Starting around 23:18 UTC on May 11th, 2025, Compute customers were unable to login or access Compute instances hosted on AP-Northeast-2 (Tokyo 2) & JP-TYO-3 (Tokyo 3) data centers. Akamai's investigation revealed that the impact was caused due to network connectivity issues at the internet exchange provider side.
Akamai's network team worked with the internet exchange provider and confirmed that the issue started following a network change at their end. For immediate mitigation, Akamai's network team applied the deny-all rule to the affected links with the internet exchange. The impact was mitigated at around 00:40 UTC on May 12, 2025. We will continue to work with the internet exchange provider to understand the root cause and will take appropriate preventive actions.
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.