From owner-freebsd-current@FreeBSD.ORG Mon Sep 17 07:19:13 2007 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E57DA16A41A for ; Mon, 17 Sep 2007 07:19:12 +0000 (UTC) (envelope-from h.schmalzbauer@omnisec.de) Received: from host.omnisec.de (host.omnisec.de [62.245.232.135]) by mx1.freebsd.org (Postfix) with ESMTP id 5805713C428 for ; Mon, 17 Sep 2007 07:19:12 +0000 (UTC) (envelope-from h.schmalzbauer@omnisec.de) Received: from tek.flintsbach.schmalzbauer.de (tek.flintsbach.schmalzbauer.de [172.21.2.3]) by host.omnisec.de (8.13.8/8.13.8) with ESMTP id l8H7J6Za047251 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Mon, 17 Sep 2007 09:19:11 +0200 (CEST) (envelope-from h.schmalzbauer@omnisec.de) Received: from titan.flintsbach.schmalzbauer.de (titan.flintsbach.schmalzbauer.de [IPv6:fec0::1:0:0:1:1]) by tek.flintsbach.schmalzbauer.de (8.13.8/8.13.8) with ESMTP id l8H7J6lG058043 for ; Mon, 17 Sep 2007 09:19:06 +0200 (CEST) (envelope-from h.schmalzbauer@omnisec.de) Received: from localhost (localhost [[UNIX: localhost]]) by titan.flintsbach.schmalzbauer.de (8.14.1/8.14.1/Submit) id l8H7KMGd007927 for freebsd-current@freebsd.org; Mon, 17 Sep 2007 09:20:22 +0200 (CEST) (envelope-from h.schmalzbauer@omnisec.de) X-Authentication-Warning: titan.flintsbach.schmalzbauer.de: harry set sender to h.schmalzbauer@omnisec.de using -f From: Harald Schmalzbauer Organization: OmniSEC To: freebsd-current@freebsd.org Date: Mon, 17 Sep 2007 09:20:22 +0200 User-Agent: KMail/1.9.7 References: <20070916225019.B921C4500C@ptavv.es.net> <46EDCC48.2090405@FreeBSD.org> <20070916202402.X4507@10.0.0.1> In-Reply-To: <20070916202402.X4507@10.0.0.1> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1548833.otytbA23j6"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <200709170920.22477.h.schmalzbauer@omnisec.de> Subject: Re: SCHED_ULE on desktop system 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: Mon, 17 Sep 2007 07:19:13 -0000 --nextPart1548833.otytbA23j6 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Am Montag, 17. September 2007 05:26:28 schrieb Jeff Roberson: [snip] > >> I run gkrellm and can tell at a glance when swap usage starts to > >> increase. The linkage is clear and not terribly surprising. It may be > >> that you need to add a bit more RAM. > > > > Yes, not surprising in the least. When your system touches swap, > > performance will drop to a tiny fraction of its normal performance. > > Depending on your disk this could be 1% or lower. Anyone who is seeing > > poor interactive performance needs to rule this out as the cause. > > Ah, I think I know why people are reporting worse problems with ULE. ULE > is not properly accounting swtime so different threads are being chosen > for swapout with ULE and 4BSD. My test systems all have more than enough > memory to do parallel buildworlds without swapping. This is likely why I > haven't run into this. > > I really need to fix p_swtime with ULE. Could the people reporting bad > behavior please verify whether or not you're seeing swapping activity? > Even just looking for swap used in top will help me verify that this is > the problem. In my case swap wasn't used. Of course do I have to expect overall performance loss if I don't have enou= gh=20 RAM, but even a heavily swapping machine shouldn't stop the mouse. I can remember old FreeBSD 3.1 times when it was very common for all of my= =20 machines to use at least the size of RAM additionally for SWAP (about 16MB)= =20 and the machine was feeling smooth nevertheless. I haven't tested if PREEMPTION makes any difference yet. I just remember I = was=20 really suprised that the difference between UP and SMP kernels on that=20 machine is so extremely big. Thanks for all your work! =2DHarry --nextPart1548833.otytbA23j6 Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part. -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.4 (FreeBSD) iD8DBQBG7iq2LDqVQ9VXb8gRAvjqAJ9wU2iroEZ/iKAVa51WfVdvdZpXIwCdG6tW 9T1T2j6LxFYun8sYVChtqnI= =HDMI -----END PGP SIGNATURE----- --nextPart1548833.otytbA23j6--