A few weeks ago we discovered that the performance of our Windows 2012 guest on KVM hypervisors was very bad and it was caused by the "Performance per Watt (DAPC)" profile in the BIOS of our Dell m620 servers. After that, I got curious and started to test with other systems: Linux guests and bare metal. According to the Dell BIOS Performance and Power Tuning documentation, the difference between the performance per watt (dapc) and performance per watt (os) profile should be only a few percent:
If you run Windows 2012 guests on RHEV or Ovirt (or probably any KVM based hypervisor) and notice performance is lower than expected, take a look at the power management in the BIOS of your servers. After lot's of test benchmarks with mixed results with Windows 2012 guests on RHEV with Dell m620 blades, we finally discovered our performance problems were caused by the system profile "Performance Per Watt (DAPC-System)" in the BIOS. Changing this profile to "Performance Per Watt (OS)" almost doubled the performance for some CPU intensive tasks in our case. Power usage of a (mostly idle) dual socket blade increases with 30-50 Watts when you change this. Used servers in production are using already more power and I guess the difference will be less there.