Add remote alert

Author: videlov

charts/controlplane-operations/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v2
 name: controlplane-operations
-version: 1.0.1
+version: 1.0.2
 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-bond.yaml

@@ -24,5 +24,5 @@ groups:
       {{ include "controlplane-operations.additionalRuleLabels" . | nindent 6 }}
     annotations:
       description: Interface `{{`{{ $labels.device }}`}}` on `{{`{{ $labels.node }}`}}` is down. Tenant network outage for this node.
-      summary: Interface `{{`{{ $labels.device }}`}}` is down. Node network connectivity is degraded. 
+      summary: Interface `{{`{{ $labels.device }}`}}` is down. Node network connectivity is degraded.
 {{- end }}

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

@@ -8,7 +8,7 @@ groups:
     labels:
       severity: {{ dig "KubernetesNodeBridgeFilterVLANTagged" "severity" "info" .Values.prometheusRules }}
       playbook: https://github.com/cobaltcore-dev/controlplane-operations/playbooks/KubernetesNodeBridgeFilterVLANTagged.md
-      {{ include "controlplane-operations.additionalRuleLabels" . | nindent 6 }} 
+      {{ include "controlplane-operations.additionalRuleLabels" . | nindent 6 }}
     annotations:
       description: VLAN-tagged ARP/IP traffic is filtered by ARPtables/IPtables on `{{`{{ $labels.node }}`}}`. Network datapath threatened!
       summary: Bridged VLAN-tagged traffic is filtered by IPtables.

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

@@ -2,7 +2,7 @@ groups:
 - name: controlplane-pvc
   rules:
     - record: kubelet_volume_stats_available_percent
-      expr: (min by (persistentvolumeclaim, namespace) (100 * kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes)) 
+      expr: (min by (persistentvolumeclaim, namespace) (100 * kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes))
 
 - name: controlplane.pvc.alerts
   rules:

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

@@ -0,0 +1,17 @@
+groups:
+- name: controlplane-remote
+  rules:
+{{- if not (.Values.prometheusRules.disabled.ArgoraUpdateInError | default false) }}
+  - alert: ArgoraUpdateInError
+    expr: >
+      kube_customresource_status_state{customresource_kind="Update",customresource_group="argora.cloud.sap",state=~"Error"}
+      == 1
+    for: {{ dig "ArgoraUpdateInError" "for" "1m" .Values.prometheusRules }}
+    labels:
+      severity: {{ dig "ArgoraUpdateInError" "severity" "warning" .Values.prometheusRules }}
+      playbook: https://github.com/cobaltcore-dev/controlplane-operations/playbooks/ArgoraUpdateInError.md
+      {{ include "controlplane-operations.additionalRuleLabels" . | nindent 6 }}
+    annotations:
+      description: Argora Update CR status is in Error state for more than 1 minute.
+      summary: Update CR in Error state.
+{{- end }}

charts/controlplane-operations/plugindefinition.yaml

@@ -3,15 +3,15 @@ kind: PluginDefinition
 metadata:
   name: controlplane-operations
 spec:
-  version: 1.0.1
+  version: 1.0.2
   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: 1.0.1
+    version: 1.0.2
   options:
     - name: prometheusRules.create
       description: Create Prometheus rules

charts/controlplane-operations/templates/dashboards.yaml

@@ -7,9 +7,9 @@ kind: ConfigMap
 metadata:
   name: {{ printf "%s-%s" $root.Release.Name ($path | replace ".json" "" | replace "/" "-" | trunc 63) }}
   labels:
-{{ include "controlplane-operations.persesDashboardSelectorLabels" (list $path $root) | indent 4 }} 
+{{ include "controlplane-operations.persesDashboardSelectorLabels" (list $path $root) | indent 4 }}
 {{ include "controlplane-operations.labels" (list $path $root) | indent 4 }}
-data:     
+data:
 {{ printf "%s: |-" ($path | replace "/" "-" | indent 2) }}
 {{ printf "%s" $bytes | indent 4 }}
 {{- end }}