Add alert for failing helmreleases deploying aws components (#1432)

* Add alert for failing helmreleases deploying aws components

* Add alerts for azure cloud components HelmReleases

* Use generic alert for all providers

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Add `cloud-provider-controller.rules` to monitor the cloud-provider-controller components across providers.
 - Add alerts to monitor the `HelmReleases` for `cilium` and `coredns`.
 - Add alert to monitor the `HelmRelease` for the `vertical-pod-autoscaler-crd` app.
 

helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/cloud-provider-controller.rules.yml

@@ -0,0 +1,32 @@
+{{- if eq .Values.managementCluster.provider.flavor "capi" }}
+# This rule applies to CAPI management clusters only
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  creationTimestamp: null
+  labels:
+    {{- include "labels.common" . | nindent 4 }}
+  name: cloud-provider-controller.rules
+  namespace: {{ .Values.namespace  }}
+spec:
+  groups:
+  - name: cloud-provider-controller
+    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=~".*(aws-ebs-csi-driver|cloud-provider-aws|azure-cloud-controller-manager|azure-cloud-node-manager|azuredisk-csi-driver|azurefile-csi-driver|cloud-provider-vsphere|cloud-provider-cloud-director)"} > 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: {{ include "providerTeam" . }}
+        topic: managementcluster
+        namespace: |-
+          {{`{{ $labels.exported_namespace }}`}}
+{{- end }}