Platform health

Live

Traffic, errors and saturation across every production service.

Requests

1458.1k

8.1%

vs previous day: 1348.8k

Error rate

0.43%

2.4%

vs previous day: 0.42%

p95 latency

310ms

1.3%

vs previous day: 314ms

Saturation

60%

3.2%

vs previous day: 62%

Request throughput

31,982

total, last 24h

04:0008:0012:0016:0020:00

Incident activity

  • Checkout API timeoutsCritical

    payments-edge · 09:12

    The charge endpoint exceeded its 8s budget on six consecutive calls, holding four orders at authorisation.

  • Retry storm containedMajor

    invoice-worker · 08:47

    Backoff was applied after a vendor 503 spike, capping retries and draining the queued backlog.

  • Search index degradedMinor

    search-api · 08:05

    Read latency on the embeddings index rose to 1.9s, slowing lookups for eleven minutes before recovering.