From: Nikita Danilov <nikita@clusterfs.com>
To: Howard Chu <hyc@symas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Robert Hancock <hancockr@shaw.ca>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: sched_yield() makes OpenLDAP slow
Date: Sun, 21 Aug 2005 15:33:02 +0400 [thread overview]
Message-ID: <17160.26222.678122.362194@gargle.gargle.HOWL> (raw)
In-Reply-To: <43079FA9.700@symas.com>
Howard Chu writes:
> Lee Revell wrote:
> > On Sat, 2005-08-20 at 11:38 -0700, Howard Chu wrote:
> > > But I also found that I needed to add a new yield(), to work around
> > > yet another unexpected issue on this system - we have a number of
> > > threads waiting on a condition variable, and the thread holding the
> > > mutex signals the var, unlocks the mutex, and then immediately
> > > relocks it. The expectation here is that upon unlocking the mutex,
> > > the calling thread would block while some waiting thread (that just
> > > got signaled) would get to run. In fact what happened is that the
> > > calling thread unlocked and relocked the mutex without allowing any
> > > of the waiting threads to run. In this case the only solution was
> > > to insert a yield() after the mutex_unlock().
> >
> > That's exactly the behavior I would expect. Why would you expect
> > unlocking a mutex to cause a reschedule, if the calling thread still
> > has timeslice left?
>
> That's beside the point. Folks are making an assertion that
> sched_yield() is meaningless; this example demonstrates that there are
> cases where sched_yield() is essential.
It is not essential, it is non-portable.
Code you described is based on non-portable "expectations" about thread
scheduling. Linux implementation of pthreads fails to satisfy
them. Perfectly reasonable. Code is then "fixed" by adding sched_yield()
calls and introducing more non-portable assumptions. Again, there is no
guarantee this would work on any compliant implementation.
While "intuitive" semantics of sched_yield() is to yield CPU and to give
other runnable threads their chance to run, this is _not_ what standard
prescribes (for non-RT threads).
>
> --
> -- Howard Chu
Nikita.
next prev parent reply other threads:[~2005-08-21 11:33 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4D8eT-4rg-31@gated-at.bofh.it>
2005-08-20 3:20 ` sched_yield() makes OpenLDAP slow Robert Hancock
2005-08-20 4:18 ` Nick Piggin
2005-08-20 18:38 ` Howard Chu
2005-08-20 20:57 ` Lee Revell
2005-08-20 21:24 ` Howard Chu
2005-08-21 0:36 ` Nick Piggin
2005-08-21 11:33 ` Nikita Danilov [this message]
2005-08-22 8:06 ` Howard Chu
2005-08-20 21:50 ` Lee Revell
2005-08-21 1:04 ` Robert Hancock
2005-08-22 11:44 ` linux-os (Dick Johnson)
2005-08-22 14:26 ` Robert Hancock
2005-08-23 11:17 ` linux-os (Dick Johnson)
2005-08-23 12:07 ` Denis Vlasenko
2005-08-24 3:37 ` Lincoln Dale
2006-01-24 22:59 e100 oops on resume Stefan Seyfried
2006-01-24 23:21 ` Mattia Dongili
2006-01-25 9:02 ` Olaf Kirch
2006-01-25 12:11 ` Olaf Kirch
2006-01-25 13:51 ` sched_yield() makes OpenLDAP slow Howard Chu
2006-01-25 14:38 ` Robert Hancock
2006-01-25 17:49 ` Christopher Friesen
2006-01-26 1:07 ` David Schwartz
2006-01-26 8:30 ` Helge Hafting
2006-01-26 9:01 ` Nick Piggin
2006-01-26 10:50 ` Nikita Danilov
[not found] <5uZqb-4fo-15@gated-at.bofh.it>
2006-01-14 22:47 ` Robert Hancock
-- strict thread matches above, loose matches on Subject: below --
2006-01-14 19:29 Howard Chu
[not found] <43057641.70700@symas.com.suse.lists.linux.kernel>
[not found] ` <17157.45712.877795.437505@gargle.gargle.HOWL.suse.lists.linux.kernel>
[not found] ` <430666DB.70802@symas.com.suse.lists.linux.kernel>
2005-08-20 13:48 ` Andi Kleen
2005-08-21 19:47 ` Florian Weimer
2005-08-22 5:09 ` Howard Chu
2005-08-22 13:06 ` Andi Kleen
2005-08-22 18:47 ` Howard Chu
2005-08-22 13:20 ` Florian Weimer
2005-08-22 23:19 ` Howard Chu
2005-08-19 6:03 Howard Chu
2005-08-19 6:34 ` Nick Piggin
2005-08-19 6:59 ` Chris Wedgwood
2005-08-19 22:45 ` Howard Chu
2005-08-19 10:21 ` Nikita Danilov
2005-08-19 23:10 ` Howard Chu
2005-08-20 13:23 ` Nikita Danilov
2005-08-20 19:49 ` Howard Chu
2005-08-20 22:08 ` Nikita Danilov
[not found] <4303DB48.8010902@develer.com.suse.lists.linux.kernel>
[not found] ` <20050818010703.GA13127@nineveh.rivenstone.net.suse.lists.linux.kernel>
[not found] ` <4303F967.6000404@yahoo.com.au.suse.lists.linux.kernel>
[not found] ` <43054D9A.7090509@develer.com.suse.lists.linux.kernel>
2005-08-19 3:19 ` Andi Kleen
2005-08-19 3:30 ` Bernardo Innocenti
2005-08-18 0:50 Bernardo Innocenti
2005-08-18 0:47 ` Con Kolivas
2005-08-18 10:48 ` Maciej Soltysiak
2005-08-18 1:07 ` Joseph Fannin
2005-08-18 2:25 ` Bernardo Innocenti
2005-08-18 2:58 ` Nick Piggin
2005-08-19 3:10 ` Bernardo Innocenti
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=17160.26222.678122.362194@gargle.gargle.HOWL \
--to=nikita@clusterfs.com \
--cc=hancockr@shaw.ca \
--cc=hyc@symas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
/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;
as well as URLs for NNTP newsgroup(s).