Friday, January 23, 2009

IBM again leads Oracle (and everyone else) on SPECjAppServer2004 performance and cost

I recently had someone email me on a performance topic and they referenced WebSphere Application Server's SPECjAppServer leadership. They actually didn't know that IBM regained total leadership in this benchmark late last year. Maybe the fun of the holidays didn't allow folks to notice? I wanted to post this update, so if other folks missed it they would notice.

In these times of tough economic conditions, it's really important to focus on total cost of ownership and ways to improve efficiency. IBM's continuous leadership in performance proves we care about performance as it relates to end to end J2EE enterprise computing scenarios. This increased performance means you can host more workload and applications on the same resources that you used before. Our performance engineers are continuously improving performance of your applications and we use SPECjAppServer to demonstrate those improvements.

Sometimes people ask me how SPECjAppServer matters to them. It's this continuously increasing performance that matters to them. Originally SPECjAppServer helped the J2EE programming model transition from a programming model to a capable enterprise ready programming model (stressing basic performance and scalability). Now, SPECjAppServer leadership helps customers know the middleware they are buying from IBM is helping them improve their efficiency.

This view is a technology view (leadership at 22634.13 JOPS), however it has business impacts as well. That result was achieved at roughly one half of the cost of our closest competitor. That just acquisition cost. If you consider the power savings on top of that you're not only being more green, but saving green.

Again, great work by the WebSphere Application Server performance team!

Disclaimer: SPEC is a non-profit organization that establishes, maintains and endorses standardized benchmarks to measure the performance of the newest generation of high-performance computers. Its membership comprises leading computer hardware and software vendors, universities, and research organizations worldwide. For complete details on benchmark results and the Standard Performance Evaluation Corporation, please see www.spec.org. Competitive claims reflect results published on www.spec.org as of January 23, 2009 when comparing SPECjAppServer2004 Total JOPS on all published results.

2 comments:

Anonymous said...

You mention cost. Can you please post the cost of this configuration with 3-5 years TCO (HW+SW+Service)?

Thanks.

Chris Adkin said...

The excellent nineteen (used to be eleven) best practices for J2EE development on the developer works website should be mandatory reading for anyone developing on WebSphere. The reason I say this is because there should be something similar to cover performance best practices. If applications are not architected, designed and coded correctly, people may not realize the full benefits of the fine work that goes into honing the performance of WebSphere, due to such efforts being undermined by the use of "performance anti-patterns". Off the top of my head as I write this response, the following sort of things spring to mind:-

1. Usage of design patters for performance: service locator, data transfer object, session facade etc . . .

2. Caching of lookup data from the database in WebSphere.

3. Preference of shared nothing architectures over distributed object architectures.

4. The batching and consolidation of calls to integration end points in order to minimize performance loss due to network latency and round trips.

5. Use network deployment friendly designs, use of DistribMap etc . . .

This should be trivial work with the wealth of knowledge at IBM. There is the excellent Coding Applications for Scalability and Performance red book, which is in fact better than a lot of publications I've paid good money for. If possible it would still be nice to see a boiled down list of performance best practices.

I'm so glad to see that this blog is not one of those faux vendor blogs that does not take replies.

As to the holiday period, people must have been having way too much fun not to realize that IBM still topped the jAppServer2004 table ;-) All the best to you and the team, have a good 2009.

Regards,

Chris