From: Hans Reiser <reiser@namesys.com>
To: linux-kernel@vger.kernel.org,
reiserfs mailing list <reiserfs-list@namesys.com>,
Linus Torvalds <torvalds@transmeta.com>,
Marcelo Tosatti <marcelo@conectiva.com.br>
Subject: Reiser4 status: benchmarked vs. V3 (and ext3)
Date: Thu, 24 Jul 2003 01:02:19 +0400 [thread overview]
Message-ID: <3F1EF7DB.2010805@namesys.com> (raw)
Please look at http://www.namesys.com/benchmarks/v4marks.html
In brief, V4 is way faster than V3, and the wandering logs are indeed
twice as fast as fixed location logs when performing writes in large
batches.
We are able to perform all filesystem operations fully atomically, while
getting dramatic performance improvements. (Other attempts at
introducing transactions into filesystems are said to have failed for
performance reasons.)
Balancing at flush time works well, not using blobs works well,
allocating at flush time works well. CPU time is good enough to get by,
and it will improve over the next few months as we tweak a lot of little
details, but the IO performance is what matters, and this performance is
quite good enough to use. In all the places where V3 sacrifices
performance to save disk space, V4 saves more disk space and gains
rather than loses performance.
The plugin infrastructure works well, expect lots of plugins over the
next year or two.
Look for a repacker to come out in a few weeks that will make these
numbers especially good for filesystems that have 80% of their files
unmoving for long periods of time (which is to say most systems), and
might otherwise suffer from fragmentation.
These benchmarks mean to me that our performance is now good enough to
ship V4 to users (which means we need persons willing to try to crash it
so that the stability can become good enough to ship to users).
Sometime during the next week or two we will probably send a patch in,
and ask for inclusion. We need to run another round of stress tests
after our latest tweaks, and kill off two bugs that got added just
recently, and then we will ask for testers.
I will be going to Budapest to discuss filesystem semantics with Peter
Foldiak for a week, so V4 may get sent in for inclusion by members of my
team while I am absent. If so, please include it in 2.5/2.6.
--
Hans
next reply other threads:[~2003-07-23 20:47 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-07-23 21:02 Hans Reiser [this message]
2003-07-24 4:26 ` Reiser4 status: benchmarked vs. V3 (and ext3) Tupshin Harper
2003-07-24 4:31 ` Shawn
2003-07-24 4:56 ` Tupshin Harper
2003-07-24 5:21 ` Shawn
2003-07-24 5:33 ` Shawn
2003-07-24 11:10 ` Nikita Danilov
2003-07-24 15:10 ` Tupshin Harper
2003-07-24 15:26 ` Larry McVoy
2003-07-24 15:32 ` Tupshin Harper
2003-07-24 15:54 ` Larry McVoy
2003-07-24 15:32 ` Shawn
2003-07-27 12:28 ` Hans Reiser
2003-07-27 12:45 ` Tomas Szepe
2003-07-27 14:01 ` Hans Reiser
2003-07-27 15:04 ` Gene Heskett
2003-07-24 15:59 ` Daniel Egger
2003-07-24 17:07 ` Nikita Danilov
2003-07-24 21:10 ` Tupshin Harper
2003-07-25 12:57 ` Nikita Danilov
2003-07-25 0:39 ` Daniel Egger
2003-07-25 13:02 ` Nikita Danilov
2003-07-25 14:20 ` Daniel Egger
2003-07-25 14:39 ` Yury Umanets
2003-07-26 1:08 ` Daniel Egger
2003-07-26 7:19 ` Yury Umanets
2003-07-26 14:13 ` Daniel Egger
2003-07-26 14:54 ` Yury Umanets
2003-07-26 15:21 ` Daniel Egger
2003-07-27 3:28 ` Valdis.Kletnieks
2003-07-27 10:30 ` Yury Umanets
2003-07-27 11:05 ` Daniel Egger
2003-07-27 11:46 ` Yury Umanets
2003-08-08 14:01 ` David Woodhouse
2003-08-08 14:28 ` Bernd Eckenfels
2003-08-08 23:58 ` David Woodhouse
2003-08-09 0:29 ` Bernd Eckenfels
2003-08-09 0:38 ` David Woodhouse
2003-07-27 13:31 ` Hans Reiser
2003-07-27 14:13 ` Yury Umanets
2003-07-27 13:28 ` Hans Reiser
2003-07-27 14:10 ` Daniel Egger
2003-07-27 14:15 ` Yury Umanets
2003-08-13 20:12 ` Bill Davidsen
2003-08-14 5:04 ` Yury Umanets
2003-08-14 14:10 ` David Woodhouse
2003-08-15 11:15 ` Yury Umanets
2003-08-15 15:28 ` Bill Davidsen
2003-08-15 15:53 ` David Woodhouse
2003-08-14 13:58 ` David Woodhouse
2003-07-27 15:30 ` Bernd Eckenfels
2003-07-27 15:49 ` Alan Cox
2003-08-08 13:23 ` David Woodhouse
2003-07-28 11:30 ` Hans Reiser
2003-07-26 17:14 ` Jussi Laako
2003-07-27 13:35 ` Hans Reiser
2003-08-08 14:08 ` David Woodhouse
2003-07-27 12:59 ` Hans Reiser
2003-07-27 14:16 ` Daniel Egger
2003-07-27 15:32 ` Bernd Eckenfels
2003-08-08 14:29 ` David Woodhouse
2003-07-28 12:44 ` Hans Reiser
2003-07-28 13:06 ` Daniel Egger
2003-07-28 13:29 ` Hans Reiser
2003-07-28 13:48 ` Hans Reiser
2003-07-27 12:38 ` Hans Reiser
2003-07-26 8:33 ` Andrew Morton
2003-07-27 13:24 ` Hans Reiser
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=3F1EF7DB.2010805@namesys.com \
--to=reiser@namesys.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo@conectiva.com.br \
--cc=reiserfs-list@namesys.com \
--cc=torvalds@transmeta.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 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).