Amazon Web Services says it has resolved the major outage that caused widespread connectivity problems for numerous popular websites and apps globally.

In an update on Monday, AWS confirmed that the “underlying DNS issue has been fully mitigated,” adding that most of its service operations are now running normally.

“Some requests may be throttled while we work toward full resolution,” it added.

The company said the problem originated from DynamoDB, a database service hosted in one of Amazon’s key data centres in Virginia, United States, known as US-EAST-1.

It advised users still affected by the outage to try flushing their DNS caches.

The disruption caused significant problems for major websites and apps worldwide, including AI startup Perplexity, trading app Robinhood, messaging app Signal, and crypto exchange Coinbase, all of which reported issues linked to the AWS outage.

“Perplexity is down right now. The root cause is an AWS issue. We’re working on resolving it,” Perplexity CEO Aravind Srinivas said in a post on X.

AWS is one of the world’s largest cloud computing providers, competing with Google and Microsoft to deliver on-demand computing power, data storage, and other digital services to businesses and institutions.

Because so many companies depend on its infrastructure, problems with AWS servers can cause widespread disruption across the internet.