All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oleg Drokin <green@namesys.com>
To: Ookhoi <ookhoi@humilis.net>
Cc: reiserfs-list@namesys.com
Subject: Re: reiser4 and 2.5.60
Date: Tue, 18 Feb 2003 13:05:44 +0300	[thread overview]
Message-ID: <20030218130544.A31947@namesys.com> (raw)
In-Reply-To: <20030218105247.D20771@humilis>

Hello!

On Tue, Feb 18, 2003 at 10:52:47AM +0100, Ookhoi wrote:
> > On Tue, Feb 18, 2003 at 10:31:51AM +0100, Ookhoi wrote:
> > > Sure. It is a P-MMX, 200MHz, with 512MB ram, and a 4GB scsi disk.
> > Hm. That must be real slow, is it? (just because not all of the RAM is
> > covered by L2 cache, I mean. Or do you have some sensible chipset in
> > there?).
> It is slow, but I am not aware of issues with too little L2 cache. A

Well, some common chipsets of that time could only cache limited amounts of RAM
(64Mb for TX or VX chipsets, 256Mb for some other chipsets I dont remember about).
Accesses to RAM regions that are not cached are awfully slow.
But these accesses are still faster than hitting HDD ;)
So the "slram" driver was developed that allowed to use
non-cached memory as a RAM-disk for swap usage.

> quick look at dmesg didn't give me more clue. Can you please explain a
> bit, or give some google keywords?

There is some sensible (from a quick look) article at
http://www.computerwriter.com/archives/1998/cw050798.htm

> It is only 200MHz, so I expect it to be slow, but if I can make it
> faster that would be nice (without removing the ram if possible ;-)

Well, try to remove the ram, first to make it to be only 256M then
64M and see if the system becomes faster at trivial non-memory hungry
stuff.
If this is indeed the case, consider changing motherboard/increasing L2
cache size (hard to do nowadays, when you cannot buy even P3 equipment
easily ;) ).
Nothing else comes to mind.

> > <joke>Because it is already perfect, nothing to improve</joke> ;)
> Goody :-)  Well, let me know if you want me to test something. I'll let
> you know what happens with reiser4 on a partition.

Thank you.

Bye,
    Oleg

  reply	other threads:[~2003-02-18 10:05 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-02-15 15:00 reiser4 and 2.5.60 Ookhoi
2003-02-18  9:12 ` Oleg Drokin
2003-02-18  9:31   ` Ookhoi
2003-02-18  9:33     ` Ookhoi
2003-02-18  9:42     ` Oleg Drokin
2003-02-18  9:52       ` Ookhoi
2003-02-18 10:05         ` Oleg Drokin [this message]
2003-02-18 14:11           ` Ookhoi
2003-02-18 10:08       ` Ookhoi

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=20030218130544.A31947@namesys.com \
    --to=green@namesys.com \
    --cc=ookhoi@humilis.net \
    --cc=reiserfs-list@namesys.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.