Is that 24,000 connections every 10 seconds? nice!
On 11/29/06, Michael Bauroth <[EMAIL PROTECTED]> wrote:
Trustin Lee schrieb: > Hi Gaston, > > On 11/29/06, Gaston Dombiak <[EMAIL PROTECTED]> wrote: >> >> Sounds good to me. BTW, do you have an estimate (or range) for MINA 2.0 ? >> Today I read that trunk (i.e. 2.0) is 10%-20% faster than 1.0 or branch >> 1.1. We are now in the process of adopting MINA as the networking layer >> for Wildfire. I would like to see if our roadmaps/milestones match >> nicely. :) FYI, I'm using branch 1.1 for our development. > > > There's no estimate so far actually. What we actually have to focus is > documentation of MINA 1.0. You won't see any difference in performance if > your connection last for a long time. It only affects when the number of > connections are small and disconnection occurs often. Of course, it's > entirely up to your team whether to use trunk or not. :) > > Trustin If you refer to my last post: There is a measurable difference between 0.x and newer versions, but non documented from my side between 1.x and trunk. The mentioned 10%-20% come here from a test with Java 6 against Java 5, which I have made with the trunk. The test performed very well under heavy load (24.000 connections sent every 10 seconds 300 Bytes of bundeled string messages, which were demultiplexed to different decoders, decoded to POJOs and written to a MySQL database as batches). All this happened on a simple Xeon Dualcore with at least under 50 percent of load. Best Regards Michael
