XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-23 09:58:16 +08:00
Code Issues Projects Releases Packages Wiki Activity

Publish

Browse source
This commit is contained in:
samber 2025-02-16 22:47:17 +00:00
parent 11a78f0f06
commit 4e49e77d29
1 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
dist/rules/docker-containers/google-cadvisor.yml vendored
View file

@ -57,17 +57,16 @@ groups:
annotations: annotations:
summary: Container high throttle rate (instance {{ $labels.instance }}) summary: Container high throttle rate (instance {{ $labels.instance }})
description: "Container is being throttled\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Container is being throttled\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ContainerHighLowChangeCpuUsage - alert: ContainerHighLowChangeCpuUsage
expr: '(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' expr: '(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'
for: 0m for: 0m
labels: labels:
severity: info severity: info
annotations: annotations:
summary: Container change CPU utilization (instance {{ $labels.instance }}) summary: Container high low change CPU usage (instance {{ $labels.instance }})
description: "This alert rule monitors the absolute change in CPU usage within a time window and triggers an alert when the change exceeds 25%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "This alert rule monitors the absolute change in CPU usage within a time window and triggers an alert when the change exceeds 25%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ContainerLowCpuUtilization - alert: ContainerLowCpuUtilization
expr: '(sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) < 20' expr: '(sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) < 20'
for: 7d for: 7d