WebSphere Loves Windows…Who Knew?

  • Article

For years I’ve heard people say that Microsoft technology is great for mid range solutions. I can’t tell you how many CIOs have told me things like “we use WinTel for department level applications but the big iron apps run on Unix.” There’s a general belief in the industry that the further you get into the datacenter, the less Microsoft technology you tend to find. While license numbers, data from IDC and other major third parties paint a different story, we decided it was time to put ourselves to the test against one of the biggest players in the space – AIX running on optimized IBM Power6 with WebSphere.

About a year ago, I blogged about some .NET / Windows Server benchmark testing results produced by Greg Leake. After taking some well deserved time off, Greg went back to the lab, expanded his testing and agreed to help get to the bottom of the “back office” debate. For the first time, the results include IBM hardware (POWER6) which allows us to evaluate price / performance using typical customer configurations. In an era of cost cutting and the need to squeeze as much optimization out of systems as possible, we think customers will find this information very interesting.

Let’s start with costs… Greg’s findings demonstrate that customers save up to 81% in total system costs by running applications on Microsoft .NET and Windows Server 2008 vs. IBM WebSphere 7 on POWER6/AIX. The study also showed that customers who run their IBM WebSphere 7 applications on Windows Server 2008 and Hewlett Packard/Intel 64-bit blade servers can save up to 66% in total system costs when compared to running the same applications on IBM WebSphere 7 on an IBM Power6/AIX platform. These results illuminate significant savings for businesses of all sizes, and particularly speak to the value of the Windows Server platform. Our hope is that people are able to make use of these findings to get more for their money, either by making new investments or by maximizing assets they are already using. Who knew WebSphere and Windows Server were such a match?

Most folks tend to buy into the potential for cost savings but speculate that they give up performance to get it. The study also found that for the hardware configurations tested the Microsoft .NET Framework on Windows Server 2008 handles 57% more load than WebSphere 7 running on IBM Power6/AIX. We also found that Windows Server 2008 running WebSphere 7 handles 37% more load than IBM WebSphere 7 running on POWER6.

So, what do these findings really mean and why am I sharing them with you today? A few important things to know:

1) Windows Server and the .NET Framework continue to be a powerful, leading combination for application development, deployment and management.

2) Customers who have made a bet on WebSphere can improve performance and reduce costs by running WebSphere on Windows.

Please visit https://www.wholoveswindows.com/websphere/ to read more about these results and check out the .NET StockTrader downloads. We think the .NET StockTrader is a GREAT example of how small bits of innovation can have BIG impact. Don’t take our word for it – these sample applications and guidelines are available to anyone. Instructions on how to replicate the testing we conducted are also available here, and I strongly encourage customers, and all third parties, to conduct tests for themselves. Let us know what you think

Comments

  • Anonymous
    April 30, 2009
    PingBack from http://microsoft-sharepoint.simplynetdev.com/websphere-loves-windows%e2%80%a6who-knew/

  • Anonymous
    April 30, 2009
    Websphere on Windows Outperforms Websphere on AIX by 37%, Who Knew?

  • Anonymous
    April 30, 2009
    Microsoft is taking it's "I'm a PC" campaign to the server and busting some myths in

  • Anonymous
    May 01, 2009
    Yesterday I blogged about some recent findings regarding both system cost and performance when comparing

  • Anonymous
    May 05, 2009
    Why test an HP blade against an enterprise server like a 570?  The 570 is better suited to large scale server consolidation as a system that supports 32-cores and 3/4TB of memory.  Why pit blade against blade and test against the JS22?  Why not put your money where your mouth is against the new JS23/JS43?  If I read the pdf correctly you also test 8-core POWER6 single system with 32GB of memory against a scale out cluster of 4 blades each with 4-cores and 32GB of memory.  8-core 32GB vs. 16-cores 128GB?  Sorry, this benchmark seems a bit tainted to anyone who knows what a 570 is.

  • Anonymous
    May 06, 2009
    The comment has been removed

  • Anonymous
    May 12, 2009
    The comment has been removed

  • Anonymous
    May 13, 2009
    Well, if you have not noticed there are new benchmark results for the Trade application running as a

  • Anonymous
    May 13, 2009
    Interesting feedback and objections.  Since I ran these tests over the past 6 months, I have re-posted your objections along with my responses on my blog at: http://blogs.msdn.com/gregleak/ Greg Leake Microsoft Corporation PS:  excellent debate!