Date: Sun, 12 Nov 2006 07:16:10 +0800 From: David Xu <davidxu@freebsd.org> To: Bruce Evans <bde@zeta.org.au> Cc: cvs-src@freebsd.org, src-committers@freebsd.org, cvs-all@freebsd.org Subject: Re: cvs commit: src/sys/kern sched_4bsd.c Message-ID: <200611120716.10773.davidxu@freebsd.org> In-Reply-To: <20061112031308.I69769@delplex.bde.org> References: <200611111311.kABDBVNH042993@repoman.freebsd.org> <20061112031308.I69769@delplex.bde.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sunday 12 November 2006 00:22, Bruce Evans wrote: > On Sat, 11 Nov 2006, David Xu wrote: > > davidxu 2006-11-11 13:11:30 UTC > > > > FreeBSD src repository > > > > Modified files: > > sys/kern sched_4bsd.c > > Log: > > Unbreak userland priority inheriting in NO_KSE case. > > Is this what made the non-KSE case unusable? At least with the load > average bug fixed, it gave very unfair scheduling, and would only start > about 4 concurrent hog processes on a 2-way SMP system. > > Improvements in some benchmarks may have depended on the bugs. Maybe > a random load average is optimal for some loads :-). > > Bruce No, this change is unrelated, the bug is in kern_idle.c, John should use mi_switch(), not the choosethread(), otherwise the loadavg is not maintianed correctly. David Xu
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200611120716.10773.davidxu>