mirror of
https://gitverse.ru/kpa39l/monitoring.git
synced 2026-09-29 09:55:09 +00:00
kpa39l
34 lines
930 B
YAML
34 lines
930 B
YAML
groups:
|
|
- name: garage
|
|
rules:
|
|
- alert: GarageNodeDown
|
|
expr: up{job="garage"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Garage node {{ $labels.instance }} is down"
|
|
|
|
- alert: GarageNoQuorum
|
|
expr: (count(up{job="garage"} == 1) < 2)
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Garage cluster lost quorum (<2 nodes up)"
|
|
|
|
- alert: GarageResyncErrors
|
|
expr: garage_block_resync_error_count > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Garage resync errors on {{ $labels.instance }}"
|
|
|
|
- alert: GarageNodeUnstable
|
|
expr: garage_rpc_node_health_is_up == 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Garage RPC health of some node is down" |