From: "Benjamin C.R. LaHaise" <blah@kvack.org>
To: "Stephen C. Tweedie" <sct@dcs.ed.ac.uk>
Cc: linux-mm@kvack.org
Subject: Re: PATCH: Swap shared pages (was: How to read-protect a vm_area?)
Date: Mon, 23 Feb 1998 19:08:59 -0500 (U\x01) [thread overview]
Message-ID: <Pine.LNX.3.95.980223184015.28517B-100000@as200.spellcast.com> (raw)
In-Reply-To: <199802232317.XAA06136@dax.dcs.ed.ac.uk>
Hello,
On Mon, 23 Feb 1998, Stephen C. Tweedie wrote:
...
> The patch below, against 2.1.88, adds a bunch of new functionality to
> the swapper. The main changes are:
>
> * All swapping goes through the swap cache (aka. page cache) now.
...
I noticed you're using just one inode for the swapper/page cache... What
I've been working on is a slightly different approach: Create inodes for
each anonymous mapping. The actual implementation uses one inode per
mm_struct, with the virtual address within the process providing the
offset. This has the advantage of giving us an easy way to find all ptes
that use an anonymous page. Anonymous mappings end up looking more like
shared mappings, which gives us some interesting possibilities - it
becomes almost trivial to implement a MAP_SHARED on another process'
address space. What do you think of this approach? My main goal is to
reimplement the page-oriented swapping my pte-list patch performed, which
makes the running time try_to_free_page drastically shorter, even
predictable... (at most 1 pass over mem_map to find a page using the old
style aging, or just one list operation using the inactive list approach)
-ben
next prev parent reply other threads:[~1998-02-24 0:08 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <199802192321.XAA06580@dax.dcs.ed.ac.uk>
1998-02-20 5:41 ` How to read-protect a vm_area? Benjamin C.R. LaHaise
1998-02-23 23:17 ` PATCH: Swap shared pages (was: How to read-protect a vm_area?) Stephen C. Tweedie
1998-02-23 23:27 ` Linus Torvalds
1998-02-24 0:08 ` Benjamin C.R. LaHaise [this message]
1998-02-24 9:45 ` Stephen C. Tweedie
1998-02-24 9:42 ` Rik van Riel
1998-02-24 23:38 ` Stephen C. Tweedie
1998-02-25 10:41 ` Rik van Riel
1998-02-25 19:00 ` Stephen C. Tweedie
1998-02-25 22:05 ` Rik van Riel
1998-02-24 11:16 ` Thomas Sailer
[not found] ` <Pine.LNX.3.96.980224152231.7112A-100000@renass3.u-strasbg.fr>
1998-02-24 23:38 ` Stephen C. Tweedie
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.3.95.980223184015.28517B-100000@as200.spellcast.com \
--to=blah@kvack.org \
--cc=linux-mm@kvack.org \
--cc=sct@dcs.ed.ac.uk \
/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