Amazon Web Services, a leader in the cloud infrastructure market, reported a major outage on Monday, taking down numerous major websites.
Many sites came back online within a few hours, although Downdetector showed another spike in user reports around noon ET of outages at Amazon, AWS and Alexa.
Amazon said in a blog post Monday afternoon that AWS customers were still experiencing "increased error rates" when trying to launch new instances in EC2, its popular cloud service that provides virtual server capacity.
The company also confirmed that the outage impacted Amazon.com, some of its subsidiaries and AWS customer support operations.
"We are working to fully restore service as quickly as possible," the company wrote.
The outage was first reported at 3:11 a.m. ET in AWS' main US-East-1 region hosted in northern Virginia. A notice on AWS' status page said it was experiencing DNS problems with DynamoDB, its database service that underpins many other AWS applications.
DNS, or Domain Name System, translates website names to IP addresses so browsers and other applications can load.
AWS cited an "operational issue" affecting "multiple services" and said it was "working on multiple parallel paths to accelerate recovery," in an update at 5:01 a.m. ET. More than 70 of its own services were affected.
Shortly afterward, AWS said it was seeing "significant signs of recovery."
AWS said in an update at 6:35 a.m. ET that the DNS issue had been "fully mitigated" and that AWS service operations were "succeeding normally."
AWS is the leading provider of cloud infrastructure technology, accounting for around a third of the market, ahead of Microsoft and Google, according to Synergy Research Group. Millions of companies and organizations rely on AWS for cloud computing services, such as servers and storage.