ansible-infra/resources/chaosknoten/grafana/docker_compose/prometheus_alerts-fux.rules.yaml
c6ristian 83b1f2cba9
Some checks failed
/ Ansible Lint (push) Has been cancelled
/ Ansible Lint (pull_request) Failing after 47s
grafana: make alerts better for fux
2025-09-09 18:44:50 +02:00

39 lines
1.5 KiB
YAML

groups:
- name: Fux-Generic
rules:
- alert: HostJobFlaky
expr: group by(host, job) (changes(up{org="fux", job!="integrations/unix"}[24h]) > 5)
for: 0m
labels:
severity: info
annotations:
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 }}"
- name: Fux-SNMP
rules:
- alert: SnmpTargetMissing
expr: up{job=~".*snmp|SNMP.*"} == 0
for: 15m
labels:
severity: critical
annotations:
summary: SNMP target missing (instance {{ $labels.instance }})
description: "A SNMP target has disappeared for more the 15 min.\n VALUE = {{ $value }}"
- name: Fux-DHCP
rules:
- alert: DhcpFuxSharedFailed
expr: script_success{script="check_dhcp_fux_shared"} == 0
for: 0m
labels:
severity: critical
annotations:
summary: DHCP for Fux Shared stoped working
description: "No DHCP lease for the Fux Shared range was received"
- alert: DhcpFuxAdminFailed
expr: script_success{script_success="check_dhcp_fux_admin"} == 0
for: 0m
labels:
severity: critical
annotations:
summary: DHCP for Fux Admin stoped working
description: "No DHCP lease for the Fux Admin range was received"