From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756625AbXKBOfp (ORCPT ); Fri, 2 Nov 2007 10:35:45 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754243AbXKBOfi (ORCPT ); Fri, 2 Nov 2007 10:35:38 -0400 Received: from netops-testserver-4-out.sgi.com ([192.48.171.29]:34637 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753889AbXKBOfh (ORCPT ); Fri, 2 Nov 2007 10:35:37 -0400 Date: Fri, 2 Nov 2007 07:35:35 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: Peter Zijlstra cc: David Miller , akpm@linux-foundation.org, linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org, mathieu.desnoyers@polymtl.ca, penberg@cs.helsinki.fi Subject: Re: [patch 0/7] [RFC] SLUB: Improve allocpercpu to reduce per cpu access overhead In-Reply-To: <1193999326.27652.348.camel@twins> Message-ID: References: <20071101.153824.91808126.davem@davemloft.net> <20071101.155805.65012933.davem@davemloft.net> <1193999326.27652.348.camel@twins> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2 Nov 2007, Peter Zijlstra wrote: > On Thu, 2007-11-01 at 15:58 -0700, David Miller wrote: > > > Since you're the one who wants to change the semantics and guarentees > > of this interface, perhaps it might help if you did some greps around > > the tree to see how alloc_percpu() is actually used. That's what > > I did when I started running into trouble with your patches. > > This fancy new BDI stuff also lives off percpu_counter/alloc_percpu(). Yes there are numerous uses. I even can increase page allocator performance and reduce its memory footprint by using it here. > That means that for example each NFS mount also consumes a number of > words - not quite sure from the top of my head how many, might be in the > order of 24 bytes or something. > > I once before started looking at this, because the current > alloc_percpu() can have some false sharing - not that I have machines > that are overly bothered by that. I like the idea of a strict percpu > region, however do be aware of the users. Well I wonder if I should introduce it not as a replacement but as an alternative to allocpercpu? We can then gradually switch over. The existing API does not allow the specification of gfp_masks or alignements.