public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: "Pádraig Brady" <P@draigBrady.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: userspace pagecache management tool
Date: Mon, 5 Mar 2007 03:12:05 -0800	[thread overview]
Message-ID: <20070305031205.61590e55.akpm@linux-foundation.org> (raw)
In-Reply-To: <45EBF8D3.1020609@draigBrady.com>

On Mon, 05 Mar 2007 11:02:43 +0000 Pádraig Brady <P@draigBrady.com> wrote:

> Andrew Morton wrote:
> > I've uploaded to http://userweb.kernel.org/~akpm/pagecache-management/ a
> > little tool which permits the management of the pagecache usage of
> > arbitrary applications.  Effectively it prevents the targetted application
> > from using any pagecache at all.
> 
> Cool, Kinda like noca?
> http://kernel.umbrella.ro/vm/

yup, same concept.

> Though I could easily read your code,
> but couldn't immediately figure out what noca was doing.
> 
> I used posix_fadvise in an app I did recently:
> http://www.pixelbeat.org/programs/dvd-vr/
> There is a stream_data() func there that does:
> 
> read(src)
> write(dst)
> posix_fadvise(src)
> posix_fadvise(dst)
> 
> for performance I found I needed to do it in that order
> so that any readahead done with the read(src)
> was not thrown away by the posix_fadvise(src).
> In addition to the order, one must be careful
> to throw away only what you've actually written.
> 
> I'm not sure your lib gives enough control over this,
> as you essentially do:
> 
> posix_fadvise(src)
> read(src)
> posix_fadvise(dst)
> write(dst)

That could be so - it's just a demo.  But readahead should be OK - I only
invalidate from start-of-file up to current-offset-minus-pagesize.  So the
cache at and ahead of the linear reader is undisturbed.



      reply	other threads:[~2007-03-05 11:12 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-03-03 20:29 userspace pagecache management tool Andrew Morton
2007-03-03 20:40 ` Rik van Riel
2007-03-03 21:12   ` Andrew Morton
2007-03-03 21:30     ` Rik van Riel
2007-03-03 21:41       ` bert hubert
2007-03-03 22:14         ` Andrew Morton
2007-03-03 22:19           ` Rik van Riel
2007-03-03 22:26             ` Andrew Morton
2007-03-03 22:28               ` Rik van Riel
2007-03-03 22:38                 ` Andrew Morton
2007-03-03 22:56               ` Erik Andersen
2007-03-03 23:01               ` bert hubert
2007-03-03 23:45                 ` Andrew Morton
2007-03-06 12:10                   ` Pádraig Brady
2007-03-06 21:40                     ` Andrew Morton
2007-03-06 21:44                       ` Rik van Riel
2007-03-07 11:39                       ` Pádraig Brady
2007-03-07 18:50                         ` Andrew Morton
2007-03-08  7:59                   ` Vaidyanathan Srinivasan
2007-03-08  8:12                     ` Andrew Morton
2007-03-03 22:07       ` Andrew Morton
2007-03-03 22:25         ` Rik van Riel
2007-03-03 22:37           ` Andrew Morton
2007-03-03 22:52           ` Andrew Morton
2007-03-04  0:01             ` Rik van Riel
2007-03-04  1:02               ` Andrew Morton
2007-03-04  1:23                 ` Rik van Riel
2007-03-04  1:49                   ` Andrew Morton
2007-03-04  1:56                     ` Rik van Riel
2007-03-04 12:07                       ` Andrew Morton
2007-03-04 14:35                         ` Peter Zijlstra
2007-03-04 16:01                         ` Rik van Riel
2007-03-03 22:58 ` Ray Lee
2007-03-03 23:34   ` Andrew Morton
2007-03-04  1:02     ` Ray Lee
2007-03-04  1:21       ` Andrew Morton
2007-03-04  0:14 ` Eric St-Laurent
2007-03-04  1:10   ` Andrew Morton
2007-03-04  1:39   ` Rik van Riel
2007-03-04  1:16 ` Lee Revell
2007-03-04  1:39   ` Andrew Morton
2007-03-04  2:35     ` Lee Revell
2007-03-04  4:35       ` Andrew Morton
2007-03-05 11:02 ` Pádraig Brady
2007-03-05 11:12   ` Andrew Morton [this message]

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=20070305031205.61590e55.akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=P@draigBrady.com \
    --cc=linux-kernel@vger.kernel.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