Our proactive monitoring has indicated that a potential CPU chip fault on the node: ATL102KVM. This may be causing CPU related performance degradation to some VM's.
During this emergency maintenance event we will be re-applying thermal paste and re-seating both of the processors on the node, as well as using this as an opportunity to perform a BIOS update to the physical host node.
Due to the nature of the issue causing symptoms that could be negatively impactful to production, we will be proceeding with this emergency maintenance as soon as possible (within approximately one hour from the time of this message). During this maintenance, access to your VM may be unavailable for up to 2 hours, though, we will do everything in our power to expedite and to restore services as soon as humanly possible.
We will be updating our status page at https://status.racknerd.com/ - please follow this page for updates. Upon the completion of this maintenance we will be posting an update on the status page. Please feel free to open a support ticket in your client area if you have any questions or concerns regarding this emergency maintenance event.
UPDATE: We have successfully re-applied thermal paste and re-seated the processors at this time, and VM's are now back online on ATL102KVM. We will need to schedule one more maintenance next week to wrap this up. We will email all customers on ATL102KVM again to schedule another maintenance window at that time.