kubernetes/namespaces/monitoring/alerts/alerts.d/etcd.yaml


1
2
3
4
5
6
7
8
9
10
11

groups:
  - name: etcd
    rules:
      - alert: etcd/error-spike
        expr: rate(etcd_request_error_total[5m]) > 0
        for: 5m
        labels:
          severity: page
        annotations:
          summary: "Etcd request errors are spiking"
          description: "Etcd request errors are spiking on {{ $labels.instance }} for {{ $labels.operation }}s to {{ $labels.type }}"