VMware has been built around the “emulate everything” way of thinking. This is not a bad thing, and it has served them well in the past. They’ve been able to offer a very broad range of supported guest OSes, and they’ve done that very well so far.

Hyper-V is built around synthetic devices to provide improved performance. This also means that their emulation has not been optimized heavily for performance.

Of course this benchmark still serves a purpose: If you plan on running OS on Hyper-V that do not have ICs, expect worse performance.

VMware has been built around the “emulate everything” way of thinking. This is not a bad thing, and it has served them well in the past. They’ve been able to offer a very broad range of supported guest OSes, and they’ve done that very well so far.

Hyper-V is built around synthetic devices to provide improved performance. This also means that their emulation has not been optimized heavily for performance.

Of course this benchmark still serves a purpose: If you plan on running OS on Hyper-V that do not have ICs, expect worse performance.

Agreed. However, if VDI takes off your OS installation responsibilities may change. Then again, Windows 7 will probably be the OS of choice soon enough.

Who knows, MS will probably develop a “Windows VM” OS tailored, and licensed, for VDI. If I can think of it then I’m sure somebody in Redmond is way ahead of me!

Agreed. However, if VDI takes off your OS installation responsibilities may change. Then again, Windows 7 will probably be the OS of choice soon enough.

Who knows, MS will probably develop a “Windows VM” OS tailored, and licensed, for VDI. If I can think of it then I’m sure somebody in Redmond is way ahead of me!

I understand your point, and I had a similar debate with myself about reporting these benchmarks on VM /ETC. In the end I decided that thehypervisor.com post was significant because Hyper-V is being marketed as a free, enterprise production ready alternative to ESX. The tests were also fair in that both products were configured consistently – ie no guest tools, performing same tasks, and running on the same hardware. If the reality is that a hosted virtualization product designed for desktop testing and development out performs Hyper-V in any capacity it’s worth talking about.

Hopefully, we will soon see benchmark tests where Domain Controllers, Messaging Servers, Database Servers, Terminal Servers, etc. are compared head to head on the various virtualization platforms with the proper, optimized configuration of each product (installations of guest tools, etc)