At beginning of February 2006 VMware released a 22-pages whitepaper comparing performances of its ESX Server 3.0.1 against Xen 3.0.1, where Xen resulted slightly inferior.
Because of restrictive VMware EULA XenSource (as well as other virtualization competitors) is not able to respond with same tone, providing their own analysis of benchmarks.
But it’s clear XenSource is not satisfied with current state of things and just released a counter-attack paper where results are completely different, but are not showing ESX Server performances measurements:
VMware is tilting at windmills once again. For a start, Xen 3.0.3 is not a commercial product, it’s a code base. Second, Xen 3.0.3 only had partial support for hardware virtualization, and third, the VMware results are off – it seems ESX can get more than 1Gb/s out of a GigE NIC! Also, we have no idea what VMware did to build their Xen bits – a good example of why we care so much about what can and and cannot be called Xen.
We have of course run exactly the same benchmarks, on the same kind of machine, pitting our commercial XenEnterprise product against ESX. As a result, I now understand why the ESX EULA forbids us from publishing the results without VMware’s approval – they would find the results extremely embarrassing.
All of XenSource’s commercial products match or beat ESX performance for Windows in all but a couple of benchmarks…
XenSource is waiting for official permission from competitor before releasing the complete paper, but making available the stripped version will be hard for VMware to not allow it, considering open source community and industry pressure to have a second opinion.
This counter-attack arrives in a very timely moment considering XenSource is a Microsoft partner since July 2006 and VMware challenged Redmond company on Windows licensing just few days ago.