proxy-pool/deploy/prometheus/rules/proxy-pool.yml

49 lines
1.6 KiB
YAML

groups:
- name: proxy-pool
rules:
- alert: ProxyPoolGatewayHighErrorRate
expr: |
sum(rate(proxy_pool_gateway_requests_total{result="error"}[5m]))
/ clamp_min(sum(rate(proxy_pool_gateway_requests_total[5m])), 1) > 0.02
for: 10m
labels:
severity: warning
annotations:
summary: Gateway 错误率持续高于 2%
- alert: ProxyPoolGatewaySnapshotStale
expr: proxy_pool_snapshot_age_seconds > 60
for: 2m
labels:
severity: critical
annotations:
summary: Gateway Snapshot 已超过安全陈旧时间
- alert: ProxyPoolNoAvailableSlots
expr: sum(proxy_pool_available_slots) == 0
for: 1m
labels:
severity: critical
annotations:
summary: Gateway 可分配容量耗尽
- alert: ProxyPoolProviderFetchErrors
expr: sum by (upstream) (rate(proxy_pool_provider_fetch_total{result="error"}[10m])) > 0.2
for: 10m
labels:
severity: warning
annotations:
summary: Provider Fetch 错误持续发生
- alert: ProxyPoolCheckerBacklog
expr: proxy_pool_checker_queue_depth > 10000
for: 5m
labels:
severity: warning
annotations:
summary: Checker 队列积压
- alert: ProxyPoolExtractionConflict
expr: sum(rate(proxy_pool_extraction_total{result="conflict"}[5m])) > 0
for: 5m
labels:
severity: warning
annotations:
summary: 独占提取发生持续事务冲突