> you have tp put it in a VM , which gives you a performance penalty

This claim is dubious for many configurations of hardware accelerated virtualization. The hardware creates another ring 0 for each guest kernel, and guests run at the same level as the host. It's true that layering things like filesystems and networking incur overhead, but it's just as easy to pass through a physical disk, and bridge virtual TAP interfaces to physical NICs.

Hardware virtualization is very flexible, and there's a configuration out there that will meet the performance requirements of the vast majority of projects.