mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-24 02:17:00 +08:00
Added hardware temperature alerts
This commit is contained in:
parent
c2c9a58959
commit
58f843dbc6
1 changed files with 9 additions and 0 deletions
|
|
@ -77,6 +77,15 @@ services:
|
||||||
description: 'SystemD service crashed'
|
description: 'SystemD service crashed'
|
||||||
query: 'node_systemd_unit_state{state="failed"} == 1'
|
query: 'node_systemd_unit_state{state="failed"} == 1'
|
||||||
severity: warning
|
severity: warning
|
||||||
|
- name: Physical component too hot
|
||||||
|
description: 'Physical hardware component too hot'
|
||||||
|
query: 'node_hwmon_temp_celsius > 75'
|
||||||
|
severity: warning
|
||||||
|
- name: Node overtemperature alarm
|
||||||
|
description: 'Physical node temperature alarm triggered'
|
||||||
|
query: 'node_hwmon_temp_alarm == 1'
|
||||||
|
severity: critical
|
||||||
|
|
||||||
|
|
||||||
- name: Docker containers
|
- name: Docker containers
|
||||||
exporters:
|
exporters:
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue