Performance Testing with Hyper-V RC1
1/23/2008 -- Comments

I wrapped up a quick round of performance testing with the Release Candidate 1 of Hyper-V (Included with Windows Server 2008 RC1) using the same test that I used with RC0. The initial test with RC0 was just to measure how well Hyper-V distributed the system resources among 8 virtual machines that were under load. In the case of RC0, and now in RC1, it appears that Hyper-V does a pretty good job of evenly distributing these system resources. The test showed that the variation in performance between the 8 VMs was small.

By using the same test (same server, storage, and test application) it is now also possible to compare the performance of RC0 vs RC1. The performance guy from the Hyper-V team at Microsoft claims on their performance blog page that performance is improved with RC1, which were able to confirm with an increase of 3% in Orders Per Minute and a 5% decrease in average response time. These percentages are not large, but they are improvements!

Todd -- Comments




Perfmon with Hyper-V
1/15/2008 -- Comments

While testing and evaluating the new beta of Hyper-V that is included with Windows Server 2008 I have run across some interesting performance monitor stuff.

First a little background - I have been testing and evaluating the performance of VMs on VMware's ESX server since early 2004 with the first whitepaper I'm aware of that took an detailed look at the performance of VMotion. So I have been using esxtop ever since to monitor the performance of ESX servers.

Windows Server 2008 RC1 has a new Perfmon that is much improved over previous versions, so I was really looking forward to using it for my Hyper-V testing. The first testing that I did with W2K8 RC0 showed that Hyper-V (called Windows Server Virtualization at the time) was able to evenly distribute limited resources across 8 VMs all under load. When using perfmon to monitor the CPU during these tests - it at first looked like the server wasn't loaded at all. I was looking at the standard %Processor Time for the entire server. I knew that the load I was running should be pushing the server well over %50 utilization, so I started digging into this new perfmon to see what was going on.

I found a set of counter objects that were labeled as hypervisor. Here there were Hypervisor Virtual Processor, Hypervisor Root Virtual Processor, Hypervisor Root Partition, Hypervisor Partition, and Hypervisor Logical Processor. It seemed that surely one of these would give me the overall CPU utilization that I was looking for, but it wasn't really clear which one was the counter to look at. As this is still beta code, there was no documentation for these counters to clearly state what each one meant. I decided in the end that the CPU utilization wasn't really that important to report as part of my results, and I just decided to look at it again when the next beta was released.

It seemed like a big issue to me because it would be possible for admins to look at %Processor Time and see a low utilization number while the system was actually very heavily loaded with several very active virtual machines.

With the Hyper-V beta that is included with W2K8 RC1 (released in Dec 07) I am currently doing a new round of testing to see if there is any change in performance. I'm doing the same test with the DVD Store database, but this time the perfmon results are very different. The %Processor Time for the server now seems to reflect the activity of the virtual machines (or partitions as they are referred to in perfmon).

I'm still working on finalizing the results of the RC1 testing - I'll have an entry here when they are ready.

Todd - Comments




Disk Management in Windows Server 2008 RC1
1/8/2008 -- Comments

Immediately after finishing the post on performance testing of Windows Server Virtualizaiton testing, Microsoft released W2K8 release candidate 1 with a updated version of their virtualization layer. The virtualizaiton role is now referred to as Hyper-V.

I've set out to do a new round of testing with Hyper-V and W2K8 RC1. However, I ran into a problem getting connected to the iSCSI LUN on the MD3000i. I was unable to get the Disk Management tool to load from within Server Manager. At first I thought that it was an issue with how I setup the iSCSI initiator on WK8, but some google searches revealed that this was a more generic issue with the Disk Management tool. And infoworld reviewer Paul Venezia ran into the exact same problem as me during his review.

I was able to workaround this by using the DISKPART command line utility to mount the drive that resided on the MD3000i. I was using the same LUN as with my previous testing, so I just needed to use the DISK ONLINE command to get my drive up and running, but there are other commands such as CREATE and FORMAT that can be used to get a brand-new LUN partitioned and ready for use.

I was also able to boot the VMs from the previous testing, proving that they are portable. I will most likely recreate new VMs however, to evaluate the create VM wizards in this new version.

Todd - Comments