From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nick Piggin Subject: Re: scalability investigation: Where can I get your latest patches? Date: Thu, 5 Aug 2010 21:44:38 +1000 Message-ID: <20100805114438.GA9547@amd> 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=us-ascii Cc: Nick Piggin , andi.kleen@intel.com, alexs.shi@intel.com, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org To: "Zhang, Yanmin" Return-path: Received: from ipmail07.adl2.internode.on.net ([150.101.137.131]:25299 "EHLO ipmail07.adl2.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759097Ab0HELon (ORCPT ); Thu, 5 Aug 2010 07:44:43 -0400 Content-Disposition: inline In-Reply-To: <1280883843.2125.20.camel@ymzhang.sh.intel.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Wed, Aug 04, 2010 at 09:04:03AM +0800, Zhang, Yanmin wrote: > We ran lots of benchmarks on many machines. Below is something to > share with you. > > Improvement: > 1) We get about 30% improvement with kbuild workload on Nehalem > machines. It's hard to improve kbuild performance. Your tree does. > > 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. Oh one other thing I wanted to ask about. d_seq changing should not be too common. If the directory is renamed, or if it is turned negative should be the only cases in which we should see a d_seq changes. Or unless there is a bug and it is checking the wrong sequence or against the wrong dentry. How often would you say nameidata_drop_rcu fails (without the following acl rcu patches)?