Cloud · Amazon Web Services
AWS US-EAST-1 use1-az4 thermal event
- Started
- May 7, 2026, 23:20 UTC
- Resolved
- May 9, 2026, 03:04 UTC
- Duration
- 27h 44m (from provider timestamps)
- Affected
- Amazon EC2, Amazon EBS, Elastic Load Balancing, Amazon EKS, Amazon ElastiCache, Amazon Redshift, Amazon OpenSearch Service, Amazon MSK, AWS NAT Gateway, AWS IoT Core, Amazon SageMaker
- Cause
- Preliminary causeTemperatures rose in a single data center in Availability Zone use1-az4 of US-EAST-1, and servers shut themselves down when they passed operating thresholds, cutting power to EC2 instances and EBS volumes. AWS shifted traffic away from the zone and spent most of the event bringing cooling capacity back online. AWS has not said what caused the cooling loss.
- Was it an attack?
- Not stated
- State
- resolved
Anatomy
1. Trigger
Cooling failure
2. Already broken
None stated
3. What made it spread
None stated
4. Blast radius
single zone: us-east-1 (use1-az4)
5. Cause category
Power or cooling
Labels follow the root-cause taxonomy. A person's change is recorded as the trigger and the missing safeguard as what was already broken; “human error” is never a cause here.
How the explanation changed
May 8, 2026 · Preliminary cause
“We have experienced an increase in temperatures within a single data center, which in some cases has caused impairments for instances in the Availability Zone.”
AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log)
May 8, 2026 · Preliminary cause
“During such an event, servers automatically shut down when the temperatures exceeded the operating thresholds in order to protect the hardware.”
AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log)
May 9, 2026 · Preliminary cause
“The issue was caused by a thermal event resulting in a loss of power.”
AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log)
Impact, as reported
- scope: one data center in one Availability Zone (use1-az4), according to AWS Health Dashboard (AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log)).
- residual impairment at resolution: a small number of instances and volumes, according to AWS Health Dashboard (AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log)).
- Coinbase trading: extended outage of core trading services, according to Coinbase (via CoinDesk) (CoinDesk: Coinbase blames AWS for hours-long crypto trading outage (8 May 2026)).
Every figure is attributed to whoever stated it. Crowd reports are labelled user reports and never treated as users affected.
Other Amazon Web Services incidents
Sources
- AWS Health Dashboard history JSON (US-EAST-1 EC2 'Increased Error Rate and Latency' event log) (provider, read November 17, 2026)
- AWS Health Dashboard (provider, read November 17, 2026)
- Network World: AWS hit by US-East-1 outage after data center thermal event (11 May 2026) (news, read November 17, 2026)
- CoinDesk: Coinbase blames AWS for hours-long crypto trading outage (8 May 2026) (news, read November 17, 2026)
Last verified November 17, 2026. Spot an error? The methodology page says how corrections work.