Starting at approximately 22:15 UTC on December 8, 2024, end-user traffic routed through the Stockholm data center began experiencing connectivity issues over both IPv4 and IPv6. As a result, Akamai Cloud computing customers encountered reduced availability and/or degraded performance. While IPv4 connectivity stabilized around 23:00 UTC on December 8, 2024, IPv6 connectivity remained impacted until ~00:05 UTC on December 9, 2024.
Our investigation found that the 45 minutes of packet loss over IPv4 resulted from link congestion caused by an external service provider’s maintenance activity. In response, our mapping system automatically initiated safety mechanisms that reduced overall datacenter traffic, effectively mitigating the impact of the congestion. We are refining our processes to prevent similar disruptions during future external driven maintenance activities.
For IPv6 connectivity, the disruption was linked to an incorrect router configuration at one of our transit providers in Stockholm. This issue remained hidden under normal conditions - due to redundant transit links - but became exposed when all the links went offline during the external driven maintenance. By restoring a redundant transit link around 00:05 UTC on December 9, 2024, we alleviated the IPv6 connectivity impact. We continue to collaborate with our transit provider to identify the root cause of the issue and implement additional safeguards.
We sincerely apologize for any inconvenience caused and appreciate your patience and continued support. We are committed to continuously enhancing our systems and implementing measures to prevent similar incidents from occurring in the future. This summary provides an overview of our current understanding of the incident given the information available. Our investigation is still ongoing and any information herein is subject to change.