From: Aashish Sharma Date: Fri, 8 Oct 2021 09:58:13 +0000 (+0530) Subject: mgr/dashboard: monitoring: grafonnet refactoring for osds dashboards X-Git-Tag: v17.1.0~650^2~1 X-Git-Url: http://git.apps.os.sepia.ceph.com/?a=commitdiff_plain;h=e490e2f3abe707a2e891171f3c230d44e282c601;p=ceph-ci.git mgr/dashboard: monitoring: grafonnet refactoring for osds dashboards This PR intends to refactor osds dashboards using grafonnet Fixes:https://tracker.ceph.com/issues/52777 Signed-off-by: Aashish Sharma --- diff --git a/monitoring/grafana/dashboards/jsonnet/grafana_dashboards.jsonnet b/monitoring/grafana/dashboards/jsonnet/grafana_dashboards.jsonnet index 8966544452b..238ff48a292 100644 --- a/monitoring/grafana/dashboards/jsonnet/grafana_dashboards.jsonnet +++ b/monitoring/grafana/dashboards/jsonnet/grafana_dashboards.jsonnet @@ -540,4 +540,148 @@ local addStyle(alias, colorMode, colors, dateFormat, decimals, mappingType, patt {"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 ) ]) -} \ No newline at end of file +} +{ + "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'); + + 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='$datasource', title='Distribution of PGs per OSD', x_axis_buckets=20, x_axis_mode='histogram', x_axis_values=['total'], formatY1='short', formatY2='short', labelY1='# of OSDs', min='0', nullPointMode='null') + .addTarget(addTargetSchema('ceph_osd_numpg\n', 1, 'time_series', 'PGs per OSD')) + {gridPos: {x: 12, y: 8, w: 12, h: 8}}, + addRowSchema(false, true, 'R/W Profile') + {gridPos: {x: 0, y: 16, w: 24, h: 1}}, + OsdOverviewGraphPanel( + {},'Read/Write Profile', 'Show the read/write workload profile overtime', 'short', null, null, 'round(sum(irate(ceph_pool_rd[30s])))', 'Reads', 0, 17, 24, 8) + .addTargets([addTargetSchema('round(sum(irate(ceph_pool_wr[30s])))', 1, 'time_series', 'Writes')]) + ]) +} +{ + "osd-device-details.json": + local OsdDeviceDetailsPanel(title, description, formatY1, labelY1, expr1, expr2, legendFormat1, legendFormat2, x, y, w, h) = + graphPanelSchema({}, title, description, 'null', false, formatY1, 'short', labelY1, null, null, 1, '$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")', 'label_replace(irate(node_disk_reads_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")', 'label_replace(irate(node_disk_written_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")', 1, 'time_series', '{{device}} on {{instance}}')) + {gridPos: {x: 18, y: 11, w: 6, h: 9}}, + ]) +} diff --git a/monitoring/grafana/dashboards/osd-device-details.json b/monitoring/grafana/dashboards/osd-device-details.json index eefb5912579..6d59f3be401 100644 --- a/monitoring/grafana/dashboards/osd-device-details.json +++ b/monitoring/grafana/dashboards/osd-device-details.json @@ -1,800 +1,822 @@ { - "__inputs": [], - "__requires": [ - { - "type": "grafana", - "id": "grafana", - "name": "Grafana", - "version": "5.3.2" - }, - { - "type": "panel", - "id": "graph", - "name": "Graph", - "version": "5.0.0" - } - ], - "annotations": { - "list": [ + "__inputs": [ ], + "__requires": [ { - "builtIn": 1, - "datasource": "-- Grafana --", - "enable": true, - "hide": true, - "iconColor": "rgba(0, 211, 255, 1)", - "name": "Annotations & Alerts", - "type": "dashboard" - } - ] - }, - "editable": false, - "gnetId": null, - "graphTooltip": 0, - "id": null, - "iteration": 1557395861896, - "links": [], - "panels": [ - { - "collapsed": false, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 0 - }, - "id": 14, - "panels": [], - "title": "OSD Performance", - "type": "row" - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 0, - "gridPos": { - "h": 9, - "w": 6, - "x": 0, - "y": 1 - }, - "id": 2, - "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": "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": "$osd Latency", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 0, - "gridPos": { - "h": 9, - "w": 6, - "x": 6, - "y": 1 - }, - "id": 8, - "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": "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": "$osd R/W IOPS", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 0, - "gridPos": { - "h": 9, - "w": 6, - "x": 12, - "y": 1 - }, - "id": 7, - "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": "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": "$osd R/W Bytes", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "collapsed": false, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 10 - }, - "id": 12, - "panels": [], - "title": "Physical Device Performance", - "type": "row" - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 0, - "gridPos": { - "h": 9, - "w": 6, - "x": 0, - "y": 11 - }, - "id": 9, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 0, - "gridPos": { - "h": 9, - "w": 6, - "x": 6, - "y": 11 + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" }, - "id": 5, - "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": "/.*Reads/", - "transform": "negative-Y" - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "label_replace(irate(node_disk_writes_completed_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 1, - "gridPos": { - "h": 9, - "w": 6, - "x": 12, - "y": 11 - }, - "id": 10, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false + ], + "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" }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [ - { - "alias": "/.*Reads/", - "transform": "negative-Y" - } - ], - "spaceLength": 10, - "stack": true, - "steppedLine": false, - "targets": [ - { - "expr": "label_replace(irate(node_disk_read_bytes_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": "$osd Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": "$osd R/W IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] }, - "yaxes": [ - { - "format": "Bps", - "label": "Read (-) / Write (+)", - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 1, - "gridPos": { - "h": 9, - "w": 6, - "x": 18, - "y": 11 + { + "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 + } + ] }, - "id": 4, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false + { + "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" }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "label_replace(irate(node_disk_io_time_seconds_total[1m]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] }, - "yaxes": [ - { - "format": "percentunit", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } - } - ], - "schemaVersion": 16, - "style": "dark", - "tags": [], - "templating": { - "list": [ { - "current": { - "text": "default", - "value": "default" - }, - "hide": 0, - "label": "Data Source", - "name": "datasource", - "options": [], - "query": "prometheus", - "refresh": 1, - "regex": "", - "skipUrlSync": false, - "type": "datasource" + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] }, { - "allValue": null, - "current": {}, - "datasource": "$datasource", - "hide": 0, - "includeAll": false, - "label": "OSD", - "multi": false, - "name": "osd", - "options": [], - "query": "label_values(ceph_osd_metadata,ceph_daemon)", - "refresh": 1, - "regex": "(.*)", - "skipUrlSync": false, - "sort": 0, - "tagValuesQuery": "", - "tags": [], - "tagsQuery": "", - "type": "query", - "useTags": false + "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\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device) label_replace(label_replace(ceph_disk_occupation{ceph_daemon=~\"$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 $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] } - ] - }, - "time": { - "from": "now-3h", - "to": "now" - }, - "timepicker": { - "refresh_intervals": [ - "5s", - "10s", - "30s", - "1m", - "5m", - "15m", - "30m", - "1h", - "2h", - "1d" - ], - "time_options": [ - "5m", - "15m", - "1h", - "6h", - "12h", - "24h", - "2d", - "7d", - "30d" - ] - }, - "timezone": "", - "title": "OSD device details", - "uid": "CrAHE0iZz", - "version": 3 + ], + "refresh": "", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { }, + "datasource": "$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 } diff --git a/monitoring/grafana/dashboards/osds-overview.json b/monitoring/grafana/dashboards/osds-overview.json index 4b91df9ebce..8a873090ad7 100644 --- a/monitoring/grafana/dashboards/osds-overview.json +++ b/monitoring/grafana/dashboards/osds-overview.json @@ -1,876 +1,837 @@ { - - "__requires": [ - { - "type": "grafana", - "id": "grafana", - "name": "Grafana", - "version": "5.0.0" - }, - { - "type": "panel", - "id": "grafana-piechart-panel", - "name": "Pie Chart", - "version": "1.3.3" - }, - { - "type": "panel", - "id": "graph", - "name": "Graph", - "version": "5.0.0" - }, - { - "type": "panel", - "id": "table", - "name": "Table", - "version": "5.0.0" - } - ], - "annotations": { - "list": [ + "__inputs": [ ], + "__requires": [ { - "builtIn": 1, - "datasource": "-- Grafana --", - "enable": true, - "hide": true, - "iconColor": "rgba(0, 211, 255, 1)", - "name": "Annotations & Alerts", - "type": "dashboard" - } - ] - }, - "editable": false, - "gnetId": null, - "graphTooltip": 0, - "id": null, - "iteration": 1538083987689, - "links": [], - "panels": [ - { - "aliasColors": { - "@95%ile": "#e0752d" - }, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 1, - "gridPos": { - "h": 8, - "w": 8, - "x": 0, - "y": 0 - }, - "id": 12, - "legend": { - "avg": false, - "current": true, - "max": false, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "AVG read", - "refId": "A" - }, - { - "expr": "max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "MAX read", - "refId": "B" - }, - { - "expr": "quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "@95%ile", - "refId": "C" - } - ], - "thresholds": [], - "timeFrom": null, - "timeShift": null, - "title": "OSD Read Latencies", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "ms", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ] - }, - { - "columns": [], - "datasource": "$datasource", - "description": "This table shows the osd's that are delivering the 10 highest read latencies within the cluster", - "fontSize": "100%", - "gridPos": { - "h": 8, - "w": 4, - "x": 8, - "y": 0 - }, - "id": 15, - "links": [], - "pageSize": null, - "scroll": true, - "showHeader": true, - "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, - "pattern": "ceph_daemon", - "thresholds": [], - "type": "string", - "unit": "short" - }, - { - "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": 0, - "pattern": "Value", - "thresholds": [], - "type": "number", - "unit": "none" - }, - { - "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, - "pattern": "/.*/", - "thresholds": [], - "type": "hidden", - "unit": "short" - } - ], - "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", - "instant": true, - "intervalFactor": 1, - "legendFormat": "", - "refId": "A" - } - ], - "title": "Highest READ Latencies", - "transform": "table", - "type": "table" - }, - { - "aliasColors": { - "@95%ile write": "#e0752d" + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.0.0" }, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "fill": 1, - "gridPos": { - "h": 8, - "w": 8, - "x": 12, - "y": 0 - }, - "id": 13, - "legend": { - "avg": false, - "current": true, - "max": false, - "min": false, - "show": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "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": 2, - "value_type": "individual" + { + "id": "grafana-piechart-panel", + "name": "Pie Chart", + "type": "panel", + "version": "1.3.3" }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" }, - "yaxes": [ - { - "format": "ms", - "label": null, - "logBase": 1, - "max": null, - "min": "0", - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } + { + "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" + } ] - }, - { - "columns": [], - "datasource": "$datasource", - "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster", - "fontSize": "100%", - "gridPos": { - "h": 8, - "w": 4, - "x": 20, - "y": 0 - }, - "id": 16, - "links": [], - "pageSize": null, - "scroll": true, - "showHeader": true, - "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, - "pattern": "ceph_daemon", - "thresholds": [], - "type": "string", - "unit": "short" - }, - { - "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": 0, - "pattern": "Value", - "thresholds": [], - "type": "number", - "unit": "none" - }, - { - "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, - "pattern": "/.*/", - "thresholds": [], - "type": "hidden", - "unit": "short" - } - ], - "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", - "instant": true, - "intervalFactor": 1, - "legendFormat": "", - "refId": "A" - } - ], - "title": "Highest WRITE Latencies", - "transform": "table", - "type": "table" - }, - { - "aliasColors": {}, - "breakPoint": "50%", - "cacheTimeout": null, - "combine": { - "label": "Others", - "threshold": 0 - }, - "datasource": "$datasource", - "fontSize": "80%", - "format": "none", - "gridPos": { - "h": 8, - "w": 4, - "x": 0, - "y": 8 - }, - "id": 2, - "interval": null, - "legend": { - "show": true, - "values": true - }, - "legendType": "Under graph", - "links": [], - "maxDataPoints": 3, - "nullPointMode": "connected", - "pieType": "pie", - "strokeWidth": 1, - "targets": [ - { - "expr": "count by (device_class) (ceph_osd_metadata)", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "{{device_class}}", - "refId": "A" - } - ], - "title": "OSD Types Summary", - "type": "grafana-piechart-panel", - "valueName": "current" - }, - { - "aliasColors": { - "Non-Encrypted": "#E5AC0E" - }, - "breakPoint": "50%", - "cacheTimeout": null, - "combine": { - "label": "Others", - "threshold": 0 - }, - "datasource": "$datasource", - "fontSize": "80%", - "format": "none", - "gridPos": { - "h": 8, - "w": 4, - "x": 4, - "y": 8 + }, + "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 + } + ] }, - "height": "200px", - "hideTimeOverride": true, - "id": 4, - "interval": null, - "legend": { - "percentage": false, - "show": true, - "values": 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" }, - "legendType": "Under graph", - "links": [], - "maxDataPoints": "1", - "minSpan": 4, - "nullPointMode": "connected", - "pieType": "pie", - "strokeWidth": 1, - "targets": [ - { - "expr": "count(ceph_bluefs_wal_total_bytes)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "bluestore", - "refId": "A", - "step": 240 - }, - { - "expr": "count(ceph_osd_metadata) - count(ceph_bluefs_wal_total_bytes)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "filestore", - "refId": "B", - "step": 240 - }, - { - "expr": "absent(ceph_bluefs_wal_total_bytes)*count(ceph_osd_metadata)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "filestore", - "refId": "C", - "step": 240 - } - ], - "timeFrom": null, - "timeShift": null, - "title": "OSD Objectstore Types", - "type": "grafana-piechart-panel", - "valueName": "current" - }, - { - "aliasColors": {}, - "breakPoint": "50%", - "cacheTimeout": null, - "combine": { - "label": "Others", - "threshold": "0.05" + { + "aliasColors": { + "@95%ile write": "#e0752d" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "gridPos": { + "h": 8, + "w": 8, + "x": 12, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "AVG write", + "refId": "A" + }, + { + "expr": "max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "MAX write", + "refId": "B" + }, + { + "expr": "quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "@95%ile write", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "OSD Write Latencies", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + } + ] }, - "datasource": "$datasource", - "description": "The pie chart shows the various OSD sizes used within the cluster", - "fontSize": "80%", - "format": "none", - "gridPos": { - "h": 8, - "w": 4, - "x": 8, - "y": 8 + { + "columns": [ ], + "datasource": "$datasource", + "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster", + "gridPos": { + "h": 8, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 5, + "sort": { + "col": 2, + "desc": true + }, + "styles": [ + { + "alias": "OSD ID", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "ceph_daemon", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Latency (ms)", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n", + "format": "table", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest WRITE Latencies", + "transform": "table", + "type": "table" }, - "height": "220", - "hideTimeOverride": true, - "id": 8, - "interval": null, - "legend": { - "header": "", - "percentage": false, - "show": true, - "sideWidth": null, - "sortDesc": true, - "values": true + { + "aliasColors": { }, + "datasource": "$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" }, - "legendType": "Under graph", - "links": [], - "maxDataPoints": "", - "minSpan": 6, - "nullPointMode": "connected", - "pieType": "pie", - "strokeWidth": "1", - "targets": [ - { - "expr": "count(ceph_osd_stat_bytes < 1099511627776)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<1 TB", - "refId": "A", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 1099511627776 < 2199023255552)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<2 TB", - "refId": "B", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 2199023255552 < 3298534883328)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<3TB", - "refId": "C", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 3298534883328 < 4398046511104)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<4TB", - "refId": "D", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 4398046511104 < 6597069766656)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<6TB", - "refId": "E", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 6597069766656 < 8796093022208)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<8TB", - "refId": "F", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 8796093022208 < 10995116277760)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<10TB", - "refId": "G", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 10995116277760 < 13194139533312)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "<12TB", - "refId": "H", - "step": 2 - }, - { - "expr": "count(ceph_osd_stat_bytes >= 13194139533312)", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "12TB+", - "refId": "I", - "step": 2 - } - ], - "timeFrom": null, - "timeShift": null, - "title": "OSD Size Summary", - "type": "grafana-piechart-panel", - "valueName": "current" - }, - { - "aliasColors": {}, - "bars": true, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", - "description": "Each bar indicates the number of OSD's that have a PG count in a specific range as shown on the x axis.", - "fill": 1, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 8 + { + "aliasColors": { + "Non-Encrypted": "#E5AC0E" + }, + "datasource": "$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" }, - "id": 6, - "legend": { - "alignAsTable": false, - "avg": false, - "current": false, - "hideEmpty": false, - "hideZero": false, - "max": false, - "min": false, - "rightSide": false, - "show": false, - "total": false, - "values": false + { + "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" }, - "lines": false, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "percentage": false, - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "expr": "ceph_osd_numpg\n", - "format": "time_series", - "instant": true, - "intervalFactor": 1, - "legendFormat": "PGs per OSD", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeShift": null, - "title": "Distribution of PGs per OSD", - "tooltip": { - "shared": false, - "sort": 0, - "value_type": "individual" + { + "aliasColors": { }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + "h": 8, + "w": 12, + "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 + } + ] }, - "type": "graph", - "xaxis": { - "buckets": 20, - "mode": "histogram", - "name": null, - "show": true, - "values": [ - "total" - ] + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 16 + }, + "id": 10, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "R/W Profile", + "titleSize": "h6", + "type": "row" }, - "yaxes": [ - { - "decimals": 0, - "format": "short", - "label": "# of OSDs", - "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", + "description": "Show the read/write workload profile overtime", + "fill": 1, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 17 + }, + "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", + "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" + } ] - }, - { - "collapsed": false, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 16 - }, - "id": 20, - "panels": [], - "title": "R/W Profile", - "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": 10, - "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": [], - "spaceLength": 10, - "stack": true, - "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" - } + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" ], - "thresholds": [], - "timeFrom": null, - "timeShift": null, - "title": "Read/Write Profile", - "tooltip": { - "shared": true, - "sort": 2, - "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 - } + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" ] - } - ], - "refresh": "10s", - "schemaVersion": 16, - "style": "dark", - "tags": [], - "templating": { - "list": [ - { - "current": { - "tags": [], - "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": 3 + }, + "timezone": "", + "title": "OSD Overview", + "uid": "lo02I1Aiz", + "version": 0 }