Merge pull request #119 from openebs/alert_changes

chore(alerting): changes on rules and alert config

deploy/charts/Chart.yaml

@@ -22,16 +22,16 @@ keywords:
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 3.0.0
+version: 4.0.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
-appVersion: 3.0.0
+appVersion: 4.0.0
 
 dependencies:
   - name: kube-prometheus-stack
-    version: "58.0.*"
+    version: "61.0.*"
     repository: https://prometheus-community.github.io/helm-charts
     condition: kube-prometheus-stack.install
   - name: node-problem-detector

deploy/charts/rules/lvmLocalPV/lvmlocalpv-rules.json

@@ -14,6 +14,8 @@
                "expr": "lvm_vg_missing_pv_count > 0",
                "for": "5m",
                "labels": {
+                  "engine": "localpv-lvm",
+                  "product": "openebs",
                   "severity": "critical"
                }
             },
@@ -28,6 +30,8 @@
                "expr": "((lvm_vg_total_size_bytes - lvm_vg_free_size_bytes)/lvm_vg_total_size_bytes)*100 > 90",
                "for": "5m",
                "labels": {
+                  "engine": "localpv-lvm",
+                  "product": "openebs",
                   "severity": "critical"
                }
             },
@@ -42,6 +46,8 @@
                "expr": "lvm_lv_used_percent{segtype=\"thin-pool\"} > 90",
                "for": "5m",
                "labels": {
+                  "engine": "localpv-lvm",
+                  "product": "openebs",
                   "severity": "critical"
                }
             }

deploy/charts/templates/podmonitors.yaml

@@ -1,3 +1,4 @@
+{{ if (.Capabilities.APIVersions.Has "monitoring.coreos.com/v1") }}
 {{- range $monitoringAddon, $fields := .Values.openebsMonitoringAddon }}
 {{- if (and (hasKey $fields "enabled") ($fields.enabled)) }}
 {{- if (hasKey $fields "podMonitor") }}
@@ -27,3 +28,4 @@ spec:
 {{- end }}
 {{- end }}
 {{- end }}
+{{- end }}

deploy/charts/templates/prometheusRules.yaml

@@ -1,3 +1,4 @@
+{{ if (.Capabilities.APIVersions.Has "monitoring.coreos.com/v1") }}
 {{- $alertRules := dict -}}
 {{- range $monitoringAddon,$fields := .Values.openebsMonitoringAddon }}
 {{- if (and (hasKey $fields "enabled") ($fields.enabled)) }}
@@ -28,3 +29,4 @@ spec:
 {{- end }}
 {{- end }}
 {{- end }}
+{{- end }}

deploy/charts/templates/servicemonitors.yaml

@@ -1,3 +1,4 @@
+{{ if (.Capabilities.APIVersions.Has "monitoring.coreos.com/v1") }}
 {{- range $monitoringAddon, $fields := .Values.openebsMonitoringAddon }}
 {{- if (and (hasKey $fields "enabled") ($fields.enabled)) }}
 {{- if (hasKey $fields "serviceMonitor") }}
@@ -27,3 +28,4 @@ spec:
 {{- end }}
 {{- end }}
 {{- end }}
+{{- end }}

deploy/charts/values.yaml

@@ -101,6 +101,12 @@ kube-prometheus-stack:
         group_interval: 5m
         repeat_interval: 4h
         receiver: "null"
+        ## This route specifically groups openebs alerts.
+        routes:
+          - matchers:
+              - product="openebs"
+            receiver: "null"
+      ## Add receivers as required. Ref: https://prometheus.io/docs/alerting/latest/configuration/#receiver-integration-settings
       receivers:
         - name: "null"
       templates:
@@ -271,11 +277,11 @@ openebsMonitoringAddon:
         any: true
 
   npd:
-    enabled: true
+    enabled: false
     dashboards:
-      enabled: true
+      enabled: false
     alertRules:
-      enabled: true
+      enabled: false
 
   volume:
     enabled: true

jsonnet/openebs-mixin/dashboards/dashboards.libsonnet

@@ -5,9 +5,9 @@ function(param) {
   grafanaDashboards+:: {
     [if dashboard._config.dashboards.lvmLocalPV then 'lvmlocalpv-pool.json']: import './openebs/lvmlocalpv-pool.json',
     [if dashboard._config.dashboards.zfsLocalPV then 'zfslocalpv.json']: import './openebs/zfslocalpv.json',
-    [if dashboard._config.dashboards.mayastor then 'diskpool.json']: import './mayastor/diskpool.json',
-    [if dashboard._config.dashboards.mayastor then 'volume.json']: import './mayastor/volume.json',
-    [if dashboard._config.dashboards.mayastor then 'volume-replica.json']: import './mayastor/volume-replica.json',
+    [if dashboard._config.dashboards.mayastor then 'mayastor-diskpool.json']: import './mayastor/mayastor-diskpool.json',
+    [if dashboard._config.dashboards.mayastor then 'mayastor-volume.json']: import './mayastor/mayastor-volume.json',
+    [if dashboard._config.dashboards.mayastor then 'mayastor-volume-replica.json']: import './mayastor/mayastor-volume-replica.json',
     [if dashboard._config.dashboards.npd then 'npd-node-volume-problem.json']: import './npd/npd-node-volume-problem.json',
   },
 }

jsonnet/openebs-mixin/rules/openebs/lvmlocalpv-rules.libsonnet

@@ -19,6 +19,8 @@ function(param) {
               'for': '5m',
               labels: {
                 severity: 'critical',
+                product: 'openebs',
+                engine: 'localpv-lvm',
               },
             },
             {
@@ -33,6 +35,8 @@ function(param) {
               'for': '5m',
               labels: {
                 severity: 'critical',
+                product: 'openebs',
+                engine: 'localpv-lvm',
               },
             },
             {
@@ -47,6 +51,8 @@ function(param) {
               'for': '5m',
               labels: {
                 severity: 'critical',
+                product: 'openebs',
+                engine: 'localpv-lvm',
               },
             },
           ],