1 criticalUpdated 2s ago · auto-refresh 30s

System overview

5 / 6 services healthy, 18.42M requests in the last 24h, 99.94% uptime.

Uptime 24h

99.94%

+0.02%

p50 latency

128ms

+4ms

Error rate

0.80%

+0.2pp

Deploys today

+8

ml-inference · p95 latency · last 60 min

2,240ms

↑ 4,660%

Services

Production services

api-gatewayv2.18.4 · tpe1

4.8k rpm · p50 48ms · p95 142ms · error 1.20%

Healthy

ml-inferencev3.4.2 · tpe1

1.8k rpm · p50 680ms · p95 2240ms · error 3.40%

Degraded

embeddings-servicev1.22.0 · tpe1

720 rpm · p50 82ms · p95 280ms · error 0.40%

Healthy

job-queue-workerv1.5.8 · tpe1

2.3k rpm · p50 0ms · p95 0ms · error 0.20%

Healthy

vector-storev0.9.4 · tpe1

3.4k rpm · p50 24ms · p95 96ms · error 0.80%

Healthy

webhook-dispatcherv2.0.1 · tpe1

680 rpm · p50 18ms · p95 64ms · error 0.10%

Healthy

Alerts

2 open

p95 latency exceeded 2s

ml-inference · 18m ago

p95=2240ms · threshold=1500ms · sustained 12m

Error rate elevated to 3.4%

ml-inference · 18m ago

baseline 0.5% · affected endpoint /infer/chat

Rate limit approaching ceiling

api-gateway · 34m ago

82% of 10k rpm quota used

Deployments

Status	Service	Env	Commit	Branch	Author	Duration	Started
building	ml-inference	staging	a4c8de2	feat/batching-v2	Zhou H.	3m 12s	2m ago
ready	ml-inference	prod	e12f8b1	main	Chen Y.	4m 52s	18m ago
ready	api-gateway	prod	7f28c41	main	Liu K.	2m 08s	2h ago
ready	embeddings-service	preview	ba1d9ef	fix/memory-leak	Wang R.	3m 42s	4h ago
error	api-gateway	preview	1c3a582	feat/rate-limit	Zhou H.	0m 48s	5h ago
ready	job-queue-worker	prod	8d4e07a	main	Chen Y.	1m 24s	5h ago