From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1754281AbcHYQgP (ORCPT <rfc822;w@1wt.eu>);
        Thu, 25 Aug 2016 12:36:15 -0400
Received: from merlin.infradead.org ([205.233.59.134]:47566 "EHLO
        merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1750703AbcHYQgN (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 25 Aug 2016 12:36:13 -0400
Date: Thu, 25 Aug 2016 18:35:55 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Waiman Long <waiman.long@hpe.com>
Cc: Jason Low <jason.low2@hpe.com>, Davidlohr Bueso <dave@stgolabs.net>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Ding Tianhong <dingtianhong@huawei.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Will Deacon <Will.Deacon@arm.com>, Ingo Molnar <mingo@redhat.com>,
        Imre Deak <imre.deak@intel.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        "Paul E. McKenney" <paulmck@us.ibm.com>, jason.low2@hp.com
Subject: Re: [RFC][PATCH 0/3] locking/mutex: Rewrite basic mutex
Message-ID: <20160825163555.GJ10138@twins.programming.kicks-ass.net>
References: <20160823124617.015645861@infradead.org>
 <20160823161750.GD31186@linux-80c1.suse>
 <1471970103.2381.51.camel@j-VirtualBox>
 <1472001223.2381.96.camel@j-VirtualBox>
 <20160825154331.GI10138@twins.programming.kicks-ass.net>
 <57BF1DC0.60308@hpe.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <57BF1DC0.60308@hpe.com>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, Aug 25, 2016 at 12:33:04PM -0400, Waiman Long wrote:
> On 08/25/2016 11:43 AM, Peter Zijlstra wrote:
> >On Tue, Aug 23, 2016 at 06:13:43PM -0700, Jason Low wrote:
> >>I tested this patch on an 8 socket system with the high_systime AIM7
> >>workload with diskfs. The patch provided big performance improvements in
> >>terms of throughput in the highly contended cases.
> >>
> >>-------------------------------------------------
> >>|  users      | avg throughput | avg throughput |
> >>               | without patch  | with patch     |
> >>-------------------------------------------------
> >>| 10 - 90     |   13,943 JPM   |   14,432 JPM   |
> >>-------------------------------------------------
> >>| 100 - 900   |   75,475 JPM   |  102,922 JPM   |
> >>-------------------------------------------------
> >>| 1000 - 1900 |   77,299 JPM   |  115,271 JPM   |
> >>-------------------------------------------------
> >>
> >>Unfortunately, at 2000 users, the modified kernel locked up.
> >>
> >># INFO: task reaim:<#>  blocked for more than 120 seconds.
> >>
> >>So something appears to be buggy.
> >So with the previously given changes to reaim, I get the below results
> >on my 4 socket Haswell with the new version of 1/3 (also below).
> >
> >I still need to update 3/3..
> >
> >Note that I think my reaim change wrecked the jobs/min calculation
> >somehow, as it keeps increasing. I do think however that the numbers are
> >comparable between runs, since they're wrecked the same way.
> 
> The performance data for the 2 kernels were roughly the same. This was what
> I had been expecting as there was no change in algorithm in how the slowpath
> was being handled. So I was surprised by Jason's result yesterday showing
> such a big difference.

Its because the mutex wasn't quite exclusive enough :-) If you let in
multiple owner, like with that race you found, you get big gains in
throughput ...