awesome-prometheus-alerts/dist/rules/mongodb/percona-mongodb-exporter.yml
2024-05-23 12:45:56 +00:00

68 lines
2.9 KiB
YAML

groups:
- name: PerconaMongodbExporter
rules:
- alert: MongodbDown
expr: 'mongodb_up == 0'
for: 0m
labels:
severity: critical
annotations:
summary: MongoDB Down (instance {{ $labels.instance }})
description: "MongoDB instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: MongodbReplicaMemberUnhealthy
expr: 'mongodb_rs_members_health == 0'
for: 0m
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 }}"
- 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: 'avg by(instance) (rate(mongodb_ss_connections{conn_type="current"}[1m])) / avg by(instance) (sum (mongodb_ss_connections) by (instance)) * 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 }}"