Alerts/Solidev · Engine
Productionv2.4.1 · ap-northeast-2
활성 알람
1
오늘 발생
14
평균 해결
8m
침묵 중
3
active alerts
P1GPU memory > 92% · worker-03fire14:11 · on-call
P2p95 latency > 300ms · chest-ctack13:48 · solidev
P3Queue depth > 50 · 30 minresolved12:40 · auto
alert rules · 5 enabled
rulewindowsevescalation
GPU memory > 92%5mP1PagerDuty
p95 latency > 300ms10mP2Slack · #infer
Queue depth > 5030mP3Email
Worker down1mP1PagerDuty
Error rate > 1%10mP2Slack · #infer
● READYrps246/sp95184msGPU73%
uptime42d 8hUTF-8 · ko-KR