Internet users around the world faced widespread disruption early Monday because of a problem at Amazon’s cloud computing service that took down dozens of major online services, including social media site Snapchat, video games Roblox and Fortnite, and chat app Signal.
About three hours after the outage began, Amazon Web Services said it was starting to recover from the problem.
Amazon Web Services provides behind-the-scenes cloud computing infrastructure to many government departments, universities and businesses, including The Associated Press, which allows them to provide online services.
On DownDetector, a website that tracks online outages, users reported issues with Snapchat, Roblox, Fortnite, online broker Robinhood, the McDonald’s app and many other services. DownDetector said the problems were “possibly related to issues at Amazon Web Services.”
Coinbase and Signal both said on X that they were experiencing issues related to the AWS outage.
Even Amazon’s own services weren’t immune. Users of the company’s Ring doorbell cameras and Alexa-powered smart speakers posted on DownDetector that they weren’t working, while others said they were unable to access the Amazon website or download books to their Kindle.
Amazon pinned the outage on issues related to their domain name system, an apparatus that converts web addresses into IP addresses so websites and apps can load on internet-connected devices.
The first signs of trouble emerged around 3:11 a.m. Eastern Time, when Amazon Web Services reported on its Health Dashboard that it was “investigating increased error rates and latencies for multiple AWS services in the US-EAST-1 Region.”
Later, the company reported there were “significant error rates” and that engineers were “actively working” on the problem.
Around 6 a.m. Eastern Time, the company said it was seeing recovery across most affected services. “We can confirm global services and features that rely on US-EAST-1 have also recovered,” it said, adding that it is working on a “full resolution.”
This is not the first time issues with Amazon’s key services have caused widespread disruptions. Many popular internet services were down after a brief outage in 2023. AWS’s longest outage in recent history occurred in late 2021, when companies, everything from airline reservations and auto dealerships to payment apps and video streaming services, were affected for more than five hours. Outages also happened in 2020 and 2017.
The company reported that 64 internal AWS services were affected by the issue.
AWS customers include some of the world’s biggest businesses and organizations.
“So much of the world now relies on these three or four big (cloud) compute companies who provide the underlying infrastructure that when there’s an issue like this, it can be really impactful across a broad range, a broad spectrum” of online services, said Patrick Burgess, a cybersecurity expert at U.K.-based BCS, The Chartered Institute for IT.
“The world now runs on the cloud,” and the internet is seen as a utility like water or electricity, as we spend so much of our lives on our smartphones, Burgess said.
And because so much of the online world’s plumbing is underpinned by a handful of companies, when something goes wrong, “it’s very difficult for users to pinpoint what is happening because we don’t see Amazon, we just see Snapchat or Roblox,” Burgess said.
“The good news is that this kind of issue is usually relatively fast (to resolve)” and there’s no indication that it was caused by a cyber incident like a cyberattack, Burgess said. “This looks like a good old-fashioned technology issue, something’s gone wrong and it will be fixed by Amazon,” he said.
There are “well-established processes” to deal with outages at Amazon Web Services, as well as rivals Google and Microsoft, which together provide most of the world’s cloud computing infrastructure, Burgess said, adding that such outages are usually fixed in “hours rather than days.”
Amazon Web Services said at about 6:30 a.m. Eastern time that “most AWS Service operations are succeeding normally now.”
The US-EAST-1 Region, located in Northern Virginia, serves as AWS’s largest and oldest data center cluster, making it a critical point of failure when problems arise. Many companies default to hosting services in this region due to its extensive features and service availability, creating concentration risk.
Domain name system failures represent particularly disruptive outages because DNS serves as the internet’s address book, translating human-readable website names into machine-readable IP addresses. Without functioning DNS, services remain operational but unreachable by users.
The three-hour resolution time demonstrates AWS’s incident response capabilities, though the global impact during those hours affected millions of users and likely cost businesses significant revenue during the early morning disruption.
Amazon’s Seattle headquarters houses much of the AWS leadership team, though the actual infrastructure experiencing problems operates in Virginia data centers thousands of miles away, illustrating the geographic distribution of cloud computing operations.
The outage’s impact on Amazon’s own Ring and Alexa products highlights how even the service provider becomes vulnerable to its own infrastructure failures, demonstrating the challenge of maintaining redundancy when operating at massive scale.
The concentration of internet infrastructure among Amazon, Microsoft, and Google creates systemic risk where a single provider’s failure cascades across seemingly unrelated services, raising questions about whether regulatory intervention is needed to ensure redundancy and resilience.
