Added hardware temperature alerts

This commit is contained in:
Rob Brown 2019-12-12 17:29:23 +00:00
parent c2c9a58959
commit 58f843dbc6

View file

@ -77,6 +77,15 @@ services:
description: 'SystemD service crashed'
query: 'node_systemd_unit_state{state="failed"} == 1'
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
exporters: