grafana: make alerts better for fux
Some checks failed
/ Ansible Lint (push) Failing after 48s
/ Ansible Lint (pull_request) Failing after 49s

This commit is contained in:
chris 2025-09-01 01:25:11 +02:00
commit 068b261745
Signed by: c6ristian
SSH key fingerprint: SHA256:B3m+yzpaxGXSEcDBpPHfvza/DNC0wuX+CKMeGq8wgak
6 changed files with 47 additions and 4 deletions

View file

@ -410,7 +410,7 @@ groups:
summary: Prometheus job missing (instance {{ $labels.instance }})
description: "A Prometheus job has disappeared\n VALUE = {{ $value }}"
- alert: PrometheusTargetMissing
expr: up == 0
expr: up{job!~"snmp|noc_room_temp"} == 0
for: 0m
labels:
severity: critical
@ -418,7 +418,7 @@ groups:
summary: Prometheus target missing (instance {{ $labels.instance }})
description: "A Prometheus target has disappeared. An exporter might be crashed.\n VALUE = {{ $value }}"
- alert: PrometheusAllTargetsMissing
expr: sum by (job) (up) == 0
expr: sum by (job) (up{job!~"snmp|noc_room_temp"}) == 0
for: 0m
labels:
severity: critical