From: lsorense@csclub.uwaterloo.ca (Lennart Sorensen)
To: johnrobertbanks@fastmail.fm
Cc: "H. Peter Anvin" <hpa@zytor.com>, Ignatich <ignatich@gmail.com>,
reiserfs-list@namesys.com, linux-kernel@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: Re: Reiser4. BEST FILESYSTEM EVER.
Date: Sat, 7 Apr 2007 21:27:45 -0400 [thread overview]
Message-ID: <20070408012745.GH3508@csclub.uwaterloo.ca> (raw)
In-Reply-To: <1175993097.32498.1183512070@webmail.messagingengine.com>
On Sat, Apr 07, 2007 at 05:44:57PM -0700, johnrobertbanks@fastmail.fm wrote:
> Lennart. Tell me again that these results from
>
> http://linuxhelp.150m.com/resources/fs-benchmarks.htm and
> http://m.domaindlx.com/LinuxHelp/resources/fs-benchmarks.htm
Hmm, copying kernel sources around. Not that interesting. How does it
handle mpeg2 files (the majority of my personal data files is on a
mythtv system). So a few large files, with mostly linear access, and
the occational file deletion. Compression would gain nothing.
> are not of interest to you. I still don't understand why you have your
> head in the sand.
Well I find it hard to get excited about new filesystems. I had
sufficiently nasty data loses due to reiserfs 3 back in the early 2.4
kernel days, that I no longer get excited about new filesystems. now I
want something I trust that hasn't destroyed any of my data. I tried
XFS for a while, ut the early 2.6 kernels had some nasty bugs in XFS too
that made that pretty much unusable. Now I just stick with ext3. Screw
performance, give me something that works all the time.
> .-------------------------.
> | FILESYSTEM | TIME |DISK |
> | TYPE |(secs)|USAGE|
> .-------------------------.
> |REISER4 lzo | 1938 | 278 |
> |REISER4 gzip| 2295 | 213 |
> |REISER4 | 3462 | 692 |
> |EXT2 | 4092 | 816 |
> |JFS | 4225 | 806 |
> |EXT4 | 4408 | 816 |
> |EXT3 | 4421 | 816 |
> |XFS | 4625 | 779 |
> |REISER3 | 6178 | 793 |
> |FAT32 |12342 | 988 |
> |NTFS-3g |10414 | 772 |
> .-------------------------.
>
>
> Column one measures the time taken to complete the bonnie++ benchmarking
> test (run with the parameters bonnie++ -n128:128k:0)
Time without cpu usage is not interesting. If you can increase
filesystem speed by 10% by doubling cpu load, then I don't want the
increase. It is all relative. Wall clock time by itself just doesn't
contain enough data to be useful.
> Column two, Disk Usage: measures the amount of disk used to store 655MB
> of raw data (which was 3 different copies of the Linux kernel sources).
I remember disk compression from the DOS days. Disk space is too cheap
to bother with that crap anymore. I don't care if it can theoretically
turn idle cpu cycles into improved disk speed. Sometimes I don't have
idle cpu cycles to waste on that.
> OR LOOK AT THE FULL RESULTS:
>
> .-------------------------------------------------.
> |File |Disk |Copy |Copy |Tar |Unzip| Del |
> |System |Usage|655MB|655MB|Gzip |UnTar| 2.5 |
> |Type | (MB)| (1) | (2) |655MB|655MB| Gig |
> .-------------------------------------------------.
> |REISER4 gzip | 213 | 148 | 68 | 83 | 48 | 70 |
> |REISER4 lzo | 278 | 138 | 56 | 80 | 34 | 84 |
> |REISER4 tails| 673 | 148 | 63 | 78 | 33 | 65 |
> |REISER4 | 692 | 148 | 55 | 67 | 25 | 56 |
> |NTFS3g | 772 |1333 |1426 | 585 | 767 | 194 |
> |NTFS | 779 | 781 | 173 | X | X | X |
> |REISER3 | 793 | 184 | 98 | 85 | 63 | 22 |
> |XFS | 799 | 220 | 173 | 119 | 90 | 106 |
> |JFS | 806 | 228 | 202 | 95 | 97 | 127 |
> |EXT4 extents | 806 | 162 | 55 | 69 | 36 | 32 |
> |EXT4 default | 816 | 174 | 70 | 74 | 42 | 50 |
> |EXT3 | 816 | 182 | 74 | 73 | 43 | 51 |
> |EXT2 | 816 | 201 | 82 | 73 | 39 | 67 |
> |FAT32 | 988 | 253 | 158 | 118 | 81 | 95 |
> .-------------------------------------------------.
>
>
> Each test was preformed 5 times and the average value recorded.
> Disk Usage: The amount of disk used to store the data (which was 3
> different copies of the Linux kernel sources).
> The raw data (without filesystem meta-data, block alignment wastage,
> etc) was 655MB.
> Copy 655MB (1): Copy the data over a partition boundary.
> Copy 655MB (2): Copy the data within a partition.
> Tar Gzip 655MB: Tar and Gzip the data.
> Unzip UnTar 655MB: UnGzip and UnTar the data.
> Del 2.5 Gig: Delete everything just written (about 2.5 Gig).
>
> To get a feel for the performance increases that can be achieved by
> using compression, we look at the total time (in seconds) to run the
> test:
kernel sources are some of the most compressable data files around. Try
with some interesting data instead, like something with larger files,
mostly binary, which isn't likely to compess very much.
> bonnie++ -n128:128k:0 (bonnie++ is Version 1.93c)
>
> .-------------------.
> | FILESYSTEM | TIME |
> .-------------------.
> |REISER4 lzo | 1938|
> |REISER4 gzip| 2295|
> |REISER4 | 3462|
> |EXT4 | 4408|
> |EXT2 | 4092|
> |JFS | 4225|
> |EXT3 | 4421|
> |XFS | 4625|
> |REISER3 | 6178|
> |FAT32 | 12342|
> |NTFS-3g |>10414|
> .-------------------.
> --
Well Reiser4 certainly looks impresive, but I still want to know what the
cpu load is like, what the repair tools are like, how well it handles
power failures in the middle of a write (I didn't like the way reiser3
would claim to have the filesystem back to a sane state, but the file
it had been in the middle of writing now contained garbage in many parts
of it, with no warning what so ever that this had taken place).
Performance looks impresive, but based on the history of reiser3 there
is a lot of historical damage to undo before I will even consider
testing it out.
--
Len Sorensen
next prev parent reply other threads:[~2007-04-08 1:27 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-05 22:42 REISER4: fix for reiser4_write_extent Ignatich
2007-04-06 0:05 ` Reiser4. BEST FILESYSTEM EVER? I need help johnrobertbanks
2007-04-06 0:23 ` H. Peter Anvin
2007-04-06 0:34 ` johnrobertbanks
2007-04-06 0:39 ` H. Peter Anvin
2007-04-06 1:34 ` Reiser4. BEST FILESYSTEM EVER johnrobertbanks
2007-04-06 3:12 ` Valdis.Kletnieks
2007-04-06 4:07 ` H. Peter Anvin
2007-04-06 4:32 ` johnrobertbanks
[not found] ` <20070406152119.GC4228@delft.aura.cs.cmu.edu>
2007-04-07 2:47 ` johnrobertbanks
2007-04-07 3:30 ` Jan Harkes
2007-04-07 5:58 ` johnrobertbanks
2007-04-07 7:15 ` Willy Tarreau
2007-04-07 13:47 ` johnrobertbanks
2007-04-07 14:11 ` Krzysztof Halasa
2007-04-07 15:07 ` johnrobertbanks
2007-04-07 16:05 ` Pekka Enberg
2007-04-07 17:10 ` Valdis.Kletnieks
2007-04-08 16:31 ` Adrian Bunk
2007-04-07 17:21 ` Valdis.Kletnieks
2007-04-08 0:41 ` Krzysztof Halasa
2007-04-07 17:39 ` Valdis.Kletnieks
2007-04-07 19:17 ` Lennart Sorensen
2007-04-08 0:44 ` johnrobertbanks
2007-04-08 1:27 ` Lennart Sorensen [this message]
2007-04-08 2:56 ` Theodore Tso
2007-04-08 4:13 ` johnrobertbanks
2007-04-08 12:48 ` Jose Celestino
2007-04-08 13:21 ` johnrobertbanks
2007-04-08 14:14 ` Willy Tarreau
2007-04-08 17:03 ` Theodore Tso
2007-04-08 18:18 ` Jeff Mahoney
2007-04-08 4:32 ` Christer Weinigel
2007-04-08 21:50 ` Reiser4. BEST FILESYSTEM EVER - Christer Weinigel johnrobertbanks
2007-04-08 22:58 ` Richard Knutsson
2007-04-09 5:14 ` johnrobertbanks
2007-04-09 7:07 ` Willy Tarreau
2007-04-09 16:10 ` Richard Knutsson
2007-04-09 18:35 ` Reiser4. BEST FILESYSTEM EVER Nate Diller
2007-04-07 1:26 ` COMPILING AND CONFIGURING A NEW KERNEL johnrobertbanks
2007-04-07 7:45 ` johnrobertbanks
2007-04-07 16:57 ` Valdis.Kletnieks
2007-04-08 1:11 ` johnrobertbanks
2007-04-07 16:42 ` Valdis.Kletnieks
2007-04-08 1:02 ` johnrobertbanks
2007-04-08 1:42 ` Lennart Sorensen
2007-04-07 12:51 ` REISER4: fix for reiser4_write_extent Laurent Riffard
2007-04-07 19:29 ` Edward Shishkin
2007-04-07 12:59 Reiser4. BEST FILESYSTEM EVER Dale Amon
2007-04-07 15:28 ` johnrobertbanks
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=20070408012745.GH3508@csclub.uwaterloo.ca \
--to=lsorense@csclub.uwaterloo.ca \
--cc=hpa@zytor.com \
--cc=ignatich@gmail.com \
--cc=johnrobertbanks@fastmail.fm \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®