From: Dave McCracken <dmccr@us.ibm.com>
To: Ray Bryant <raybry@mpdtxmail.amd.com>
Cc: Robin Holt <holt@sgi.com>, Hugh Dickins <hugh@veritas.com>,
Linux Kernel <linux-kernel@vger.kernel.org>,
Linux Memory Management <linux-mm@kvack.org>
Subject: Re: [PATCH/RFC] Shared page tables
Date: Mon, 23 Jan 2006 18:19:14 -0600 [thread overview]
Message-ID: <6BC41571790505903C7D3CD6@[10.1.1.4]> (raw)
In-Reply-To: <200601231758.08397.raybry@mpdtxmail.amd.com>
--On Monday, January 23, 2006 17:58:08 -0600 Ray Bryant
<raybry@mpdtxmail.amd.com> wrote:
> Like Robin, I would appreciate a test application, or at least a
> description of how to write one, or some other trick to figure out if
> this is working.
My apologies. I do have a small test program and intended to clean it up
to send to Robin, but got sidetracked (it's fugly at the moment). I'll see
about getting it a bit more presentable.
> I scanned through this thread looking for a test application, and didn't
> see one. Is it sufficient just to create a large shared read-only
> mmap'd file and share it across a bunch of process to get this code
> invoked? How large of a file is needed (on x86_64), assuming that we
> just turn on the pte level of sharing? And what kind of alignment
> constraints do we end up under in order to make the sharing happen?
> (My guess would be that there aren't any such constraints (well, page
> alignment.. :-) if we are just sharing pte's.)
The basic rule for pte sharing is that some portion of a memory region must
span an entire pte page. For i386 and x96_64 that would be 2 meg. The
region must either be read-only or marked to be shared if it is writeable.
The code does opportunistically look for any pte page that is fully within
a shareable vma, and will share if it finds one.
Oh, and one more caveat. The region must be mapped to the same address in
each process.
> I turned on the PT_DEBUG stuff, but thus far have found no evidence of
> pte sharing actually occurring in a normal system boot. I'm surprised
> by that as I (naively?) would have expected shared libraries to use
> shared ptes.
Most system software, including the shared libraries, don't have any
regions that are big enough for sharing (the text section for libc, for
example, is about 1.5 meg).
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2006-01-24 0:19 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-05 16:19 Dave McCracken
2006-01-07 12:25 ` Heiko Carstens
2006-01-07 18:09 ` Dave McCracken
2006-01-08 12:09 ` Heiko Carstens
2006-01-08 14:04 ` Dave McCracken
2006-01-13 5:15 ` Brian Twichell
2006-01-13 22:34 ` Ray Bryant
2006-01-17 4:50 ` Brian Twichell
2006-01-25 4:14 ` Brian Twichell
2006-01-13 15:18 ` Phillip Susi
2006-01-14 20:45 ` Brian Twichell
2006-01-17 23:53 ` Robin Holt
2006-01-18 0:17 ` Dave Hansen
2006-01-18 6:11 ` Dave McCracken
2006-01-18 1:27 ` Chen, Kenneth W
2006-01-18 3:32 ` Robin Holt
2006-01-23 23:58 ` Ray Bryant
2006-01-24 0:16 ` Ray Bryant
2006-01-24 0:39 ` Andi Kleen
2006-01-24 0:51 ` Dave McCracken
2006-01-24 1:11 ` Andi Kleen
2006-01-24 1:26 ` Dave McCracken
2006-01-24 0:53 ` Ray Bryant
2006-01-24 1:00 ` Dave McCracken
2006-01-24 1:10 ` Andi Kleen
2006-01-24 1:23 ` Benjamin LaHaise
2006-01-24 1:38 ` Andi Kleen
2006-01-24 7:08 ` Arjan van de Ven
2006-01-24 7:06 ` Arjan van de Ven
2006-01-24 7:18 ` Andi Kleen
2006-01-27 18:16 ` Martin Bligh
2006-02-01 9:49 ` Nick Piggin
2006-01-24 14:48 ` Dave McCracken
2006-01-24 14:56 ` Arjan van de Ven
2006-01-24 0:19 ` Dave McCracken [this message]
2006-01-24 0:46 ` Ray Bryant
2006-01-24 23:43 ` Ray Bryant
2006-01-24 23:50 ` Dave McCracken
2006-01-25 0:21 ` Ray Bryant
2006-01-25 22:48 ` Ray Bryant
2006-01-25 22:52 ` Dave McCracken
2006-01-26 0:16 ` Ray Bryant
2006-01-26 0:58 ` Ray Bryant
2006-01-26 4:06 ` Robin Holt
2006-01-20 21:24 ` Hugh Dickins
2006-01-20 21:54 ` Chen, Kenneth W
2006-01-23 17:39 ` Dave McCracken
2006-01-23 20:19 ` Benjamin LaHaise
2006-01-24 17:50 ` Hugh Dickins
2006-01-24 18:07 ` Dave McCracken
2006-01-24 18:20 ` Hugh Dickins
2006-01-27 22:50 ` Brian Twichell
2006-01-30 18:46 ` Ray Bryant
2006-01-31 18:47 ` Brian Twichell
2006-01-31 19:18 ` Dave McCracken
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='6BC41571790505903C7D3CD6@[10.1.1.4]' \
--to=dmccr@us.ibm.com \
--cc=holt@sgi.com \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=raybry@mpdtxmail.amd.com \
/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