diff --git a/charts/controlplane-operations/Chart.yaml b/charts/controlplane-operations/Chart.yaml index 4fd3778..2b80ba1 100644 --- a/charts/controlplane-operations/Chart.yaml +++ b/charts/controlplane-operations/Chart.yaml @@ -1,6 +1,6 @@ apiVersion: v2 name: controlplane-operations -version: 1.1.19 +version: 1.1.20 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) diff --git a/charts/controlplane-operations/alerts/controlplane-remote.yaml b/charts/controlplane-operations/alerts/controlplane-remote.yaml index d6d39c2..8d61995 100644 --- a/charts/controlplane-operations/alerts/controlplane-remote.yaml +++ b/charts/controlplane-operations/alerts/controlplane-remote.yaml @@ -35,6 +35,23 @@ groups: summary: ClusterImport CR in Error state. {{- end }} +{{- if not (.Values.prometheusRules.disabled.ArgoraIPPoolImportInError | default false) }} + - alert: ArgoraIPPoolImportInError + expr: > + kube_customresource_ip_pool_import_status{customresource_kind="IPPoolImport",customresource_group="argora.cloud.sap",state=~"Error"} + == 1 + for: {{ dig "ArgoraIPPoolImportInError" "for" "10m" .Values.prometheusRules }} + labels: + {{ include "controlplane-operations.additionalRuleLabels" . }} + severity: {{ dig "ArgoraIPPoolImportInError" "severity" "warning" .Values.prometheusRules }} + playbook: https://operations.global.cloud.sap/docs/support/playbook/argora-ippoolimport-in-error/ + service: {{ dig "ArgoraIPPoolImportInError" "service" .Values.prometheusRules.defaultService .Values.prometheusRules }} + support_group: {{ dig "ArgoraIPPoolImportInError" "support_group" .Values.prometheusRules.defaultSupportGroup .Values.prometheusRules }} + annotations: + description: Argora IPPoolImport CR status is in Error state for more than {{ dig "ArgoraIPPoolImportInError" "for" "10m" .Values.prometheusRules }}. + summary: IPPoolImport CR in Error state. +{{- end }} + {{- if not (.Values.prometheusRules.disabled.ArgoraPodNotReadyError | default false) }} - alert: ArgoraPodNotReadyError expr: > diff --git a/charts/controlplane-operations/plugindefinition.yaml b/charts/controlplane-operations/plugindefinition.yaml index 7bd84a1..19394d2 100644 --- a/charts/controlplane-operations/plugindefinition.yaml +++ b/charts/controlplane-operations/plugindefinition.yaml @@ -3,7 +3,7 @@ kind: PluginDefinition metadata: name: controlplane-operations spec: - version: 1.1.19 + version: 1.1.20 displayName: Controlplane operations bundle description: Operations bundle for Controlplane clusters docMarkDownUrl: https://raw.githubusercontent.com/cloudoperators/controlplane-operations/main/README.md @@ -11,7 +11,7 @@ spec: helmChart: name: controlplane-operations repository: oci://ghcr.io/cloudoperators/controlplane-operations/charts - version: 1.1.19 + version: 1.1.20 options: - name: prometheusRules.create description: Create Prometheus rules