Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754495AbYLHXI5 (ORCPT ); Mon, 8 Dec 2008 18:08:57 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753958AbYLHXIi (ORCPT ); Mon, 8 Dec 2008 18:08:38 -0500 Received: from bombadil.infradead.org ([18.85.46.34]:37544 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753916AbYLHXIg (ORCPT ); Mon, 8 Dec 2008 18:08:36 -0500 Subject: Re: [PATCH] percpu_counter: Fix __percpu_counter_sum() From: Peter Zijlstra To: Theodore Tso Cc: Andrew Morton , Eric Dumazet , linux kernel , "David S. Miller" , Mingming Cao , linux-ext4@vger.kernel.org In-Reply-To: <1228777500.12729.4.camel@twins> References: <4936D287.6090206@cosmosbay.com> <4936EB04.8000609@cosmosbay.com> <20081206202233.3b74febc.akpm@linux-foundation.org> <493BCF60.1080409@cosmosbay.com> <20081207092854.f6bcbfae.akpm@linux-foundation.org> <493C0F40.7040304@cosmosbay.com> <20081207205250.dbb7fe4b.akpm@linux-foundation.org> <20081208221241.GA2501@mit.edu> <1228774836.16244.22.camel@lappy.programming.kicks-ass.net> <20081208230047.GC2501@mit.edu> <1228777500.12729.4.camel@twins> Content-Type: text/plain Content-Transfer-Encoding: 7bit Date: Tue, 09 Dec 2008 00:08:07 +0100 Message-Id: <1228777687.12729.6.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.24.2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1105 Lines: 25 On Tue, 2008-12-09 at 00:05 +0100, Peter Zijlstra wrote: > On Mon, 2008-12-08 at 18:00 -0500, Theodore Tso wrote: > > On Mon, Dec 08, 2008 at 11:20:35PM +0100, Peter Zijlstra wrote: > > > > > > atomic_t is pretty good on all archs, but you get to keep the cacheline > > > ping-pong. > > > > > > > Stupid question --- if you're worried about cacheline ping-pongs, why > > aren't each cpu's delta counter cacheline aligned? With a 64-byte > > cache-line, and a 32-bit counters entry, with less than 16 CPU's we're > > going to be getting cache ping-pong effects with percpu_counter's, > > right? Or am I missing something? > > sorta - a new per-cpu allocator is in the works, but we do cacheline > align the per-cpu allocations (or used to), also, the allocations are > node affine. Indeed we still (or again) do, see mm/allocpercpu.c:percpu_populate(). -- 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/