ceph filesystem are all down, rendering the filesystem offline.
- - alert: CephFilesystemDegraded
- expr: ceph_health_detail{name="FS_DEGRADED"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.4
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded
- summary: Ceph filesystem is degraded
- description: >
- One or more metdata daemons (MDS ranks) are failed or in a
- damaged state. At best the filesystem is partially available,
- worst case is the filesystem is completely unusable.
- - alert: CephFilesystemMDSRanksLow
- expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max
- summary: Ceph MDS daemon count is lower than configured
- description: >
- The filesystem's "max_mds" setting defined the number of MDS ranks in
- the filesystem. The current number of active MDS daemons is less than
- this setting.
- - alert: CephFilesystemInsufficientStandby
- expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby
- summary: Ceph filesystem standby daemons too low
- description: >
- The minimum number of standby daemons determined by standby_count_wanted
- is less than the actual number of standby daemons. Adjust the standby count
- or increase the number of mds daemons within the filesystem.
- - alert: CephFilesystemFailureNoStandby
- expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.5
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds
- summary: Ceph MDS daemon failed, no further standby available
- description: >
- An MDS daemon has failed, leaving only one active rank without
- further standby. Investigate the cause of the failure or add a
- standby daemon
- - alert: CephFilesystemReadOnly
- expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.2
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
- summary: Ceph filesystem in read only mode, due to write error(s)
- description: >
- The filesystem has switched to READ ONLY due to an unexpected
- write error, when writing to the metadata pool
-
- Either analyse the output from the mds daemon admin socket, or
- escalate to support
-
- - name: mgr
- rules:
- - alert: CephMgrModuleCrash
- expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1
- for: 5m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.6.1
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash
- summary: A mgr module has recently crashed
- description: >
- One or more mgr modules have crashed and are yet to be acknowledged by the administrator. A
- crashed module may impact functionality within the cluster. Use the 'ceph crash' commands to
- investigate which module has failed, and archive it to acknowledge the failure.
- - alert: CephMgrPrometheusModuleInactive
- expr: up{job="ceph"} == 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.6.2
- annotations:
- summary: Ceph's mgr/prometheus module is not available
- description: >
- The mgr/prometheus module at {{ $labels.instance }} is unreachable. This
- could mean that the module has been disabled or the mgr itself is down.
-
- Without the mgr/prometheus module metrics and alerts will no longer
- function. Open a shell to ceph and use 'ceph -s' to to determine whether the
- mgr is active. If the mgr is not active, restart it, otherwise you can check
- the mgr/prometheus module is loaded with 'ceph mgr module ls' and if it's
- not listed as enabled, enable it with 'ceph mgr module enable prometheus'
-
- - name: pgs
- rules:
- - alert: CephPGsInactive
- expr: ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_active) > 0
- for: 5m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.1
- annotations:
- summary: One or more Placement Groups are inactive
- description: >
- {{ $value }} PGs have been inactive for more than 5 minutes in pool {{ $labels.name }}.
- Inactive placement groups aren't able to serve read/write
- requests.
- - alert: CephPGsUnclean
- expr: ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_clean) > 0
- for: 15m
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.2
- annotations:
- summary: One or more platcment groups are marked unclean
- description: >
- {{ $value }} PGs haven't been clean for more than 15 minutes in pool {{ $labels.name }}.
- Unclean PGs haven't been able to completely recover from a previous failure.
- - alert: CephPGsDamaged
- expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1
- for: 5m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.4
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged
- summary: Placement group damaged, manual intervention needed
- description: >
- During data consistency checks (scrub), at least one PG has been flagged as being
- damaged or inconsistent.
-
- Check to see which PG is affected, and attempt a manual repair if neccessary. To list
- problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use
- the 'ceph pg repair <pg_num>' command.
- - alert: CephPGRecoveryAtRisk
- expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.5
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full
- summary: OSDs are too full for automatic recovery
- description: >
- Data redundancy may be reduced, or is at risk, since one or more OSDs are at or above their
- 'full' threshold. Add more capacity to the cluster, or delete unwanted data.
- - alert: CephPGUnavilableBlockingIO
- # PG_AVAILABILITY, but an OSD is not in a DOWN state
- expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"})) == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.3
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability
- summary: Placement group is unavailable, blocking some I/O
- description: >
- Data availability is reduced impacting the clusters abilty to service I/O to some data. One or
- more placement groups (PGs) are in a state that blocks IO.
- - alert: CephPGBackfillAtRisk
- expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.6
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full
- summary: Backfill operations are blocked, due to lack of freespace
- description: >
- Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs
- have breached their 'backfillfull' threshold. Add more capacity, or delete unwanted data.
- - alert: CephPGNotScrubbed
- expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed
- summary: Placement group(s) have not been scrubbed
- description: |
- One or more PGs have not been scrubbed recently. The scrub process is a data integrity
- feature, protectng against bit-rot. It checks that objects and their metadata (size and
- attributes) match across object replicas. When PGs miss their scrub window, it may
- indicate the scrub window is too small, or PGs were not in a 'clean' state during the
- scrub window.
-
- You can manually initiate a scrub with: ceph pg scrub <pgid>
- - alert: CephPGsHighPerOSD
- expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs
- summary: Placement groups per OSD is too high
- description: |
- The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).
-
- Check that the pg_autoscaler hasn't been disabled for any of the pools, with 'ceph osd pool autoscale-status'
- and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide
- the autoscaler based on the expected relative size of the pool
- (i.e. 'ceph osd pool set cephfs.cephfs.meta target_size_ratio .1')
- - alert: CephPGNotDeepScrubbed
- expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed
- summary: Placement group(s) have not been deep scrubbed
- description: |
- One or more PGs have not been deep scrubbed recently. Deep scrub is a data integrity
- feature, protectng against bit-rot. It compares the contents of objects and their
- replicas for inconsistency. When PGs miss their deep scrub window, it may indicate
- that the window is too small or PGs were not in a 'clean' state during the deep-scrub
- window.
-
- You can manually initiate a deep scrub with: ceph pg deep-scrub <pgid>
-
- - name: nodes
- rules:
- - alert: CephNodeRootFilesystemFull
- expr: node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 5
- for: 5m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.8.1
- annotations:
- summary: Root filesystem is dangerously full
- description: >
- Root volume (OSD and MON store) is dangerously full: {{ $value | humanize }}% free.
-
- # alert on nic packet errors and drops rates > 1% packets/s
- - alert: CephNodeNetworkPacketDrops
- expr: |
- (
- increase(node_network_receive_drop_total{device!="lo"}[1m]) +
- increase(node_network_transmit_drop_total{device!="lo"}[1m])
- ) / (
- increase(node_network_receive_packets_total{device!="lo"}[1m]) +
- increase(node_network_transmit_packets_total{device!="lo"}[1m])
- ) >= 0.0001 or (
- increase(node_network_receive_drop_total{device!="lo"}[1m]) +
- increase(node_network_transmit_drop_total{device!="lo"}[1m])
- ) >= 10
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.8.2
- annotations:
- summary: One or more Nics is seeing packet drops
- description: >
- Node {{ $labels.instance }} experiences packet drop > 0.01% or >
- 10 packets/s on interface {{ $labels.device }}.
-
- - alert: CephNodeNetworkPacketErrors
- expr: |
- (
- increase(node_network_receive_errs_total{device!="lo"}[1m]) +
- increase(node_network_transmit_errs_total{device!="lo"}[1m])
- ) / (
- increase(node_network_receive_packets_total{device!="lo"}[1m]) +
- increase(node_network_transmit_packets_total{device!="lo"}[1m])
- ) >= 0.0001 or (
- increase(node_network_receive_errs_total{device!="lo"}[1m]) +
- increase(node_network_transmit_errs_total{device!="lo"}[1m])
- ) >= 10
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.8.3
- annotations:
- summary: One or more Nics is seeing packet errors
- description: >
- Node {{ $labels.instance }} experiences packet errors > 0.01% or
- > 10 packets/s on interface {{ $labels.device }}.
-
- # Restrict to device names beginning with '/' to skip false alarms from
- # tmpfs, overlay type filesystems
- - alert: CephNodeDiskspaceWarning
- expr: |
- predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *
- on(instance) group_left(nodename) node_uname_info < 0
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.8.4
- annotations:
- summary: Host filesystem freespace is getting low
- description: >
- Mountpoint {{ $labels.mountpoint }} on {{ $labels.nodename }}
- will be full in less than 5 days assuming the average fill-up
- rate of the past 48 hours.
-
- - alert: CephNodeInconsistentMTU
- expr: |
- node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
- scalar(
- max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
- quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
- )
- or
- node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
- scalar(
- min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
- quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
- )
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: MTU settings across Ceph hosts are inconsistent
- description: >
- Node {{ $labels.instance }} has a different MTU size ({{ $value }})
- than the median of devices named {{ $labels.device }}.
-
- - name: pools
- rules:
- - alert: CephPoolGrowthWarning
- expr: |
- (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id)
- group_right ceph_pool_metadata) >= 95
- labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.9.2
- annotations:
- summary: Pool growth rate may soon exceed it's capacity
- description: >
- Pool '{{ $labels.name }}' will be full in less than 5 days
- assuming the average fill-up rate of the past 48 hours.
- - alert: CephPoolBackfillFull
- expr: ceph_health_detail{name="POOL_BACKFILLFULL"} > 0
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: Freespace in a pool is too low for recovery/rebalance
- description: >
- A pool is approaching it's near full threshold, which will
- prevent rebalance operations from completing. You should
- consider adding more capacity to the pool.
-
- - alert: CephPoolFull
- expr: ceph_health_detail{name="POOL_FULL"} > 0
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.9.1
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full
- summary: Pool is full - writes are blocked
- description: |
- A pool has reached it's MAX quota, or the OSDs supporting the pool
- have reached their FULL threshold. Until this is resolved, writes to
- the pool will be blocked.
- Pool Breakdown (top 5)
- {{- range query "topk(5, sort_desc(ceph_pool_percent_used * on(pool_id) group_right ceph_pool_metadata))" }}
- - {{ .Labels.name }} at {{ .Value }}%
- {{- end }}
- Either increase the pools quota, or add capacity to the cluster first
- then increase it's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
- - alert: CephPoolNearFull
- expr: ceph_health_detail{name="POOL_NEAR_FULL"} > 0
- for: 5m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- summary: One or more Ceph pools are getting full
- description: |
- A pool has exceeeded it warning (percent full) threshold, or the OSDs
- supporting the pool have reached their NEARFULL thresholds. Writes may
- continue, but you are at risk of the pool going read only if more capacity
- isn't made available.
-
- Determine the affected pool with 'ceph df detail', for example looking
- at QUOTA BYTES and STORED. Either increase the pools quota, or add
- capacity to the cluster first then increase it's quota
- (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
- - name: healthchecks
- rules:
- - alert: CephSlowOps
- expr: ceph_healthcheck_slow_ops > 0
- for: 30s
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
- summary: MON/OSD operations are slow to complete
- description: >
- {{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)
-# cephadm alerts
- - name: cephadm
- rules:
- - alert: CephadmUpgradeFailed
- expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0
- for: 30s
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.11.2
- annotations:
- summary: Ceph version upgrade has failed
- description: >
- The cephadm cluster upgrade process has failed. The cluster remains in
- an undetermined state.
-
- Please review the cephadm logs, to understand the nature of the issue
- - alert: CephadmDaemonFailed
- expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0
- for: 30s
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.11.1
- annotations:
- summary: A ceph daemon manged by cephadm is down
- description: >
- A daemon managed by cephadm is no longer active. Determine, which
- daemon is down with 'ceph health detail'. you may start daemons with
- the 'ceph orch daemon start <daemon_id>'
- - alert: CephadmPaused
- expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0
- for: 1m
- labels:
- severity: warning
- type: ceph_default
- annotations:
- documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused
- summary: Orchestration tasks via cephadm are PAUSED
- description: >
- Cluster management has been paused manually. This will prevent the
- orchestrator from service management and reconciliation. If this is
- not intentional, resume cephadm operations with 'ceph orch resume'
-
-# prometheus alerts
- - name: PrometheusServer
- rules:
- - alert: PrometheusJobMissing
- expr: absent(up{job="ceph"})
- for: 30s
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.12.1
- annotations:
- summary: The scrape job for Ceph is missing from Prometheus
- description: |
- The prometheus job that scrapes from Ceph is no longer defined, this
- will effectively mean you'll have no metrics or alerts for the cluster.
-
- Please review the job definitions in the prometheus.yml file of the prometheus
- instance.
-# Object related events
- - name: rados
- rules:
- - alert: CephObjectMissing
- expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1
- for: 30s
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.10.1
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound
- summary: Object(s) has been marked UNFOUND
- description: |
- A version of a RADOS object can not be found, even though all OSDs are up. I/O
- requests for this object from clients will block (hang). Resolving this issue may
- require the object to be rolled back to a prior version manually, and manually verified.
-# Generic
- - name: generic
- rules:
- - alert: CephDaemonCrash
- expr: ceph_health_detail{name="RECENT_CRASH"} == 1
- for: 1m
- labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.1.2
- annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash
- summary: One or more Ceph daemons have crashed, and are pending acknowledgement
- description: |
- One or more daemons have crashed recently, and need to be acknowledged. This notification
- ensures that software crashes don't go unseen. To acknowledge a crash, use the
- 'ceph crash archive <id>' command.
\ No newline at end of file
+++ /dev/null
-if(WITH_TESTS)
- include(AddCephTest)
- # add_tox_test(prometheus-alerts ${CMAKE_CURRENT_SOURCE_DIR} TOX_ENVS py3)
-endif()
+++ /dev/null
-
-## Alert Rule Standards
-
-The alert rules should adhere to the following principles
-- each alert must have a unique name
-- each alert should define a common structure
- - labels : must contain severity and type
- - annotations : must provide description
- - expr : must define the promql expression
- - alert : defines the alert name
-- alerts that have a corresponding section within docs.ceph.com must include a
- documentation field in the annotations section
-- critical alerts should declare an oid in the labels section
-- critical alerts should have a corresponding entry in the Ceph MIB
-
-
-## Testing Prometheus Rules
-Once you have updated the `ceph_default_alerts.yml` file, you should use the
-`validate_rules.py` script directly, or via `tox` to ensure the format of any update
-or change aligns to our rule structure guidelines. The validate_rules.py script will
-process the rules and look for any configuration anomalies and output a report if
-problems are detected.
-
-Here's an example run, to illustrate the format and the kinds of issues detected.
-
-```
-[paul@myhost tests]$ ./validate_rules.py
-
-Checking rule groups
- cluster health : ..
- mon : E.W..
- osd : E...W......W.E..
- mds : WW
- mgr : WW
- pgs : ..WWWW..
- nodes : .EEEE
- pools : EEEW.
- healthchecks : .
- cephadm : WW.
- prometheus : W
- rados : W
-
-Summary
-
-Rule file : ../alerts/ceph_default_alerts.yml
-Unit Test file : test_alerts.yml
-
-Rule groups processed : 12
-Rules processed : 51
-Rule errors : 10
-Rule warnings : 16
-Rule name duplicates : 0
-Unit tests missing : 4
-
-Problem Report
-
- Group Severity Alert Name Problem Description
- ----- -------- ---------- -------------------
- cephadm Warning Cluster upgrade has failed critical level alert is missing an SNMP oid entry
- cephadm Warning A daemon managed by cephadm is down critical level alert is missing an SNMP oid entry
- mds Warning Ceph Filesystem damage detected critical level alert is missing an SNMP oid entry
- mds Warning Ceph Filesystem switched to READ ONLY critical level alert is missing an SNMP oid entry
- mgr Warning mgr module failure critical level alert is missing an SNMP oid entry
- mgr Warning mgr prometheus module is not active critical level alert is missing an SNMP oid entry
- mon Error Monitor down, quorum is at risk documentation link error: #mon-downwah not found on the page
- mon Warning Ceph mon disk space critically low critical level alert is missing an SNMP oid entry
- nodes Error network packets dropped invalid alert structure. Missing field: for
- nodes Error network packet errors invalid alert structure. Missing field: for
- nodes Error storage filling up invalid alert structure. Missing field: for
- nodes Error MTU Mismatch invalid alert structure. Missing field: for
- osd Error 10% OSDs down invalid alert structure. Missing field: for
- osd Error Flapping OSD invalid alert structure. Missing field: for
- osd Warning OSD Full critical level alert is missing an SNMP oid entry
- osd Warning Too many devices predicted to fail critical level alert is missing an SNMP oid entry
- pgs Warning Placement Group (PG) damaged critical level alert is missing an SNMP oid entry
- pgs Warning Recovery at risk, cluster too full critical level alert is missing an SNMP oid entry
- pgs Warning I/O blocked to some data critical level alert is missing an SNMP oid entry
- pgs Warning Cluster too full, automatic data recovery impaired critical level alert is missing an SNMP oid entry
- pools Error pool full invalid alert structure. Missing field: for
- pools Error pool filling up (growth forecast) invalid alert structure. Missing field: for
- pools Error Ceph pool is too full for recovery/rebalance invalid alert structure. Missing field: for
- pools Warning Ceph pool is full - writes blocked critical level alert is missing an SNMP oid entry
- prometheus Warning Scrape job is missing critical level alert is missing an SNMP oid entry
- rados Warning Data not found/missing critical level alert is missing an SNMP oid entry
-
-Unit tests are incomplete. Tests missing for the following alerts;
- - Placement Group (PG) damaged
- - OSD Full
- - storage filling up
- - pool filling up (growth forecast)
-
-```
+++ /dev/null
-pyyaml==6.0
-bs4
+++ /dev/null
-ALERTS_FILE = '../alerts/ceph_default_alerts.yml'
-UNIT_TESTS_FILE = 'test_alerts.yml'
\ No newline at end of file
+++ /dev/null
-rule_files:
- - ../alerts/ceph_default_alerts.yml
-evaluation_interval: 5m
-tests:
- # health error
- - interval: 5m
- input_series:
- - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
- values: '2 2 2 2 2 2 2'
- promql_expr_test:
- - expr: ceph_health_status == 2
- eval_time: 5m
- exp_samples:
- - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
- value: 2
- alert_rule_test:
- - eval_time: 1m
- alertname: CephHealthError
- - eval_time: 6m
- alertname: CephHealthError
- exp_alerts:
- - exp_labels:
- instance: ceph:9283
- job: ceph
- oid: 1.3.6.1.4.1.50495.1.2.1.2.1
- type: ceph_default
- severity: critical
- exp_annotations:
- summary: Cluster is in an ERROR state
- description: >
- Ceph in HEALTH_ERROR state for more than 5 minutes.
- Please check "ceph health detail" for more information.
-
- # health warning
- - interval: 5m
- input_series:
- - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
- values: '1 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_status == 1
- eval_time: 15m
- exp_samples:
- - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
- value: 1
- alert_rule_test:
- - eval_time: 10m
- alertname: CephHealthWarning
- - eval_time: 20m
- alertname: CephHealthWarning
- exp_alerts:
- - exp_labels:
- instance: ceph:9283
- job: ceph
- type: ceph_default
- severity: warning
- exp_annotations:
- summary: Cluster is in a WARNING state
- description: >
- Ceph has been in HEALTH_WARN for more than 15 minutes.
- Please check "ceph health detail" for more information.
-
- # 10% OSDs down
- - interval: 1m
- input_series:
- - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
- values: '1 1 1 1 1'
- - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
- values: '0 0 0 0 0'
- - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
- values: '1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1'
- promql_expr_test:
- - expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10
- eval_time: 1m
- exp_samples:
- - labels: '{}'
- value: 3.333333333333333E+01
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDDownHigh
- exp_alerts:
- - exp_labels:
- oid: 1.3.6.1.4.1.50495.1.2.1.4.1
- type: ceph_default
- severity: critical
- exp_annotations:
- summary: More than 10% of OSDs are down
- description: |
- 33.33% or 1 of 3 OSDs are down (>= 10%).
-
- The following OSDs are down:
- - osd.1 on ceph
-
- # flapping OSD
- - interval: 1s
- input_series:
- - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
- values: '1+1x100'
- - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
- values: '1+0x100'
- - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
- values: '1+0x100'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- promql_expr_test:
- - expr: |
- (
- rate(ceph_osd_up[5m])
- * on(ceph_daemon) group_left(hostname) ceph_osd_metadata
- ) * 60 > 1
- eval_time: 1m
- exp_samples:
- - labels: '{ceph_daemon="osd.0", hostname="ceph", instance="ceph:9283",
- job="ceph"}'
- value: 1.2200000000000001E+01
- alert_rule_test:
- - eval_time: 5m
- alertname: CephOSDFlapping
- exp_alerts:
- - exp_labels:
- ceph_daemon: osd.0
- hostname: ceph
- instance: ceph:9283
- job: ceph
- oid: 1.3.6.1.4.1.50495.1.2.1.4.4
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds
- summary: Network issues are causing OSD's to flap (mark each other out)
- description: >
- OSD osd.0 on ceph was
- marked down and back up at 20.1 times once a minute for 5 minutes.
- This could indicate a network issue (latency, packet drop, disruption)
- on the clusters "cluster network". Check the network environment on the
- listed host(s).
-
- # high pg count deviation
- - interval: 1m
- input_series:
- - series: 'ceph_osd_numpg{ceph_daemon="osd.0",instance="ceph:9283",
- job="ceph"}'
- values: '100 100 100 100 100 160'
- - series: 'ceph_osd_numpg{ceph_daemon="osd.1",instance="ceph:9283",
- job="ceph"}'
- values: '100 100 100 100 100 320'
- - series: 'ceph_osd_numpg{ceph_daemon="osd.2",instance="ceph:9283",
- job="ceph"}'
- values: '100 100 100 100 100 160'
- - series: 'ceph_osd_numpg{ceph_daemon="osd.3",instance="ceph:9283",
- job="ceph"}'
- values: '100 100 100 100 100 160'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.3",
- ceph_version="ceph version 17.0.0-189-g3558fd72
- (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
- cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
- hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
- public_addr="172.20.0.2"}'
- values: '1 1 1 1 1 1'
- promql_expr_test:
- - expr: |
- abs(
- (
- (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0)
- by (job)
- ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)
- ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30
-
- eval_time: 5m
- exp_samples:
- - labels: '{ceph_daemon="osd.1", hostname="ceph", instance="ceph:9283",
- job="ceph"}'
- value: 6E-01
- alert_rule_test:
- - eval_time: 10m
- alertname: CephPGImbalance
- exp_alerts:
- - exp_labels:
- ceph_daemon: osd.1
- hostname: ceph
- instance: ceph:9283
- job: ceph
- oid: 1.3.6.1.4.1.50495.1.2.1.4.5
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: PG allocations are not balanced across devices
- description: >
- OSD osd.1 on ceph deviates
- by more than 30% from average PG count.
-
- # pgs inactive
- - interval: 1m
- input_series:
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="2"}'
- values: '1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="3"}'
- values: '1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
- values: '32 32 32 32 32 32 32 32'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
- values: '33 32 32 32 32 33 33 32'
- - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="2"}'
- values: '32 32 32 32 32 32 32 32'
- - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="3"}'
- values: '32 32 32 32 32 32 32 32'
- promql_expr_test:
- - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
- (ceph_pg_total - ceph_pg_active) > 0
- eval_time: 5m
- exp_samples:
- - labels: '{instance="ceph:9283", job="ceph",
- name="device_health_metrics",
- pool_id="3"}'
- value: 1
- alert_rule_test:
- - eval_time: 5m
- alertname: CephPGsInactive
- exp_alerts:
- - exp_labels:
- instance: ceph:9283
- job: ceph
- name: device_health_metrics
- oid: 1.3.6.1.4.1.50495.1.2.1.7.1
- pool_id: 3
- severity: critical
- type: ceph_default
- exp_annotations:
- summary: One or more Placement Groups are inactive
- description: >
- 1 PGs have been inactive for more than 5 minutes in pool
- device_health_metrics.
- Inactive placement groups aren't able to serve read/write
- requests.
-
- #pgs unclean
- - interval: 1m
- input_series:
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="2"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="device_health_metrics",pool_id="3"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
- values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32 32'
- - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
- values: '33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33
- 33 33'
- - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="2"}'
- values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32'
- - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="3"}'
- values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32'
- promql_expr_test:
- - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
- (ceph_pg_total - ceph_pg_clean) > 0
- eval_time: 15m
- exp_samples:
- - labels: '{instance="ceph:9283", job="ceph",
- name="device_health_metrics", pool_id="3"}'
- value: 1
- alert_rule_test:
- - eval_time: 16m
- alertname: CephPGsUnclean
- exp_alerts:
- - exp_labels:
- instance: ceph:9283
- job: ceph
- name: device_health_metrics
- oid: 1.3.6.1.4.1.50495.1.2.1.7.2
- pool_id: 3
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: One or more platcment groups are marked unclean
- description: >
- 1 PGs haven't been clean for more than 15 minutes in pool
- device_health_metrics.
- Unclean PGs haven't been able to completely recover from a
- previous failure.
-
- # root volume full
- - interval: 1m
- input_series:
- - series: 'node_filesystem_avail_bytes{device="/dev/mapper/fedora_localhost
- --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
- mountpoint="/"}'
- values: '35336400896 35336400896 35336400896 35336400896 35336400896
- 3525385519.104 3533640089'
- - series: 'node_filesystem_size_bytes{device="/dev/mapper/fedora_localhost
- --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
- mountpoint="/"}'
- values: '73445531648 73445531648 73445531648 73445531648 73445531648
- 73445531648 73445531648'
- promql_expr_test:
- - expr: node_filesystem_avail_bytes{mountpoint="/"} /
- node_filesystem_size_bytes{mountpoint="/"} * 100 < 5
- eval_time: 5m
- exp_samples:
- - labels: '{device="/dev/mapper/fedora_localhost --live-home",
- fstype="ext4", instance="node-exporter", job="node-exporter",
- mountpoint="/"}'
- value: 4.8E+00
- alert_rule_test:
- - eval_time: 10m
- alertname: CephNodeRootFilesystemFull
- exp_alerts:
- - exp_labels:
- device: /dev/mapper/fedora_localhost --live-home
- fstype: ext4
- instance: node-exporter
- job: node-exporter
- mountpoint: /
- oid: 1.3.6.1.4.1.50495.1.2.1.8.1
- severity: critical
- type: ceph_default
- exp_annotations:
- summary: Root filesystem is dangerously full
- description: >
- Root volume (OSD and MON store) is dangerously full: 4.811% free.
-
- # network packets dropped
- - interval: 1s
- input_series:
- - series: 'node_network_receive_drop_total{device="eth0",
- instance="node-exporter",job="node-exporter"}'
- values: '1+1x500'
- - series: 'node_network_transmit_drop_total{device="eth0",
- instance="node-exporter",job="node-exporter"}'
- values: '1+1x500'
- promql_expr_test:
- - expr: |
- (
- increase(node_network_receive_drop_total{device!="lo"}[1m]) +
- increase(node_network_transmit_drop_total{device!="lo"}[1m])
- ) / (
- increase(node_network_receive_packets_total{device!="lo"}[1m]) +
- increase(node_network_transmit_packets_total{device!="lo"}[1m])
- ) >= 0.0001 or (
- increase(node_network_receive_drop_total{device!="lo"}[1m]) +
- increase(node_network_transmit_drop_total{device!="lo"}[1m])
- ) >= 10
-
- eval_time: 5m
- exp_samples:
- - labels: '{device="eth0", instance="node-exporter",
- job="node-exporter"}'
- value: 1.2E+02
- alert_rule_test:
- - eval_time: 5m
- alertname: CephNodeNetworkPacketDrops
- exp_alerts:
- - exp_labels:
- device: eth0
- instance: node-exporter
- job: node-exporter
- oid: 1.3.6.1.4.1.50495.1.2.1.8.2
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: One or more Nics is seeing packet drops
- description: >
- Node node-exporter experiences packet drop > 0.01% or >
- 10 packets/s on interface eth0.
-
- # network packets errors
- - interval: 1s
- input_series:
- - series: 'node_network_receive_errs_total{device="eth0",
- instance="node-exporter",job="node-exporter"}'
- values: '1+1x500'
- - series: 'node_network_transmit_errs_total{device="eth0",
- instance="node-exporter",job="node-exporter"}'
- values: '1+1x500'
- promql_expr_test:
- - expr: |
- (
- increase(node_network_receive_errs_total{device!="lo"}[1m]) +
- increase(node_network_transmit_errs_total{device!="lo"}[1m])
- ) / (
- increase(node_network_receive_packets_total{device!="lo"}[1m]) +
- increase(node_network_transmit_packets_total{device!="lo"}[1m])
- ) >= 0.0001 or (
- increase(node_network_receive_errs_total{device!="lo"}[1m]) +
- increase(node_network_transmit_errs_total{device!="lo"}[1m])
- ) >= 10
-
- eval_time: 5m
- exp_samples:
- - labels: '{device="eth0", instance="node-exporter",
- job="node-exporter"}'
- value: 1.2E+02
- alert_rule_test:
- - eval_time: 5m
- alertname: CephNodeNetworkPacketErrors
- exp_alerts:
- - exp_labels:
- device: eth0
- instance: node-exporter
- job: node-exporter
- oid: 1.3.6.1.4.1.50495.1.2.1.8.3
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: One or more Nics is seeing packet errors
- description: >
- Node node-exporter experiences packet errors > 0.01% or > 10
- packets/s on interface eth0.
-
-# Node Storage disk space filling up
- - interval: 1m
- # 20GB = 21474836480, 256MB = 268435456
- input_series:
- - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
- fstype="xfs",instance="node-1",mountpoint="/rootfs"}'
- values: '21474836480-268435456x48'
- - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
- fstype="xfs",instance="node-2",mountpoint="/rootfs"}'
- values: '21474836480+0x48'
- - series: 'node_uname_info{instance="node-1", nodename="node-1.unittests.com"}'
- values: 1+0x48
- - series: 'node_uname_info{instance="node-2", nodename="node-2.unittests.com"}'
- values: 1+0x48
- promql_expr_test:
- - expr: |
- predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *
- on(instance) group_left(nodename) node_uname_info < 0
- eval_time: 5m
- exp_samples:
- - labels: '{device="/dev/mapper/vg-root",instance="node-1",fstype="xfs",
- mountpoint="/rootfs",nodename="node-1.unittests.com"}'
- value: -1.912602624E+12
- alert_rule_test:
- - eval_time: 5m
- alertname: CephNodeDiskspaceWarning
- exp_alerts:
- - exp_labels:
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.8.4
- device: /dev/mapper/vg-root
- fstype: xfs
- instance: node-1
- mountpoint: /rootfs
- nodename: node-1.unittests.com
- exp_annotations:
- summary: Host filesystem freespace is getting low
- description: >
- Mountpoint /rootfs on node-1.unittests.com
- will be full in less than 5 days assuming the average fill-up
- rate of the past 48 hours.
- # MTU Mismatch
- - interval: 1m
- input_series:
- - series: 'node_network_mtu_bytes{device="eth0",instance="node-exporter",
- job="node-exporter"}'
- values: '1500 1500 1500 1500 1500'
- - series: 'node_network_mtu_bytes{device="eth1",instance="node-exporter",
- job="node-exporter"}'
- values: '1500 1500 1500 1500 1500'
- - series: 'node_network_mtu_bytes{device="eth2",instance="node-exporter",
- job="node-exporter"}'
- values: '1500 1500 1500 1500 1500'
- - series: 'node_network_mtu_bytes{device="eth3",instance="node-exporter",
- job="node-exporter"}'
- values: '1500 1500 1500 1500 1500'
- - series: 'node_network_mtu_bytes{device="eth4",instance="node-exporter",
- job="node-exporter"}'
- values: '9000 9000 9000 9000 9000'
- - series: 'node_network_mtu_bytes{device="eth4",instance="hostname1",
- job="node-exporter"}'
- values: '2200 2200 2200 2200 2200'
- - series: 'node_network_mtu_bytes{device="eth4",instance="hostname2",
- job="node-exporter"}'
- values: '2400 2400 2400 2400 2400'
- - series: 'node_network_up{device="eth0",instance="node-exporter",
- job="node-exporter"}'
- values: '0 0 0 0 0'
- - series: 'node_network_up{device="eth1",instance="node-exporter",
- job="node-exporter"}'
- values: '0 0 0 0 0'
- - series: 'node_network_up{device="eth2",instance="node-exporter",
- job="node-exporter"}'
- values: '1 1 1 1 1'
- - series: 'node_network_up{device="eth3",instance="node-exporter",
- job="node-exporter"}'
- values: '1 1 1 1 1'
- - series: 'node_network_up{device="eth4",instance="node-exporter",
- job="node-exporter"}'
- values: '1 1 1 1 1'
- - series: 'node_network_up{device="eth4",instance="hostname1",
- job="node-exporter"}'
- values: '1 1 1 1 1'
- - series: 'node_network_up{device="eth4",instance="hostname2",
- job="node-exporter"}'
- values: '0 0 0 0 0'
- promql_expr_test:
- - expr: |
- node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
- scalar(
- max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
- quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
- )
- or
- node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
- scalar(
- min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
- quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
- )
- eval_time: 1m
- exp_samples:
- - labels: '{device="eth4", instance="node-exporter", job="node-exporter"}'
- value: 9000
- - labels: '{device="eth4", instance="hostname1", job="node-exporter"}'
- value: 2200
- alert_rule_test:
- - eval_time: 1m
- alertname: CephNodeInconsistentMTU
- exp_alerts:
- - exp_labels:
- device: eth4
- instance: hostname1
- job: node-exporter
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: MTU settings across Ceph hosts are inconsistent
- description: >
- Node hostname1 has a different MTU size (2200)
- than the median of devices named eth4.
- - exp_labels:
- device: eth4
- instance: node-exporter
- job: node-exporter
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: MTU settings across Ceph hosts are inconsistent
- description: >
- Node node-exporter has a different MTU size (9000)
- than the median of devices named eth4.
-
- # pool full, data series has 6 but using topk(5) so to ensure the
- # results are working as expected
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="POOL_FULL"}'
- values: '0 0 0 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_percent_used{pool_id="1"}'
- values: '32+0x10'
- - series: 'ceph_pool_percent_used{pool_id="2"}'
- values: '96+0x10'
- - series: 'ceph_pool_percent_used{pool_id="3"}'
- values: '90+0x10'
- - series: 'ceph_pool_percent_used{pool_id="4"}'
- values: '72+0x10'
- - series: 'ceph_pool_percent_used{pool_id="5"}'
- values: '19+0x10'
- - series: 'ceph_pool_percent_used{pool_id="6"}'
- values: '10+0x10'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="cephfs_data",pool_id="1"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="rbd",pool_id="2"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="iscsi",pool_id="3"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="default.rgw.index",pool_id="4"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="default.rgw.log",pool_id="5"}'
- values: '1 1 1 1 1 1 1 1 1'
- - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
- name="dummy",pool_id="6"}'
- values: '1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="POOL_FULL"} > 0
- eval_time: 5m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="POOL_FULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPoolFull
- - eval_time: 10m
- alertname: CephPoolFull
- exp_alerts:
- - exp_labels:
- name: POOL_FULL
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.9.1
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full
- summary: Pool is full - writes are blocked
- description: |
- A pool has reached it's MAX quota, or the OSDs supporting the pool
- have reached their FULL threshold. Until this is resolved, writes to
- the pool will be blocked.
- Pool Breakdown (top 5)
- - rbd at 96%
- - iscsi at 90%
- - default.rgw.index at 72%
- - cephfs_data at 32%
- - default.rgw.log at 19%
- Either increase the pools quota, or add capacity to the cluster first
- then increase it's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
- # slow OSD ops
- - interval : 1m
- input_series:
- - series: 'ceph_healthcheck_slow_ops{instance="ceph:9283",job="ceph"}'
- values: '1+0x120'
- promql_expr_test:
- - expr: ceph_healthcheck_slow_ops > 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_healthcheck_slow_ops", instance="ceph:9283",
- job="ceph"}'
- value: 1
- alert_rule_test:
- - eval_time: 20m
- alertname: CephSlowOps
- exp_alerts:
- - exp_labels:
- instance: ceph:9283
- job: ceph
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
- summary: MON/OSD operations are slow to complete
- description: >
- 1 OSD requests are taking too long to process
- (osd_op_complaint_time exceeded)
-
-# CEPHADM orchestrator alert triggers
- - interval: 30s
- input_series:
- - series: 'ceph_health_detail{name="UPGRADE_EXCEPTION"}'
- values: '1+0x40'
- promql_expr_test:
- - expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="UPGRADE_EXCEPTION"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephadmUpgradeFailed
- - eval_time: 5m
- alertname: CephadmUpgradeFailed
- exp_alerts:
- - exp_labels:
- name: UPGRADE_EXCEPTION
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.11.2
- exp_annotations:
- summary: Ceph version upgrade has failed
- description: >
- The cephadm cluster upgrade process has failed. The cluster remains in
- an undetermined state.
-
- Please review the cephadm logs, to understand the nature of the issue
- - interval: 30s
- input_series:
- - series: 'ceph_health_detail{name="CEPHADM_FAILED_DAEMON"}'
- values: '1+0x40'
- promql_expr_test:
- - expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="CEPHADM_FAILED_DAEMON"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephadmDaemonFailed
- - eval_time: 5m
- alertname: CephadmDaemonFailed
- exp_alerts:
- - exp_labels:
- name: CEPHADM_FAILED_DAEMON
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.11.1
- exp_annotations:
- summary: A ceph daemon manged by cephadm is down
- description: >
- A daemon managed by cephadm is no longer active. Determine, which
- daemon is down with 'ceph health detail'. you may start daemons with
- the 'ceph orch daemon start <daemon_id>'
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="CEPHADM_PAUSED"}'
- values: '1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="CEPHADM_PAUSED"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephadmPaused
- - eval_time: 5m
- alertname: CephadmPaused
- exp_alerts:
- - exp_labels:
- name: CEPHADM_PAUSED
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused
- summary: Orchestration tasks via cephadm are PAUSED
- description: >
- Cluster management has been paused manually. This will prevent the
- orchestrator from service management and reconciliation. If this is
- not intentional, resume cephadm operations with 'ceph orch resume'
-# MDS
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MDS_DAMAGE"}'
- values: '1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="MDS_DAMAGE"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MDS_DAMAGE"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemDamaged
- - eval_time: 5m
- alertname: CephFilesystemDamaged
- exp_alerts:
- - exp_labels:
- name: MDS_DAMAGE
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.1
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
- summary: Ceph filesystem is damaged.
- description: >
- The filesystems metadata has been corrupted. Data access
- may be blocked.
-
- Either analyse the output from the mds daemon admin socket, or
- escalate to support
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MDS_HEALTH_READ_ONLY"}'
- values: '1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MDS_HEALTH_READ_ONLY"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemReadOnly
- - eval_time: 5m
- alertname: CephFilesystemReadOnly
- exp_alerts:
- - exp_labels:
- name: MDS_HEALTH_READ_ONLY
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.2
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
- summary: Ceph filesystem in read only mode, due to write error(s)
- description: >
- The filesystem has switched to READ ONLY due to an unexpected
- write error, when writing to the metadata pool
-
- Either analyse the output from the mds daemon admin socket, or
- escalate to support
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MDS_ALL_DOWN"}'
- values: '0 0 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MDS_ALL_DOWN"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemOffline
- - eval_time: 10m
- alertname: CephFilesystemOffline
- exp_alerts:
- - exp_labels:
- name: MDS_ALL_DOWN
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.3
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down
- summary: Ceph filesystem is offline
- description: >
- All MDS ranks are unavailable. The ceph daemons providing the metadata
- for the Ceph filesystem are all down, rendering the filesystem offline.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="FS_DEGRADED"}'
- values: '0 0 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="FS_DEGRADED"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="FS_DEGRADED"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemDegraded
- - eval_time: 10m
- alertname: CephFilesystemDegraded
- exp_alerts:
- - exp_labels:
- name: FS_DEGRADED
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.4
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded
- summary: Ceph filesystem is degraded
- description: >
- One or more metdata daemons (MDS ranks) are failed or in a
- damaged state. At best the filesystem is partially available,
- worst case is the filesystem is completely unusable.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"}'
- values: '0 0 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MDS_INSUFFICIENT_STANDBY"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemInsufficientStandby
- - eval_time: 10m
- alertname: CephFilesystemInsufficientStandby
- exp_alerts:
- - exp_labels:
- name: MDS_INSUFFICIENT_STANDBY
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby
- summary: Ceph filesystem standby daemons too low
- description: >
- The minimum number of standby daemons determined by standby_count_wanted
- is less than the actual number of standby daemons. Adjust the standby count
- or increase the number of mds daemons within the filesystem.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="FS_WITH_FAILED_MDS"}'
- values: '0 0 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="FS_WITH_FAILED_MDS"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemFailureNoStandby
- - eval_time: 10m
- alertname: CephFilesystemFailureNoStandby
- exp_alerts:
- - exp_labels:
- name: FS_WITH_FAILED_MDS
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.5.5
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds
- summary: Ceph MDS daemon failed, no further standby available
- description: >
- An MDS daemon has failed, leaving only one active rank without
- further standby. Investigate the cause of the failure or add a
- standby daemon
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"}'
- values: '0 0 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0
- eval_time: 2m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MDS_UP_LESS_THAN_MAX"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephFilesystemMDSRanksLow
- - eval_time: 10m
- alertname: CephFilesystemMDSRanksLow
- exp_alerts:
- - exp_labels:
- name: MDS_UP_LESS_THAN_MAX
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max
- summary: Ceph MDS daemon count is lower than configured
- description: >
- The filesystem's "max_mds" setting defined the number of MDS ranks in
- the filesystem. The current number of active MDS daemons is less than
- this setting.
-# MGR
- - interval: 1m
- input_series:
- - series: 'up{job="ceph", instance="ceph-mgr:9283"}'
- values: '1+0x2 0+0x10'
- promql_expr_test:
- - expr: up{job="ceph"} == 0
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="up", job="ceph", instance="ceph-mgr:9283"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMgrPrometheusModuleInactive
- - eval_time: 10m
- alertname: CephMgrPrometheusModuleInactive
- exp_alerts:
- - exp_labels:
- instance: ceph-mgr:9283
- job: ceph
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.6.2
- exp_annotations:
- summary: Ceph's mgr/prometheus module is not available
- description: >
- The mgr/prometheus module at ceph-mgr:9283 is unreachable. This
- could mean that the module has been disabled or the mgr itself is down.
-
- Without the mgr/prometheus module metrics and alerts will no longer
- function. Open a shell to ceph and use 'ceph -s' to to determine whether the
- mgr is active. If the mgr is not active, restart it, otherwise you can check
- the mgr/prometheus module is loaded with 'ceph mgr module ls' and if it's
- not listed as enabled, enable it with 'ceph mgr module enable prometheus'
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="RECENT_MGR_MODULE_CRASH"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMgrModuleCrash
- - eval_time: 15m
- alertname: CephMgrModuleCrash
- exp_alerts:
- - exp_labels:
- name: RECENT_MGR_MODULE_CRASH
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.6.1
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash
- summary: A mgr module has recently crashed
- description: >
- One or more mgr modules have crashed and are yet to be acknowledged by the administrator. A
- crashed module may impact functionality within the cluster. Use the 'ceph crash' commands to
- investigate which module has failed, and archive it to acknowledge the failure.
-# MON
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MON_DISK_CRIT"}'
- values: '0+0x2 1+0x10'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
- values: '1+0x13'
- promql_expr_test:
- - expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MON_DISK_CRIT"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMonDiskspaceCritical
- - eval_time: 10m
- alertname: CephMonDiskspaceCritical
- exp_alerts:
- - exp_labels:
- name: "MON_DISK_CRIT"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.3.2
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit
- summary: Disk space on at least one monitor is critically low
- description: |
- The free space available to a monitor's store is critically low (<5% by default).
- You should increase the space available to the monitor(s). The
- default location for the store sits under /var/lib/ceph. Your monitor hosts are;
- - ceph-mon-a
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MON_DISK_LOW"}'
- values: '0+0x2 1+0x10'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
- values: '1+0x13'
- promql_expr_test:
- - expr: ceph_health_detail{name="MON_DISK_LOW"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MON_DISK_LOW"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMonDiskspaceLow
- - eval_time: 10m
- alertname: CephMonDiskspaceLow
- exp_alerts:
- - exp_labels:
- name: "MON_DISK_LOW"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low
- summary: Disk space on at least one monitor is approaching full
- description: |
- The space available to a monitor's store is approaching full (>70% is the default).
- You should increase the space available to the monitor store. The
- default location for the store sits under /var/lib/ceph. Your monitor hosts are;
- - ceph-mon-a
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MON_CLOCK_SKEW"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="MON_CLOCK_SKEW"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMonClockSkew
- - eval_time: 10m
- alertname: CephMonClockSkew
- exp_alerts:
- - exp_labels:
- name: "MON_CLOCK_SKEW"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew
- summary: Clock skew across the Monitor hosts detected
- description: |
- The ceph monitors rely on a consistent time reference to maintain
- quorum and cluster consistency. This event indicates that at least
- one of your mons is not sync'd correctly.
-
- Review the cluster status with ceph -s. This will show which monitors
- are affected. Check the time sync status on each monitor host.
-
-# Check 3 mons one down, quorum at risk
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="MON_DOWN"}'
- values: '0+0x2 1+0x12'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
- values: '1+0x2 0+0x12'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
- values: '1+0x14'
- promql_expr_test:
- - expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1
- eval_time: 3m
- exp_samples:
- - labels: '{}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMonDownQuorumAtRisk
- # shouldn't fire
- - eval_time: 10m
- alertname: CephMonDownQuorumAtRisk
- exp_alerts:
- - exp_labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.3.1
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
- summary: Monitor quorum is at risk
- description: |
- Quorum requires a majority of monitors (x 2) to be active
- Without quorum the cluster will become inoperable, affecting all connected clients and services.
-
- The following monitors are down:
- - mon.c on ceph-mon-3
-# check 5 mons, 1 down - warning only
- - interval: 1m
- input_series:
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.d"}'
- values: '1+0x14'
- - series: 'ceph_mon_quorum_status{ceph_daemon="mon.e"}'
- values: '1+0x2 0+0x12'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.d", hostname="ceph-mon-4"}'
- values: '1+0x14'
- - series: 'ceph_mon_metadata{ceph_daemon="mon.e", hostname="ceph-mon-5"}'
- values: '1+0x14'
- promql_expr_test:
- - expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1))
- eval_time: 3m
- exp_samples:
- - labels: '{}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephMonDown
- - eval_time: 10m
- alertname: CephMonDown
- exp_alerts:
- - exp_labels:
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
- summary: One of more ceph monitors are down
- description: |
- You have 1 monitor down.
- Quorum is still intact, but the loss of further monitors will make your cluster inoperable.
-
- The following monitors are down:
- - mon.e on ceph-mon-5
-# Device Health
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="DEVICE_HEALTH"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephDeviceFailurePredicted
- - eval_time: 10m
- alertname: CephDeviceFailurePredicted
- exp_alerts:
- - exp_labels:
- name: "DEVICE_HEALTH"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2
- summary: Device(s) have been predicted to fail soon
- description: |
- The device health module has determined that one or more devices will fail
- soon. To review the device states use 'ceph device ls'. To show a specific
- device use 'ceph device info <dev id>'.
-
- Mark the OSD as out (so data may migrate to other OSDs in the cluster). Once
- the osd is empty remove and replace the OSD.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_TOOMANY"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephDeviceFailurePredictionTooHigh
- - eval_time: 10m
- alertname: CephDeviceFailurePredictionTooHigh
- exp_alerts:
- - exp_labels:
- name: "DEVICE_HEALTH_TOOMANY"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.7
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany
- summary: Too many devices have been predicted to fail, unable to resolve
- description: |
- The device health module has determined that the number of devices predicted to
- fail can not be remediated automatically, since it would take too many osd's out of
- the cluster, impacting performance and potentially availabililty. You should add new
- OSDs to the cluster to allow data to be relocated to avoid the data integrity issues.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="DEVICE_HEALTH_IN_USE"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_IN_USE"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephDeviceFailureRelocationIncomplete
- - eval_time: 10m
- alertname: CephDeviceFailureRelocationIncomplete
- exp_alerts:
- - exp_labels:
- name: "DEVICE_HEALTH_IN_USE"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use
- summary: A device failure is predicted, but unable to relocate data
- description: |
- The device health module has determined that one or more devices will fail
- soon, but the normal process of relocating the data on the device to other
- OSDs in the cluster is blocked.
-
- Check the the cluster has available freespace. It may be necessary to add
- more disks to the cluster to allow the data from the failing device to
- successfully migrate.
-# OSD
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_HOST_DOWN"}'
- values: '0+0x2 1+0x10'
- - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
- values: '1+0x2 0+0x10'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
- values: '1+0x12'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_HOST_DOWN"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDHostDown
- - eval_time: 10m
- alertname: CephOSDHostDown
- exp_alerts:
- - exp_labels:
- name: "OSD_HOST_DOWN"
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.8
- exp_annotations:
- summary: An OSD host is offline
- description: |
- The following OSDs are down:
- - ceph-osd-1 : osd.0
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_FRONT"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDTimeoutsPublicNetwork
- - eval_time: 10m
- alertname: CephOSDTimeoutsPublicNetwork
- exp_alerts:
- - exp_labels:
- name: "OSD_SLOW_PING_TIME_FRONT"
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: Network issues delaying OSD heartbeats (public network)
- description: |
- OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network
- for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_BACK"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDTimeoutsClusterNetwork
- - eval_time: 10m
- alertname: CephOSDTimeoutsClusterNetwork
- exp_alerts:
- - exp_labels:
- name: "OSD_SLOW_PING_TIME_BACK"
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: Network issues delaying OSD heartbeats (cluster network)
- description: |
- OSD heartbeats on the cluster's 'cluster' network (backend) are running slow. Investigate the network
- for any latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="BLUESTORE_DISK_SIZE_MISMATCH"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDInternalDiskSizeMismatch
- - eval_time: 10m
- alertname: CephOSDInternalDiskSizeMismatch
- exp_alerts:
- - exp_labels:
- name: "BLUESTORE_DISK_SIZE_MISMATCH"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch
- summary: OSD size inconsistency error
- description: |
- One or more OSDs have an internal inconsistency between the size of the physical device and it's metadata.
- This could lead to the OSD(s) crashing in future. You should redeploy the effected OSDs.
- - interval: 30s
- input_series:
- - series: 'ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDReadErrors
- - eval_time: 10m
- alertname: CephOSDReadErrors
- exp_alerts:
- - exp_labels:
- name: "BLUESTORE_SPURIOUS_READ_ERRORS"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors
- summary: Device read errors detected
- description: >
- An OSD has encountered read errors, but the OSD has recovered by retrying
- the reads. This may indicate an issue with the Hardware or Kernel.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_DOWN"}'
- values: '0+0x2 1+0x10'
- - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
- values: '1+0x12'
- - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
- values: '1+0x2 0+0x10'
- - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
- values: '1+0x12'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
- values: '1+0x12'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.1", hostname="ceph-osd-2"}'
- values: '1+0x12'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.2", hostname="ceph-osd-3"}'
- values: '1+0x12'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_DOWN"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_DOWN"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDDown
- - eval_time: 10m
- alertname: CephOSDDown
- exp_alerts:
- - exp_labels:
- name: "OSD_DOWN"
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.2
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down
- summary: An OSD has been marked down/unavailable
- description: |
- 1 OSD down for over 5mins.
-
- The following OSD is down:
- - osd.1 on ceph-osd-2
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_NEARFULL"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_NEARFULL"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_NEARFULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDNearFull
- - eval_time: 10m
- alertname: CephOSDNearFull
- exp_alerts:
- - exp_labels:
- name: "OSD_NEARFULL"
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.3
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull
- summary: OSD(s) running low on free space (NEARFULL)
- description: |
- One or more OSDs have reached their NEARFULL threshold
-
- Use 'ceph health detail' to identify which OSDs have reached this threshold.
- To resolve, either add capacity to the cluster, or delete unwanted data
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_FULL"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_FULL"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_FULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDFull
- - eval_time: 10m
- alertname: CephOSDFull
- exp_alerts:
- - exp_labels:
- name: "OSD_FULL"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.4.6
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full
- summary: OSD(s) is full, writes blocked
- description: |
- An OSD has reached it's full threshold. Writes from all pools that share the
- affected OSD will be blocked.
-
- To resolve, either add capacity to the cluster, or delete unwanted data
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OSD_BACKFILLFULL"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_BACKFILLFULL"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_BACKFILLFULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDBackfillFull
- - eval_time: 10m
- alertname: CephOSDBackfillFull
- exp_alerts:
- - exp_labels:
- name: "OSD_BACKFILLFULL"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull
- summary: OSD(s) too full for backfill operations
- description: |
- An OSD has reached it's BACKFILL FULL threshold. This will prevent rebalance operations
- completing for some pools. Check the current capacity utilisation with 'ceph df'
-
- To resolve, either add capacity to the cluster, or delete unwanted data
- - interval: 30s
- input_series:
- - series: 'ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="OSD_TOO_MANY_REPAIRS"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephOSDTooManyRepairs
- - eval_time: 10m
- alertname: CephOSDTooManyRepairs
- exp_alerts:
- - exp_labels:
- name: "OSD_TOO_MANY_REPAIRS"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs
- summary: OSD has hit a high number of read errors
- description: |
- Reads from an OSD have used a secondary PG to return data to the client, indicating
- a potential failing disk.
-# Pools
- # trigger percent full prediction on pools 1 and 2 only
- - interval: 12h
- input_series:
- - series: 'ceph_pool_percent_used{pool_id="1"}'
- values: '70 75 80 87 92'
- - series: 'ceph_pool_percent_used{pool_id="2"}'
- values: '22 22 23 23 24'
- - series: 'ceph_pool_metadata{pool_id="1",name="rbd",type="replicated"}'
- values: '1 1 1 1 1'
- - series: 'ceph_pool_metadata{pool_id="2",name="default.rgw.index",type="replicated"}'
- values: '1 1 1 1 1'
- promql_expr_test:
- - expr: |
- (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id)
- group_right ceph_pool_metadata) >= 95
- eval_time: 36h
- exp_samples:
- - labels: '{name="rbd",pool_id="1",type="replicated"}'
- value: 1.424E+02 # 142%
- alert_rule_test:
- - eval_time: 48h
- alertname: CephPoolGrowthWarning
- exp_alerts:
- - exp_labels:
- name: rbd
- pool_id: 1
- severity: warning
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.9.2
- exp_annotations:
- summary: Pool growth rate may soon exceed it's capacity
- description: >
- Pool 'rbd' will be full in less than 5 days
- assuming the average fill-up rate of the past 48 hours.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="POOL_BACKFILLFULL"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="POOL_BACKFILLFULL"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="POOL_BACKFILLFULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPoolBackfillFull
- - eval_time: 5m
- alertname: CephPoolBackfillFull
- exp_alerts:
- - exp_labels:
- name: "POOL_BACKFILLFULL"
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: Freespace in a pool is too low for recovery/rebalance
- description: >
- A pool is approaching it's near full threshold, which will
- prevent rebalance operations from completing. You should
- consider adding more capacity to the pool.
-
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="POOL_NEAR_FULL"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="POOL_NEAR_FULL"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="POOL_NEAR_FULL"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPoolNearFull
- - eval_time: 10m
- alertname: CephPoolNearFull
- exp_alerts:
- - exp_labels:
- name: "POOL_NEAR_FULL"
- severity: warning
- type: ceph_default
- exp_annotations:
- summary: One or more Ceph pools are getting full
- description: |
- A pool has exceeeded it warning (percent full) threshold, or the OSDs
- supporting the pool have reached their NEARFULL thresholds. Writes may
- continue, but you are at risk of the pool going read only if more capacity
- isn't made available.
-
- Determine the affected pool with 'ceph df detail', for example looking
- at QUOTA BYTES and STORED. Either increase the pools quota, or add
- capacity to the cluster first then increase it's quota
- (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)
-
-# PGs
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_NOT_SCRUBBED"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="PG_NOT_SCRUBBED"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGNotScrubbed
- - eval_time: 10m
- alertname: CephPGNotScrubbed
- exp_alerts:
- - exp_labels:
- name: "PG_NOT_SCRUBBED"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed
- summary: Placement group(s) have not been scrubbed
- description: |
- One or more PGs have not been scrubbed recently. The scrub process is a data integrity
- feature, protectng against bit-rot. It checks that objects and their metadata (size and
- attributes) match across object replicas. When PGs miss their scrub window, it may
- indicate the scrub window is too small, or PGs were not in a 'clean' state during the
- scrub window.
-
- You can manually initiate a scrub with: ceph pg scrub <pgid>
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_DAMAGED"}'
- values: '0+0x4 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1
- eval_time: 5m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="PG_DAMAGED"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGsDamaged
- - eval_time: 10m
- alertname: CephPGsDamaged
- exp_alerts:
- - exp_labels:
- name: "PG_DAMAGED"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.4
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged
- summary: Placement group damaged, manual intervention needed
- description: >
- During data consistency checks (scrub), at least one PG has been flagged as being
- damaged or inconsistent.
-
- Check to see which PG is affected, and attempt a manual repair if neccessary. To list
- problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use
- the 'ceph pg repair <pg_num>' command.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="TOO_MANY_PGS"}'
- values: '0+0x4 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1
- eval_time: 5m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="TOO_MANY_PGS"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGsHighPerOSD
- - eval_time: 10m
- alertname: CephPGsHighPerOSD
- exp_alerts:
- - exp_labels:
- name: "TOO_MANY_PGS"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs
- summary: Placement groups per OSD is too high
- description: |
- The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).
-
- Check that the pg_autoscaler hasn't been disabled for any of the pools, with 'ceph osd pool autoscale-status'
- and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide
- the autoscaler based on the expected relative size of the pool
- (i.e. 'ceph osd pool set cephfs.cephfs.meta target_size_ratio .1')
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_RECOVERY_FULL"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="PG_RECOVERY_FULL"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGRecoveryAtRisk
- - eval_time: 10m
- alertname: CephPGRecoveryAtRisk
- exp_alerts:
- - exp_labels:
- name: "PG_RECOVERY_FULL"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.5
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full
- summary: OSDs are too full for automatic recovery
- description: >
- Data redundancy may be reduced, or is at risk, since one or more OSDs are at or above their
- 'full' threshold. Add more capacity to the cluster, or delete unwanted data.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_BACKFILL_FULL"}'
- values: '0+0x2 1+0x20'
- promql_expr_test:
- - expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 0
- eval_time: 1m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="PG_BACKFILL_FULL"}'
- value: 0
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGBackfillAtRisk
- - eval_time: 10m
- alertname: CephPGBackfillAtRisk
- exp_alerts:
- - exp_labels:
- name: "PG_BACKFILL_FULL"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.6
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full
- summary: Backfill operations are blocked, due to lack of freespace
- description: >
- Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs
- have breached their 'backfillfull' threshold. Add more capacity, or delete unwanted data.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_AVAILABILITY"}'
- values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_health_detail{name="OSD_DOWN"}'
- values: '0 0 0 1 1 1 1 1 1 0 0 0 0 0 0 0'
- promql_expr_test:
- - expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"}))
- eval_time: 1m
- # empty set at 1m
- exp_samples:
- alert_rule_test:
- # PG_AVAILABILITY and OSD_DOWN not firing .. no alert
- - eval_time: 1m
- alertname: CephPGUnavilableBlockingIO
- exp_alerts:
- # PG_AVAILABILITY firing, but osd_down is active .. no alert
- - eval_time: 5m
- alertname: CephPGUnavilableBlockingIO
- exp_alerts:
- # PG_AVAILABILITY firing, AND OSD_DOWN is not active...raise the alert
- - eval_time: 15m
- alertname: CephPGUnavilableBlockingIO
- exp_alerts:
- - exp_labels:
- name: "PG_AVAILABILITY"
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.7.3
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability
- summary: Placement group is unavailable, blocking some I/O
- description: >
- Data availability is reduced impacting the clusters abilty to service I/O to some data. One or
- more placement groups (PGs) are in a state that blocks IO.
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"}'
- values: '0+0x2 1+0x10'
- promql_expr_test:
- - expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1
- eval_time: 3m
- exp_samples:
- - labels: '{__name__="ceph_health_detail", name="PG_NOT_DEEP_SCRUBBED"}'
- value: 1
- alert_rule_test:
- - eval_time: 1m
- alertname: CephPGNotDeepScrubbed
- - eval_time: 10m
- alertname: CephPGNotDeepScrubbed
- exp_alerts:
- - exp_labels:
- name: "PG_NOT_DEEP_SCRUBBED"
- severity: warning
- type: ceph_default
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed
- summary: Placement group(s) have not been deep scrubbed
- description: |
- One or more PGs have not been deep scrubbed recently. Deep scrub is a data integrity
- feature, protectng against bit-rot. It compares the contents of objects and their
- replicas for inconsistency. When PGs miss their deep scrub window, it may indicate
- that the window is too small or PGs were not in a 'clean' state during the deep-scrub
- window.
-
- You can manually initiate a deep scrub with: ceph pg deep-scrub <pgid>
-
-# Prometheus
- - interval: 1m
- input_series:
- - series: 'up{job="myjob"}'
- values: '1+0x10'
- promql_expr_test:
- - expr: absent(up{job="ceph"})
- eval_time: 1m
- exp_samples:
- - labels: '{job="ceph"}'
- value: 1
- alert_rule_test:
- - eval_time: 5m
- alertname: PrometheusJobMissing
- exp_alerts:
- - exp_labels:
- job: ceph
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.12.1
- exp_annotations:
- summary: The scrape job for Ceph is missing from Prometheus
- description: |
- The prometheus job that scrapes from Ceph is no longer defined, this
- will effectively mean you'll have no metrics or alerts for the cluster.
-
- Please review the job definitions in the prometheus.yml file of the prometheus
- instance.
-# RADOS
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="OBJECT_UNFOUND"}'
- values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
- values: '1 1 1 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.0"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.1"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- - series: 'ceph_osd_metadata{ceph_daemon="osd.2"}'
- values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1
- eval_time: 1m
- exp_samples:
- alert_rule_test:
- # OBJECT_UNFOUND but osd.2 is down, so don't fire
- - eval_time: 5m
- alertname: CephObjectMissing
- exp_alerts:
- # OBJECT_UNFOUND and all osd's are online, so fire
- - eval_time: 15m
- alertname: CephObjectMissing
- exp_alerts:
- - exp_labels:
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.10.1
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound
- summary: Object(s) has been marked UNFOUND
- description: |
- A version of a RADOS object can not be found, even though all OSDs are up. I/O
- requests for this object from clients will block (hang). Resolving this issue may
- require the object to be rolled back to a prior version manually, and manually verified.
-# Generic Alerts
- - interval: 1m
- input_series:
- - series: 'ceph_health_detail{name="RECENT_CRASH"}'
- values: '0 0 0 1 1 1 1 1 1 1 1'
- promql_expr_test:
- - expr: ceph_health_detail{name="RECENT_CRASH"} == 1
- eval_time: 1m
- exp_samples:
- alert_rule_test:
- # not firing
- - eval_time: 1m
- alertname: CephDaemonCrash
- exp_alerts:
- # firing
- - eval_time: 10m
- alertname: CephDaemonCrash
- exp_alerts:
- - exp_labels:
- name: RECENT_CRASH
- severity: critical
- type: ceph_default
- oid: 1.3.6.1.4.1.50495.1.2.1.1.2
- exp_annotations:
- documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash
- summary: One or more Ceph daemons have crashed, and are pending acknowledgement
- description: |
- One or more daemons have crashed recently, and need to be acknowledged. This notification
- ensures that software crashes don't go unseen. To acknowledge a crash, use the
- 'ceph crash archive <id>' command.
\ No newline at end of file
+++ /dev/null
-import pytest
-import os
-import yaml
-from .utils import promtool_available, call
-from .settings import ALERTS_FILE, UNIT_TESTS_FILE
-
-
-def load_yaml(file_name):
- yaml_data = None
- with open(file_name, 'r') as alert_file:
- raw = alert_file.read()
- try:
- yaml_data = yaml.safe_load(raw)
- except yaml.YAMLError as e:
- pass
-
- return yaml_data
-
-
-def test_alerts_present():
- assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found"
-
-
-def test_unittests_present():
- assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found"
-
-
-@pytest.mark.skipif(not os.path.exists(ALERTS_FILE), reason=f"{ALERTS_FILE} missing")
-def test_rules_format():
- assert load_yaml(ALERTS_FILE)
-
-
-@pytest.mark.skipif(not os.path.exists(UNIT_TESTS_FILE), reason=f"{UNIT_TESTS_FILE} missing")
-def test_unittests_format():
- assert load_yaml(UNIT_TESTS_FILE)
-
-
-@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to check syntax")
-def test_rule_syntax():
- completion = call(f"promtool check rules {ALERTS_FILE}")
- assert completion.returncode == 0
- assert b"SUCCESS" in completion.stdout
+++ /dev/null
-import pytest
-import os
-from .utils import promtool_available, call
-from .settings import ALERTS_FILE, UNIT_TESTS_FILE
-
-
-def test_alerts_present():
- assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found"
-
-
-def test_unittests_present():
- assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found"
-
-
-@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to run unit tests")
-def test_run_unittests():
- completion = call(f"promtool test rules {UNIT_TESTS_FILE}")
- assert completion.returncode == 0
- assert b"SUCCESS" in completion.stdout
+++ /dev/null
-[tox]
-envlist = py3
-skipsdist = true
-
-[testenv]
-deps =
- -rrequirements.txt
- pytest
-commands =
- pytest -rA test_syntax.py test_unittests.py
- ./validate_rules.py
+++ /dev/null
-import pytest
-import shutil
-import subprocess
-
-
-def promtool_available() -> bool:
- return shutil.which('promtool') is not None
-
-
-def call(cmd):
- completion = subprocess.run(cmd.split(), stdout=subprocess.PIPE)
- return completion
+++ /dev/null
-#!/usr/bin/python3 -u
-#
-# Check the Prometheus rules for format, and integration
-# with the unit tests. This script has the following exit
-# codes:
-# 0 .. Everything worked
-# 4 .. rule problems or missing unit tests
-# 8 .. Missing fields in YAML
-# 12 .. Invalid YAML - unable to load
-# 16 .. Missing input files
-#
-# Externals
-# snmptranslate .. used to determine the oid's in the MIB to verify the rule -> MIB is correct
-#
-
-import re
-import os
-import sys
-import yaml
-import shutil
-import string
-from bs4 import BeautifulSoup
-from typing import List, Any, Dict, Set, Optional, Tuple
-import subprocess
-
-import urllib.request
-import urllib.error
-from urllib.parse import urlparse
-
-DOCLINK_NAME = 'documentation'
-DEFAULT_RULES_FILENAME = '../alerts/ceph_default_alerts.yml'
-DEFAULT_TEST_FILENAME = 'test_alerts.yml'
-MIB_FILE = '../../snmp/CEPH-MIB.txt'
-
-
-def isascii(s: str) -> bool:
- try:
- s.encode('ascii')
- except UnicodeEncodeError:
- return False
- return True
-
-
-def read_file(file_name: str) -> Tuple[str, str]:
- try:
- with open(file_name, 'r') as input_file:
- raw_data = input_file.read()
- except OSError:
- return '', f"Unable to open {file_name}"
-
- return raw_data, ''
-
-
-def load_yaml(file_name: str) -> Tuple[Dict[str, Any], str]:
- data = {}
- errs = ''
-
- raw_data, err = read_file(file_name)
- if not err:
-
- try:
- data = yaml.safe_load(raw_data)
- except yaml.YAMLError as e:
- errs = f"filename '{file_name} is not a valid YAML file"
-
- return data, errs
-
-
-def run_command(command: str):
- c = command.split()
- completion = subprocess.run(c, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
- return (completion.returncode,
- completion.stdout.decode('utf-8').split('\n'),
- completion.stderr.decode('utf-8').split('\n'))
-
-
-class HTMLCache:
- def __init__(self) -> None:
- self.cache: Dict[str, Tuple[int, str]] = {}
-
- def fetch(self, url_str: str) -> None:
- parsed = urlparse(url_str)
- url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
-
- if url in self.cache:
- return self.cache[url]
-
- req = urllib.request.Request(url)
- try:
- r = urllib.request.urlopen(req)
- except urllib.error.HTTPError as e:
- self.cache[url] = e.code, e.reason
- return self.cache[url]
- except urllib.error.URLError as e:
- self.cache[url] = 400, e.reason
- return self.cache[url]
-
- if r.status == 200:
- html = r.read().decode('utf-8')
- self.cache[url] = 200, html
- return self.cache[url]
-
- self.cache[url] = r.status, r.reason
- return r.status, r.reason
-
- @property
- def cached_pages(self) -> List[str]:
- return self.cache.keys()
-
- @property
- def cached_pages_total(self) -> int:
- return len(self.cache.keys())
-
-class PrometheusRule:
- expected_attrs = [
- 'alert',
- 'expr',
- 'labels',
- 'annotations'
- ]
-
- def __init__(self, rule_group, rule_data: Dict[str, Any]):
-
- assert 'alert' in rule_data
- self.group: RuleGroup = rule_group
- self.name = rule_data.get('alert')
- self.rule = rule_data
- self.errors: List[str] = []
- self.warnings: List[str] = []
- self.validate()
-
- @property
- def has_oid(self):
- return True if self.rule.get('labels', {}).get('oid', '') else False
-
- @property
- def labels(self) -> Dict[str, str]:
- return self.rule.get('labels', {})
-
- @property
- def annotations(self) -> Dict[str, str]:
- return self.rule.get('annotations', {})
-
- def _check_alert_name(self):
- # this is simplistic, but works in the context of the alert name
- if self.name[0] in string.ascii_uppercase and \
- self.name != self.name.lower() and \
- self.name != self.name.upper() and \
- " " not in self.name and \
- "_" not in self.name:
- return
-
- self.warnings.append("Alert name is not in CamelCase format")
-
- def _check_structure(self):
- rule_attrs = self.rule.keys()
- missing_attrs = [a for a in PrometheusRule.expected_attrs if a not in rule_attrs]
-
- if missing_attrs:
- self.errors.append(
- f"invalid alert structure. Missing field{'s' if len(missing_attrs) > 1 else ''}"
- f": {','.join(missing_attrs)}")
-
- def _check_labels(self):
- for rqd in ['severity', 'type']:
- if rqd not in self.labels.keys():
- self.errors.append(f"rule is missing {rqd} label definition")
-
- def _check_annotations(self):
- for rqd in ['summary', 'description']:
- if rqd not in self.annotations:
- self.errors.append(f"rule is missing {rqd} annotation definition")
-
- def _check_doclink(self):
- doclink = self.annotations.get(DOCLINK_NAME, '')
-
- if doclink:
- url = urlparse(doclink)
- status, content = self.group.fetch_html_page(doclink)
- if status == 200:
- if url.fragment:
- soup = BeautifulSoup(content, 'html.parser')
- if not soup.find(id=url.fragment):
- self.errors.append(f"documentation link error: {url.fragment} anchor not found on the page")
- else:
- # catch all
- self.errors.append(f"documentation link error: {status} {content}")
-
- def _check_snmp(self):
- oid = self.labels.get('oid', '')
-
- if self.labels.get('severity', '') == 'critical' and not oid:
- self.warnings.append("critical level alert is missing an SNMP oid entry")
- if oid and not re.search('^1.3.6.1.4.1.50495.1.2.\\d+.\\d+.\\d+$', oid):
- self.errors.append("invalid OID format provided")
- if self.group.get_oids():
- if oid and oid not in self.group.get_oids():
- self.errors.append(f"rule defines an OID {oid} that is missing from the MIB file({os.path.basename(MIB_FILE)})")
-
- def _check_ascii(self):
- if 'oid' not in self.labels:
- return
-
- desc = self.annotations.get('description', '')
- summary = self.annotations.get('summary', '')
- if not isascii(desc):
- self.errors.append(f"non-ascii characters found in 'description' field will cause issues in associated snmp trap.")
- if not isascii(summary):
- self.errors.append(f"non-ascii characters found in 'summary' field will cause issues in associated snmp trap.")
-
- def validate(self):
-
- self._check_alert_name()
- self._check_structure()
- self._check_labels()
- self._check_annotations()
- self._check_doclink()
- self._check_snmp()
- self._check_ascii()
- char = '.'
-
- if self.errors:
- char = 'E'
- self.group.update('error', self.name)
- elif self.warnings:
- char = 'W'
- self.group.update('warning', self.name)
-
- sys.stdout.write(char)
-
-
-class RuleGroup:
-
- def __init__(self, rule_file, group_name: str, group_name_width: int):
- self.rule_file: RuleFile = rule_file
- self.group_name = group_name
- self.rules: Dict[str, PrometheusRule] = {}
- self.problems = {
- "error": [],
- "warning": [],
- }
-
- sys.stdout.write(f"\n\t{group_name:<{group_name_width}} : ")
-
- def add_rule(self, rule_data:Dict[str, Any]):
- alert_name = rule_data.get('alert')
- self.rules[alert_name] = PrometheusRule(self, rule_data)
-
- def update(self, problem_type:str, alert_name:str):
- assert problem_type in ['error', 'warning']
-
- self.problems[problem_type].append(alert_name)
- self.rule_file.update(self.group_name)
-
- def fetch_html_page(self, url):
- return self.rule_file.fetch_html_page(url)
-
- def get_oids(self):
- return self.rule_file.oid_list
-
- @property
- def error_count(self):
- return len(self.problems['error'])
-
- def warning_count(self):
- return len(self.problems['warning'])
-
- @property
- def count(self):
- return len(self.rules)
-
-
-class RuleFile:
-
- def __init__(self, parent, file_name, rules, oid_list):
- self.parent = parent
- self.file_name = file_name
- self.rules: Dict[str, Any] = rules
- self.oid_list = oid_list
- self.problems: Set[str] = set()
- self.group: Dict[str, RuleGroup] = {}
- self.alert_names_seen: Set[str] = set()
- self.duplicate_alert_names:List[str] = []
- self.html_cache = HTMLCache()
-
- assert 'groups' in self.rules
- self.max_group_name_width = self.get_max_group_name()
- self.load_groups()
-
- def update(self, group_name):
- self.problems.add(group_name)
- self.parent.mark_invalid()
-
- def fetch_html_page(self, url):
- return self.html_cache.fetch(url)
-
- @property
- def group_count(self):
- return len(self.rules['groups'])
-
- @property
- def rule_count(self):
- rule_count = 0
- for _group_name, rule_group in self.group.items():
- rule_count += rule_group.count
- return rule_count
-
- @property
- def oid_count(self):
- oid_count = 0
- for _group_name, rule_group in self.group.items():
- for _rule_name, rule in rule_group.rules.items():
- if rule.has_oid:
- oid_count += 1
- return oid_count
-
- @property
- def group_names(self):
- return self.group.keys()
-
- @property
- def problem_count(self):
- return len(self.problems)
-
- def get_max_group_name(self):
- group_name_list = []
- for group in self.rules.get('groups'):
- group_name_list.append(group['name'])
- return max([len(g) for g in group_name_list])
-
- def load_groups(self):
- sys.stdout.write("\nChecking rule groups")
- for group in self.rules.get('groups'):
- group_name = group['name']
- rules = group['rules']
- self.group[group_name] = RuleGroup(self, group_name, self.max_group_name_width)
- for rule_data in rules:
- if 'alert' in rule_data:
- alert_name = rule_data.get('alert')
- if alert_name in self.alert_names_seen:
- self.duplicate_alert_names.append(alert_name)
- else:
- self.alert_names_seen.add(alert_name)
- self.group[group_name].add_rule(rule_data)
- else:
- # skipped recording rule
- pass
-
- def report(self):
- def max_width(item_list: Set[str], min_width: int = 0) -> int:
- return max([len(i) for i in item_list] + [min_width])
-
- if not self.problems and not self.duplicate_alert_names:
- print("\nNo problems detected in the rule file")
- return
-
- print("\nProblem Report\n")
-
- group_width = max_width(self.problems, 5)
- alert_names = set()
- for g in self.problems:
- group = self.group[g]
- alert_names.update(group.problems.get('error', []))
- alert_names.update(group.problems.get('warning', []))
- alert_width = max_width(alert_names, 10)
-
- template = " {group:<{group_width}} {severity:<8} {alert_name:<{alert_width}} {description}"
-
- print(template.format(
- group="Group",
- group_width=group_width,
- severity="Severity",
- alert_name="Alert Name",
- alert_width=alert_width,
- description="Problem Description"))
-
- print(template.format(
- group="-----",
- group_width=group_width,
- severity="--------",
- alert_name="----------",
- alert_width=alert_width,
- description="-------------------"))
-
- for group_name in sorted(self.problems):
- group = self.group[group_name]
- rules = group.rules
- for alert_name in group.problems.get('error', []):
- for desc in rules[alert_name].errors:
- print(template.format(
- group=group_name,
- group_width=group_width,
- severity="Error",
- alert_name=alert_name,
- alert_width=alert_width,
- description=desc))
- for alert_name in group.problems.get('warning', []):
- for desc in rules[alert_name].warnings:
- print(template.format(
- group=group_name,
- group_width=group_width,
- severity="Warning",
- alert_name=alert_name,
- alert_width=alert_width,
- description=desc))
- if self.duplicate_alert_names:
- print("Duplicate alert names detected:")
- for a in self.duplicate_alert_names:
- print(f" - {a}")
-
-
-class UnitTests:
- expected_attrs = [
- 'rule_files',
- 'tests',
- 'evaluation_interval'
- ]
- def __init__(self, filename):
- self.filename = filename
- self.unit_test_data: Dict[str, Any] = {}
- self.alert_names_seen: Set[str] = set()
- self.problems: List[str] = []
- self.load()
-
- def load(self):
- self.unit_test_data, errs = load_yaml(self.filename)
- if errs:
- print(f"\n\nError in unit tests file: {errs}")
- sys.exit(12)
-
- missing_attr = [a for a in UnitTests.expected_attrs if a not in self.unit_test_data.keys()]
- if missing_attr:
- print(f"\nMissing attributes in unit tests: {','.join(missing_attr)}")
- sys.exit(8)
-
- def _check_alert_names(self, alert_names: List[str]):
- alerts_tested: Set[str] = set()
- for t in self.unit_test_data.get('tests'):
- test_cases = t.get('alert_rule_test', [])
- if not test_cases:
- continue
- for case in test_cases:
- alertname = case.get('alertname', '')
- if alertname:
- alerts_tested.add(alertname)
-
- alerts_defined = set(alert_names)
- self.problems = list(alerts_defined.difference(alerts_tested))
-
- def process(self, defined_alert_names: List[str]):
- self._check_alert_names(defined_alert_names)
-
- def report(self) -> None:
-
- if not self.problems:
- print("\nNo problems detected in unit tests file")
- return
-
- print("\nUnit tests are incomplete. Tests missing for the following alerts;")
- for p in self.problems:
- print(f" - {p}")
-
-class RuleChecker:
-
- def __init__(self, rules_filename: str = None, test_filename: str = None):
- self.rules_filename = rules_filename or DEFAULT_RULES_FILENAME
- self.test_filename = test_filename or DEFAULT_TEST_FILENAME
- self.rule_file: Optional[RuleFile] = None
- self.unit_tests: Optional[UnitTests] = None
- self.rule_file_problems: bool = False
- self.errors = {}
- self.warnings = {}
- self.error_count = 0
- self.warning_count = 0
- self.oid_count = 0
-
- self.oid_list = self.build_oid_list()
-
- def build_oid_list(self) -> List[str]:
-
- cmd = shutil.which('snmptranslate')
- if not cmd:
- return []
-
- rc, stdout, stderr = run_command(f"{cmd} -Pu -Tz -M ../../snmp:/usr/share/snmp/mibs -m CEPH-MIB")
- if rc != 0:
- return []
-
- oid_list: List[str] = []
- for line in stdout[:-1]:
- _label, oid = line.replace('"', '').replace('\t', ' ').split()
- oid_list.append(oid)
-
- return oid_list
-
- @property
- def status(self):
- if self.rule_file_problems or self.unit_tests.problems:
- return 4
-
- return 0
-
- def mark_invalid(self):
- self.rule_file_problems = True
-
- def summarise_rule_file(self):
- for group_name in self.rule_file.problems:
- group = self.rule_file.group[group_name]
- self.error_count += len(group.problems['error'])
- self.warning_count += len(group.problems['warning'])
-
- def ready(self):
- errs: List[str] = []
- ready_state = True
- if not os.path.exists(self.rules_filename):
- errs.append(f"rule file '{self.rules_filename}' not found")
- ready_state = False
-
- if not os.path.exists(self.test_filename):
- errs.append(f"test file '{self.test_filename}' not found")
- ready_state = False
-
- return ready_state, errs
-
- def run(self):
-
- ready, errs = self.ready()
- if not ready:
- print("Unable to start:")
- for e in errs:
- print(f"- {e}")
- sys.exit(16)
-
- rules, errs = load_yaml(self.rules_filename)
- if errs:
- print(errs)
- sys.exit(12)
-
- self.rule_file = RuleFile(self, self.rules_filename, rules, self.oid_list)
- self.summarise_rule_file()
-
- self.unit_tests = UnitTests(self.test_filename)
- self.unit_tests.process(self.rule_file.alert_names_seen)
-
- def report(self):
- print("\n\nSummary\n")
- print(f"Rule file : {self.rules_filename}")
- print(f"Unit Test file : {self.test_filename}")
- print(f"\nRule groups processed : {self.rule_file.group_count:>3}")
- print(f"Rules processed : {self.rule_file.rule_count:>3}")
- print(f"SNMP OIDs declared : {self.rule_file.oid_count:>3} {'(snmptranslate missing, unable to cross check)' if not self.oid_list else ''}")
- print(f"Rule errors : {self.error_count:>3}")
- print(f"Rule warnings : {self.warning_count:>3}")
- print(f"Rule name duplicates : {len(self.rule_file.duplicate_alert_names):>3}")
- print(f"Unit tests missing : {len(self.unit_tests.problems):>3}")
-
- self.rule_file.report()
- self.unit_tests.report()
-
-
-def main():
- checker = RuleChecker()
-
- checker.run()
- checker.report()
- print()
-
- sys.exit(checker.status)
-
-
-if __name__ == '__main__':
- main()
if os.environ.get('CEPH_DEV') == '1' or 'UNITTEST' in os.environ:
path = os.path.abspath(os.path.join(
os.path.dirname(__file__),
- '../../../../monitoring/grafana/dashboards/'
+ '../../../../monitoring/ceph-mixin/dashboards_out/'
))
else:
path = '/etc/grafana/dashboards/ceph-dashboard'
[testenv:check]
commands =
- python ci/check_grafana_dashboards.py frontend/src/app ../../../../monitoring/grafana/dashboards
+ python ci/check_grafana_dashboards.py frontend/src/app ../../../../monitoring/ceph-mixin/dashboards_out
[testenv:openapi-{check,fix}]
basepython = python3
add_ceph_test(smoke.sh ${CMAKE_CURRENT_SOURCE_DIR}/smoke.sh)
-find_program(PROMTOOL_EXECUTABLE promtool)
-if(PROMTOOL_EXECUTABLE)
- execute_process(
- COMMAND ${PROMTOOL_EXECUTABLE} test rules /dev/null
- RESULT_VARIABLE rc
- OUTPUT_QUIET)
- if(NOT rc)
- add_ceph_test(run-promtool-unittests
- ${PROMTOOL_EXECUTABLE} test rules ${CMAKE_SOURCE_DIR}/monitoring/prometheus/tests/test_alerts.yml)
- elseif(NOT promtool_executable_checked)
- message(WARNING "'${PROMTOOL_EXECUTABLE} test rules' does not work, "
- "please use a newer prometheus")
- endif()
-else()
- add_ceph_test(run-promtool-unittests
- {CMAKE_CURRENT_SOURCE_DIR}/run-promtool-unittests.sh)
-endif()
-
set_property(
TEST ${tox_tests}
PROPERTY ENVIRONMENT ${env_vars_for_tox_tests})
projects / ceph.git / commitdiff