文件

48 行
1.6 KiB
YAML

groups:
- name: hyb-oa-slo
rules:
- alert: HybOAApiAvailabilityLow
expr: |
(
sum(rate(http_server_requests_total{route=~"/api/.*",status!~"5.."}[5m]))
/
clamp_min(sum(rate(http_server_requests_total{route=~"/api/.*"}[5m])), 0.001)
) < 0.999
for: 10m
labels:
severity: warning
slo: availability
annotations:
summary: "hyb-oa API availability below SLO"
description: "API availability fell below 99.9% for 10m. Check recent releases and feature-flag changes."
- alert: HybOADashboardP99High
expr: |
histogram_quantile(
0.99,
sum by (le, route) (
rate(http_server_request_duration_seconds_bucket{route=~"/api/dashboard/.*"}[5m])
)
) > 0.5
for: 15m
labels:
severity: warning
slo: latency
annotations:
summary: "hyb-oa dashboard P99 latency above SLO"
description: "Dashboard API P99 exceeded 500ms for 15m. Investigate DB load and aggregation queries."
- alert: HybOAApi5xxSpike
expr: |
sum(rate(http_server_requests_total{route=~"/api/.*",status=~"5.."}[5m]))
/
clamp_min(sum(rate(http_server_requests_total{route=~"/api/.*"}[5m])), 0.001)
> 0.01
for: 5m
labels:
severity: critical
slo: availability
annotations:
summary: "hyb-oa API 5xx ratio spike"
description: "API 5xx ratio is above 1% for 5m. Consider force_off for high-risk feature flags."