On Fri, Apr 20, 2007 at 12:13:19PM -0700, Sean McNeil wrote: > Greg Lewis wrote: > >On Fri, Apr 20, 2007 at 03:09:34AM -0400, Kris Kennaway wrote: > > > >>On Fri, Apr 20, 2007 at 04:59:12PM +1000, Michael Vince wrote: > >> > >>>Kris Kennaway wrote: > >>> > >>>>On Thu, Apr 19, 2007 at 12:32:53PM +1000, Michael Vince wrote: > >>>> > >>>> > >>>>>Hey All, > >>>>>I been benchmarking Diablo Java under AMD64 on 6.2R and using the same > >>>>>methods I posted a while ago detailed somewhat here > >>>>>http://lists.freebsd.org/pipermail/freebsd-java/2006-August/005576.html > >>>>> > >>>>>The difference here is that libthr now works under Amd64. > >>>>>But it appears libthr to be about half the speed of libpthread under > >>>>>AMD64 mode which is the opposite behavior when using it under i386. > >>>>> > >>>>> > >>>>That's contrary to my benchmarks :( Dunno what might be wrong though, > >>>>assuming you have checked all the obvious. > >>>> > >>>>Kris > >>>> > >>>> > >>>OK, > >>>I did more testing and it appears the 6.1R Diablo Java binary package on > >>>Amd64 on 6.2/libthr appears to be the problem, it's as much as 60% > >>>slower then libpthread. > >>> > >>>On 6.2R Amd64 I built the ports version of jdk1.5 and libthr appeared to > >>>be around 25% faster then libpthread. > >>>But using the Diablo jdk package for 6.1R on 6.2 under libpthread is > >>>even faster by around 15% over anything I could do for any combination > >>>of Java and libthr. > >>> > >>>I would guess that a new 6.2R Amd64 Diablo package would probably turn > >>>it around again for libthr and I would guess it would again around 20% > >>>faster then anything I can get from Java under AMD64 6.2R, what's going > >>>on here exactly I don't know. > >>> > >>That's weird, I thought the diablo package was just compiled from > >>jdk1.5. It could be there was a performance regression from a change > >>made to the port after 6.1 - it would be great if you can follow it up > >>with the java@ people. > >> > > > >Diablo is compiled from the partner source. jdk15 is built on the SCSL > >release. The SCSL release was done when 1.5.0 was released. The current > >release of Diablo is based off of 1.5.0_07, so there were changes in > >between > >the two that may/will affect performance. > > > I am confused why this is thought to be a problem with Java. Is it not > true that libthr does not allow new threads to be scheduled on other > CPUs?
Yes, that is not true. You are confusing it with the old libc_r. Kris _______________________________________________ [email protected] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-performance To unsubscribe, send any mail to "[EMAIL PROTECTED]"
