Add NodeSystemdServiceCrashlooping alert to mixin (#3039)

* Add NodeSystemdServiceCrashlooping alert

---------

Signed-off-by: Vitaly Zhuravlev <v-zhuravlev@users.noreply.github.com>
This commit is contained in:
v-zhuravlev 2025-02-16 18:05:46 +08:00 committed by GitHub
parent edc40d1e0b
commit f252c4616a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -407,6 +407,20 @@
description: 'Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }}',
},
},
{
alert: 'NodeSystemdServiceCrashlooping',
expr: |||
increase(node_systemd_service_restart_total{%(nodeExporterSelector)s}[5m]) > 2
||| % $._config,
'for': '15m',
labels: {
severity: 'warning',
},
annotations: {
summary: 'Systemd service keeps restaring, possibly crash looping.',
description: 'Systemd service {{ $labels.name }} has being restarted too many times at {{ $labels.instance }} for the last 15 minutes. Please check if service is crash looping.',
},
},
{
alert: 'NodeBondingDegraded',
expr: |||