mgr/dashboard: fix OSDs Host details/overview grafana graphs

Fixes: https://tracker.ceph.com/issues/50686
Signed-off-by: Alfonso Martínez <almartin@redhat.com>
(cherry picked from commit 7d79efb0252e970b3621d1540e69e2115788dcc3)

diff --git a/monitoring/grafana/dashboards/host-details.json b/monitoring/grafana/dashboards/host-details.json
index cfa2b9f1027e2d4f36da159e38eccea273fa84d8..237349dd36a1f42a9ddb10e4e5b837949c87d0b1 100644 (file)
--- a/monitoring/grafana/dashboards/host-details.json
+++ b/monitoring/grafana/dashboards/host-details.json
@@ -798,7 +798,7 @@
       "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,\n      \"device\",\n      \"$1\",\n      \"device\",\n      \"/dev/(.*)\"\n    ),\n    \"instance\",\n    \"$1\",\n    \"instance\",\n    \"([^:.]*).*\"\n  )",
+          "expr": "label_replace(\n  (\n    irate(node_disk_writes_completed{instance=~\"($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, ceph_daemon) group_left\n  label_replace(\n    label_replace(\n      ceph_disk_occupation,\n      \"device\",\n      \"$1\",\n      \"device\",\n      \"/dev/(.*)\"\n    ),\n    \"instance\",\n    \"$1\",\n    \"instance\",\n    \"([^:.]*).*\"\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{device}}({{ceph_daemon}}) writes",
@@ -807,7 +807,7 @@
           "textEditor": true
         },
         {
-          "expr": "label_replace(\n    (irate(node_disk_reads_completed{instance=~\"($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,\n      \"device\",\n      \"$1\",\n      \"device\",\n      \"/dev/(.*)\"\n    ),\n    \"instance\",\n    \"$1\",\n    \"instance\",\n    \"([^:.]*).*\"\n  )",
+          "expr": "label_replace(\n    (irate(node_disk_reads_completed{instance=~\"($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, ceph_daemon) group_left\n  label_replace(\n    label_replace(\n      ceph_disk_occupation,\n      \"device\",\n      \"$1\",\n      \"device\",\n      \"/dev/(.*)\"\n    ),\n    \"instance\",\n    \"$1\",\n    \"instance\",\n    \"([^:.]*).*\"\n  )",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -899,14 +899,14 @@
       "steppedLine": false,
       "targets": [
         {
-          "expr": "label_replace((irate(node_disk_bytes_written{instance=~\"($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, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+          "expr": "label_replace((irate(node_disk_bytes_written{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_written_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device, ceph_daemon) group_left label_replace(label_replace(ceph_disk_occupation, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{device}}({{ceph_daemon}}) write",
           "refId": "B"
         },
         {
-          "expr": "label_replace((irate(node_disk_bytes_read{instance=~\"($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, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+          "expr": "label_replace((irate(node_disk_bytes_read{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) or irate(node_disk_read_bytes_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m])), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device, ceph_daemon) group_left label_replace(label_replace(ceph_disk_occupation, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{device}}({{ceph_daemon}}) read",
@@ -992,7 +992,7 @@
       "steppedLine": false,
       "targets": [
         {
-          "expr": "max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~\"($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\", \"$1\", \"instance\", \"([^:.]*).*\")) *  on(instance,device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+          "expr": "max by(instance,device) (label_replace((irate(node_disk_write_time_seconds_total{ instance=~\"($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\", \"$1\", \"instance\", \"([^:.]*).*\")) *  on(instance, device, ceph_daemon) group_left label_replace(label_replace(ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -1083,7 +1083,7 @@
       "steppedLine": false,
       "targets": [
         {
-          "expr": "label_replace(((irate(node_disk_io_time_ms{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) / 10 ) or  irate(node_disk_io_time_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device) group_left(ceph_daemon) label_replace(label_replace(ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
+          "expr": "label_replace(((irate(node_disk_io_time_ms{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) / 10 ) or  irate(node_disk_io_time_seconds_total{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}[5m]) * 100), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device, ceph_daemon) group_left label_replace(label_replace(ceph_disk_occupation{instance=~\"($ceph_hosts)([\\\\.:].*)?\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\")",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,

diff --git a/monitoring/grafana/dashboards/hosts-overview.json b/monitoring/grafana/dashboards/hosts-overview.json
index fe272a8a785f3d728021dc3a7d573c79aac9579f..b179d5717d536c37c37a3d67f96cab130a05fbd9 100644 (file)
--- a/monitoring/grafana/dashboards/hosts-overview.json
+++ b/monitoring/grafana/dashboards/hosts-overview.json
@@ -431,7 +431,7 @@
       "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\", \"$1\", \"instance\", \"([^.:]*).*\"\n  ) *\n  on(instance, device) label_replace(label_replace(ceph_disk_occupation{instance=~\"($osd_hosts).*\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\")\n)",
+          "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\", \"$1\", \"instance\", \"([^.:]*).*\"\n  ) *\n  on(instance, device, ceph_daemon) label_replace(label_replace(ceph_disk_occupation{instance=~\"($osd_hosts).*\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\")\n)",
           "format": "time_series",
           "instant": true,
           "intervalFactor": 1,