39 lines
1.5 KiB
YAML
39 lines
1.5 KiB
YAML
groups:
|
|
- name: node_alerts
|
|
rules:
|
|
- alert: HighCPULoad
|
|
expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High CPU load (instance {{ $labels.instance }})"
|
|
description: "CPU load is > 80%\n VALUE = {{ $value }}%\n LABELS: {{ $labels }}"
|
|
|
|
- alert: HighMemoryLoad
|
|
expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High memory load (instance {{ $labels.instance }})"
|
|
description: "Memory load is > 80%\n VALUE = {{ $value }}%\n LABELS: {{ $labels }}"
|
|
|
|
- alert: HighDiskUsage
|
|
expr: (node_filesystem_size_bytes{fstype=~"ext4|xfs"} - node_filesystem_free_bytes{fstype=~"ext4|xfs"}) / node_filesystem_size_bytes{fstype=~"ext4|xfs"} * 100 > 85
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High disk usage (instance {{ $labels.instance }})"
|
|
description: "Disk usage is > 85%\n VALUE = {{ $value }}%\n LABELS: {{ $labels }}"
|
|
|
|
- alert: UnusualMemoryGrowth
|
|
expr: deriv(node_memory_MemAvailable_bytes[30m]) < -10 * 1024 * 1024
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Unusual memory consumption rate (instance {{ $labels.instance }})"
|
|
description: "Memory is being consumed at a rate of more than 10MB/min\n VALUE = {{ $value | humanize }}B/s"
|