Compare commits

..

1 commit

Author SHA1 Message Date
816e7fc3e0
grafana: make alerts better for fux
Some checks failed
/ Ansible Lint (push) Failing after 48s
/ Ansible Lint (pull_request) Failing after 47s
2025-09-09 19:03:54 +02:00

View file

@ -2,22 +2,20 @@ groups:
- name: Fux-Generic
rules:
- alert: HostJobFlaky
expr: group by(instance, job) (changes(up{org="fux"}[24h]) > 7)
expr: group by(host, job) (changes(up{org="fux"}[24h]) > 7)
for: 0m
labels:
severity: info
org: fux
annotations:
summary: Job {{ $labels.job }} flaky on (instance {{ $labels.instance }})
description: "The job {{ $labels.job }} on target: {{ $labels.instance }} has been flaky over the last 24 hours."
summary: Job {{ $labels.job }} flaky on (host {{ $labels.instance }})
description: "The job {{ $labels.job }} on target: {{ $labels.host }} has been flaky over the last 24 hours."
- name: Fux-SNMP
rules:
- alert: SnmpTargetMissing
expr: up{job=~".*snmp.*", org="fux"} == 0
expr: up{job=~".*snmp|SNMP.*"} == 0
for: 15m
labels:
severity: critical
org: fux
annotations:
summary: SNMP target missing (instance {{ $labels.instance }})
description: "SNMP target: {{ $labels.instance }} has disappeared for more the 15 min."