Alerts

alert: MirrorMissingNars
expr: narherder_nar_files_total{instance=~"hydra-guix-129.guix.gnu.org:443|hatysa.cbaines.net:443",stored="false"}
  > 250
for: 10m
labels:
  severity: critical
annotations:
  description: Mirror missing {{ $value }} nars
  summary: Mirror missing nars (instance {{ $labels.instance }})

alert: TooManyNarsOnBordeaux
expr: narherder_nar_files_total{instance="bordeaux.guix.gnu.org:443",stored="true"}
  > 250
for: 10m
labels:
  severity: critical
annotations:
  description: Bordeaux has {{ $value }} nars
  summary: Too many nars on bordeaux

alert: BuildCoordinatorHookEventsNotBeingProcessed
expr: rate(guixbuildcoordinator_hook_duration_seconds_count[30m])
  < 0.001 and rate(guixbuildcoordinator_unprocessed_hook_events_total[30m]) >
  0.001
for: 10m
labels:
  severity: critical
annotations:
  description: '{{ $labels.event }} events are not being processed'
  summary: Build coordinator events not being processed

alert: GuixTargetMissing
expr: up{job=~"bordeaux.guix.gnu.org-nar-herders|coordinator.bayfront.guix.gnu.org|data.qa.guix.gnu.org-guix-data-service|data.guix.gnu.org-guix-data-service|hatysa.cbaines.net/node-exporter|hamal.cbaines.net/node-exporter|rumbia.cbaines.net/node-exporter|ranggung.cbaines.net/node-exporter|milano-guix-1/node-exporter"}
  == 0
for: 10m
labels:
  severity: critical
annotations:
  description: |-
    A Prometheus target has disappeared. An exporter might be crashed.
      VALUE = {{ $value }}
      LABELS = {{ $labels }}
  summary: Prometheus target missing (instance {{ $labels.instance }})

alert: HostOutOfDiskSpace
expr: (node_filesystem_avail_bytes{instance!="capella.cbaines.net:9100"}
  * 100) / node_filesystem_size_bytes < 10
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    Disk is almost full (< 10% left)
      VALUE = {{ $value }}
      LABELS: {{ $labels }}
  summary: Host out of disk space (instance {{ $labels.instance }})