Incident
Start:
October 15, 2026 08:20
Resolved:
October 15, 2026 08:20
Retrospective: London Storage Issues
Summary of impact:
Between approximately 06:49 and 07:52 UTC, some virtual machines in the London region had storage operations (I/O) paused. During this period, affected instances may have been unresponsive or logged storage timeout warnings.
Cause:
An update to our internal routing configuration interrupted communication between platform components. As a result, some storage requests could not be completed until communication was restored.
Resolution:
Our engineering team identified the cause and restored normal operation. The platform has been stable since 07:52 UTC. A permanent fix has been applied to stop this issue from recurring, and we are reviewing our change procedures to further reduce the risk of similar events.
Recommended actions:
No customer action is normally required, and storage operations resumed automatically once service was restored. If an instance is still not responding, we recommend restarting it. If any issues persist, please contact our support team with your instance details.
We sincerely apologise for any disruption this may have caused to your services. We appreciate your patience and remain committed to providing a reliable platform.
Updates
-
2026-10-15 08:20:54 Issue is resolved. See recommended actions above for next steps. If an instance is still not responding, we recommend restarting it. If any issues persist, please contact our support team with your instance details.