Everything is operational again.

We have started live migrating vms over to the new healthy node.

We are adding a new node XS-03, which will replace XS-01 and allow us to live migrate effected customers over to the new node.

We are still actively looking into the issue, it seems to be an underlying issue with the hypervisor operating system.

We are currently seeing elevated errors on our control (start/stop/kill) endpoint towards this machine.

We are actively investigating this.

All enterprise customers have been live migrated to a healthy node without any impact or disruption.