Gardener alerts

charts/controlplane-operations/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v2
 name: controlplane-operations
-version: 1.0.13
+version: 1.0.14
 description: A set of Plutono dashboards and Prometheus alerting rules combined with playbooks to ensure effective operations of Controlplane clusters.
 maintainers:
   - name: Vladimir Videlov (d051408)

charts/controlplane-operations/alerts/controlplane-gardener.yaml

@@ -0,0 +1,17 @@
+groups:
+- name: controlplane-gardener
+  rules:
+{{- if not (.Values.prometheusRules.disabled.ShootUnavailability | default false) }}
+  - alert: ShootUnavailability
+    expr: shoot:availability == 0
+    for: {{ dig "ShootUnavailability" "for" "10m" .Values.prometheusRules }}
+    labels:
+      {{ include "controlplane-operations.additionalRuleLabels" . }}
+      severity: {{ dig "ShootUnavailability" "severity" "info" .Values.prometheusRules }}
+      playbook: https://github.com/cobaltcore-dev/controlplane-operations/playbooks/ShootUnavailability.md
+      service: {{ dig "ShootUnavailability" "service" .Values.prometheusRules.defaultService .Values.prometheusRules }}
+      support_group: {{ dig "ShootUnavailability" "supportGroup" .Values.prometheusRules.defaultSupportGroup .Values.prometheusRules }}
+    annotations:
+      description: Shoot cluster is unavailable for more than 10 minutes.
+      summary: Shoot cluster is unavailable for more than 10 minutes.
+{{- end }}

charts/controlplane-operations/alerts/controlplane-remote.yaml

@@ -1,5 +1,5 @@
 groups:
-- name: controlplane-remote.alerts
+- name: controlplane-remote
   rules:
 {{- if not (.Values.prometheusRules.disabled.ArgoraUpdateInError | default false) }}
   - alert: ArgoraUpdateInError

charts/controlplane-operations/plugindefinition.yaml

@@ -3,15 +3,15 @@ kind: PluginDefinition
 metadata:
   name: controlplane-operations
 spec:
-  version: 1.0.13
+  version: 1.0.14
   displayName: Controlplane operations bundle
   description: Operations bundle for Controlane clusters
   docMarkDownUrl: https://raw.githubusercontent.com/cloudoperators/controlplane-operations/main/README.md
   icon: https://raw.githubusercontent.com/cloudoperators/controlplane-operations/main/charts/controlplane-operations/kubernetes-logo.png
   helmChart:
     name: controlplane-operations
     repository: oci://ghcr.io/cloudoperators/controlplane-operations/charts
-    version: 1.0.13
+    version: 1.0.14
   options:
     - name: prometheusRules.create
       description: Create Prometheus rules

charts/controlplane-operations/templates/alerts.yaml

@@ -11,6 +11,9 @@ metadata:
 {{- if $.Values.prometheusRules.labels }}
 {{ toYaml $.Values.prometheusRules.labels | indent 4 }}
 {{- end }}
+{{- if and $.Values.prometheusRules.gardenerRuleLabels (contains "gardener" $path) }}
+{{ toYaml $.Values.prometheusRules.gardenerRuleLabels | indent 4 }}
+{{- end }}
 {{- if $.Values.prometheusRules.annotations }}
   annotations:
 {{ toYaml $.Values.prometheusRules.annotations | indent 4 }}

charts/controlplane-operations/values.yaml

@@ -36,6 +36,9 @@ prometheusRules:
   ## This is useful for adding additional labels of alerts to each rule
   additionalRuleLabels: {}
 
+  ## Additional labels for Gardener related PrometheusRule alerts
+  gardenerRuleLabels: {}
+
   ## Additional annotations for PrometheusRule alerts
   additionalRuleAnnotations: {}
 
@@ -44,10 +47,10 @@ prometheusRules:
   # KubernetesApiServerDown: true
   # KubeletDown: true
 
-  # NodeVirtualInterfaceDown:
-  #   service: "cc-cp"
-  #   supportGroup: "containers"
-  #   for: "15m"
+  # ServerStuckInDiscovery:
+  #   service: "metal-api"
+  #   supportGroup: "foundation"
+  #   for: "10m"
   #   severity: "warning"
 
 ## Create default dashboards for monitoring the cluster