# Systemd state alerts. Managed by Ansible (roles/prometheus).
#
# node_exporter's systemd collector exposes node_systemd_unit_state. A unit in
# the failed state is exactly the kind of thing that needs paging at 03:00.
groups:
  - name: systemd
    rules:
      - alert: SystemdUnitFailed
        expr: node_systemd_unit_state{state="failed"} == 1
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "systemd unit {{ $labels.name }} is in failed state ({{ $labels.instance }})"
          description: >-
            Unit {{ $labels.name }} (type {{ $labels.type }}) has been failed
            for more than 5 minutes on {{ $labels.instance }}.