From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Zhang, Yanmin" Subject: RE: scalability investigation: Where can I get your latest patches? Date: Wed, 04 Aug 2010 15:58:37 +0800 Message-ID: <1280908717.2125.33.camel@ymzhang.sh.intel.com> References: <1278579387.2096.889.camel@ymzhang.sh.intel.com> <20100720031201.GC21274@amd> <1280883843.2125.20.camel@ymzhang.sh.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Cc: Nick Piggin , "alexs.shi@intel.com" , "linux-mm@kvack.org" , "linux-fsdevel@vger.kernel.org" To: "Kleen, Andi" Return-path: Received: from mga02.intel.com ([134.134.136.20]:60522 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750699Ab0HDHz7 (ORCPT ); Wed, 4 Aug 2010 03:55:59 -0400 In-Reply-To: Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Wed, 2010-08-04 at 08:21 +0100, Kleen, Andi wrote: > > Issues: > > 1) Compiling fails on a couple of file systems, such like > > CONFIG_ISO9660_FS=y. > > 2) dbenchthreads has about 50% regression. We connect a JBOD of 12 > > disks to > > a machine. Start 4 dbench threads per disk. > > We run the workload under a regular user account. If we run it under > > root account, > > we get 22% improvement instead of regression. > > The root cause is ACL checking. With your patch, do_path_lookup firstly > > goes through > > rcu steps which including a exec permission checking. With ACL, the > > __exec_permission > > always fails. Then a later nameidata_drop_rcu often fails as dentry- > > >d_seq is changed. > > I believe the latest version of Nick's patchkit has a likely fix for that. > > http://git.kernel.org/?p=linux/kernel/git/npiggin/linux-npiggin.git;a=commitdiff;h=9edd35f9aeafc8a5e1688b84cf4488a94898ca45 Thanks Andi. The patch has no ext3 part.