From 989453a16a81448129a5b6764a3e55c5a9c87cc0 Mon Sep 17 00:00:00 2001 From: vincent Date: Thu, 14 Sep 2023 20:26:16 +0200 Subject: [PATCH] prometheus: add nomadbatch error alert --- nomad-job/prometheus.nomad | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/nomad-job/prometheus.nomad b/nomad-job/prometheus.nomad index be26457..287d707 100644 --- 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