Skip to content
Merged
Show file tree
Hide file tree
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
6 changes: 4 additions & 2 deletions chart/infra-server/templates/monitoring/rules.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,15 @@ kind: PrometheusRule
metadata:
name: argo-workflow-failures
namespace: monitoring
labels:
release: {{ .Release.Name }}
spec:
groups:
- name: Workflow failures
interval: 30s
rules:
- alert: Workflow Error
expr: increase(argo_workflows_gauge{status="Error"}[5m]) > 0
expr: increase(argo_workflows_gauge{phase="Error"}[5m]) > 0
for: 1m
annotations:
summary: A workflow has errored
Expand All @@ -21,7 +23,7 @@ spec:
namespace: monitoring
environment: {{ .Values.environment }}
- alert: Workflow Failure
expr: increase(argo_workflows_gauge{status="Failed"}[5m]) > 0
expr: increase(argo_workflows_gauge{phase="Failed"}[5m]) > 0
for: 1m
annotations:
summary: A workflow has failed.
Expand Down
2 changes: 2 additions & 0 deletions chart/infra-server/templates/monitoring/services.yaml
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
{{- if .Values.monitoring.enabled }}
---
apiVersion: v1
kind: Service
Expand Down Expand Up @@ -30,3 +31,4 @@ spec:
targetPort: 9101
selector:
app.kubernetes.io/name: infra-server
{{- end }}
Loading