Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753389AbYCIKaJ (ORCPT ); Sun, 9 Mar 2008 06:30:09 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751593AbYCIK36 (ORCPT ); Sun, 9 Mar 2008 06:29:58 -0400 Received: from smtp-out04.alice-dsl.net ([88.44.63.6]:3594 "EHLO smtp-out04.alice-dsl.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751464AbYCIK35 (ORCPT ); Sun, 9 Mar 2008 06:29:57 -0400 To: Thomas Gleixner Cc: LKML , Linus Torvalds , Andrew Morton , Ingo Molnar , Christoph Lameter , Bart Van Assche Subject: Re: quicklists confuse meminfo References: From: Andi Kleen Date: 09 Mar 2008 11:29:54 +0100 In-Reply-To: Message-ID: <87iqzw197h.fsf@basil.nowhere.org> User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-OriginalArrivalTime: 09 Mar 2008 10:23:23.0475 (UTC) FILETIME=[9AC31A30:01C881CF] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1062 Lines: 20 Thomas Gleixner writes: > Bart reported http://bugzilla.kernel.org/show_bug.cgi?id=9991. He > assumed a memory leak in 32bit kernels when he analyzed the output of > /proc/meminfo. > > The leak is not a leak, it's an accounting bug. quicklists keep a > large amount of pages which are accounted as used memory. There are various other subsystems which can cache substantial memory under the right circumstances. Do you want to add all of them to /proc/meminfo? I'm not sure that will scale long term. One more general possibility would be to integrate this with with the shrinker callbacks. Everyone who caches memory should have a shrinker. Perhaps that could be integrated with some reporting facility that adds a dynamic counter field that is displayed somewhere in /proc or /sys. -Andi -- 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/