[Paris] Multiple hypervisors are experiencing issues
Resolved:
Status: We are currently investigating infrastructure issues impacting multiple hypervisors in the Paris availability zone.
Update 06:22 UTC – The investigation remains in progress.
Update 06:23 UTC – The orchestration system has been temporarily stopped.
Update 06:24 UTC – A potential cooling issue has been identified in one of our Paris datacenters.
Update 06:44 UTC – Root cause investigation is ongoing, and preparations to relaunch orchestration are underway.
Update 07:08 UTC – Orchestration has been relaunched and is now catching up.
Update 07:25 UTC – We have observed that additional hypervisors in the same datacenter are also experiencing issues, and our teams are actively investigating.
Update 07:45 UTC – The datacenter team is actively addressing the cooling issue, with resolution expected by the end of the morning. In the meantime, most infrastructure has been migrated to other datacenters within the same availability zone.
Updates
08:20 UTC – The affected hypervisors are back online. The access logs stack is currently being restarted.
We’re monitoring the situation to ensure full service stability.
Systems have remained stable since the last update. As no new alerts or impacts were observed during the monitoring period, the incident is now closed.