YAMLalerting-rules.yaml
Copy
1
# Prometheus alerting rules
2
groups:
3
  - name: application
4
    interval: 30s
5
    rules:
6
      - alert: HighErrorRate
7
        expr: |
8
          sum(rate(http_requests_total{status=~"5.."}[5m]))
9
            / sum(rate(http_requests_total[5m])) > 0.05
10
        for: 5m
11
        labels:
12
          severity: critical
13
          team: backend
14
        annotations:
15
          summary: "High HTTP error rate"
16
          description: "Error rate is {{ $value | humanizePercentage }} over 5m"
17
 
18
      - alert: PodCrashLooping
19
        expr: increase(kube_pod_container_status_restarts_total[15m]) > 3
20
        for: 2m
21
        labels:
22
          severity: warning
23
          team: platform
24
        annotations:
25
          summary: "Pod {{ $labels.pod }} is crash-looping"
26
 
27
      - alert: HighMemoryUsage
28
        expr: |
29
          container_memory_usage_bytes
30
            / container_spec_memory_limit_bytes > 0.9
31
        for: 10m
32
        labels:
33
          severity: warning
34
        annotations:
35
          summary: "Container {{ $labels.container }} memory > 90%"
36
 
37
  - name: sla
38
    rules:
39
      - alert: SLABreach
40
        expr: |
41
          sum(rate(http_requests_total{status=~"2.."}[1h]))
42
            / sum(rate(http_requests_total[1h])) < 0.995
43
        for: 15m
44
        labels:
45
          severity: critical
46
          team: sre
47
        annotations:
48
          summary: "SLA breach: availability < 99.5%"
49