Windows Experience Index – Parallels vs. Fusion: How Do They Stack Up?

Since the release of Parallels 5 I have been a huge fan.  Previous to that, I really liked VMware Fusion as the product was much more mature and seemed more stable.  I really had no means to measure performance other than to gauge it by my perception over regular use.

Earlier this week, VMware announced their VMware Fusion 3.1 beta, which I had to run out and try.  I like to keep tabs on both of these products and am always curious when either of them releases an update.

That being said, I downloaded the beta ad built up a new Windows 7 virtual machine, installed the machine additions and played around a little bit.

In the past I’ve done things like measure the boot time for the operating system on each product and in most cases Parallels topped Fusion.  Especially after Parallels released version 5, the gap between those numbers seemed to grow especially when it came to the amount of time it takes to come back on a resume.

As part of my test I also built a new Parallels virtual machine with Windows 7 installed.  I thought an equal way to measure the differences would be by running the tests that provide the results of the Windows Experience Index.  The scale of the Windows Experience Index ranges from 1.0 to 5.9. A higher base score generally means that your computer will perform better and faster than a computer with a lower base score, especially when performing more advanced and resource-intensive tasks.

This host hardware was an iMac with a Core 2 Duo 2.8 GHz processor and equipped with 4 GB of RAM.  Each virtual machine (although not ran simultaneously) had 1 GB of RAM allocated to it.

So, how did each virtual machine fair?  I was actually very surprised.  As VMware has touted lots of improvements around its graphics driver and performance, it actually seemed slower than the 3.0 release.

Here’s how the numbers stacked up:

VMware Fusion Results:

fusion

Parallels Desktop Results:

fusion

Interestingly enough, it seems that Parallels does a better job in more of the categories than not.  Parallels implementation and support of Aero in Windows 7 seems to be more solid as well.

What has your experience been with these products?  Have you found the optimal virtual machine configuration on your Mac?

VMware Fusion 3 or Parallels 5?

It’s a bitter battle between the two – which provides the best feature set while maintaining optimal performance?  I’ve tried both, been back and forth, and can’t quite decide for myself.  Have you tried either or both?  Which do you prefer and why?

Windows 2008 Hyper-V Resource Kit Now Available

On June 10, Microsoft Press published the new “Windows 2008 Hyper-V Resource Kit” by Robert Larson and Janique Carbone.

For the past year, Shane Burton a fellow Microsoft Product Specialist here at Compellent, and myself have been working with Robert and Janique on this project and providing content, particularly “Notes from the Field” for the book, while our Compellent Marketing Alliance partner, John Porterfield kept us in line.

Compellent is a project sponsor at the Microsoft Partner Solution Center and provided Robert and Janique access to a Compellent Storage Center for testing storage-related scenarios that are included in the book. Compellent users will recognize a lot of the screenshots which were taken directly from the Storage Center Manager.

Shane and I are proud to be contributing authors on this project. We hope the Windows 2008 Hyper-V Resource Kit will prove to be an invaluable reference for administrators and IT pros who are responsible for the architecture, design, implementation and ongoing maintenance of a Hyper-V environment.

The book is now available at Amazon and Barnes & Noble.


Virtualized Performance Part 2: Parallels

A couple of weeks ago I posted a story about virtualized performance where I did a comparison between VMware Fusion and Sun’s VirtualBox.

I wanted to update that story to include some details on Windows performance when Parallels is added to the mix.

Interestingly enough, Parallels really isn’t that much further behind Fusion in terms of average boot time. To be precise, the difference is about .8 seconds between the two. Probably not that noticeable to the average user.

It comes down to features in that case. I also think there is a lot to be said about the stability of Fusion given VMware’s years of experience and product maturity.

This will be a very important year in the Parallels development cycle. We’ll see what they have up their sleeves.

Should You Virtualize Your Exchange 2007 SP1 Environment?

Lots of folks are trying to save money in their data centers by optimizing their infrastructure usage with virtualization.

Interestingly enough, with the release of Hyper-V and Microsoft’s program for hardware virtualization vendors, the support policy for Exchange and other applications has changed.

A couple of weeks ago, a post appeared on the Exchange Team Blog asking the question, “Should you virtualize your Exchange 2007 environment?” They lay out several scenarios where virtualizing at least some of the Exchange infrastructure might make sense.

Take a look here.

Virtualized Performance: Fusion vs. VirtualBox

Been playing around a little bit with VMware’s Fusion 2.0 and Sun’s VirtualBox 2.1.2, two virtualization platforms that are available for Mac users.

I will eventually expand this brief test to include Parallels 4.0, since it seems that Parallels and Fusion are the frontrunners when it comes to virtualization on the Mac platform.

For this initial test, I wanted to understand the differences in which the virtual disks were accessed and how that impacted performance.

Sun’s VirtualBox, although a nice little application for being free, doesn’t allow for the configuration of multiple processors, the network interface binding is a little strange, and merely doesn’t seem to have the flexibility. Fusion (and Parallels for that fact) provides the capabilities to support multiple virtual processors, works great with multiple Ethernet interfaces, and provides better integration into the platform being virtualized.

With that being said, boot time was of particular interest to me. In this scenario, I measured with a stopwatch the time from when I hit the power button on the virtual machine to the time that the GUI was up and the login screen was loaded.

I’m a Windows guy by trade, so naturally I included those numbers, but in the spirit of trying something new, I also loaded Ubuntu 8.10 desktop to see how they compared.

All of the virtual machines were configured for IDE disk access (VirtualBox does offer a SATA option) for the boot time tests. Each virtual machine had the virtualization guest extensions or additions running. Boot time was measured five times each per platform, per virtualization product and then averaged.

When comparing Windows Vista running on Fusion versus Windows Vista running on VirtualBox, Fusion loads Vista 22% (almost 9 seconds) faster than VirtualBox.

Looking at a platform other than Windows, I chose to test Ubuntu, a Linux platform available online for free. In this test, Fusion won again. This time, Ubuntu loaded almost 9% (almost 3 seconds) faster than VirtualBox.

Another interesting point is that VirtualBox supports a virtualized SATA controller. This differs from the standard IDE controller as more of the work (processing) is done by the CPU instead of the controller. I thought it would be interesting to show load times between IDE and SATA.

CM Capture 4Using Ubuntu running on VirtualBox as an example, I found that the SATA configuration actually booted slower than that of a virtual hard disk configured to use IDE. There was almost a 3 second difference between the two.

In one of my next posts I can to cover disk file write performance on the these virtualized platforms. Also look for the addition of Parallels to the mix.

Ballmer on Virtualization

Interesting quote from Steve Ballmer on virtualization that he gave during his September 25 Churchill Club speech:

“If you want virtualization on 80 percent of servers instead of 5 percent of servers, you better not charge three times as much as the price of the server for the virtualization,” Ballmer said. “For certain high-end applications, the approach that VMware has used is a perfectly good approach, but it’s not an approach that is going to lead to virtualization of a high percentage of servers.”

See the whole speech and more details here.