From owner-cvs-all@FreeBSD.ORG  Sat Nov 11 23:16:16 2006
Return-Path: <owner-cvs-all@FreeBSD.ORG>
X-Original-To: cvs-all@freebsd.org
Delivered-To: cvs-all@freebsd.org
Received: from localhost.my.domain (localhost [127.0.0.1])
	by hub.freebsd.org (Postfix) with ESMTP id 6A1CA16A403;
	Sat, 11 Nov 2006 23:16:16 +0000 (UTC)
	(envelope-from davidxu@freebsd.org)
From: David Xu <davidxu@freebsd.org>
To: Bruce Evans <bde@zeta.org.au>
Date: Sun, 12 Nov 2006 07:16:10 +0800
User-Agent: KMail/1.8.2
References: <200611111311.kABDBVNH042993@repoman.freebsd.org>
	<20061112031308.I69769@delplex.bde.org>
In-Reply-To: <20061112031308.I69769@delplex.bde.org>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
Message-Id: <200611120716.10773.davidxu@freebsd.org>
Cc: cvs-src@freebsd.org, src-committers@freebsd.org, cvs-all@freebsd.org
Subject: Re: cvs commit: src/sys/kern sched_4bsd.c
X-BeenThere: cvs-all@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: CVS commit messages for the entire tree <cvs-all.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/cvs-all>,
	<mailto:cvs-all-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/cvs-all>
List-Post: <mailto:cvs-all@freebsd.org>
List-Help: <mailto:cvs-all-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/cvs-all>,
	<mailto:cvs-all-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sat, 11 Nov 2006 23:16:16 -0000

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