From 2fe4e2435dfe8fbf36e69cb3a7a2edfaf6477cd9 Mon Sep 17 00:00:00 2001 From: nd Date: Thu, 6 Aug 2020 09:21:09 +0200 Subject: [PATCH] add alert for systemd services --- defaults/main.yml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/defaults/main.yml b/defaults/main.yml index 516268a..ebe7017 100644 --- a/defaults/main.yml +++ b/defaults/main.yml @@ -188,6 +188,18 @@ prometheus_agent: annotations: title: '{%raw%}{{ $labels.instance }}: TempCritical{%endraw%}' description: "Too hot!" + SystemdServices: + group: nodeexporter + enabled: True + alert: systemd + expr: | + node_systemd_units{job="node", instance=~"{{ inventory_hostname }}", state="failed"} > 0 + for: 5m + labels: + severity: critical + annotations: + title: '{%raw%}{{ $labels.instance }}: Not all systemd services are running{%endraw%}' + description: "Service not running" tls: mode: stunnel