---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
    app.kubernetes.io/part-of: {{ $.Chart.Name }}
    app.kubernetes.io/version: {{ $.Chart.Version }}
    app.kubernetes.io/managed-by: {{ $.Release.Service }}
    prometheus: k8s
    role: alert-rules
  name: grafana-rules
  namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
spec:
  groups:
  - name: GrafanaAlerts
    rules:
    - alert: GrafanaRequestsFailing
      annotations:
        message: '{{`{{`}} $labels.namespace }}/{{`{{`}} $labels.job }}/{{`{{`}} $labels.handler }} is experiencing {{`{{`}} $value | humanize }}% errors'
        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/grafana/grafanarequestsfailing
      expr: |
        100 * namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query", status_code=~"5.."}
        / ignoring (status_code)
        sum without (status_code) (namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query"})
        > 50
      for: 5m
      labels:
        severity: warning
  - name: grafana_rules
    rules:
    - expr: |
        sum by (namespace, job, handler, status_code) (rate(grafana_http_request_duration_seconds_count[5m]))
      record: namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m