Langfuse incident

Degraded LLMaJ execution in EU

Resolved after 1 hour 18 minutes, affecting EU (cloud.langfuse.com) (LLM-as-a-judge) and US (us.cloud.langfuse.com) (LLM-as-a-judge) and 1 more, on August 18, 2026.

resolved Aug 18, 2026, 01:25 PM UTC

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

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

Affected components

EU (cloud.langfuse.com) (LLM-as-a-judge)US (us.cloud.langfuse.com) (LLM-as-a-judge)HIPAA (hipaa.cloud.langfuse.com) (LLM-as-a-judge)JP (jp.cloud.langfuse.com (LLM-as-a-judge)

Update timeline

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

    Eval execution in EU region is taking longer than usual

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

    Eval execution in EU region is taking longer than usual

  3. 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.

  4. 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.

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

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

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

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

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

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

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

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

Your product runs on more than Langfuse

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 →