Add alerts for azure cloud components HelmReleases

giantswarm · Nov 19, 2024 · 5d9f2a8 · 5d9f2a8
1 parent 0c2a896
commit 5d9f2a8
Show file tree

Hide file tree

Showing 3 changed files with 36 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Add `aws-cloud-components.rules` to monitor the AWS cloud-controller and the ebs-csi-driver.
+- Add `azure-cloud-components.rules` to monitor the Azure cloud-controller and the azure csi drivers.
 
 ## [4.26.1] - 2024-11-19
 

diff --git a/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/aws-cloud-components.rules.yml b/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/aws-cloud-components.rules.yml
@@ -10,12 +10,12 @@ metadata:
   namespace: {{ .Values.namespace  }}
 spec:
   groups:
-  - name: aws-cloud-controller-manager
+  - name: aws-cloud-components
     rules:
     - alert: FluxHelmReleaseFailed
       annotations:
         description: |-
-        {{`Flux HelmRelease {{ $labels.name }} in ns {{ $labels.exported_namespace }} on {{ $labels.installation }}/{{ $labels.cluster_id }} is stuck in Failed state.`}}
+          {{`Flux HelmRelease {{ $labels.name }} in ns {{ $labels.exported_namespace }} on {{ $labels.installation }}/{{ $labels.cluster_id }} is stuck in Failed state.`}}
         opsrecipe: fluxcd-failing-helmrelease/
       expr: gotk_reconcile_condition{type="Ready", status="False", kind="HelmRelease", cluster_type="management_cluster", exported_namespace!="flux-giantswarm", name=~".*(aws-ebs-csi-driver|cloud-provider-aws)"} > 0
       for: 20m
@@ -28,5 +28,5 @@ spec:
         team: phoenix
         topic: managementcluster
         namespace: |-
-        {{`{{ $labels.exported_namespace }}`}}
+          {{`{{ $labels.exported_namespace }}`}}
 {{- end }}
diff --git a/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/azure-cloud-components.rules.yml b/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/azure-cloud-components.rules.yml
@@ -0,0 +1,32 @@
+{{- if eq .Values.managementCluster.provider.kind "capz" }}
+# This rule applies to capa management clusters only
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  creationTimestamp: null
+  labels:
+    {{- include "labels.common" . | nindent 4 }}
+  name: azure-cloud-components.rules
+  namespace: {{ .Values.namespace  }}
+spec:
+  groups:
+  - name: azure-cloud-components
+    rules:
+    - alert: FluxHelmReleaseFailed
+      annotations:
+        description: |-
+          {{`Flux HelmRelease {{ $labels.name }} in ns {{ $labels.exported_namespace }} on {{ $labels.installation }}/{{ $labels.cluster_id }} is stuck in Failed state.`}}
+        opsrecipe: fluxcd-failing-helmrelease/
+      expr: gotk_reconcile_condition{type="Ready", status="False", kind="HelmRelease", cluster_type="management_cluster", exported_namespace!="flux-giantswarm", name=~".*(azure-cloud-controller-manager|azure-cloud-node-manager|azuredisk-csi-driver|azurefile-csi-driver)"} > 0
+      for: 20m
+      labels:
+        area: kaas
+        cancel_if_outside_working_hours: "true"
+        cancel_if_kube_state_metrics_down: "true"
+        cancel_if_monitoring_agent_down: "true"
+        severity: page
+        team: phoenix
+        topic: managementcluster
+        namespace: |-
+          {{`{{ $labels.exported_namespace }}`}}
+{{- end }}