Monitoring
服务监控Service health, latency and incidents across the product fleet.
3 active incidents99.8% uptime
Fleet uptime
99.83%
10 degraded services
p95 latency
508ms
Requests / min
3.5K
5M / 24h
Error rate
0.35%
MTTR
68m
25 incidents / 30d
Services
38
10 need attention
Latency trend
p50 / p95 over 30 days
Uptime trend
Fleet uptime over 30 days
Services
Sorted by error rate
| Service | Status | p95 | Errors |
|---|---|---|---|
web-frontend Analytics Copilot · 1 replicas | Degraded | 316ms | 0.99% |
api-gateway Code Review AI · 1 replicas | Degraded | 694ms | 0.92% |
api-gateway Support Desk AI · 1 replicas | Healthy | 668ms | 0.9% |
ai-inference Marketing OS · 2 replicas | Degraded | 1.5s | 0.88% |
web-frontend Code Review AI · 1 replicas | Healthy | 263ms | 0.67% |
web-frontend Support Desk AI · 1 replicas | Healthy | 195ms | 0.66% |
ai-inference Support Desk AI · 2 replicas | Degraded | 1.2s | 0.66% |
api-gateway Analytics Copilot · 1 replicas | Degraded | 805ms | 0.65% |
ai-inference Translate Pro · 2 replicas | Degraded | 1.2s | 0.65% |
api-gateway Marketing OS · 2 replicas | Degraded | 571ms | 0.6% |
ai-inference Invoice AI · 2 replicas | Healthy | 1s | 0.55% |
worker-queue Marketing OS · 1 replicas | Degraded | 938ms | 0.53% |
ai-inference CRM Copilot · 2 replicas | Healthy | 1.3s | 0.51% |
ai-inference Legal AI · 2 replicas | Degraded | 1.1s | 0.43% |
Incidents
Recent and open
| Incident | Severity | Status | Started |
|---|---|---|---|
Redis eviction storm collapsed cache hit rate Resume AI | High | investigating | 18h ago |
Elevated 5xx responses from api-gateway Resume AI | Critical | investigating | 20h ago |
Postgres connection pool exhausted Support Desk AI | Medium | identified | 24h ago |
Auth tokens rejected after key rotation Invoice AI | Low | resolved | 1d ago |
Redis eviction storm collapsed cache hit rate Support Desk AI | High | resolved | 2d ago |
CDN cache purge caused an origin overload Translate Pro | Medium | resolved | 4d ago |
Auth tokens rejected after key rotation Analytics Copilot | High | resolved | 5d ago |
Failed migration required an emergency rollback Recorder AI | Medium | resolved | 9d ago |
Elevated 5xx responses from api-gateway Docs Chat | Low | resolved | 9d ago |
Queue consumer lag on the events topic Code Review AI | Low | resolved | 10d ago |