public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jason Low <jason.low2@hpe.com>
To: Davidlohr Bueso <dave@stgolabs.net>
Cc: jason.low2@hpe.com, Peter Zijlstra <peterz@infradead.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Waiman Long <waiman.long@hpe.com>,
	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
Date: Tue, 23 Aug 2016 18:13:43 -0700	[thread overview]
Message-ID: <1472001223.2381.96.camel@j-VirtualBox> (raw)
In-Reply-To: <1471970103.2381.51.camel@j-VirtualBox>

On Tue, 2016-08-23 at 09:35 -0700, Jason Low wrote:
> On Tue, 2016-08-23 at 09:17 -0700, Davidlohr Bueso wrote:
> > I have not looked at the patches yet, but are there any performance minutia
> > to be aware of?
> 
> This would remove all of the mutex architecture specific optimizations
> in the (common) fastpath, so that is one thing that could reduce
> performance. I'll run some benchmarks to see what some of the
> performance impacts of these patches would be.

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.

  parent reply	other threads:[~2016-08-24  1:22 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-08-23 12:46 [RFC][PATCH 0/3] locking/mutex: Rewrite basic mutex Peter Zijlstra
2016-08-23 12:46 ` [RFC][PATCH 1/3] locking/mutex: Rework mutex::owner Peter Zijlstra
2016-08-23 19:55   ` Waiman Long
2016-08-23 20:52     ` Tim Chen
2016-08-23 21:03       ` Peter Zijlstra
2016-08-23 21:09     ` Peter Zijlstra
2016-08-23 20:17   ` Waiman Long
2016-08-23 20:31     ` Peter Zijlstra
2016-08-24  9:56   ` Will Deacon
2016-08-24 15:34     ` Peter Zijlstra
2016-08-24 16:52       ` Peter Zijlstra
2016-08-24 16:54         ` Will Deacon
2016-08-23 12:46 ` [RFC][PATCH 2/3] locking/mutex: Allow MUTEX_SPIN_ON_OWNER when DEBUG_MUTEXES Peter Zijlstra
2016-08-23 12:46 ` [RFC][PATCH 3/3] locking/mutex: Add lock handoff to avoid starvation Peter Zijlstra
2016-08-23 12:56   ` Peter Zijlstra
     [not found]   ` <57BCA869.1050501@hpe.com>
2016-08-23 20:32     ` Peter Zijlstra
2016-08-24 19:50       ` Waiman Long
2016-08-25  8:11         ` Peter Zijlstra
2016-08-23 16:17 ` [RFC][PATCH 0/3] locking/mutex: Rewrite basic mutex Davidlohr Bueso
2016-08-23 16:35   ` Jason Low
2016-08-23 16:57     ` Peter Zijlstra
2016-08-23 19:36       ` Waiman Long
2016-08-23 20:41         ` Peter Zijlstra
2016-08-23 22:34           ` Waiman Long
2016-08-24  1:13     ` Jason Low [this message]
2016-08-25 12:32       ` Peter Zijlstra
2016-08-25 15:43       ` Peter Zijlstra
2016-08-25 16:33         ` Waiman Long
2016-08-25 16:35           ` Peter Zijlstra
2016-08-27 18:27             ` Ingo Molnar
2016-08-25 19:11         ` huang ying
2016-08-25 19:26           ` Peter Zijlstra
2016-08-23 18:53   ` Linus Torvalds
2016-08-23 20:34     ` Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1472001223.2381.96.camel@j-VirtualBox \
    --to=jason.low2@hpe.com \
    --cc=Will.Deacon@arm.com \
    --cc=dave@stgolabs.net \
    --cc=dingtianhong@huawei.com \
    --cc=imre.deak@intel.com \
    --cc=jason.low2@hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=paulmck@us.ibm.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=tim.c.chen@linux.intel.com \
    --cc=torvalds@linux-foundation.org \
    --cc=waiman.long@hpe.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox