From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755129AbYKNDaw (ORCPT ); Thu, 13 Nov 2008 22:30:52 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751345AbYKNDao (ORCPT ); Thu, 13 Nov 2008 22:30:44 -0500 Received: from cantor.suse.de ([195.135.220.2]:59259 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751308AbYKNDan (ORCPT ); Thu, 13 Nov 2008 22:30:43 -0500 Date: Fri, 14 Nov 2008 04:30:41 +0100 From: Nick Piggin To: Linus Torvalds Cc: Andi Kleen , Ingo Molnar , Linux Kernel Mailing List Subject: Re: [rfc] x86: optimise page fault path a little Message-ID: <20081114033041.GD24414@wotan.suse.de> References: <20081113072821.GB2946@wotan.suse.de> <20081114015817.GC5063@wotan.suse.de> <20081114024347.GB24414@wotan.suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.9i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Nov 13, 2008 at 07:18:11PM -0800, Linus Torvalds wrote: > > > On Fri, 14 Nov 2008, Nick Piggin wrote: > > > > I don't exactly know what you mean by random micro-optimization. It is > > what it is. I like counting cachelines and branches and I thought you > > did as well. > > You're missing the point. > > If you spent a bit more time on it, it would be a cleanup too, and we > wouldn't need this discussion. > As it is, it's a wash. At which point I'd simply rather not touch the > code. > > You can have your cake and eat it too, and I tried to explain how. And I > don't understand why you argue against it. Oh OK. I am going to add those changes that you suggested (in fact, I already have). I just thought for some reason you wanted it to make further cleanups or something. I wasn't arguing against that. Or against refactoring the code in as clean a way possible if there is any refactoring happening at all for any reason (eg. performance or functionality as the primary reason). I just wasn't going to repost the patch because as I said, my level of testing and the relative urgency of it wouldn't justify it.