ESX Server 3.0.1 vs XenEnterprise 3.2 performance comparison

One of most visited articles since February has been VMware ESX Server 3.0.1 vs Xen 3.0.3 performance comparison.

In that article I reported about a VMware paper highlighting ESX Server 3.0.1 commercial hypervisor performances superiority over Xen 3.0.3 open source hypervisor.

Such claims from VMware cannot be easily confuted because of company’s EULA, which prevents anybody publishing of any comparison without explicit permission. But XenSource, which founded the Xen project and is currently offering a commercial solution based on it, found such behaviour pretty unfair and VMware paper’s conclusions misleading, so that, in March, challengingly published a similar paper, this time comparing ESX Server 3.0.1 against its XenEnterprise 3.2.

To avoid any lawsuit XenSource ripped off ESX Server benchmarking, and asked VMware for full publishing permission.

Now VMware, possibly under the community pressure waiting to see real numbers or just to limit negative advertising its EULA is providing, allowed publishing of XenSource complete comparison.

This document reveals very similar performances between two virtualization platforms, and in some tests shows XenEnterprise 3.2 (which is still in beta and it’s based on Xen 3.0.4) outperforming ESX Server 3.0.1, so that you can read in conclusion:

VMware appears to have failed to appreciate the difference between our Xen open source code base and our commercial XenServer products. For example, had they read the release notes for Xen 3.0.3, they would quickly have established that Intel VT was only partially supported in that release. Moreover, XenSource’s Xen Tools for Windows, which optimize the I/O path, were not installed. The VMware benchmarks should thus be disregarded in their entirety.

Our performance results show convincingly that XenEnterprise 3.2 performs equally well or better than VMware ESX Server 3.0.1 in all but a couple of tests. Given that we have not spent much time on optimizing our product for traditional benchmarks we are pleased to see that there is essentially no difference between the two products. Our tests highlighted a couple of areas in which ESX marginally outperforms XenEnterprise, namely on compile time, and for Netperf TX. XenEnterprise outperforms ESX on the Passmark memory operations. XenEnterprise scales well to utilize multiple CPUs to allow a wide variety of workloads to be run. Additionally the scalability testing found that XenEnterprise
provides similar scalability to ESX when additional virtual machines are added to the platform.

VMware also appears to have under-appreciated the performance advantages of the latest generation of Intel and AMD processors with built-in support for virtualization. Although VMware’s legacy technology cannot exploit these features, XenEnterprise’s high performance is proof that these technologies deliver tremendous price/performance advantages to end users…

Read the whole comparison whitepaper here.