public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Christopher Friesen" <cfriesen@nortel.com>
To: Esben Nielsen <simlo@phys.au.dk>
Cc: Arjan van de Ven <arjan@infradead.org>,
	Daniel Walker <dwalker@mvista.com>, Ingo Molnar <mingo@elte.hu>,
	linux-kernel@vger.kernel.org, Ulrich Drepper <drepper@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Andrew Morton <akpm@osdl.org>
Subject: Re: [patch 0/6] lightweight robust futexes: -V3 - Why in userspace?
Date: Thu, 16 Feb 2006 14:23:48 -0600	[thread overview]
Message-ID: <43F4DF54.6030303@nortel.com> (raw)
In-Reply-To: <Pine.OSF.4.05.10602162057040.20911-100000@da410>

Esben Nielsen wrote:
> On Thu, 16 Feb 2006, Arjan van de Ven wrote:
> 
> 
>>On Thu, 2006-02-16 at 20:06 +0100, Esben Nielsen wrote:

>>>Why does the list have to be in userspace?
>>
>>because it's faster ;)

> Faster??? 
> As I see it, extra manipulations have to be done even in the non-congested
> case: Every time the lock is taken the locking thread has to add the lock
> to a the list, and reversely remove the lock from the list. I.e.
> instructions are _added_ to the fast path where you stay purely in
> userspace.
> 
> I am ofcourse comparing to a solution where you do a syscall on everytime
> you do a lock.


The whole *point* of futexes is that on uncontested operations you don't 
have to do a syscall.  Thus, if you can avoid taking a syscall while 
still getting reliability, you'll be faster.

Dropping to kernelspace isn't free.

Chris


  parent reply	other threads:[~2006-02-16 20:24 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-02-16  9:41 [patch 0/6] lightweight robust futexes: -V3 Ingo Molnar
2006-02-16 16:33 ` Daniel Walker
2006-02-16 17:24   ` Ingo Molnar
2006-02-16 17:34     ` Daniel Walker
2006-02-16 19:06       ` [patch 0/6] lightweight robust futexes: -V3 - Why in userspace? Esben Nielsen
2006-02-16 19:34         ` Arjan van de Ven
2006-02-16 20:04           ` Esben Nielsen
2006-02-16 20:17             ` Esben Nielsen
2006-02-16 20:23             ` Christopher Friesen [this message]
2006-02-16 20:36             ` Ingo Molnar
2006-02-16 22:32               ` Esben Nielsen
2006-02-16 22:36                 ` Ingo Molnar
2006-02-16 23:20                   ` Esben Nielsen
2006-02-16 23:39                     ` Ingo Molnar
2006-02-17  0:20                       ` Esben Nielsen
2006-02-17  0:42                         ` Ingo Molnar
2006-02-17 23:47                     ` Andrew James Wade
2006-02-16 20:23       ` [patch 0/6] lightweight robust futexes: -V3 Ingo Molnar
2006-02-16 20:54         ` Daniel Walker
2006-02-16 21:26           ` Ingo Molnar
2006-02-16 21:50             ` Christopher Friesen
2006-02-16 21:55               ` Ingo Molnar
2006-02-16 20:47       ` Paul Jackson
2006-02-16 21:35         ` Ingo Molnar
2006-02-16 21:23 ` Paul Jackson
2006-02-16 21:50   ` Ingo Molnar
2006-02-17  4:56     ` Paul Jackson
2006-02-17  9:41       ` Ingo Molnar
2006-02-17 11:59       ` Ingo Molnar
2006-02-17 20:50         ` Paul Jackson

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=43F4DF54.6030303@nortel.com \
    --to=cfriesen@nortel.com \
    --cc=akpm@osdl.org \
    --cc=arjan@infradead.org \
    --cc=drepper@redhat.com \
    --cc=dwalker@mvista.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=simlo@phys.au.dk \
    --cc=tglx@linutronix.de \
    /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