feat: add postgres/gitea/blackbox alerts and more node alerts
This commit is contained in:
@ -0,0 +1,19 @@
|
||||
name: "DEV ADIBROV - Container OOM Killed"
|
||||
expression: |
|
||||
increase(container_oom_events_total{job="cadvisor", name!=""}[5m])
|
||||
threshold: 0
|
||||
for: "1m"
|
||||
condition_type: "gt"
|
||||
need_reduce: true
|
||||
reducer_type: "sum"
|
||||
no_data_state: "OK"
|
||||
exec_err_state: "Error"
|
||||
labels:
|
||||
service: "containers"
|
||||
severity: "critical"
|
||||
team: "infra"
|
||||
summary: |
|
||||
Контейнер {{ $labels.name }} убит OOM killer на {{ $labels.instance }}
|
||||
description: |
|
||||
Контейнер {{ $labels.name }} на {{ $labels.instance }} был убит ядром из-за нехватки памяти.
|
||||
Нужно проверить лимиты памяти контейнера и текущее потребление.
|
||||
Reference in New Issue
Block a user