On August 22, 2025, at approximately 8:00 UTC, we encountered an issue with Block Storage in Osaka, Japan. During the incident, users may have experienced performance degradation.
Our initial investigation into the cause of the performance degradation revealed that two components of our Block Storage service were unreachable. Following initial recovery steps, we restored functionality to one of the components, however the second one remained down. A subsequent on-site inspection revealed that certain power cables were not securely connected to the components which had caused them to become unreachable. Once the cables were properly secured, full functionality was confirmed, and the issue was considered resolved at approximately 13:37 UTC.
To prevent a recurrence, we have reinforced our procedures to emphasize the importance of exercising caution in the datacenter and ensuring that power cables remain undisturbed while other tasks are being carried out.
We also performed an audit to ensure that the remaining power cables are properly seated.
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.