Langfuse incident

Degraded LLMaJ execution in EU

Minor Resolved

Langfuse experienced a minor incident on August 18, 2026, lasting 1h 18m. The incident has been resolved; the full update timeline is below.

Started
Aug 18, 2026, 12:06 PM UTC
Resolved
Aug 18, 2026, 01:25 PM UTC
Duration
1h 18m
Detected by Pingoru
Aug 18, 2026, 12:06 PM UTC

Update timeline

  1. investigating Aug 18, 2026, 12:06 PM UTC

    Eval execution in EU region is taking longer than usual

  2. identified Aug 18, 2026, 12:27 PM UTC

    evaluation throughput was overwhelmed by a slow tenant/model workload, with lock-expiry retries multiplying work; the concurrent worker rollout prolonged the incident.

  3. monitoring Aug 18, 2026, 12:47 PM UTC

    our autoscaling responded slower than expected, but responded nonetheless. the backlog is draining

  4. resolved Aug 18, 2026, 01:25 PM UTC

    Steady throughput for the last 30 minutes. Delay < 5min.