|
A power outage in one of Amazon Web Services’ data center has caused downtime for Elastic Compute Cloud customers early Wednesday. Service outage lasted about 44 minutes.
Apparent Networks said in a statement that the services AWS provided in one availability zone in its Northern Virginia data center lost connectivity and causing downtime that began around 3:30 a.m. EST and lasted until about 4:20 a.m.
The cloud service monitoring company said Amazon later confirmed that a power loss caused the connectivity failure.
In its “service health” log, AWS said the outage was caused by failure of a component of its power distribution system, followed by failure of a second component installed for redundancy, before the first component could be repaired.
The company did not specify which components failed, but explained that power was restored and the VM instances on servers that had been down began to restore, once “defective power distribution units were bypassed.”
AWS first reported that it was “investigating connectivity issues” at the facility at 10:08 p.m. EST. About 20 minutes later, the company said it was “experiencing power issues for a subset of instances in a single availability zone” in the region.
The provider said it restored most of the VM instances around 3:40 a.m. EST and was continuing “to attempt to restore all instances or notify users directly if the instances (remained) degraded.”
The last reported incident of extended downtime of an AWS client happened in October, when part of the company’s public cloud was attacked by a hacker.
Related news: Amazon cloud to extend over Asia-Pacific
Related analysis: Lessons learned from one of Amazon’s cloud computing client’s prolonged downtime
Related news: Scientists expose attack vulnerability within public clouds
Keywords: Amazon cloud, cloud computing, Amazon cloud failure, downtime, AWS, EC2, Amazon Cloud Services, Elastic Compute Cloud, data center outage | | 
