It is understood that many of the outages link to issues at Amazon Web Services, which offers the infrastructure that underpins much of the internet.

Many of the world’s biggest websites and apps, including Perplexity, Canva, Signal, Amazon, Roblox, Coinbase and Atlassian, began experiencing issues at around 8am this morning (20 October).

Downdetector, the popular crowdsourced disruptions reporting platform, has recorded a spike in user reports for nearly 50 websites over the last few hours.

It is understood that the outages link to issues at Amazon Web Services (AWS), which offers the infrastructure that underpins much of these  internet sites.

At 11.35am, AWS reported a return of many services. “The underlying DNS issue has been fully mitigated, and most AWS Service operations are succeeding normally now.

“We continue to work toward full resolution.”

AWS’ health dashboard confirmed “significant error rates” earlier this morning, finding that the issues appear to be related to “DNS resolution of the DynamoDB API endpoint in US-EAST-1”.

“This issue also affects other AWS services in the US-EAST-1 Region,” it said, as well as global services or features that rely on its US-EAST-1 endpoints.

“Perplexity is down right now. The root cause is an AWS issue. We’re working on resolving it,” said the AI search engine start-up’s CEO Aravind Srinivas, in a post on X.

“We are aware that Signal is down for some people. This appears to be related to a major AWS outage,” posted Meredith Whittaker, the president of Signal Foundation.

The BBC reports that several banks have been affected, with customers facing issues including card payments being declined.

75 AWS and Amazon services have also been affected by the outage, from AWS Systems Manager and Network Firewall to the Support Centre. “During this time, customers may be unable to create of update support cases,” one of the updates read.

This follows just months after a major outage at Google Cloud disrupted platforms such as OpenAI, Spotify, as well as Google’s own services, including Gmail and Google Drive.

At the peak of the incident, Downdetector recorded nearly 15,000 incident reports relating to the incident. The disruption ended up affecting IT service management company Cloudfare, which is estimated to be used by roughly 24m websites.

Don’t miss out on the knowledge you need to succeed. Sign up for the Daily Brief, Silicon Republic’s digest of need-to-know sci-tech news.

Updated, 11.40am, 20 October 2025: This article was updated with the latest statement from AWS on the outage.