From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765254AbYEOV57 (ORCPT ); Thu, 15 May 2008 17:57:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752349AbYEOV5t (ORCPT ); Thu, 15 May 2008 17:57:49 -0400 Received: from smtp-out04.alice-dsl.net ([88.44.63.6]:41815 "EHLO smtp-out04.alice-dsl.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752298AbYEOV5s (ORCPT ); Thu, 15 May 2008 17:57:48 -0400 To: Eric Dumazet Cc: Andrew Morton , Rusty Russell , linux kernel , Mike Travis Subject: Re: [PATCH] modules: Use a better scheme for refcounting From: Andi Kleen References: <482C9FC5.2070508@cosmosbay.com> Date: Thu, 15 May 2008 23:57:45 +0200 In-Reply-To: <482C9FC5.2070508@cosmosbay.com> (Eric Dumazet's message of "Thu, 15 May 2008 22:40:37 +0200") Message-ID: <87ej83z0va.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-OriginalArrivalTime: 15 May 2008 21:50:44.0801 (UTC) FILETIME=[BA2F4B10:01C8B6D5] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Eric Dumazet writes: > Instead of wasting NR_CPUS*128 bytes (on i386), we now use > num_possible_cpus*sizeof(local_t) bytes. > > On a typical distro, where NR_CPUS=8, More typical would be NR_CPUS=128, with NR_CPUS=four digits when Mike Travis et.al. are finished > shiping 2000 modules, we reduce Surely only the loaded modules count? Perhaps 20-30. But it's a cool improvement. Very nice. -Andi