Compare commits

..

1 commit

Author SHA1 Message Date
73f69f34c8
grafana: make alerts better for fux
Some checks failed
/ Ansible Lint (push) Failing after 47s
/ Ansible Lint (pull_request) Failing after 46s
2025-09-09 18:46:41 +02:00

View file

@ -2,13 +2,13 @@ groups:
- name: Fux-Generic - name: Fux-Generic
rules: rules:
- alert: HostJobFlaky - alert: HostJobFlaky
expr: group by(host, job) (changes(up{org="fux"}[24h]) > 7) expr: group by(host, job) (changes(up{org="fux", job!="integrations/unix"}[24h]) > 5)
for: 0m for: 0m
labels: labels:
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." description: "The job {{ $labels.job }} on target: {{ $labels.host }} has been flaky over the last 24 hours.\n VALUE = {{ $value }}"
- name: Fux-SNMP - name: Fux-SNMP
rules: rules:
- alert: SnmpTargetMissing - alert: SnmpTargetMissing
@ -18,7 +18,7 @@ groups:
severity: critical severity: critical
annotations: annotations:
summary: SNMP target missing (instance {{ $labels.instance }}) summary: SNMP target missing (instance {{ $labels.instance }})
description: "SNMP target: {{ $labels.instance }} has disappeared for more the 15 min." description: "A SNMP target has disappeared for more the 15 min.\n VALUE = {{ $value }}"
- name: Fux-DHCP - name: Fux-DHCP
rules: rules:
- alert: DhcpFuxSharedFailed - alert: DhcpFuxSharedFailed
@ -28,7 +28,7 @@ groups:
severity: critical severity: critical
annotations: annotations:
summary: DHCP for Fux Shared stoped working summary: DHCP for Fux Shared stoped working
description: "No DHCP lease for the Fux Shared range was received \n V" description: "No DHCP lease for the Fux Shared range was received"
- alert: DhcpFuxAdminFailed - alert: DhcpFuxAdminFailed
expr: script_success{script_success="check_dhcp_fux_admin"} == 0 expr: script_success{script_success="check_dhcp_fux_admin"} == 0
for: 0m for: 0m