Compare commits

..

1 commit

Author SHA1 Message Date
57d4fde7e4
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 18:16:28 +02:00

View file

@ -1,5 +1,5 @@
groups: groups:
- name: Fux-Generic - name: Generic
rules: rules:
- alert: HostJobFlaky - alert: HostJobFlaky
expr: group by(host, job) (changes(up{org="fux", job!="integrations/unix"}[24h]) > 5) expr: group by(host, job) (changes(up{org="fux", job!="integrations/unix"}[24h]) > 5)
@ -8,8 +8,8 @@ groups:
severity: info severity: info
annotations: annotations:
summary: Job {{ $labels.job }} flaky on (host {{ $labels.instance }}) 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.\n VALUE = {{ $value }}" description: "The job {{ $labels.job }} on target: {{ labels.host }} has been flaky over the last 24 hours.\n VALUE = {{ $value }}"
- name: Fux-SNMP - name: SNMP
rules: rules:
- alert: SnmpTargetMissing - alert: SnmpTargetMissing
expr: up{job=~".*snmp|SNMP.*"} == 0 expr: up{job=~".*snmp|SNMP.*"} == 0
@ -19,7 +19,7 @@ groups:
annotations: annotations:
summary: SNMP target missing (instance {{ $labels.instance }}) summary: SNMP target missing (instance {{ $labels.instance }})
description: "A SNMP target has disappeared for more the 15 min.\n VALUE = {{ $value }}" description: "A SNMP target has disappeared for more the 15 min.\n VALUE = {{ $value }}"
- name: Fux-DHCP - name: DHCP
rules: rules:
- alert: DhcpFuxSharedFailed - alert: DhcpFuxSharedFailed
expr: script_success{script="check_dhcp_fux_shared"} == 0 expr: script_success{script="check_dhcp_fux_shared"} == 0