Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756661AbZKEI1i (ORCPT ); Thu, 5 Nov 2009 03:27:38 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756601AbZKEI1h (ORCPT ); Thu, 5 Nov 2009 03:27:37 -0500 Received: from one.firstfloor.org ([213.235.205.2]:41208 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756593AbZKEI1f (ORCPT ); Thu, 5 Nov 2009 03:27:35 -0500 Date: Thu, 5 Nov 2009 09:27:35 +0100 From: Andi Kleen To: Christoph Lameter Cc: Andi Kleen , KAMEZAWA Hiroyuki , "hugh.dickins@tiscali.co.uk" , linux-mm@kvack.org, linux-kernel@vger.kernel.org, akpm@linux-foundation.org, Tejun Heo Subject: Re: [MM] Remove rss batching from copy_page_range() Message-ID: <20091105082735.GP31511@one.firstfloor.org> References: <87my3280mb.fsf@basil.nowhere.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.2i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 916 Lines: 26 On Wed, Nov 04, 2009 at 05:02:12PM -0500, Christoph Lameter wrote: > On Wed, 4 Nov 2009, Andi Kleen wrote: > > > > With per cpu counters in mm there is no need for batching > > > mm counter updates anymore. Update counters directly while > > > copying pages. > > > > Hmm, but with all the inlining with some luck the local > > counters will be in registers. That will never be the case > > with the per cpu counters. > > The function is too big for that to occur and the counters have to be If it's only called once then gcc doesn't care about size. > preserved across function calls. The code is shorter with the patch > applied: I see. Thanks for the data. -Andi -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/