Starting at 5:03 PM PDT, we experienced increased ENI attachment times for newly launched EC2 instances and newly attached ENIs within a single Availability Zone (USE1-AZ4) in the US-EAST-1 Region. The issue was caused by increased resource contention in the subsystem responsible for the propagation of ENI network mappings within the affected Availability Zone. Engineers worked to identify the root cause of the resource contention and took steps to resolve it. By 7:45 PM PDT, ENI attachment times had returned to low single digit minute levels, which allowed most workflows to proceed and limited the impact to other AWS services. Some internal services, such as EMR, weighted away from the affected Availability Zone, which mitigated the impact. ENI attachment times continued to improve as the resource contention issue was addressed, and by 12:50 AM PDT, ENI attachment times had returned to normal levels. The issue has been resolved and the service is operating normally.
Between 11:12 AM and 11:45 AM PDT, we experienced elevated API errors and latencies and connectivity issues in the EU-NORTH-1 Region. The issue has been resolved and the services are operating normally.