linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Anil Kumar Nanduri <anil@india.hp.com>
To: Jonathan Morton <chromi@chromatix.demon.co.uk>
Cc: Anil Kumar <anilk@cdotd.ernet.in>,
	Rik van Riel <riel@conectiva.com.br>,
	linux-mm@kvack.org
Subject: Re: Regarding Page Cache ,Buffer Cachein  disabling in LinuxKernel.
Date: Tue, 30 Jul 2002 12:25:14 +0530	[thread overview]
Message-ID: <3D463852.E6F18815@india.hp.com> (raw)
In-Reply-To: <a05111b09b96bcf853061@[192.168.239.105]>

Hi Anil,
    I suggest you to read some documents on 2.4 linux memory management
    http://home.earthlink.net/~jknapka/linux-mm/pagecache.html
    then read code of 2.4.

    Actually in 2.4 both the swap cache and page cache are unified with
    the concept of struct address_space,
    I mean Any physical page will be in active list (or) inactive clean list
    (or) inactive dirty list.

    If that page is mmaped one (i mean if it is for a file) then it will also
be
    in the inode list of that file (no swap for this page).

    If that page was identified to be swapped(!mmaped || !text || etc..)
    out then it will also be in the swapper_space inode queue until it
    is reclaimed by the system.

    Please remember it is the same page which is on two queues( not two copies)

    In your case As you will not be having any swap...
    all the mmaped files(if you have mounted partition with r/rw),
    text region of executables  will still behave as if they have swap.

    but for other pages which actually need swap like data segments
    will not be in swapper_space inode queue as the get_swap_page()
    function will fail to return an valid entry.

    Now tell me why do you want to disable page cache/ swap cache?

    May be i will suggest you one thing that might be of use to you is
    to have a compressed memory based swap
    ( I am thinking of implementing).

Please let me know if i am not clear enough.

Thanks,
-anil.


Jonathan Morton wrote:

> >  a) i allow page caching then there is going to be 2 copies of
> >   data in my system and i want to avoid it.
>
> If you're using memory, the pages will be evicted from the cache.  It
> is NOT a problem.
>
> --
> --------------------------------------------------------------
> from:     Jonathan "Chromatix" Morton
> mail:     chromi@chromatix.demon.co.uk
> website:  http://www.chromatix.uklinux.net/
> geekcode: GCS$/E dpu(!) s:- a21 C+++ UL++ P L+++ E W+ N- o? K? w--- O-- M++$
>            V? PS PE- Y+ PGP++ t- 5- X- R !tv b++ DI+++ D G e+ h+ r++ y+(*)
> tagline:  The key to knowledge is not to rely on people to teach you it.
> --
> 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/

--
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/

      reply	other threads:[~2002-07-30  6:55 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-07-29 13:30 Regarding Page Cache ,Buffer Cachein disabling in Linux Kernel Anil Kumar
2002-07-29 14:22 ` Rik van Riel
2002-07-30  5:19   ` Anil Kumar
2002-07-30  5:07     ` Jonathan Morton
2002-07-30  6:55       ` Anil Kumar Nanduri [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=3D463852.E6F18815@india.hp.com \
    --to=anil@india.hp.com \
    --cc=anilk@cdotd.ernet.in \
    --cc=chromi@chromatix.demon.co.uk \
    --cc=linux-mm@kvack.org \
    --cc=riel@conectiva.com.br \
    /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