GistPin/infrastructure/monitoring/event-alerts.yml at main · ghzhost/GistPin · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
groups:
  - name: kubernetes-events
    interval: 30s
    rules:
      - alert: CriticalEventDetected
        expr: |
          count(kube_event{type="Warning", reason=~"Failed|Error|OOMKilling|NodeNotReady|BackOff|CrashLoopBackOff"}) > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Critical Kubernetes event detected"
          description: "{{ $labels.reason }} in {{ $labels.namespace }}/{{ $labels.name }}"

      - alert: FrequentPodRestarts
        expr: |
          rate(kube_event{reason="BackOff"}[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Frequent pod restarts detected"

      - alert: NodeIssueEvent
        expr: |
          kube_event{reason=~"NodeNotReady|NodeHasDiskPressure|NodeHasMemoryPressure"}
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Node issue event: {{ $labels.reason }} on {{ $labels.name }}"

      - alert: EventArchiveFailure
        expr: |
          rate(event_exporter_s3_errors_total[5m]) > 0
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Event archive S3 upload failures detected"