On 10/16/07, Ola Bini <[EMAIL PROTECTED]> wrote: > > Something is seriously wrong with your setup. The fact that non-JIT is > faster is indicative of something really strange. > My computer goes significantly slower without JIT. > > Is this for Petstore 1? Are you sure it's not just swallowing exceptions? >
My setup: Hardware: IBM Thinkpad R40, an older one (Intel(R) Pentium(R) M processor 1300MHz, 1024MB cache, 1199.90 bogomips) OS: Ubuntu 7.04 Kernel: 2.6.20-16-generic #2 SMP Sun Sep 23 19:50:39 UTC 2007 i686 GNU/Linux Ruby: ruby 1.8.5 (2006-08-25) [i486-linux] Database: MySQL 5.0.38 Application: Petstore rev 177, http://tw-commons.rubyforge.org/svn/petstore/trunk Java: build 1.6.0-b105 Rails: 1.2.3 ar-record: 0.5 echo 'load "script/benchmark_action"' | ~/jruby_/trunk/jruby/bin/jruby -J-server -J-Djruby.jit.enabled=true -J-Djruby.objectspace.enabled=falsescript/console ar_jdbc I also checked ar_jdbc.log, but found nothing (but tons of SQL queries and stuff like that) Maybe I'm doing something wrong, but I can't imagine what it is. Previous tests on a Windows box showed the same results. I find it also interesting that the numbers you posted yesterday or so show the same MRI/JRuby ratio like mine do when the JIT is turned *ON*. When I disable the JIT, the ratio is better than with your results. What's the version of your JVM? Christian
