Beginning on January 16, 2025, at around 18:34 UTC, the Chennai data center began to experience high packet loss. This issue also impacted traffic through other data centers, including Dallas, Melbourne, Sydney, Sao Paulo, Santiago, Paris, Jakarta, Osaka, Tokyo, Kuala Lumpur, Stockholm, Denver, Houston, Miami, Chicago, and Seattle. Investigation revealed that a misconfiguration made by an upstream peer resulted in a leak of Akamai/Linode routes, causing degraded network performance. The issue was mitigated at 22:02 UTC on January 16th, 2025 when Akamai successfully de-peered from the upstream peer. During the impact window, customers may have experienced gateway timeouts when attempting to manage services via Cloud Manager or the Linode API.

Akamai is investigating alerting improvements to help facilitate a quicker response and reduced customer impact in similar situations.

‌

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.