Starting around 23:15 UTC on December 15, 2025, Akamai received several internal alerts indicating issues with some hosts in the US-Southeast (Atlanta) data center (ATL1 DC). The investigation revealed that the issue was caused by a power supply failure in one of the racks in this data center.
Customers with Linodes on these hosts would have experienced an interruption in the service. As part of the mitigation effort, Akamai manually turned down these hosts at around 02:00 UTC on December 16, 2025, and started the drive transplant activity, which was to migrate the customers to another rack. Drive transplant was believed to be the fastest mitigation action, without knowing the root cause of the outage.
Further investigation indicated that the loss of power supply was due to a planned maintenance activity at the data center. The planned maintenance was communicated to Akamai, but the internal teams missed migrating the customers to another rack (before the maintenance) due to an internal communication gap.
The power supply was restored around 03:10 UTC on December 16, 2025. However, the drive transplant action was in progress at that time, and customer impact continued until the completion of the drive transplant activity at around 04:20 UTC on December 16, 2025.
We will continue to investigate the root cause of the communication gap and will take appropriate preventive actions. We apologize for the impact and thank you for your patience and continued support.
This summary provides an overview of our current understanding of the incident given the information available. Our investigation is ongoing and any information herein is subject to change.