Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions charts/controlplane-operations/alerts/controlplane-remote.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,27 @@ groups:
expr: >
kube_customresource_status_state{customresource_kind="Update",customresource_group="argora.cloud.sap",state=~"Error"}
== 1
for: {{ dig "ArgoraUpdateInError" "for" "1m" .Values.prometheusRules }}
for: {{ dig "ArgoraUpdateInError" "for" "10m" .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" . }}
annotations:
description: "Argora Update CR status is in Error state for more than 1 minute."
description: "Argora Update CR status is in Error state for more than 10 minutes."
summary: "Update CR in Error state."
{{- end }}

{{- if not (.Values.prometheusRules.disabled.ArgoraClusterImportInError | default false) }}
- alert: ArgoraClusterImportInError
expr: >
kube_customresource_status_state{customresource_kind="ClusterImport",customresource_group="argora.cloud.sap",state=~"Error"}
== 1
for: {{ dig "ArgoraClusterImportInError" "for" "10m" .Values.prometheusRules }}
labels:
severity: {{ dig "ArgoraClusterImportInError" "severity" "warning" .Values.prometheusRules }}
playbook: https://github.com/cobaltcore-dev/controlplane-operations/playbooks/ArgoraClusterImportInError.md
{{ include "controlplane-operations.additionalRuleLabels" . }}
annotations:
description: "Argora ClusterImport CR status is in Error state for more than 10 minutes."
summary: "ClusterImport CR in Error state."
{{- end }}
Loading