This commit is contained in:
samber 2023-02-26 01:34:30 +00:00
parent 59891728e4
commit 293aba1437

View file

@ -122,7 +122,7 @@ groups:
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostHighCpuLoad
expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80'
expr: 'sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8'
for: 0m
labels:
severity: warning
@ -149,13 +149,13 @@ groups:
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuHighIowait
expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 5'
expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10'
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU high iowait (instance {{ $labels.instance }})
description: "CPU iowait > 5%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualDiskIo
expr: 'rate(node_disk_io_time_seconds_total[1m]) > 0.5'