blob: 685d59c9a3f3c131ba5739b4e762bec88c88d91a [file] [log] [blame]
groups:
- name: general
rules:
- alert: JobDown
expr: up == 0
for: 1m
labels:
category: infra
severity: critical
annotations:
abbr:
'{{ $labels.job }} - {{ $labels.hostname }} - {{
$externalLabels.cluster }}'
description:
'{{ $labels.job }} on {{ $labels.hostname }} in {{
$externalLabels.cluster }} has been down for more than 5 minutes.'
- alert: TooManyGoRoutines
expr: go_goroutines > 3000
for: 2m
labels:
category: infra
severity: warning
annotations:
abbr: '{{ $labels.job }} - {{ $externalLabels.cluster }}'
description:
'Too many Go routines in {{ $labels.hostname }} for app {{
$labels.job }}.'
- alert: TooManyOpenFDs
expr: process_open_fds > 5000
labels:
category: infra
severity: warning
annotations:
abbr: '{{ $labels.job }} - {{ $externalLabels.cluster }}'
description:
'Too many open file handles on {{ $labels.hostname }} for app {{
$labels.job }}.'