From: Erik Bourget <erik@midmaine.com>
To: Nikita Danilov <Nikita@Namesys.COM>
Cc: Josh Litherland <josh@temp123.org>, linux-kernel@vger.kernel.org
Subject: Re: Transparent compression in the FS
Date: Wed, 15 Oct 2003 10:47:42 -0400 [thread overview]
Message-ID: <87wub6o8vl.fsf@loki.odinnet> (raw)
In-Reply-To: <20031015142738.GG24799@bitwizard.nl> (Erik Mouw's message of "Wed, 15 Oct 2003 16:27:38 +0200")
Erik Mouw <erik@harddisk-recovery.com> writes:
> On Wed, Oct 15, 2003 at 05:50:38PM +0400, Nikita Danilov wrote:
>> Erik Mouw writes:
>> > Nowadays disks are so incredibly cheap, that transparent compression
>> > support is not realy worth it anymore (IMHO).
>>
>> But disk bandwidth is so incredibly expensive that compression becoming
>> more and more useful: on compressed file system bandwidth of user-data
>> transfers can be larger than raw disk bandwidth. It is the same
>> situation as with allocation of disk space for files: disks are cheap,
>> but storing several files in the same block becomes more advantageous
>> over time.
>
> You have a point, but remember that modern IDE drives can do about
> 50MB/s from medium. I don't think you'll find a CPU that is able to
> handle transparent decompression on the fly at 50MB/s, even not with a
> simple compression scheme as used in NTFS (see the NTFS docs on
> SourceForge for details).
>
> Erik
>
> PS: let me guess: among other things, reiser4 comes with transparent
> compression? ;-)
Reiser4 made my coffee this morning, it's wonderful :)
Seriously, though, (and getting off the topic), has anyone started to use
reiser4 in a high-load environment? I've got a mail system that shoots a few
million messages through it every day and a filesystem that's faster with
creating and deleting tons of ~4kb qmail queue files (with data journaling!)
would be verrry innnteresting.
- Erik Bourget
next prev parent reply other threads:[~2003-10-15 14:49 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-10-14 20:30 Transparent compression in the FS Josh Litherland
2003-10-15 13:33 ` Erik Mouw
2003-10-15 13:45 ` Josh Litherland
2003-10-15 13:50 ` Nikita Danilov
2003-10-15 14:27 ` Erik Mouw
2003-10-15 14:33 ` Nikita Danilov
2003-10-15 15:54 ` Richard B. Johnson
2003-10-15 16:21 ` Nikita Danilov
2003-10-15 17:19 ` Richard B. Johnson
2003-10-15 17:37 ` Andreas Dilger
2003-10-15 17:48 ` Dave Jones
2003-10-15 18:19 ` Richard B. Johnson
2003-10-15 18:06 ` Hans Reiser
2003-10-17 12:51 ` Edward Shushkin
2003-10-15 16:04 ` Erik Mouw
2003-10-15 17:24 ` Josh Litherland
2003-10-15 18:53 ` Erik Bourget
2003-10-15 19:03 ` Geert Uytterhoeven
2003-10-15 19:14 ` Valdis.Kletnieks
2003-10-15 19:24 ` Geert Uytterhoeven
2003-10-15 18:54 ` root
2003-10-16 2:11 ` Chris Meadors
2003-10-16 3:01 ` Shawn
2003-10-15 14:47 ` Erik Bourget [this message]
2003-10-15 15:05 ` Nikita Danilov
2003-10-15 15:06 ` Erik Bourget
2003-10-15 21:36 ` Tomas Szepe
2003-10-16 8:04 ` Ville Herva
2003-10-17 1:32 ` Eric W. Biederman
2003-10-15 15:13 ` Jeff Garzik
2003-10-15 21:00 ` Christopher Li
2003-10-16 16:29 ` Andrea Arcangeli
2003-10-16 16:41 ` P
2003-10-16 17:20 ` Jeff Garzik
2003-10-16 23:12 ` jw schultz
2003-10-17 8:03 ` John Bradford
2003-10-17 14:53 ` Eli Carter
2003-10-17 15:27 ` John Bradford
2003-10-17 16:22 ` Eli Carter
2003-10-17 17:15 ` John Bradford
2003-10-16 17:10 ` Jeff Garzik
2003-10-16 17:41 ` Andrea Arcangeli
2003-10-16 17:29 ` Larry McVoy
2003-10-16 17:49 ` Val Henson
2003-10-16 21:02 ` Jeff Garzik
2003-10-16 21:18 ` Chris Meadors
2003-10-16 21:25 ` Jeff Garzik
2003-10-16 21:33 ` Davide Libenzi
2003-10-17 3:47 ` Mark Mielke
2003-10-17 14:31 ` Jörn Engel
2003-10-16 23:04 ` jw schultz
2003-10-16 23:30 ` Jeff Garzik
2003-10-16 23:58 ` jw schultz
2003-10-16 23:53 ` David Lang
2003-10-17 1:19 ` Jeff Garzik
2003-10-17 0:45 ` Christopher Li
2003-10-17 1:16 ` Jeff Garzik
2003-10-17 1:32 ` jlnance
2003-10-17 1:47 ` Eric Sandall
2003-10-17 8:11 ` John Bradford
2003-10-17 17:53 ` Eric Sandall
2003-10-17 13:07 ` jlnance
2003-10-17 14:16 ` Jeff Garzik
2003-10-17 15:06 ` Valdis.Kletnieks
2003-10-17 1:49 ` Davide Libenzi
2003-10-17 1:59 ` Larry McVoy
2003-10-17 2:19 ` jw schultz
2003-10-17 9:44 ` Pavel Machek
2003-10-17 12:33 ` jlnance
2003-10-17 18:23 ` jw schultz
2003-10-27 2:08 ` Mike Fedyk
2003-10-27 2:15 ` jw schultz
2003-10-27 2:22 ` Mike Fedyk
2003-10-27 2:45 ` jw schultz
2003-10-16 18:28 ` John Bradford
2003-10-16 18:31 ` Robert Love
2003-10-16 20:18 ` Jeff Garzik
2003-10-16 18:43 ` Muli Ben-Yehuda
2003-10-16 18:56 ` Richard B. Johnson
2003-10-16 19:00 ` Robert Love
2003-10-16 19:27 ` John Bradford
2003-10-16 19:03 ` John Bradford
2003-10-16 19:20 ` Richard B. Johnson
2003-10-17 13:16 ` Ingo Oeser
2003-10-16 23:20 ` jw schultz
2003-10-17 14:47 ` Eli Carter
2003-10-16 8:27 ` tconnors+linuxkernel1066292516
2003-10-17 10:55 ` Ingo Oeser
2003-10-15 16:25 ` David Woodhouse
2003-10-15 16:56 ` Andreas Dilger
2003-10-15 17:44 ` David Woodhouse
[not found] <GTJr.60q.17@gated-at.bofh.it>
[not found] ` <GU2N.6v7.17@gated-at.bofh.it>
[not found] ` <GVBC.Ep.23@gated-at.bofh.it>
[not found] ` <Hjkq.3Al.1@gated-at.bofh.it>
[not found] ` <Hkgx.4Vu.7@gated-at.bofh.it>
[not found] ` <HkA0.5lh.9@gated-at.bofh.it>
[not found] ` <HnxT.3BB.27@gated-at.bofh.it>
2003-10-17 8:15 ` Ihar 'Philips' Filipau
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=87wub6o8vl.fsf@loki.odinnet \
--to=erik@midmaine.com \
--cc=Nikita@Namesys.COM \
--cc=josh@temp123.org \
--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 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.