Goal

Investigate automatic enablement of vNUMA for VMs, which requires more than x cores. Purpose of this epic is to post a VEP about automatic enablement of vNUMA in VMs and remove dependency between vNUMA and huge pages.

User Stories

• As a vm owner, I do not want my VM with numa to depend on huge pages, because the cluster admin might not have enabled huge pages.
• As a cluster administrator, I want to set a policy for automatic numa enablement, so that I can ensure large, performance-sensitive VMs are scheduled optimally
• As a VM owner, I want to create a VM guest aware of the physical NUMA topology including CPU and memory nodes, so that my VM guest can utilize this information for scheduling 

Non-Requirements

• List of things not included in this epic, to alleviate any doubt raised during the grooming process.

Notes

• Any additional details or decisions made/needed