SEATTLE - Amazon's widely used cloud-computing technology suffered significant technical problems in its eastern US operations, taking chunks of Internet-connected services from its customers off-line Tuesday morning.
The company offered few details about the outage, instead pointing to the Amazon Web Services health dashboard, which noted by Tuesday afternoon that the "root cause of this issue is an impairment of several network devices."
The issue, which hit AWS data centres in the eastern United States, had extended to its monitoring and incident response technology, "which is delaying our ability to provide updates."
By late afternoon, the company posted that some issues had been resolved, though it was still "working towards full recovery across services."
A number of AWS customers noted problems with their services late Tuesday morning. Smartsheet, which provides collaboration software, noted on its status page that its service was unavailable "due to an outage in AWS." Asana, which offers project management services, noted that some of its offerings were unavailable because of the AWS outage.
The outage hampered Amazon's business as well. The company's vast warehouse operations, which also use AWS, saw computer systems disrupted, spokesperson Richard Rocha said in an email. Computer systems at one Midwest warehouse were disrupted starting Tuesday morning, a warehouse worker said late in the day.
"We're all just standing around," said the worker, who spoke on the condition of anonymity because they weren't authorised to talk publicly.
And Amazon's own Ring home security business noted on its website that its app was having problems saving changes made by customers, as well as live views from its cameras failing to connect to the app. Ring spokeswoman Emma Daniels said the services' issues were related to the AWS problems.
Amazon spokesperson Kristin Brown declined to offer details about the outage beyond what the company posted on the AWS dashboard. (Amazon founder Jeff Bezos owns The Washington Post.)
A year ago, AWS experienced a major outage that took down large swaths of the Web, including Ring, iRobot and The Washington Post. In a lengthy post-mortem at the time, AWS said its giant Northern Virginia data centre began to fail after the company started to make "a relatively small addition of capacity" to the system. But because of "an operating system configuration," the new capacity set off a series of errors that overwhelmed Amazon's network of servers.
AWS is the world's largest provider of cloud-computing services, which let customers rent data storage and processing capabilities over the Web instead of running their own data centres.
In 2020, AWS held 40.8% of the worldwide market for infrastructure cloud services, according to market research firm Gartner. Its closest rival, Microsoft, held 19.7% of the global market.