diff --git a/charts/apps/Chart.yaml b/charts/apps/Chart.yaml index 2e9f14820..69c0ec812 100644 --- a/charts/apps/Chart.yaml +++ b/charts/apps/Chart.yaml @@ -2,4 +2,4 @@ apiVersion: v2 name: apps description: An argocd app to deploy apps inside the virtual cluster type: application -version: 0.5.18 +version: 0.5.19 diff --git a/charts/apps/templates/monitoring-application.yaml b/charts/apps/templates/monitoring-application.yaml index 327659452..7fb6b5a0f 100644 --- a/charts/apps/templates/monitoring-application.yaml +++ b/charts/apps/templates/monitoring-application.yaml @@ -9,12 +9,13 @@ metadata: spec: destination: namespace: monitoring - server: {{ .Values.destination.server }} + targetRevision: {{ .Values.monitoring.targetRevision }} project: default source: repoURL: https://github.com/DiamondLightSource/workflows.git path: charts/monitoring targetRevision: {{ .Values.monitoring.targetRevision }} + helm: valueFiles: - values.yaml diff --git a/charts/monitoring/Chart.yaml b/charts/monitoring/Chart.yaml index 45280f591..1438b6cc0 100644 --- a/charts/monitoring/Chart.yaml +++ b/charts/monitoring/Chart.yaml @@ -2,7 +2,7 @@ apiVersion: v2 name: monitoring description: A monitoring stack for the workflows deployment type: application -version: 0.1.28 +version: 0.1.29 dependencies: - name: grafana repository: https://grafana-community.github.io/helm-charts diff --git a/charts/monitoring/values.yaml b/charts/monitoring/values.yaml index 43090a910..1bac0b3da 100644 --- a/charts/monitoring/values.yaml +++ b/charts/monitoring/values.yaml @@ -168,6 +168,24 @@ thanos: prometheus: kube-state-metrics: enabled: false + serverFiles: + alerting_rules.yml: + groups: + - name: argo-workflows + rules: + - alert: ArgoWorkflowControllerFailing + expr: | + kube_pod_container_status_waiting_reason{ + namespace="workflows", + pod=~"workflows-argo-workflows-workflow-controller-.*", + reason="CrashLoopBackOff" + } > 0 + for: 10m + labels: + severity: warning + annotations: + summary: Argo Workflow Controller failing + description: Workflow controller has been in CrashLoopBackOff for more than 10 minutes. prometheus-node-exporter: enabled: false prometheus-pushgateway: