All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Machek <pavel@ucw.cz>
To: Andi Kleen <andi@firstfloor.org>
Cc: Luciano Rocha <luciano@eurotux.com>,
	Michael Meyer <mike65134@yahoo.de>,
	linux-kernel@vger.kernel.org
Subject: Re: performance differences: "maxcpus=1" vs. "echo 0 > /sys/devices/system/cpu/cpu1/online"
Date: Fri, 28 Mar 2008 15:00:57 +0100	[thread overview]
Message-ID: <20080328140056.GC4404@ucw.cz> (raw)
In-Reply-To: <87abkmhgg0.fsf@basil.nowhere.org>

On Tue 2008-03-25 18:16:47, Andi Kleen wrote:
> Luciano Rocha <luciano@eurotux.com> writes:
> 
> > On Tue, Mar 25, 2008 at 02:47:50PM +0100, Michael Meyer wrote:
> > > Hi, 
> > > 
> > > what is the difference between booting a dual core
> > > machine with "maxcpus=1" or by deactivating the second
> > > core at run time with "echo 0 >
> > > /sys/devices/system/cpu/cpu1/online"?
> > 
> > maxcpus=1 should turn off the SMP alternative and switch to UP only,
> > optimising some locks and instructions.
> 
> CPU hot unplug will do the same. But it is unlikely it accounts
> for that much performance difference.
> 
> If he used maxcpus=0 it would make sense. maxcpus=0 disables
> the IO-APIC which likely makes a large difference. But it should
> be actually slower.
> 
> There should be actually no difference in theory between max_cpus=1
> and hot unplug to one CPU. Might be some bug.

Or thermal effect.  I'd expect that behaviour with bad cooling.

							Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

  parent reply	other threads:[~2008-03-28 20:09 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-25 13:47 performance differences: "maxcpus=1" vs. "echo 0 > /sys/devices/system/cpu/cpu1/online" Michael Meyer
2008-03-25 14:08 ` Luciano Rocha
2008-03-25 16:38   ` Michael Meyer
2008-03-25 17:16   ` Andi Kleen
2008-03-25 17:23     ` Michael Meyer
2008-03-25 17:49       ` Wander Winkelhorst
2008-03-25 17:56         ` Michael Meyer
2008-03-25 17:57         ` Andi Kleen
2008-03-25 23:27       ` Len Brown
2008-03-26  7:26         ` Michael Meyer
2008-03-28 14:00     ` Pavel Machek [this message]
2008-03-28 13:59 ` Pavel Machek
2008-03-29 20:55   ` Michael Meyer
2008-03-29 21:22     ` Pavel Machek
2008-03-29 22:16       ` Michael Meyer
2008-04-02 11:31         ` Pavel Machek
2008-03-29 23:22 ` Bernd Eckenfels

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=20080328140056.GC4404@ucw.cz \
    --to=pavel@ucw.cz \
    --cc=andi@firstfloor.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luciano@eurotux.com \
    --cc=mike65134@yahoo.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 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.