[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: shared pagetable benchmarking

To: Linus Torvalds <torvalds@transmeta.com>
Subject: Re: shared pagetable benchmarking
From: Dave McCracken <dmc@austin.ibm.com>
Date: Fri, 27 Dec 2002 14:16:34 -0600
cc: Daniel Phillips <phillips@arcor.de>,Andrew Morton <akpm@digeo.com>, linux-mm@kvack.org
Fake-Sender: owner-linux-mm@kvack.org
In-Reply-To: <Pine.LNX.4.44.0212271201130.21930-100000@home.transmeta.com>
Original-Recipient: rfc822;linux-mm-archive@humbolt.geo.uu.nl
References: <Pine.LNX.4.44.0212271201130.21930-100000@home.transmeta.com>
Sender: Rik van Riel <riel@nl.linux.org>

--On Friday, December 27, 2002 12:02:56 -0800 Linus Torvalds
<torvalds@transmeta.com> wrote:

> It doesn't break even on small forks. It _slows_them_down_.

I gave Andrew a patch that does make it break even on small forks, by doing
the copy at fork time when a process only has 3 pte pages.  My tests
indicate that any process with 4 or more pte pages usually is faster by
doing the share.

Dave McCracken

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/

Follow-Ups:
- Re: shared pagetable benchmarking
  - From: Linus Torvalds <torvalds@transmeta.com>

References:
- Re: shared pagetable benchmarking
  - From: Linus Torvalds <torvalds@transmeta.com>

Prev by Date: Re: shared pagetable benchmarking
Next by Date: Re: shared pagetable benchmarking
Prev by thread: Re: shared pagetable benchmarking
Next by thread: Re: shared pagetable benchmarking
Index(es):
- Date
- Thread