Files
monitoring/alerts.yml
T

57 lines
1.5 KiB
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: block_resync_errored_blocks > 0
for: 10m
labels:
severity: warning
annotations:
summary: Garage resync errors on {{ $labels.instance }}
- alert: GarageNodeUnstable
expr: cluster_layout_node_connected == 0
for: 5m
labels:
severity: warning
annotations:
summary: Garage RPC health of some node is down
- name: tproxy
rules:
- alert: TProxyDown
expr: up{job="tproxy"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: tproxy-server (vps03) is down or unreachable
- alert: TProxyBackendErrors
expr: increase(tproxy_backend_dial_failures_total[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
summary: tproxy-server backend dial failures (MTProxy unreachable)
- name: vinograd
rules:
- alert: VinogradRostelecomDown
expr: probe_success{job="vinograd_wan"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: Vinograd WAN (Ростелеком) {{ $labels.instance }} is down or unreachable