From: Andrew Morton <akpm@linux-foundation.org>
To: Andi Kleen <andi@firstfloor.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH prototype] [0/8] Predictive bitmaps for ELF executables
Date: Tue, 18 Mar 2008 00:36:20 -0700 [thread overview]
Message-ID: <20080318003620.d84efb95.akpm@linux-foundation.org> (raw)
In-Reply-To: <20080318209.039112899@firstfloor.org>
On Tue, 18 Mar 2008 02:09:34 +0100 (CET) Andi Kleen <andi@firstfloor.org> wrote:
> This patchkit is an experimental optimization I played around with
> some time ago.
>
> This is more a prototype still, but I wanted to push it out
> so that other people can play with it.
>
> The basic idea is that most programs have the same working set
> over multiple runs. So instead of demand paging all the text pages
> in the order the program runs save the working set to disk and prefetch
> it at program start and then save it at program exit.
>
> This allows some optimizations:
> - it can avoid unnecessary disk seeks because the blocks will be fetched in
> sorted offset order instead of program execution order.
> - batch kernel entries (each demand page exception has some
> overhead just for entering the kernel). This keeps the caches hot too.
> - The prefetch could be in theory done in the background while the program
> runs (although that is not implemented currently)
Should be worthwhile for some things.
> Some details on the implementation:
Can't this all be done in userspace? Hook into exit() with an LD_PRELOAD,
use /proc/self/maps and the new pagemap code to work out which pages of
which files were faulted in, write that info into the elf file (or a
separate per-executable shadow file), then use that info the next time the
app is executed, either with an LD_PRELOAD or just a wrapper.
> Drawbacks:
> - No support for dynamic libraries right now (except very clumpsily
> through the mmap_slurp hack). This is the main reason it is not
> very useful for speed up desktops currently.
>
> - Executable files have to be writable by the user executing it
> currently to get bitmap updates. It would be possible to let the
> kernel bypass this, but I haven't thought too much about the security
> implications of it.
> However any user can use the bitmap data written by a user with
> write rights.
Those all get fixed with the userspace version?
--
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:[~2008-03-18 7:36 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-03-18 1:09 [PATCH prototype] [0/8] Predictive bitmaps for ELF executables Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [1/8] Give ELF shdr types a name Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [2/8] Add support to override mmap exec write protection with O_FORCEWRITE Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [3/8] Make readahead max pinned value a sysctl Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [4/8] Add readahead function to read-ahead based on a bitmap Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [5/8] Add ELF constants for pbitmaps Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [6/8] Core predictive bitmap engine Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [7/8] Add the sysctls to control pbitmaps Andi Kleen
2008-03-18 1:09 ` [PATCH prototype] [8/8] Add mmap_full_slurp support Andi Kleen
2008-03-18 7:36 ` Andrew Morton [this message]
2008-03-18 14:18 ` [PATCH prototype] [0/8] Predictive bitmaps for ELF executables Andi Kleen
2008-03-18 16:57 ` Andrew Morton
2008-03-18 17:20 ` Andi Kleen
2008-03-18 17:44 ` Andrew Morton
2008-03-19 8:32 ` Andi Kleen
2008-03-19 9:04 ` Andrew Morton
2008-03-19 22:45 ` Ulrich Drepper
2008-03-19 23:12 ` Andrew Morton
2008-03-20 0:09 ` David Miller, Andrew Morton
2008-03-20 9:00 ` Andi Kleen
2008-03-21 17:15 ` Ulrich Drepper
2008-03-21 17:26 ` Andi Kleen
2008-03-22 4:36 ` Ulrich Drepper
2008-03-22 7:17 ` Andi Kleen
2008-03-22 7:24 ` Nicholas Miell
2008-03-22 9:10 ` Andi Kleen
2008-03-22 10:16 ` Nicholas Miell
2008-03-22 14:29 ` Andi Kleen
2008-03-23 13:25 ` Pavel Machek
2008-03-23 17:08 ` Andi Kleen
2008-03-24 16:24 ` Pavel Machek
2008-03-24 4:20 ` Ulrich Drepper
2008-03-24 5:16 ` Nicholas Miell
2008-03-24 5:26 ` Andi Kleen
2008-03-24 19:42 ` Ulrich Drepper
2008-03-24 21:47 ` Nicholas Miell
2008-03-25 7:54 ` Andi Kleen
2008-03-26 18:15 ` Ulrich Drepper
2008-03-26 18:54 ` Andi Kleen
2008-03-22 4:38 ` Ulrich Drepper
2008-03-20 0:15 ` Diego Calleja
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=20080318003620.d84efb95.akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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;
as well as URLs for NNTP newsgroup(s).