Folks, I invested some time into performance optimization of non-blocking core components in order to push HttpCore 4.3 and HttpAsyncClient 4.0 closer to a GA release. I implemented several local optimizations in the low level transport code and also fixed a bug in the non-blocking connection pool code that can be a major performance inhibitor when executing thousands of small requests in a tight loop.
My performance benchmarks, admittedly very limited and non-comprehensive, now show pretty good results in client side test scenarios for NIO based implementations. In fact, in my tests HttpCore NIO performance matches that of blocking HttpClient even with a very modest number of concurrent connections (<20) which is something I thought I would never see. I am going to prepare HttpCore 4.3 beta2 release incorporating those improvements in a few days. I also ported some of those changes to the stable (4.2.x) branch. If enough people were able to test their applications with the latest 4.2.x snapshot for regressions we could also consider releasing those performance improvements from the stable branch. Please note all said above applies to non-blocking NIO based code only and does not affect blocking HttpCore and HttpClient. Oleg --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
