Increased Latency and Failures for SSH Git Operations

Updates timeline

1. Investigating May 5, 04:49 PM UTC

   We are investigating reports of impacted performance for some GitHub services.

2. Monitoring May 5, 04:54 PM UTC

   Between approximately 14:00 and 16:10 UTC, customers using SSH-based Git operations may have experienced elevated latency and failures. HTTP-based operations were not impacted. We've identified a suspected root cause and are working to implement a mitigation to prevent further impact.

3. Investigating May 5, 05:23 PM UTC

   Git Operations is experiencing degraded performance. We are continuing to investigate.

4. Investigating May 5, 05:26 PM UTC

   We're continuing to work on preventing further impact from the earlier issue. No SSH-based impact is expected at this time. We'll post new updates if impact recurs or once our mitigation is in place.

5. Monitoring May 5, 06:25 PM UTC

   The degradation affecting Git Operations has been mitigated. We are monitoring to ensure stability.

6. Monitoring May 5, 06:35 PM UTC

   We've completed our mitigation to prevent further impact. At this time the incident is considered resolved.

7. Resolved May 5, 06:35 PM UTC

   Between approximately 14:00 and 16:10 UTC on May 5, 2026, SSH-based Git operations experienced elevated latency and intermittent failures. On average, the error rate was 0.46% and peaked at 0.6% of SSH write requests. HTTP-based Git operations, including web UI and HTTPS clones, were not affected. <br /><br />The impact was caused by reduced SSH capacity at one of our data center sites. During a period of high traffic, the remaining hosts became overloaded, leading to connection exhaustion and some failures for SSH-based operations. <br /><br />Additional capacity was provisioned to expand SSH capacity and resolve the incident. The expanded capacity was fully online by 18:18 UTC. <br /><br />To reduce the likelihood of similar incidents, we will implement faster scaling solutions for SSH infrastructure and improved alerting for host availability and capacity thresholds.