mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-23 01:47:17 +08:00
72 lines
3.2 KiB
YAML
72 lines
3.2 KiB
YAML
groups:
|
|
|
|
- name: PerconaMongodbExporter
|
|
|
|
|
|
rules:
|
|
|
|
# 1m delay allows a restart without triggering an alert.
|
|
- alert: MongodbDown
|
|
expr: 'mongodb_up == 0'
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: MongoDB Down (instance {{ $labels.instance }})
|
|
description: "MongoDB instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# 1m delay allows a restart without triggering an alert.
|
|
- alert: MongodbReplicaMemberUnhealthy
|
|
expr: 'mongodb_rs_members_health == 0'
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Mongodb replica member unhealthy (instance {{ $labels.instance }})
|
|
description: "MongoDB replica member is not healthy\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: MongodbReplicationLag
|
|
expr: '(mongodb_rs_members_optimeDate{member_state="PRIMARY"} - on (set) group_right mongodb_rs_members_optimeDate{member_state="SECONDARY"}) / 1000 > 10'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: MongoDB replication lag (instance {{ $labels.instance }})
|
|
description: "Mongodb replication lag is more than 10s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# This query mixes old (mongodb_mongod_*) and new (mongodb_rs_*) metric names. It requires the Percona exporter to run with --compatible-mode to expose both.
|
|
- alert: MongodbReplicationHeadroom
|
|
expr: 'sum(avg(mongodb_mongod_replset_oplog_head_timestamp - mongodb_mongod_replset_oplog_tail_timestamp)) - sum(avg(mongodb_rs_members_optimeDate{member_state="PRIMARY"} - on (set) group_right mongodb_rs_members_optimeDate{member_state="SECONDARY"})) <= 0'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: MongoDB replication headroom (instance {{ $labels.instance }})
|
|
description: "MongoDB replication headroom is <= 0\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: MongodbNumberCursorsOpen
|
|
expr: 'mongodb_ss_metrics_cursor_open{csr_type="total"} > 10 * 1000'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: MongoDB number cursors open (instance {{ $labels.instance }})
|
|
description: "Too many cursors opened by MongoDB for clients (> 10k)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: MongodbCursorsTimeouts
|
|
expr: 'increase(mongodb_ss_metrics_cursor_timedOut[1m]) > 100'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: MongoDB cursors timeouts (instance {{ $labels.instance }})
|
|
description: "Too many cursors are timing out\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: MongodbTooManyConnections
|
|
expr: 'mongodb_ss_connections{conn_type="current"} / (mongodb_ss_connections{conn_type="current"} + mongodb_ss_connections{conn_type="available"}) * 100 > 80'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: MongoDB too many connections (instance {{ $labels.instance }})
|
|
description: "Too many connections (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|