I think this is a pretty significant change in behavior for a minor release, Jeff. According to the interested parties:
"I'm reporting a performance (message rate 16%, latency 3%) regression when using PSM that occurred between OMPI v1.6.5 and v1.8.1. I would guess it affects other networks too, but I haven't tested. The problem stems from the --enable-smp-locks and --enable-opal-multi-threads options." So, this has been in effect the entire 1.8 series and now you want to significantly alter the behavior. I'm of the opinion that we should live with the mistake in the 1.8.x series and provide users with clear guidance on the default behavior and advice for disabling the threading support that is consistent across this series. 1.9.x is a clean slate. My $0.02 Josh On Wed, Nov 5, 2014 at 11:51 AM, Jeff Squyres (jsquyres) <jsquy...@cisco.com > wrote: > On Nov 5, 2014, at 11:43 AM, Mike Dubman <mi...@dev.mellanox.co.il> wrote: > > > sorry, > > >>>"now we use only this "--enable-mpi-thread-multiple" and it worked." > > > > I meant it worked fine before the "configure logic" changes. > > It went back to the way it was in in the v1.6 series. > > The issue is that --enable-mpi-thread-multiple carries a performance > penalty on the v1.8 branch. On master, we need to sort these kinds of > issues out so that there is no/minimal performance penalty. > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > _______________________________________________ > devel mailing list > de...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel > Link to this post: > http://www.open-mpi.org/community/lists/devel/2014/11/16208.php >
