From owner-freebsd-current@FreeBSD.ORG Thu Jul 19 08:16:43 2007 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1B52E16A401 for ; Thu, 19 Jul 2007 08:16:43 +0000 (UTC) (envelope-from marck@rinet.ru) Received: from woozle.rinet.ru (woozle.rinet.ru [195.54.192.68]) by mx1.freebsd.org (Postfix) with ESMTP id 9669413C442 for ; Thu, 19 Jul 2007 08:16:42 +0000 (UTC) (envelope-from marck@rinet.ru) Received: from localhost (localhost [127.0.0.1]) by woozle.rinet.ru (8.14.1/8.14.1) with ESMTP id l6J8GWxf005597; Thu, 19 Jul 2007 12:16:32 +0400 (MSD) (envelope-from marck@rinet.ru) Date: Thu, 19 Jul 2007 12:16:32 +0400 (MSD) From: Dmitry Morozovsky To: Jeff Roberson In-Reply-To: <20070718154306.R561@10.0.0.1> Message-ID: <20070719121201.P67760@woozle.rinet.ru> References: <20070716233030.D92541@10.0.0.1> <20070718011332.A14574@woozle.rinet.ru> <20070718154306.R561@10.0.0.1> X-NCC-RegID: ru.rinet X-OpenPGP-Key-ID: 6B691B03 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (woozle.rinet.ru [0.0.0.0]); Thu, 19 Jul 2007 12:16:32 +0400 (MSD) Cc: current@freebsd.org Subject: Re: ULE/SCHED_SMP diff for 7.0 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 19 Jul 2007 08:16:43 -0000 On Wed, 18 Jul 2007, Jeff Roberson wrote: JR> > Works for me with MSI S420 lapton (core2duo T2400) on fresh -CURRENT/i386 JR> > CPU: Genuine Intel(R) CPU T2400 @ 1.83GHz (1833.41-MHz JR> > 686-class CPU) JR> > JR> > However, make -j3 buildworld buildkernel (trimmed GENERIC) time degraded JR> > by 7%: JR> > JR> > +------------------------------------------------------------------------------+ JR> > N Min Max Median Avg Stddev JR> > x 5 36.33 36.77 36.45 36.486 JR> > + 5 38.87 39.23 39.03 39.042 JR> > Difference at 95.0% confidence JR> > 2.556 +/- 0.216322 JR> > 7.00543% +/- 0.59289% JR> > (Student's t, pooled s = 0.148324) JR> > JR> > before = kernel with SCHED_4BSD, after = SCHED_ULE with your patchset. JR> > Both JR> > are without WITNESS/INVARIANTS. JR> JR> Hi Dmitry, JR> JR> Can you test with http://people.freebsd.org/~jeff/sched_ule.c? I believe JR> this will somewhat improve the situation with buildkernel. I have tested JR> with my own core2duo laptop. The first run after reboot is now about 7% JR> faster than before. Subsequent runs are not improved as much. Only 2-3%. JR> You can also try tuning sysctl kern.sched.steal_thresh down as low as 1 to JR> see how much this may help. Unfortunately lower values tend to really hurt JR> other tests. Well, I'm a bit puzzled: with new sched_ule.c system+user time slightly decreases (within one minute), while real time goes up from 39 to 44 minutes! And most of the time I see 10-50% of idle in top. Any hints? Sincerely, D.Marck [DM5020, MCK-RIPE, DM3-RIPN] ------------------------------------------------------------------------ *** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck@rinet.ru *** ------------------------------------------------------------------------