From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932785AbXDAGkR (ORCPT ); Sun, 1 Apr 2007 02:40:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932835AbXDAGkR (ORCPT ); Sun, 1 Apr 2007 02:40:17 -0400 Received: from mail-in-08.arcor-online.net ([151.189.21.48]:57455 "EHLO mail-in-08.arcor-online.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932785AbXDAGkP (ORCPT ); Sun, 1 Apr 2007 02:40:15 -0400 From: Prakash Punnoor To: ck@vds.kolivas.org Subject: Re: [ck] [PATCH] sched: staircase deadline misc fixes Date: Sun, 1 Apr 2007 08:40:07 +0200 User-Agent: KMail/1.9.6 Cc: linux list References: <200703290237.38777.kernel@kolivas.org> <200703281934.17932.prakash@punnoor.de> In-Reply-To: <200703281934.17932.prakash@punnoor.de> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1314662.aESkcNa9nf"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <200704010840.11387.prakash@punnoor.de> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org --nextPart1314662.aESkcNa9nf Content-Type: text/plain; charset="iso-8859-15" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Am Mittwoch 28 M=E4rz 2007 schrieb Prakash Punnoor: > Am Mittwoch 28 M=E4rz 2007 schrieb Con Kolivas: > > I'm cautiously optimistic that we're at the thin edge of the bugfix wed= ge > > now. > > > > --- > > set_load_weight() should be performed after p->quota is set. This fixes= a > > large SMP performance regression. > > Hi, I am using 2.6.21-rc5 with rsdl 0.37 and think I still see a regressi= on > with my Athlon X2. Namely using this ac3 encoder > (http://aften.sourceforge.net/), which I parallelized in a simple way, wi= th > my test sample I remember having encoding times of ~5.4sec with vanilla a= nd > ~5.8 sec with rsdl - once the whole test wave is in cache. Otherwise you > can easily I/O limit the encoder. ;-) You need to get sources from svn > though. The current 0.06 release doesn't have threads support. BTW, I confirmed this regression. With vanilla 2.76.21-rc5 I get back my 5.= 4=20 secs with the test sample and two threads. Furtmermore for me vanilla=20 actually feels nicer on my dual core, even with load - just subjectively=20 that's why I ditched rsdl... Cheers, =2D-=20 (=B0=3D =3D=B0) //\ Prakash Punnoor /\\ V_/ \_V --nextPart1314662.aESkcNa9nf Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.3 (GNU/Linux) iD8DBQBGD1PLxU2n/+9+t5gRAiVjAKCizhqJUcWkKSKw+YhsWgWMW6xPOgCfeGyc B3tPCLfWj9kir5DBOKpYRTs= =kRiL -----END PGP SIGNATURE----- --nextPart1314662.aESkcNa9nf--