alerts.yml

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: su-pdfgen
  namespace: supstonad
  labels:
    team: supstonad
spec:
  groups:
    - name: su-pdfgen
      rules:
        - alert: su-pdfgen-metrics-scrape-feilet
          expr: sum(up{app="su-pdfgen", job="kubernetes-pods"}) < 1
          for: 1m
          annotations:
            consequence: "su-pdfgen sitt /metrics endepunktet har vært utilgjengelig i minst 1 minutt"
            action: "`kubectl describe pod {{ $labels.kubernetes_pod_name }}` for events, og `kubectl logs {{ $labels.kubernetes_pod_name }}` for logger"
          labels:
            namespace: supstonad
            severity: critical
        - alert: su-pdfgen-error-logg
          expr: 'sum(max_over_time(log_messages_errors{namespace="supstonad",app="su-pdfgen",level="Error"}[15m])
                or vector(0)) -
               sum(max_over_time(log_messages_errors{namespace="supstonad",app="su-pdfgen",level="Error"}[15m]
               offset 15m) or vector(0)) > 0'
          for: 1s
          annotations:
            consequence: "su-pdfgen har fått en ny error i loggen siste 15 min"
            action: "Det er logget en melding i Kibana. Sjekk logger her: `{{LOGS_URL}}`"
          labels:
            namespace: supstonad
            severity: critical
        - alert: su-pdfgen-pods-available
          expr: sum(kube_deployment_status_replicas_available{deployment="su-pdfgen"}) < 1
          for: 1m
          annotations:
            consequence: "Tilgjengelige kubernetes pods for su-pdfgen er mindre enn 1"
            action: "`kubectl describe pod {{ $labels.kubernetes_pod_name }}` for events, og `kubectl logs {{ $labels.kubernetes_pod_name }}` for logger"
          labels:
            namespace: supstonad
            severity: critical