From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757404AbZAWPlk (ORCPT ); Fri, 23 Jan 2009 10:41:40 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751185AbZAWPlb (ORCPT ); Fri, 23 Jan 2009 10:41:31 -0500 Received: from smtp109.mail.mud.yahoo.com ([209.191.85.219]:20425 "HELO smtp109.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1753537AbZAWPlb (ORCPT ); Fri, 23 Jan 2009 10:41:31 -0500 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com.au; h=Received:X-YMail-OSG:X-Yahoo-Newman-Property:From:To:Subject:Date:User-Agent:Cc:References:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Content-Disposition:Message-Id; b=W78bfjfhrisbt0TloXL8c4Y4+qB263Dqj5ePwUR095LWLgRuU/aiQMfKZmR8VCB0UzDZHf6nVQehbze/aJ9XB6ldRXMa+hGaGahnOoWgWe/KDcSkH5c9t46GYX76J0XYqBFblfEIvqEZDp/hGjemZzoUTC0Hz2GH6vbve1/nCjo= ; X-YMail-OSG: 2ddwK6wVM1l_slWEi6cQREbbG_BlPitVsqOtzl_4YYKJdDXb4sUR29rmNc6Urpgck7v6mJ_4OY9zCWfsDbayGgFnBzpounvKsaHITuJSJyL6X49IkF0Bk5BXghOEbHnujr__VevM7GKp7bUT4GT7KbMGxk1TEO_xDOT8UJtu1ft2OawH4svggieAIVrRLFGNcIVoYafHf7fydTHJ2l7zxEMqK9f2naxrFqVahMr7dT0u X-Yahoo-Newman-Property: ymail-3 From: Nick Piggin To: Christoph Lameter Subject: Re: [PATCH] SLUB: revert direct page allocator pass through Date: Sat, 24 Jan 2009 02:41:06 +1100 User-Agent: KMail/1.9.51 (KDE/4.0.4; ; ) Cc: Pekka Enberg , yanmin_zhang@linux.intel.com, Andi Kleen , Matthew Wilcox , linux-kernel@vger.kernel.org, akpm@linux-foundation.org References: <84144f020901230716n3f106034x8a10463b411c9a9b@mail.gmail.com> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200901240241.06670.nickpiggin@yahoo.com.au> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Saturday 24 January 2009 02:25:06 Christoph Lameter wrote: > On Fri, 23 Jan 2009, Pekka Enberg wrote: > > On Fri, Jan 23, 2009 at 5:03 PM, Christoph Lameter > > > > wrote: > > > It seems that we currently need the slab allocators to compensate for > > > the performance problems in the page allocator for these higher order > > > allocs. I'd rather have the page allocator fixed but things are as they > > > are. > > > > So, is that an ACK or a NAK for the patch?-) > > Doesnt that break down Nick's order-0 dominates-the-world scheme break > down? SLUB is your scheme. And yes it definitely goes against my liking of order-0 allocations regardless of this patch. > One of the reasons for doing this was to get the page allocator > performance issues exposed and addressed. Page allocator is never going to be as fast as slab allocator, for issues I explained a long time ago. Not to say it can't be improved, just stating facts.