Alerts

alert: KeycloakMetricsDown
expr: up{job="keycloak"}
  == 0
for: 3m
labels:
  severity: critical
annotations:
  description: Keycloak /metrics endpoint is unreachable for 3 minutes.
  source: https://prometheus.bosspacific.com.au/graph?query=up{job="keycloak"}==0
  summary: Keycloak metrics down

alert: NodeExporterDown
expr: up{job="node"}
  == 0
for: 10m
labels:
  severity: warning
annotations:
  description: Node exporter unreachable on {{ $labels.instance }} for 10 minutes.
  source: https://prometheus.bosspacific.com.au/graph?query=up%7Bjob%3D%22node%22%7D%3D%3D0
  summary: Node exporter down on {{ $labels.vm }}

alert: HostSshDown
expr: probe_success{instance=~".*
  host .*",job="probe_tcp"} == 0
for: 10m
labels:
  severity: warning
annotations:
  description: SSH TCP probe failing for {{ $labels.instance }} for 10 minutes.
  source: https://prometheus.bosspacific.com.au/graph?query=probe_success{job="probe_tcp"}==0
  summary: 'Host SSH down: {{ $labels.instance }}'

alert: PostgresTcpDown
expr: probe_success{instance=~"postgres.*",job="probe_tcp"}
  == 0
for: 5m
labels:
  severity: critical
annotations:
  description: Blackbox TCP probe failing for {{ $labels.instance }} for 5 minutes.
  source: https://prometheus.bosspacific.com.au/graph?query=probe_success{job="probe_tcp"}==0
  summary: 'Postgres TCP down: {{ $labels.instance }}'

alert: ServiceHttpDown
expr: probe_success{job="probe_http"}
  == 0
for: 5m
labels:
  severity: critical
annotations:
  description: Blackbox HTTP probe failing for {{ $labels.instance }} for 5 minutes.
  source: https://prometheus.bosspacific.com.au/graph?query=probe_success{job="probe_http"}==0
  summary: 'HTTP service down: {{ $labels.instance }}'