prometheus: add nomadbatch error alert

2023-09-14 20:26:16 +02:00 · 2023-09-14 20:26:16 +02:00 · 989453a16a
commit 989453a16a
parent 29a6f1ae1a
1 changed files with 6 additions and 0 deletions
--- a/nomad-job/prometheus.nomad
+++ b/nomad-job/prometheus.nomad
@ -160,6 +160,12 @@ groups:
    annotations:
      summary: Nomad job queued (instance {{ $labels.instance }})
      description: "Nomad job queued\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: NomadBatchError
+    expr: nomad_nomad_job_summary_failed{parent_id=~".+"}>0
+    labels:
+        severity: warning
+    annotations:
+        summary: Nomad batch {{ $labels.parent_id}} error


 EOH