From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1758731AbYCCUKg@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1758731AbYCCUKg (ORCPT <rfc822;w@1wt.eu>);
	Mon, 3 Mar 2008 15:10:36 -0500
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754938AbYCCUKO
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Mon, 3 Mar 2008 15:10:14 -0500
Received: from ns2.suse.de ([195.135.220.15]:57079 "EHLO mx2.suse.de"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754921AbYCCUKK (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Mon, 3 Mar 2008 15:10:10 -0500
Date: Mon, 3 Mar 2008 21:10:08 +0100
From: Nick Piggin <npiggin@suse.de>
To: Christoph Lameter <clameter@sgi.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>, Eric Dumazet <dada1@cosmosbay.com>,
       netdev@vger.kernel.org,
       Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
       yanmin_zhang@linux.intel.com, David Miller <davem@davemloft.net>
Subject: Re: [rfc][patch 3/3] use SLAB_ALIGN_SMP
Message-ID: <20080303201008.GD8974@wotan.suse.de>
References: <20080303093449.GA15091@wotan.suse.de> <20080303093624.GC15091@wotan.suse.de> <47CBCAB0.2040604@cosmosbay.com> <20080303124142.GB13138@wotan.suse.de> <47CBF683.10201@cosmosbay.com> <20080303134622.GD13138@wotan.suse.de> <84144f020803030553s35a40dd8yf88585ccd5a599fd@mail.gmail.com> <Pine.LNX.4.64.0803031109200.6917@schroedinger.engr.sgi.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Pine.LNX.4.64.0803031109200.6917@schroedinger.engr.sgi.com>
User-Agent: Mutt/1.5.9i
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Mar 03, 2008 at 11:09:51AM -0800, Christoph Lameter wrote:
> On Mon, 3 Mar 2008, Pekka Enberg wrote:
> 
> > At least historically SLAB_HWCACHE_ALIGN has been just a hint,
> > although slab tries very hard to satisfy it (see the comments in
> > mm/slab.c). Why do we need stronger guarantees than that, btw?
> 
> Its a hint. Alignment is specified as a parameter to kmem_cache_create not 
> as a flag. Maybe we could remove SLAB_HWCACHE_ALIGN because it is causing 
> so much confusion?

Yeah, that's what I thought too, when I got confused by these new
SLUB semantics that you made up. Actually if you look at SLAB,
it has very precise and rational semantics. SLUB should respect that.

If you really configure for tiny memory footprint, then I'm fine with
it going away. In that respect, it is still a hint (the callers can't
rely on it being a particular alignment), and that also applies for
SLAB_SMP_ALIGN, in case you are concerned that flags must only be hints.