awesome-prometheus-alerts/dist/rules/nomad/embedded-exporter.yml
2026-04-06 18:38:45 +00:00

42 lines
1.5 KiB
YAML

groups:
- name: EmbeddedExporter
rules:
- alert: NomadJobFailed
expr: 'nomad_nomad_job_summary_failed > 0'
for: 0m
labels:
severity: warning
annotations:
summary: Nomad job failed (instance {{ $labels.instance }})
description: "Nomad job {{ $labels.job }} has {{ $value }} failed allocations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: NomadJobLost
expr: 'nomad_nomad_job_summary_lost > 0'
for: 0m
labels:
severity: warning
annotations:
summary: Nomad job lost (instance {{ $labels.instance }})
description: "Nomad job {{ $labels.job }} has {{ $value }} lost allocations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: NomadJobQueued
expr: 'nomad_nomad_job_summary_queued > 0'
for: 2m
labels:
severity: warning
annotations:
summary: Nomad job queued (instance {{ $labels.instance }})
description: "Nomad job {{ $labels.job }} has {{ $value }} queued allocations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: NomadBlockedEvaluation
expr: 'nomad_nomad_blocked_evals_total_blocked > 0'
for: 0m
labels:
severity: warning
annotations:
summary: Nomad blocked evaluation (instance {{ $labels.instance }})
description: "Nomad has {{ $value }} blocked evaluations. The cluster may lack resources to place allocations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"