Home > Intel Communities > Open Port IT Community > Intel® vPro™ Expert Center > Dynamic Virtual Client > Blog > 2008 > January > 25
Up to Blog Posts in Dynamic Virtual Client
Previous Next

Dynamic Virtual Client

Currently Being Moderated
Jason Davidson

Streaming Impact on the Server and Network

Posted by Jason Davidson on Jan 25, 2008 12:31:32 PM

 

Catherine Spencewrote an IT@Intel blog on a recent lab experiment on the impact of various emerging compute models on both the server and network. You can find the blog at: http://communities.intel.com/openport/blogs/client/2008/01/25/streaming-impact-on-the-server-and-network

 

 

-

Several Intel IT folks (and others!) have expressed concern over the back-end implications of hosting a streamed computing solution. How many clients can be supported by a server? How will streaming affect the network? Well, we had the same questions so we constructed a lab experiment to find out.

 

Streaming was more efficient than we expected. We demonstrated that server utilization remained low and network utilization improved over time. We successfully executed a variety of applications including audio and video. We also encountered a few challenges.

 

Want to know more? Read our full report: Streaming and Virtual Hosted Desktop Study

 

 

 

Tags: alternate_compute_models, saas, software_delivery_models, streaming, virtual_hosted_desktop, streaming_computing, client, vhd, thin_client, benchmark, application_delivery, emerging_compute, it@intel, streamed_computing, performance, virtualization


Feb 20, 2008 2:54 PM Tom Farre Tom Farre    says:

I read your report and have a question re: the virtual desktop compared to streaming applications.

 

In your tests you found that virtual desktops ate up more server CPU power than streaming, and that some desktops were disabled by a rogue screen saver. You also found that some conventional desktop functionality did not work with virtual desktops.

 

My question concerns the fact that all of your virtual desktop testing was performed using Microsoft Virtual Server 2005 R2 SP1.

 

Did you consider how the test might have come out if you used VMware, the more mature virtualization software? I just wonder if we can generalize from your test to all virtual desktop implementations, or just those that use Microsoft's technology?

 

Tom Farre

Freelance journalist
Feb 29, 2008 10:06 AM ChristianBlack ChristianBlack    says in response to Tom Farre:

Tom, The short answer to your question is yes, IT@Intel tested the more mature virtualization software. The EULA prevents end users from sharing or publishing any performance details without the explicit consent of VMWare, which we were unable to obtain. To your final question, we ran the test in a MSVS2005 R2 SP1 and were pleasantly surprised with the performance of the homogeneous Microsoft stack, especially given the ‘intensity’ of our workload in comparison to other published office workloads.

Actions

Popular Blog Posts