Increase the alert threshold for temperatures
All checks were successful
continuous-integration/drone/push Build is passing
continuous-integration/drone/pr Build is passing

This commit is contained in:
jeltz 2021-04-03 08:04:10 +02:00
parent 1c3127dbbe
commit 91817b324c

View file

@ -59,12 +59,14 @@ groups:
La mémoire swap est utilisée à {{ raw('$value | printf "%.1f"') }}%
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 75
expr: node_hwmon_temp_celsius > 79
for: 3m
labels:
severity: critical
annotations:
summary: La température de l'hôte est de {{ raw('$value') }}°C
summary: >-
La température de l'hôte est de {{ raw('$value') }}°C
({{ raw('$labels.chip') }}, {{ raw('$labels.sensor') }})
- alert: HostNodeOvertemperatureAlarm
expr: node_hwmon_temp_crit_alarm_celsius == 1
@ -72,7 +74,9 @@ groups:
labels:
severity: critical
annotations:
summary: L'alarme de température de l'hôte est active
summary: >-
L'alarme de température de l'hôte est active
({{ raw('$labels.chip') }}, {{ raw('$labels.sensor') }})
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[1m]) > 0