8.2. 为 NetObserv 仪表板创建 Loki 速率限制警报

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: loki-alerts
  namespace: openshift-operators-redhat
spec:
  groups:
  - name: LokiRateLimitAlerts
    rules:
    - alert: LokiTenantRateLimit
      annotations:
        message: |-
          {{ $labels.job }} {{ $labels.route }} is experiencing 429 errors.
        summary: "At any number of requests are responded with the rate limit error code."
      expr: sum(irate(loki_request_duration_seconds_count{status_code="429"}[1m])) by (job, namespace, route) / sum(irate(loki_request_duration_seconds_count[1m])) by (job, namespace, route) * 100 > 0
      for: 10s
      labels:
        severity: warning

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: loki-alerts
  namespace: openshift-operators-redhat
spec:
  groups:
  - name: LokiRateLimitAlerts
    rules:
    - alert: LokiTenantRateLimit
      annotations:
        message: |-
          {{ $labels.job }} {{ $labels.route }} is experiencing 429 errors.
        summary: "At any number of requests are responded with the rate limit error code."
      expr: sum(irate(loki_request_duration_seconds_count{status_code="429"}[1m])) by (job, namespace, route) / sum(irate(loki_request_duration_seconds_count[1m])) by (job, namespace, route) * 100 > 0
      for: 10s
      labels:
        severity: warning