From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755135AbXJYR3e (ORCPT ); Thu, 25 Oct 2007 13:29:34 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752663AbXJYR3Z (ORCPT ); Thu, 25 Oct 2007 13:29:25 -0400 Received: from victor.provo.novell.com ([137.65.250.26]:47110 "EHLO victor.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752638AbXJYR3Y (ORCPT ); Thu, 25 Oct 2007 13:29:24 -0400 Subject: Re: [PATCH 3/3] RT: CPU priority management From: Gregory Haskins To: Steven Rostedt Cc: linux-rt-users@vger.kernel.org, linux-kernel@vger.kernel.org, Dmitry Adamushko , Peter Zijlstra , Ingo Molnar , Darren Hart In-Reply-To: References: <20071025144456.19876.94333.stgit@novell1.haskins.net> <20071025144633.19876.10342.stgit@novell1.haskins.net> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-DYEhY3MU/7fHnQgwm97z" Date: Thu, 25 Oct 2007 13:26:38 -0400 Message-Id: <1193333198.4021.24.camel@ghaskins-t60p.haskins.net> Mime-Version: 1.0 X-Mailer: Evolution 2.6.0 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org --=-DYEhY3MU/7fHnQgwm97z Content-Type: text/plain Content-Transfer-Encoding: quoted-printable Oh crap. I just realized this is an older version of the patch..mustv'e forgot to refresh...grr. Ill send out the refreshed one. But anyway, I digress. =20 On Thu, 2007-10-25 at 11:27 -0400, Steven Rostedt wrote: >=20 > The cpu_priority and the cp->lock will be aboslutely horrible for > cacheline bouncing. In the form presented here in this email, perhaps. I think you will see some significant improvements in the refreshed version. The big change is that the global lock is gone. > Ironically, this will kill performance for the very > machines this code is to help with. The larger the number of CPUs you > have the more cacheline bouncing this code will create. Don't forget: The same is precisely true for the current -rt2 algorithm. For instance, the -rt2 algorithm aside from being linear in general, scales cacheline bouncing linearly as well. Each cpu is going to trash rq->rt.highest_prio and then we will walk them for each scan. The fact is, you can't maintain a global dynamic policy without bouncing cachelines, period. But hopefully we can minimize it, and I just want to see the fastest code here. >=20 > I still don't see the benefit from the cpupri code. I still owe you timing data, but at this juncture I think I can beat linear (especially as we start throwing in big-iron) ;) I originally got involved in this scheduler rework from observations of poor scaling on our 8/16-ways, so I want it to scale as much as you ;) If this alg doesn't pan out, that's cool. But I think it will in the end. Linear algs in the fast path just make my skin crawl. Perhaps it will still be the best design in the end, but I am not giving up that easy until I prove it to myself. Regards, -Greg --=-DYEhY3MU/7fHnQgwm97z Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2 (GNU/Linux) iD8DBQBHINHOSW61Ku6jJPkRAsA6AJ4n4fO4o9IE5K8i8UU8J1ENoWUEPgCcDbnl PzXqHptHf1mXsDJAsARwBg8= =w/0J -----END PGP SIGNATURE----- --=-DYEhY3MU/7fHnQgwm97z--