groups:

- name: EmbeddedExporterV1

  rules:

    - alert: TraefikBackendDown
      expr: 'count(traefik_backend_server_up) by (backend) == 0'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Traefik backend down (instance {{ $labels.instance }})
        description: "All Traefik backends are down\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: TraefikHighHttp4xxErrorRateBackend
      expr: 'sum(rate(traefik_backend_requests_total{code=~"4.*"}[3m])) by (backend) / sum(rate(traefik_backend_requests_total[3m])) by (backend) * 100 > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Traefik high HTTP 4xx error rate backend (instance {{ $labels.instance }})
        description: "Traefik backend 4xx error rate is above 5%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: TraefikHighHttp5xxErrorRateBackend
      expr: 'sum(rate(traefik_backend_requests_total{code=~"5.*"}[3m])) by (backend) / sum(rate(traefik_backend_requests_total[3m])) by (backend) * 100 > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Traefik high HTTP 5xx error rate backend (instance {{ $labels.instance }})
        description: "Traefik backend 5xx error rate is above 5%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"