In an article posted to the AWS website, the company explained that an automated process caused the outage, which began around 10:30 a.m. ET (Eastern Time Zone) in the Northern Virginia area ( US-EAST-1), reports The Verge.
“An automated activity to scale the capacity of one of the AWS services hosted in the core AWS network triggered unexpected behavior from a large number of customers inside the internal network,” the company said. .
“This resulted in a sharp increase in connection activity which overwhelmed the networking devices between the internal network and the main AWS network, causing communication delays between these networks,” the company added.
According to the report, this issue even impacted Amazon’s ability to see exactly what was wrong with the system.
This prevented the company’s operations team from using its real-time monitoring system and the internal controls they typically rely on, which is why the outage took so long to be corrected.