Related Tags
Permalink | 
Post to Twitter |
Comments (3) |
Views (16366) |
Post to Twitter |
Comments (3) |
Views (16366) |
30 Jun 2008 04:21 PM EDT
posted by Bryon Thomas
One of the most common questions from the field, especially after Citrix acquired XenSource, was "What type of performance do I get if XenApp is virtualized on the server?". This Tolly Group Report conducts a performance evaluation of Citrix XenApp in a 64-bit virtualized server environment using Citrix XenServer Enterprise 4.1.0. Test highlights include:
- Achieves maximum performance of users when XenApp runs on a 64-bit XenServer virtual machine, operating with as little as 7.6% overhead versus running XenApp in a comparable physical server environment
- Virtualized 64-bit XenApp exhibits 82% higher performance than a 32-bit virtualized environment using XenServer
- Provide features to allow XenApp to run at optimal performance levels with default configuration
If you're interested in running XenApp with XenServer, be sure to check-out these other white papers:
- Benefits of Virtualizing Citrix XenApp with Citrix XenServer
- Optimizing XenApp Performance with XenServer 4.1.0 Enterprise Edition
- XenServer for XenApp Reference Architecture, Design Considerations, and Implementation Guide by Citrix Consulting
Comments (3)
Jul 17, 2008
Anonymous says:
So let me get this straight, Tolly Grp want me to believe that a 64-bit guest wi...So let me get this straight, Tolly Grp want me to believe that a 64-bit guest with 14 GB Memory can run more sessions that a 32-bit guest with 3 GB memory, tell me that can't be true!
I am being hopelessly idealistic in expecting that TG might have considered a like for like comparison and run a 32-bit Enterprise Edition guest with 14 GB Memory along side the 64-bit guest, or better yet attempted to run 3 or 4 32-bit SE guests as a more meaningful, and dare I say it real world, performance comparison?
I am totally lost for words...
Jul 17, 2008
Simon Bramfitt says:
I'd agree that the 32-bit test results are of only limited value here. Wi...I'd agree that the 32-bit test results are of only limited value here.
Without any data to indicate which resource bottleneck was responsible for limiting the performance of the 32-bit environment it isn't possible to make any meaningful assessement of XenServer's performance when running a 32-bit OS. Assuming that the processor had cycles to spare (and there's no reason to assume otherwise) then running either 32-bit Enterprise Edition or having additional 32-bit guests would have provided a better comparison. Similarly running a single 32-bit physical server instance to provide a comparison with the 32-bit virtual would have made for more of an 'apples to apples comparison'.
Still if you are able to run 64-bit Windows, then there's some value to be had from the report.
Jul 18, 2008
Bernie Hannon says:
The objective of the Tolly Group report was to present independent findings...The objective of the Tolly Group report was to present independent findings of a study undertaken by Citrix to validate assumptions that enhancements made to XenServer 4.1 would make it more condusive to virtualizing XenApp. Their independent audit included an analysis of both 32 and 64 bit VMs vs. a single physical XenApp server. The report concluded that single 32 bit XenApp VMs running on XenServer performed with 21.5% overhead vs a single physical 32 bit XenApp server, while a 64 bit XenApp VM performed with only 7.6% overhead vs a similar phyical server. There are of course, dozens, if not hundreds of possible permutations from a configuration standpoint to consider, including running multiple VMs. These were not explored in this particular study but are the subject of numerous follow-up studies being conducted right now within Citrix and with customers and SIs. This study served as a basis for creating benchmarks for these new studies to compare their results against. It was never suggested that customers should only operate XenApp on single 64 bit VMs; but rather that customers should determine for themselves where they are most comfortable in terms of 32 vs 64 bit and their desire to spread their users across multiple instances of XenApp VMs. This was clearly stated in the white paper mentioned in Bryan's post, "Optimizing XenApp perfomance on XenServer 4.1 Enterprise Edition". What was also stated is the fact that a 32 bit Windows OS is unable to utilize more than 3Gb of RAM in a XenApp environment, no longer a limitation with a 64 bit Windows OS. Our study applied the additional resources available in the 64 bit OS environment which included RAM, page file, and CPU (XenApp in particular performs better with increases in RAM and page file size) to both the physical server and a VM and pointed out the lowest possible virtualization overhead available when all such resources were made available to the VM.
Is virtualizing 64 bit XenApp realistic for all customers? Not likely, but they now have one more incentive to consider migrating to 64 bit than before. Still, virtualizing 32 bit XenApp has demonstrated to have potentially enough benefits for many to consider virtualizing XenApp without migrating to 64 bit. As much as we would like to have produced a one-size-fits-all roadmap to virtualizing XenApp, the reality is that each customer will need to determine their own path. For many XenApp customers, the traditional driver behind server virtualization, server consolidation, might not be the primary driver for them. It may instead be to realize one or more of the other potential benefits available with virtualization, flexibility, managability or availability. The Tolly Group report has pointed out the once formidable roadblocks to virtualizing XenApp, are now going away and the benefits of server virtualization with XenServer are more available than ever before.
Bernie Hannon
Director of Solutions Testing and Certification
Citrix Virtualization and Management Division
Add Comment