Mehmet D. AKIN a écrit :
Still benchmarks presented in that document seems contradicting Trustin's benchmarks. In the presentation it says Grizzly with Async web is just a little faster than a "C based web server " but almost two times faster and scalable than Mina.But Trustin's test also shows that Mina based Async Web server is a little faster than a C based Server (Apache HTTP) so there is something fishy going on here.. If only we had a wider benchmark suite which tests for different types of protocols and loads, instead of microbenchmarks. Mehmet
I think that Mladen just summarize the situation with benchmarks : everyone has one... :)
From my POV, and as I conducted a lot of benchmark on Apache Directory Project, benchmarks are good for internal use, just to see haow good you are or how far from the competitors, or to be able to answer stupid questions lie "can you afford 100 000 requests per second?" when you *know* that your potential client is expecting to have 100 req/s max ;) ...
Nothing more. But doing benchmarks, fixing the code, and getting better number is definitively great fun !
Emmanuel
