All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Gregory Haskins <ghaskins@novell.com>,
	Matthew Wilcox <matthew@wil.cx>, Andi Kleen <andi@firstfloor.org>,
	Chris Mason <chris.mason@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	linux-btrfs <linux-btrfs@vger.kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Nick Piggin <npiggin@suse.de>,
	Peter Morreale <pmorreale@novell.com>,
	Sven Dietrich <SDietrich@novell.com>,
	Dmitry Adamushko <dmitry.adamushko@gmail.com>,
	Johannes Weiner <hannes@cmpxchg.org>
Subject: Re: [GIT PULL] adaptive spinning mutexes
Date: Wed, 14 Jan 2009 20:28:11 +0100	[thread overview]
Message-ID: <20090114192811.GA19691@elte.hu> (raw)
In-Reply-To: <20090114184746.GA21334@elte.hu>


* Ingo Molnar <mingo@elte.hu> wrote:

> Latest performance figures, on a 2-socket 16-way Nehalem test-system, 
> running the code above, measured via "test-mutex V 128 10" VFS 
> creat+unlink scalability test on tmpfs and ext3:
> 
>                               no-spin           spin
> 
>  [tmpfs]    avg ops/sec:       291038         392865       (+34.9%)
>  [ext3]     avg ops/sec:       283291         435674       (+53.7%)

Btw., for historic kicks i just went back to v2.6.15-2019-gf17578d - the 
last pre-mutexes semaphore based kernel, using the same .config.

I tracked down two bugs in it to make it boot on a Nehalem, so we can now 
compare the above numbers against historic semaphore performance:

                      [v2.6.14]     [v2.6.29]

                      Semaphores  | Mutexes
            ----------------------------------------------
                                  | no-spin           spin
                                  |
  [tmpfs]   ops/sec:       50713  |  291038         392865       (+34.9%)
  [ext3]    ops/sec:       45214  |  283291         435674       (+53.7%)

A 10x macro-performance improvement on ext3, compared to 2.6.14 :-)

While lots of other details got changed meanwhile, i'm sure most of the 
performance win on this particular VFS workload comes from mutexes.

So i think the long mutex migration pain was definitely worth it.

	Ingo

  reply	other threads:[~2009-01-14 19:28 UTC|newest]

Thread overview: 100+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-12 15:37 [PATCH -v8][RFC] mutex: implement adaptive spinning Peter Zijlstra
2009-01-12 16:04 ` Linus Torvalds
2009-01-12 16:20   ` Linus Torvalds
2009-01-12 16:45     ` Chris Mason
2009-01-12 16:50       ` Peter Zijlstra
2009-01-12 17:14         ` Chris Mason
2009-01-12 17:24           ` Peter Zijlstra
2009-01-12 17:30             ` Chris Mason
2009-01-12 17:16     ` Peter Zijlstra
2009-01-12 17:33       ` Boaz Harrosh
2009-01-12 18:07         ` Peter Zijlstra
2009-01-12 16:13 ` Avi Kivity
2009-01-12 17:13   ` Peter Zijlstra
2009-01-12 17:23     ` Avi Kivity
2009-01-12 17:32     ` Avi Kivity
2009-01-14 16:46       ` Peter Zijlstra
2009-01-14 17:04         ` Nick Piggin
2009-01-14 17:23           ` Avi Kivity
2009-01-15  0:50             ` Nick Piggin
2009-01-13 15:15 ` [PATCH -v9][RFC] " Peter Zijlstra
2009-01-13 16:16   ` Linus Torvalds
2009-01-13 16:21     ` Peter Zijlstra
2009-01-13 16:39       ` Ingo Molnar
2009-01-13 16:40       ` Peter Zijlstra
2009-01-13 16:49         ` Linus Torvalds
2009-01-13 17:21           ` Peter Zijlstra
2009-01-13 18:33             ` Ingo Molnar
2009-01-13 18:40               ` Linus Torvalds
2009-01-13 19:01                 ` Ingo Molnar
2009-01-14  2:58             ` Chris Mason
2009-01-14 11:18               ` Dmitry Adamushko
2009-01-14 16:47                 ` Chris Mason
2009-01-14 17:32                   ` Dmitry Adamushko
2009-01-14 11:21               ` Ingo Molnar
2009-01-14 15:43                 ` Linus Torvalds
2009-01-14 16:23                   ` Chris Mason
2009-01-14 17:06                   ` [PATCH -v11 delta] " Ingo Molnar
2009-01-14 17:00             ` [PATCH -v11][RFC] " Peter Zijlstra
2009-01-14 17:18               ` Nick Piggin
2009-01-14 17:22                 ` Peter Zijlstra
2009-01-15  0:46                   ` Nick Piggin
2009-01-15  7:44                     ` Peter Zijlstra
2009-01-15  7:52                       ` Nick Piggin
2009-01-14 18:33               ` [GIT PULL] adaptive spinning mutexes Ingo Molnar
2009-01-14 18:40                 ` Chris Mason
2009-01-15  9:53                   ` Ingo Molnar
2009-01-14 18:47                 ` Ingo Molnar
2009-01-14 19:28                   ` Ingo Molnar [this message]
2009-01-15 17:44                     ` Matthew Wilcox
2009-01-15 18:05                       ` Linus Torvalds
2009-01-15 18:08                         ` Ingo Molnar
2009-01-15 18:16                           ` Linus Torvalds
2009-01-15 19:26                             ` Chris Mason
2009-01-15 20:13                               ` Linus Torvalds
2009-01-15 21:04                                 ` Chris Mason
2009-01-15 22:03                                   ` Ingo Molnar
2009-01-16 13:32                               ` Folkert van Heusden
2009-01-16 13:32                                 ` Folkert van Heusden
2009-01-16 13:32                                 ` Folkert van Heusden
2009-01-16 13:57                                 ` Folkert van Heusden
2009-01-16 13:57                                   ` Folkert van Heusden
2009-01-16 13:57                                   ` Folkert van Heusden
2009-01-16 18:37                               ` Bill Davidsen
2009-01-16 18:37                                 ` Bill Davidsen
2009-01-16  0:53                             ` Paul E. McKenney
2009-01-16  1:01                               ` Linus Torvalds
2009-01-16  1:34                                 ` Paul E. McKenney
2009-01-16 14:07                                 ` Folkert van Heusden
2009-01-16  3:03                             ` Nick Piggin
2009-01-15 18:06                       ` Ingo Molnar
2009-01-14 18:53                 ` Andrew Morton
2009-01-14 19:00                   ` Ingo Molnar
2009-01-14 19:36                     ` Andrew Morton
2009-01-14 19:50                       ` Peter Zijlstra
2009-01-14 20:21                         ` Andrew Morton
2009-01-14 20:27                         ` Ingo Molnar
2009-01-14 20:44                           ` Andrew Morton
2009-01-14 20:14                       ` Ingo Molnar
2009-01-14 20:30                         ` Andrew Morton
2009-01-14 20:51                           ` Ingo Molnar
2009-01-14 21:06                             ` Andrew Morton
2009-01-14 21:14                               ` Ingo Molnar
2009-01-14 21:35                                 ` Andrew Morton
2009-01-14 23:23                                   ` Ingo Molnar
2009-01-15  0:55                                   ` Nick Piggin
2009-01-14 21:41                                 ` Ingo Molnar
2009-01-14 21:50                                   ` Kay Sievers
2009-01-14 22:34                                     ` Ingo Molnar
2009-01-15 11:45                                       ` Folkert van Heusden
2009-01-15 12:53                                       ` Chris Samuel
2009-01-14 19:23                   ` Peter Zijlstra
2009-01-14 19:33                     ` Ingo Molnar
2009-01-15  8:41             ` [PATCH] mutex: set owner only once on acquisition Johannes Weiner
2009-01-15  8:56               ` Johannes Weiner
2009-01-13 18:12           ` [PATCH -v9][RFC] mutex: implement adaptive spinning Ingo Molnar
2009-01-13 18:21             ` Linus Torvalds
2009-01-13 18:24               ` Ingo Molnar
2009-01-14 11:41 ` [PATCH -v8][RFC] " Folkert van Heusden
2009-01-14 11:42   ` Peter Zijlstra
2009-01-14 11:42   ` Folkert van Heusden

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=20090114192811.GA19691@elte.hu \
    --to=mingo@elte.hu \
    --cc=SDietrich@novell.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=chris.mason@oracle.com \
    --cc=dmitry.adamushko@gmail.com \
    --cc=ghaskins@novell.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matthew@wil.cx \
    --cc=npiggin@suse.de \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=pmorreale@novell.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.