From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934092AbYEVIVS (ORCPT ); Thu, 22 May 2008 04:21:18 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756076AbYEVIUt (ORCPT ); Thu, 22 May 2008 04:20:49 -0400 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:37534 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932247AbYEVIUq (ORCPT ); Thu, 22 May 2008 04:20:46 -0400 Message-ID: <48352CDA.2030603@np.css.fujitsu.com> Date: Thu, 22 May 2008 17:20:42 +0900 From: Kentaro Makita User-Agent: Thunderbird 2.0.0.14 (X11/20080421) MIME-Version: 1.0 To: akpm@linux-foundation.org, dgc@sgi.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH][RFC]fix soft lock up at NFS mount by per-SB LRU-list of unused dentries References: <4834D8DA.30907@np.css.fujitsu.com> <20080521235510.22bff69f.akpm@linux-foundation.org> In-Reply-To: <20080521235510.22bff69f.akpm@linux-foundation.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Andrew Morton wrote: > On Thu, 22 May 2008 11:22:18 +0900 Kentaro Makita wrote: > >> [Summary] >> Split LRU-list of unused dentries to each superblocks to avoid soft lock up >> at NFS mounts and remounting any filesystem. >> >> Previosly I posted are: >> http://lkml.org/lkml/2008/3/5/590 >> >> [Descriptions] >> - background >> dentry_unused is a list of dentries which is not in use. This works >> as a cache against not-exisiting files. dentry_unused grows up when >> directories or files are removed. This list can be very long if >> there is huge free memory. > > The dentry_unused inodes are not actually not-existing files. They are > dentries which refer to live files (and, iirc, negative dentries) but > which nobody is actually using - for example, regular files which > nobody currently has open. > > I changed the changelog text to reflect that. Oh, Thank you for your good information and fixing. > >> - what's problem >> >> This patch is against linux-2.6.26-rc3. Tested on x86_64. > > Looks good to me, thanks. And no, the loss of the strict global LRU > handling of the dentry LRU is unlikely to be an issue. > >> Based on David Chinner's "Per-superblock unused dentry LRU lists V3". >> ... >> Signed-off-by: Kentaro Makita > > I guess we should ask David for his signed-off-by: on this. Thank you for your works too, David. Best Regards, Kentaro Makita