Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763447AbZAUFxo (ORCPT ); Wed, 21 Jan 2009 00:53:44 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756840AbZAUFxP (ORCPT ); Wed, 21 Jan 2009 00:53:15 -0500 Received: from hera.kernel.org ([140.211.167.34]:37623 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755673AbZAUFxO (ORCPT ); Wed, 21 Jan 2009 00:53:14 -0500 Message-ID: <4976B82E.1080002@kernel.org> Date: Wed, 21 Jan 2009 14:52:46 +0900 From: Tejun Heo User-Agent: Thunderbird 2.0.0.19 (X11/20081227) MIME-Version: 1.0 To: Ingo Molnar CC: Rusty Russell , Herbert Xu , akpm@linux-foundation.org, hpa@zytor.com, brgerst@gmail.com, ebiederm@xmission.com, cl@linux-foundation.org, travis@sgi.com, linux-kernel@vger.kernel.org, steiner@sgi.com, hugh@veritas.com, "David S. Miller" , netdev@vger.kernel.org, Mathieu Desnoyers Subject: Re: [PATCH] percpu: add optimized generic percpu accessors References: <20090115183942.GA6325@elte.hu> <200901170827.33729.rusty@rustcorp.com.au> <20090116220832.GB20653@elte.hu> <200901201328.24605.rusty@rustcorp.com.au> <20090120104022.GB29346@elte.hu> In-Reply-To: <20090120104022.GB29346@elte.hu> X-Enigmail-Version: 0.95.7 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.0 (hera.kernel.org [127.0.0.1]); Wed, 21 Jan 2009 05:52:44 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 862 Lines: 21 Ingo Molnar wrote: > The larger point still remains: the kernel dominantly uses static percpu > variables by a margin of 10 to 1, so we cannot just brush away the static > percpu variables and must concentrate on optimizing that side with > priority. It's nice if the dynamic percpu-alloc side improves as well, of > course. Well, the infrequent usage of dynamic percpu allocation is in some part due to the poor implementation, so it's sort of chicken and egg problem. I got into this percpu thing because I wanted a percpu reference count which can be dynamically allocated and it sucked. Thanks. -- tejun -- 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/