mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Ingo Oeser <ingo.oeser@informatik.tu-chemnitz.de>
To: Ulrich Drepper <drepper@cygnus.com>
Cc: Linus Torvalds <torvalds@transmeta.com>,
	Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: light weight user level semaphores
Date: Thu, 19 Apr 2001 22:22:28 +0200	[thread overview]
Message-ID: <20010419222228.J682@nightmaster.csn.tu-chemnitz.de> (raw)
In-Reply-To: <Pine.LNX.4.31.0104191036220.5052-100000@penguin.transmeta.com> <m3ofts3d4k.fsf@otr.mynet.cygnus.com>
In-Reply-To: <m3ofts3d4k.fsf@otr.mynet.cygnus.com>; from drepper@redhat.com on Thu, Apr 19, 2001 at 12:26:03PM -0700

On Thu, Apr 19, 2001 at 12:26:03PM -0700, Ulrich Drepper wrote:
> In any case all kinds of user-level operations are possible as well
> and all the schemes suggested for dealing with the common case without
> syscalls can be applied here as well.

Are you sure, you can implement SMP-safe, atomic operations (which you need
for all up()/down() in user space) WITHOUT using privileged
instructions on ALL archs Linux supports?

How do we do this on nccNUMA machines later? How on clusters[1]?

On what I can see in asm-*/atomic.h this is not possible, but I
probably miss sth. here ;-)

I didn't know that POSIX forbids using fds to implement a
semaphore. That's VERY bad.

Learning new APIs always means making a lot of mistakes and doing
this while we write production code, since nobody likes to pay for
experiments.

And I still see no point on speeding of creation and contention,
since these should be rare cases and the application overusing
these should be punished HARD.

Maybe someone can enlighten my on these aspects.

Regards

Ingo Oeser

[1] Ok, people already use other than Unix mechanisms for this
   stuff on massive parallel computing. So this might not be an
   issue. Only for libc internal sema4s
-- 
10.+11.03.2001 - 3. Chemnitzer LinuxTag <http://www.tu-chemnitz.de/linux/tag>
         <<<<<<<<<<<<     been there and had much fun   >>>>>>>>>>>>

  parent reply	other threads:[~2001-04-19 20:22 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20010417114433.D1108@w-mikek2.sequent.com>
2001-04-17 19:48 ` Linus Torvalds
2001-04-18 18:13   ` Bernd Eckenfels
2001-04-18 19:35   ` Ulrich Drepper
2001-04-19  8:20     ` Alon Ziv
2001-04-19  8:52       ` Abramo Bagnara
2001-04-19  9:08         ` Alexander Viro
2001-04-19 10:44           ` Abramo Bagnara
2001-04-19 16:11         ` Linus Torvalds
2001-04-19 16:33           ` Alexander Viro
2001-04-19 16:43             ` Linus Torvalds
2001-04-19 17:33               ` Alexander Viro
2001-04-19 17:38                 ` Linus Torvalds
2001-04-19 18:24                   ` Alexander Viro
2001-04-19 19:26                   ` Ulrich Drepper
2001-04-19 19:35                     ` Alan Cox
2001-04-19 20:06                       ` Ulrich Drepper
2001-04-19 20:11                         ` Alan Cox
2001-04-19 20:26                           ` Ulrich Drepper
2001-04-19 20:22                     ` Ingo Oeser [this message]
2001-04-19 20:40                       ` Ulrich Drepper
2001-04-19 20:51                       ` Linus Torvalds
2001-04-19 21:38                       ` Alan Cox
2001-04-19 20:49                     ` Linus Torvalds
2001-04-19 21:18                       ` Ulrich Drepper
2001-04-19 21:41                         ` Linus Torvalds
2001-04-19 22:46                           ` Ulrich Drepper
2001-04-20  1:35                             ` Alexander Viro
2001-04-20  2:45                               ` Ulrich Drepper
2001-04-19 16:43           ` Abramo Bagnara
2001-04-19 20:47           ` Ingo Oeser
2001-04-19 20:54             ` Linus Torvalds
2001-04-19  9:08       ` Ingo Oeser
2001-04-19 11:51       ` Alan Cox
2001-04-19 16:03       ` Linus Torvalds
2001-04-19 16:38         ` Alan Cox
2001-04-19 16:46           ` Linus Torvalds
2001-04-19 17:12             ` Alan Cox
2001-04-19 22:35               ` Rogier Wolff
2001-04-20  9:29             ` Olaf Titz
2001-04-20 14:19               ` Jesse Pollard
2001-04-20 18:36                 ` Olaf Titz
2001-04-20 23:33               ` Linus Torvalds
2001-04-21  4:06                 ` fd allocation [was: light weight user level semaphores] Edgar Toernig
2001-04-22  9:48                   ` Olaf Titz
2001-04-22 11:41                     ` light weight user level semaphores Alon Ziv
2001-04-22 12:44                       ` Alan Cox
2001-04-22 15:19                         ` Alon Ziv
2001-04-22 14:31                           ` Alexander Viro
2001-04-22 16:08                             ` Alon Ziv
2001-04-22 11:41                     ` Alon Ziv
2001-04-22 14:18                     ` David Woodhouse
2001-04-23 13:19                       ` David Howells
2001-04-23 14:48                         ` Alon Ziv
2001-04-23 15:40                           ` David Howells
2001-04-21 10:13                 ` Olaf Titz
2001-04-23 15:34                 ` Jeff Garzik
2001-04-23 19:18             ` Ingo Oeser
2001-04-24  0:19             ` David Wagner
2001-04-24  0:41               ` Alexander Viro
2001-04-19 19:47           ` Ulrich Drepper
2001-04-19 18:48         ` Olaf Titz
2001-04-19 13:59 George Talbot

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=20010419222228.J682@nightmaster.csn.tu-chemnitz.de \
    --to=ingo.oeser@informatik.tu-chemnitz.de \
    --cc=drepper@cygnus.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@transmeta.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

all inboxes | Powered by JetHome®