Storj incident

Performance Impact

Resolved after 3 hours 20 minutes, affecting AP1 - API and EU1 - API and 1 more, on May 22, 2025.

postmortem May 23, 2025, 05:20 PM UTC

On May 22, 2025 from 00:12 to 02:54 UTC Storj experienced a service disruption causing elevated error rates and increased request latency that affected the US1 API, Gateway, Linksharing, and US1 - Select services. We discovered lock contention triggered by high-load delete operations. In the short term, we are artificially slowing down some of these intensive requests to leave needed headroom. We will eliminate the lock contention going forward.

Started
May 22, 2025, 01:53 AM UTC
Resolved
May 22, 2025, 05:13 AM UTC
Duration
3h 20m
Detected by Pingoru
May 22, 2025, 01:53 AM UTC

Affected components

AP1 - APIEU1 - APIUS1 - APIAP1 - GatewayEU1 - GatewayUS1 - GatewayUS1 - Select

Update timeline

  1. investigating May 22, 2025, 02:09 AM UTC

    We are investigating reports of performance impacts to one or more components of our system.

  2. investigating May 22, 2025, 02:09 AM UTC

    We are continuing to investigate this issue.

  3. monitoring May 22, 2025, 02:47 AM UTC

    A fix has been implemented and we are monitoring the results.

  4. resolved May 22, 2025, 05:13 AM UTC

    This incident has been resolved.

  5. postmortem May 23, 2025, 05:20 PM UTC

    On May 22, 2025 from 00:12 to 02:54 UTC Storj experienced a service disruption causing elevated error rates and increased request latency that affected the US1 API, Gateway, Linksharing, and US1 - Select services. We discovered lock contention triggered by high-load delete operations. In the short term, we are artificially slowing down some of these intensive requests to leave needed headroom. We will eliminate the lock contention going forward.

Your product runs on more than Storj

Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.

Add your stack →