Prometheus Alertmanager Production Alert Rules Template

Supanote Core Team @supanote · 1 min read

plain (yaml) 13 hours ago · 39 lines · 6 views

groups:
  - name: host_infrastructure_alerts
    rules:
      - alert: HostHighCpuUsage
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High CPU load on host {{ $labels.instance }}"
          description: "CPU load has exceeded 85% for more than 5 minutes (current value: {{ $value }}%)."

      - alert: HostMemoryExhaustion
        expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 < 10
        for: 3m
        labels:
          severity: critical
        annotations:
          summary: "Critical RAM exhaustion on {{ $labels.instance }}"
          description: "Host available memory is below 10% (current free: {{ $value }}%)."

      - alert: HostDiskFillingFast
        expr: (node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 15
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Root filesystem low on disk space on {{ $labels.instance }}"
          description: "Remaining disk space on / is below 15%."

      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Service target {{ $labels.instance }} is down"
          description: "Prometheus scraper cannot connect to target for over 1 minute."

1groups:

2 - name: host_infrastructure_alerts

3 rules:

4 - alert: HostHighCpuUsage

5 expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85

6 for: 5m

7 labels:

8 severity: warning

9 annotations:

10 summary: "High CPU load on host {{ $labels.instance }}"

11 description: "CPU load has exceeded 85% for more than 5 minutes (current value: {{ $value }}%)."

13 - alert: HostMemoryExhaustion

14 expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 < 10

15 for: 3m

16 labels:

17 severity: critical

18 annotations:

19 summary: "Critical RAM exhaustion on {{ $labels.instance }}"

20 description: "Host available memory is below 10% (current free: {{ $value }}%)."

22 - alert: HostDiskFillingFast

23 expr: (node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 15

24 for: 10m

25 labels:

26 severity: warning

27 annotations:

28 summary: "Root filesystem low on disk space on {{ $labels.instance }}"

29 description: "Remaining disk space on / is below 15%."

31 - alert: InstanceDown

32 expr: up == 0

33 for: 1m

34 labels:

35 severity: critical

36 annotations:

37 summary: "Service target {{ $labels.instance }} is down"

38 description: "Prometheus scraper cannot connect to target for over 1 minute."

Replies 0

Reply with note

No replies yet

Every reply is a note. Start a discussion, ask a question, or attach a code snippet.

Reply with a note