Amazon Web Services incident

Service disruption: Increased Error Rates

Amazon Web Services experienced a major incident on March 2, 2026 affecting Service disruption: Increased Error Rates (global) and Service disruption: Increased Error Rates — global and 1 more component, lasting 50d 18h. The incident has been resolved; the full update timeline is below.

Started: Mar 02, 2026, 12:26 AM UTC
Resolved: Apr 21, 2026, 06:36 PM UTC
Duration: 50d 18h
Detected by Pingoru: Mar 02, 2026, 12:26 AM UTC

Affected components

Service disruption: Increased Error Rates (global)Service disruption: Increased Error Rates — globalAWS Status

Update timeline

monitoring Mar 02, 2026, 12:26 AM UTC

We are seeing significant signs of recovery for AssociateAddress requests, and continue to work toward fully mitigating this issue. This combined with the earlier recovery of the AllocateAddress API means customers can now successfully create and associate new network addresses in the unaffected AZs. Other AWS Services are also now observing sustained improvement as a result of the EC2 Networking APIs recovery. We are now focusing on implementing a change that will allow customers to Disassociate Elastic IP addresses from resources that are impacted by the underlying power issue. We expect this specific mitigation to take another hour to complete. We do not have an ETA for power restoration at this time. For customers that can, we recommend using alternate Availability Zones or other AWS Regions where applicable. We will provide another update by 6:30 PM, or sooner if we have additional information to share.