Friday, January 8, 2010

WebSphere first on SPECjEnterprise2010 Java EE Benchmark

In case you missed it, we published the first two results for a new benchmark - SPECjEnterprise 2010.

This new benchmark covers the Java EE 5.0 programming model running on an application server. You may remember SPECjAppServer 2004 and our work to lead in that benchmark. Given how old the 2004 benchmark is, it no longer represents the common practices of coding of new applications. This third version of Java enterprise application server benchmark covers areas such as the simplified Java EE 5.0 programming model for persistence and web programming, web services, and messaging.

By being first to publish, IBM continues to demonstrate its commitment to driving standard third-party trusted benchmarking. Also, we show how the WebSphere Application Server really shines on Java EE support in terms of being consistently first to market with highly performant programming models that matter to you. We published both on a simple single server (1) as well as a highly available, scalable cluster configuration (2) which demonstrates WebSphere Application Server 7.0's ability to scale from simple to complex application environments.

If you want to chat about this benchmark, IBM's results, or see some other standardized performance work we're doing at SPEC and can be in the San Jose area at the end of the month, please stop by the "First Joint WOSP/SIPEW International
Conference on Performance Engineering
". I'll be in attendance talking about the SPEC SOA benchmark work.

(1)IBM SPECjEnterprise2010 result of 7903.16 EjOPS using WebSphere Application Server V7 on IBM BladeCenter HS22 (8 nodes, 64 cores, 16 chips) and DB2 9.7 on IBM System x3850 (1 node, 24 cores, 4 chips).
(2)IBM SPECjEnterprise2010 result of 1,013.40 EjOPS using WebSphere Application Server V7 on IBM System x3650 (1 node, 8 cores, 2 chips) and DB2 9.7 on IBM System x3850 (1 node, 12 cores, 2 chips).
Source:; Results current as of 01/08/10.