groups:
  - name: Promtail

    rules:
      - alert: PromtailRequestErrors
        expr: '100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10'
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: Promtail request errors (instance {{ $labels.instance }})
          description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: PromtailRequestLatency
        expr: "histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1"
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: Promtail request latency (instance {{ $labels.instance }})
          description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"