fb7fc87d23
This change allows us to substitute values into our rules files.
Example:
- alert: my_region_is_down
expr: up{region="{{ $my_region }}"} == 0
To support this change, rule annotations that used the expansion
{{ $labels.foo }} had to be surrounded with "{{` ... `}}" to render
correctly.
Change-Id: Ia7ac891de8261acca62105a3e2636bd747a5fbea
42 lines
1.8 KiB
YAML
42 lines
1.8 KiB
YAML
---
|
|
conf:
|
|
prometheus:
|
|
rules:
|
|
postgresql:
|
|
groups:
|
|
- name: postgresql.rules
|
|
rules:
|
|
- alert: prom_exporter_postgresql_unavailable
|
|
expr: avg_over_time(up{job="postgresql-exporter"}[5m]) == 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
description: postgresql exporter is not collecting metrics or is not available for past 10 minutes
|
|
title: postgresql exporter is not collecting metrics or is not available
|
|
- alert: pg_replication_fallen_behind
|
|
expr: (pg_replication_lag > 120) and ON(instance) (pg_replication_is_replica == 1)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
description: "{{`Replication lag on server {{$labels.instance}} is currently {{$value | humanizeDuration }}`}}"
|
|
title: Postgres Replication lag is over 2 minutes
|
|
- alert: pg_connections_too_high
|
|
expr: sum(pg_stat_activity_count) BY (environment, fqdn) > ON(fqdn) pg_settings_max_connections * 0.95
|
|
for: 5m
|
|
labels:
|
|
severity: warn
|
|
channel: database
|
|
annotations:
|
|
description: "{{`Postgresql has {{$value}} connections on {{$labels.fqdn}} which is close to the maximum`}}"
|
|
- alert: pg_deadlocks_detected
|
|
expr: sum by(datname) (rate(pg_stat_database_deadlocks[1m])) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warn
|
|
annotations:
|
|
description: "{{`postgresql at {{$labels.instance}} is showing {{$value}} rate of deadlocks for database {{$labels.datname}}`}}"
|
|
title: Postgres server is experiencing deadlocks
|
|
...
|