Add alert rule for high CPU usage change

This commit is contained in:
Samuel Berthe 2025-02-16 23:43:34 +01:00 committed by GitHub
parent f25c09350b
commit 40ad2e67a0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -373,6 +373,10 @@ groups:
query: 'rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1' query: 'rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1'
severity: warning severity: warning
for: 2m for: 2m
- name: Container high low change CPU usage
description: This alert rule monitors the absolute change in CPU usage within a time window and triggers an alert when the change exceeds 25%.
query: '(abs((sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m])) * 100) - (sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m] offset 1m)) * 100)) or abs((sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m])) * 100) - (sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[5m] offset 1m)) * 100))) > 25'
severity: warning
- name: Container Low CPU utilization - name: Container Low CPU utilization
description: Container CPU utilization is under 20% for 1 week. Consider reducing the allocated CPU. description: Container CPU utilization is under 20% for 1 week. Consider reducing the allocated CPU.
query: '(sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) < 20' query: '(sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) < 20'