Re: Artemis(2.4.0) JMS transactional session queue send/receive performance

2018-02-22 Thread Youyu Shao
Hi Mike, Thank you very much for your input. In my case we do have SSD. After some reading and fumbling, I am able to get the about 2000 sending/receiving operations per second, with one message per transaction. The specific adjustments I have done to achieve the above were: 1. using MAPPED --

Re: Artemis(2.4.0) JMS transactional session queue send/receive performance

2018-02-21 Thread Michael André Pearce
Hi That is very low tbh. It looks like you have very slow disk io, not typical of data centre server grade modern disks. Is this an actual server? Or just your own personal desktop or something? Im taking this from your journal buffer timeout of 706 Your system could perform 0.14 w

Artemis(2.4.0) JMS transactional session queue send/receive performance

2018-02-21 Thread Youyu Shao
Hi, Recently we start evaluating Artemis 2.4.0 JMS queue performance. Our business logic requires the use of transactional session, where publisher sends one message per commit, and consumer receives one message per commit. Our test environment is Windows machine with 4 cores(3.70 GHz), 8 logica