lucas.mathieu/ovh-01-stacks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(monitoring): Remove the HostCpuIsUnderutilized alert

Browse Source
This commit is contained in:
Lucas Mathieu
2026-01-05 10:42:43 +01:00
parent ee1738b97d
commit 0159266889
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
monitoring/prometheus/alerts/node-exporter.yml
View File

@@ -139,14 +139,14 @@ groups:
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostCpuIsUnderutilized
expr: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
for: 1w
labels:
severity: info
annotations:
summary: Host CPU is underutilized (instance {{ $labels.instance }})
description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# - alert: HostCpuIsUnderutilized
# expr: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
# for: 1w
# labels:
# severity: info
# annotations:
# summary: Host CPU is underutilized (instance {{ $labels.instance }})
# description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuStealNoisyNeighbor
expr: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'