From: Ulrich Drepper <drepper@redhat.com>
To: Pierre Peiffer <pierre.peiffer@bull.net>
Cc: Jakub Jelinek <jakub@redhat.com>,
LKML <linux-kernel@vger.kernel.org>,
Dinakar Guniguntala <dino@in.ibm.com>,
Jean-Pierre Dion <jean-pierre.dion@bull.net>,
Ingo Molnar <mingo@elte.hu>, Darren Hart <dvhltc@us.ibm.com>,
Sebastien Dugue <sebastien.dugue@bull.net>
Subject: Re: [PATCH 2.6.20-rc4 1/4] futex priority based wakeup
Date: Wed, 10 Jan 2007 10:15:06 -0800 [thread overview]
Message-ID: <45A52D2A.2030300@redhat.com> (raw)
In-Reply-To: <45A500CC.3030408@bull.net>
[-- Attachment #1: Type: text/plain, Size: 689 bytes --]
Pierre Peiffer wrote:
> But there can be a performance impact when several processes use
> different futexes which have the same hash key.
> In fact, the plist contains all waiters _of_all_futexes_ having the same
> hash key, not only the waiters of a given futex. This can be more a
> problem,
s/can be/is/
There are systems with thousands of active futexes, maybe tens of
thousands. Not only is hash collision likely, it's also a matter of
using and administering the plist. We have to make futexes less
connected, not more. Now I definitely want to see real world tests first.
--
➧ Ulrich Drepper ➧ Red Hat, Inc. ➧ 444 Castro St ➧ Mountain View, CA ❖
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 251 bytes --]
next prev parent reply other threads:[~2007-01-10 18:15 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <45A3B330.9000104@bull.net>
2007-01-09 16:16 ` [PATCH 2.6.20-rc4 1/4] futex priority based wakeup Pierre Peiffer
2007-01-09 16:29 ` Ulrich Drepper
2007-01-10 11:47 ` Pierre Peiffer
2007-01-10 12:03 ` Pierre Peiffer
2007-01-10 12:54 ` Jakub Jelinek
2007-01-10 15:05 ` Pierre Peiffer
2007-01-10 18:15 ` Ulrich Drepper [this message]
2007-01-11 7:20 ` Ulrich Drepper
2007-01-09 17:59 ` Daniel Walker
2007-01-10 16:11 ` Daniel Walker
2007-01-10 16:29 ` Pierre Peiffer
2007-01-10 16:33 ` Daniel Walker
2007-01-09 16:16 ` [PATCH 2.6.20-rc4 2/4] Make futex_wait() use an hrtimer for timeout Pierre Peiffer
2007-01-09 16:20 ` [PATCH 2.6.20-rc4 3/4] futex_requeue_pi optimization Pierre Peiffer
2007-01-09 16:33 ` Ulrich Drepper
2007-01-10 8:17 ` Pierre Peiffer
2007-01-10 8:24 ` Ulrich Drepper
2007-01-09 16:25 ` [PATCH 2.6.20-rc4 4/4][RFC] sys_futex64 : allows 64bit futexes Pierre Peiffer
2007-01-11 21:49 ` Andrew Morton
2007-01-11 22:14 ` Jakub Jelinek
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=45A52D2A.2030300@redhat.com \
--to=drepper@redhat.com \
--cc=dino@in.ibm.com \
--cc=dvhltc@us.ibm.com \
--cc=jakub@redhat.com \
--cc=jean-pierre.dion@bull.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=pierre.peiffer@bull.net \
--cc=sebastien.dugue@bull.net \
/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.