linstor-cluster: add alerts for offline targets

Signed-off-by: Moritz Wanzenböck <[email protected]>
piraeusdatastore · Mar 5, 2024 · d6a32df · d6a32df
1 parent dda8b65
commit d6a32df
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 2 deletions.
diff --git a/charts/linstor-cluster/Chart.yaml b/charts/linstor-cluster/Chart.yaml
@@ -13,5 +13,5 @@ keywords:
   - storage
 sources:
   - https://github.com/piraeusdatastore/linstor-cluster
-version: 1.0.0
-appVersion: "v2.3.0"
+version: 1.0.1
+appVersion: "v2.4.0"
diff --git a/charts/linstor-cluster/templates/monitoring.yaml b/charts/linstor-cluster/templates/monitoring.yaml
@@ -78,6 +78,13 @@ spec:
   groups:
   - name: linstor.rules
     rules:
+    - alert: linstorControllerOffline
+      annotations:
+        description: |
+          LINSTOR Controller is not reachable.
+      expr: up{job="linstor-controller"} == 0
+      labels:
+        severity: critical
     - alert: linstorSatelliteErrorRate
       annotations:
         description: |
@@ -118,6 +125,13 @@ spec:
         severity: warn
   - name: drbd.rules
     rules:
+    - alert: drbdReactorOffline
+      annotations:
+        description: |
+          DRBD Reactor on "{{`{{ $labels.node }}`}}" is not reachable.
+      expr: up{job="{{ .Release.Namespace }}/linstor-satellite"} == 0
+      labels:
+        severity: critical
     - alert: drbdConnectionNotConnected
       annotations:
         description: |