GistPin/infrastructure/monitoring/node-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
41
42
43
44
45
46
47
48
49
50
51
52
groups:
  - name: node-problems
    interval: 30s
    rules:
      - alert: NodeProblemDetected
        expr: node_problem_detector_conditions{status="true"} > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Node problem detected on {{ $labels.node }}"
          description: "{{ $labels.reason }} on node {{ $labels.node }}"

      - alert: NodeKernelPanic
        expr: node_problem_detector_kernel_panic_total > 0
        for: 0s
        labels:
          severity: critical
        annotations:
          summary: "Kernel panic on node {{ $labels.node }}"

      - alert: NodeOOMKill
        expr: rate(node_problem_detector_oom_kill_total[5m]) > 0
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "OOM kills detected on node {{ $labels.node }}"

      - alert: NodeHighMemoryPressure
        expr: node_memory_Pressure > 0.9
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory pressure on node {{ $labels.node }}"

      - alert: NodeDiskPressure
        expr: node_filesystem_avail_bytes{mountpoint="/",fstype!="tmpfs"} / node_filesystem_size_bytes{mountpoint="/",fstype!="tmpfs"} < 0.1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Low disk space on node {{ $labels.node }}"

      - alert: NodeNotReady
        expr: kube_node_status_condition{condition="Ready",status="true"} == 0
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Node {{ $labels.node }} is not ready"