Date: Mon, 23 Aug 2004 10:43:43 -0700 From: Julian Elischer <julian@elischer.org> To: "Simon L. Nielsen" <simon@freebsd.org> Cc: freebsd-current@freebsd.org Subject: Re: PLEASE TEST: IPI deadlock avoidance patch Message-ID: <412A2CCF.4050809@elischer.org> In-Reply-To: <20040823111304.GA767@zaphod.nitro.dk> References: <20040822115345.Y94593@carver.gumbysoft.com> <20040823111304.GA767@zaphod.nitro.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
Now to start work on the preemption hangs.. Simon L. Nielsen wrote: >On 2004.08.22 12:05:39 -0700, Doug White wrote: > > >>Hey folks, >> >>If you have a reasonably fast i386 or amd64 multiprocessor and/or >>hyperthreading machine and are experiencing reproducible hangs during -j >>buildwords and other highly parallel operations, please try this patch: >> >>http://people.freebsd.org/~dwhite/smp_rv_mtx.patch >> >> > >With stock CURRENT my Dual XEON test system has hung most of the time >when I did a parallel buildworld. Since I applied this patch last >night the system has completed 12 -j100 buildworlds, and it's still >going on, without any problems :-). > >Thanks to all the people who have worked on this problem! :-) > >BTW. these tests were with the 4BSD scheduler, I'm going to try to >switch to ULE soon and se how that works out. > > >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?412A2CCF.4050809>