From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754022AbbIJCLs (ORCPT ); Wed, 9 Sep 2015 22:11:48 -0400 Received: from g1t6225.austin.hp.com ([15.73.96.126]:42122 "EHLO g1t6225.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752102AbbIJCLq (ORCPT ); Wed, 9 Sep 2015 22:11:46 -0400 Message-ID: <55F0E492.4060607@hpe.com> Date: Wed, 09 Sep 2015 22:01:54 -0400 From: Waiman Long User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.12) Gecko/20130109 Thunderbird/10.0.12 MIME-Version: 1.0 To: Dave Chinner CC: linux-kernel@vger.kernel.org, peterz@infradead.org, Waiman.Long@hp.com, torvalds@linux-foundation.org Subject: Re: [4.2, Regression] Queued spinlocks cause major XFS performance regression References: <20150904054820.GY3902@dastard> In-Reply-To: <20150904054820.GY3902@dastard> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/04/2015 01:48 AM, Dave Chinner wrote: > Hi Waiman, > > For the first time in months I just turned of spinlock debugging on > my performance test machine and I just got an unpleasant surprise on > my standard inode allocation and reclaim test. I've described this > test to you before, because it's found regressions in your previous > lock scaling changes: > > http://permalink.gmane.org/gmane.linux.kernel/1768786 > > This time it is the fsmark run that I use to populate the filesystem > that is demonstrating a locking regression. I'll asked you before > if you could add this test to your lock scaling regression test > suite; please do it this time. > > Now, the regression. With spinlock debugging turned on, the > performance of my usual XFS inode allocation benchmark using fsmark > reports performance like this: > > FSUse% Count Size Files/sec App Overhead > 0 1600000 0 312594.0 9944159 > 0 3200000 0 295668.6 10399679 > 0 4800000 0 279026.1 11397617 > ..... > > This has been pretty stable for several releases - it varies +/- a > few percent, but it's pretty much been like this since about 3.2 > when CONFIG_XFS_DEBUG=n, with or without basic spinlock debugging. > > When I turned spinlock debugging off on 4.2 to get some perf numbers > a request from Linus, I got this: > > FSUse% Count Size Files/sec App Overhead > 0 1600000 0 114143.9 9597599 > 0 3200000 0 95486.9 9460413 > 0 4800000 0 93918.2 9784699 > . I am sorry that I was on vacation over the past weekend and so was not able to respond in a timely manner. As Peter already has a patch to address the root cause of this problem. I think this problem is all set. Cheers, Longman