From: Davide Libenzi <davidel@xmailserver.org>
To: Ulrich Drepper <drepper@redhat.com>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: getting processor numbers
Date: Tue, 3 Apr 2007 12:15:14 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0704031152370.23808@alien.or.mcafeemobile.com> (raw)
In-Reply-To: <461286D6.2040407@redhat.com>
On Tue, 3 Apr 2007, Ulrich Drepper wrote:
> More and more code depends on knowing the number of processors in the
> system to efficiently scale the code. E.g., in OpenMP it is used by
> default to determine how many threads to create. Creating more threads
> than there are processors/cores doesn't make sense.
>
> glibc for a long time provides functionality to retrieve the number
> through sysconf() and this is what fortunately most programs use. The
> problem is that we are currently using /proc/cpuinfo since this is all
> there was available at that time. Creating /proc/cpuinfo takes the
> kernel quite a long time, unfortunately (I think Jakub said it is mainly
> the interrupt information).
>
> The alternative today is to use /sys/devices/system/cpu and count the
> number of cpu* directories in it. This is somewhat faster. But there
> would be another possibility: simply stat /sys/devices/system/cpu and
> use st_nlink - 2.
>
> This last step unfortunately it made impossible by recent changes:
>
> http://article.gmane.org/gmane.linux.kernel/413178
>
> I would like to propose changing that patch, move the sched_*
> pseudo-files in some other directly and permanently ban putting any new
> file into /sys/devices/system/cpu.
>
> To get some numbers, you can try
>
> http://people.redhat.com/drepper/nproc-timing.c
>
> The numbers I see on x86-64:
>
> cpuinfo 10145810 cycles for 100 accesses
> readdir /sys 3113870 cycles for 100 accesses
> stat /sys 741070 cycles for 100 accesses
It sucks when seen from a micro-bench POV, but does it really matter
overall? The vast majority of software usually calls
sysconf(_SC_NPROCESSORS_*) with very little frequency (mostly once at
initialization time) anyway. That's what 50us / call?
- Davide
next prev parent reply other threads:[~2007-04-03 19:15 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-03 16:54 Ulrich Drepper
2007-04-03 17:30 ` linux-os (Dick Johnson)
2007-04-03 17:37 ` Ulrich Drepper
2007-04-03 17:56 ` Dr. David Alan Gilbert
2007-04-03 18:11 ` Andi Kleen
2007-04-03 17:17 ` Ulrich Drepper
2007-04-03 17:22 ` Alan Cox
2007-04-03 17:30 ` Andi Kleen
2007-04-03 20:24 ` Jeremy Fitzhardinge
2007-04-03 17:27 ` Andi Kleen
2007-04-03 17:30 ` Ulrich Drepper
2007-04-03 17:35 ` Andi Kleen
2007-04-03 17:45 ` Ulrich Drepper
2007-04-03 17:58 ` Andi Kleen
2007-04-03 18:05 ` Ulrich Drepper
2007-04-03 18:11 ` Andi Kleen
2007-04-03 18:21 ` Ulrich Drepper
2007-04-03 17:44 ` Siddha, Suresh B
2007-04-03 17:59 ` Ulrich Drepper
2007-04-03 19:40 ` Jakub Jelinek
2007-04-03 20:13 ` Ingo Oeser
2007-04-03 23:38 ` J.A. Magallón
2007-04-03 19:55 ` Ulrich Drepper
2007-04-03 20:13 ` Siddha, Suresh B
2007-04-03 20:19 ` Ulrich Drepper
2007-04-03 20:32 ` Eric Dumazet
2007-04-03 20:20 ` Nathan Lynch
2007-04-03 19:15 ` Davide Libenzi [this message]
2007-04-03 19:32 ` Ulrich Drepper
2007-04-04 0:31 ` H. Peter Anvin
2007-04-04 0:35 ` Jeremy Fitzhardinge
2007-04-04 0:38 ` H. Peter Anvin
2007-04-04 5:09 ` Eric Dumazet
2007-04-04 5:16 ` H. Peter Anvin
2007-04-04 5:22 ` Jeremy Fitzhardinge
2007-04-04 5:40 ` H. Peter Anvin
2007-04-04 5:46 ` Eric Dumazet
2007-04-04 5:29 ` Eric Dumazet
2007-04-03 20:16 ` Andrew Morton
[not found] ` <4612BB89.8040102@redhat.com>
[not found] ` <20070403141348.9bcdb13e.akpm@linux-foundation.org>
2007-04-03 22:13 ` Ulrich Drepper
2007-04-03 22:48 ` Andrew Morton
2007-04-03 23:00 ` Ulrich Drepper
2007-04-03 23:23 ` Andrew Morton
2007-04-03 23:54 ` Ulrich Drepper
2007-04-04 2:55 ` Paul Jackson
2007-04-04 8:39 ` Oleg Nesterov
2007-04-04 9:39 ` Ingo Molnar
2007-04-04 8:57 ` Oleg Nesterov
2007-04-04 10:01 ` Ingo Molnar
2007-04-04 2:58 ` Paul Jackson
2007-04-04 3:04 ` Paul Jackson
2007-04-04 2:52 ` Paul Jackson
2007-04-04 2:04 ` Paul Jackson
2007-04-04 6:47 ` Jakub Jelinek
2007-04-04 7:02 ` Paul Jackson
2007-04-04 14:51 ` Cliff Wickman
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=Pine.LNX.4.64.0704031152370.23808@alien.or.mcafeemobile.com \
--to=davidel@xmailserver.org \
--cc=akpm@linux-foundation.org \
--cc=drepper@redhat.com \
--cc=linux-kernel@vger.kernel.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 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®