Code Archaeology

Nov 21, 2025 · Operations

AWS US-EAST-1 Outage: DynamoDB DNS Race Condition Triggers EC2 Congestion Collapse

This analysis of the October 2025 AWS US-EAST-1 outage details how a race condition in DynamoDB's automated DNS management system caused DNS resolution failures, triggering a 12-hour EC2 congestion collapse due to lease backlog and an NLB health-check failover driven by stale network configuration.