On Sun, 20 May 2001 at 13:29, Gino LV. Ledesma wrote:
> The article points to a Spanish LUG member who did some benchmarks
> with various file systems, including ext2 and FAT32. Here is the
> english-translated page by Google:

Just as a follow-up, several discussions resulted because of this
benchmark, and had the developers of both XFS and ReiserFS cross-posting
mail in both mailing lists. Some people did "more serious" benchmarks as
Hans Reiser recommended, and contrary to this Spanish report, it looks
like ReiserFS is faster on most things especially for a lot of small
files, but ReiserFS slows down as the file size increases and ReiserFS and
XFS start performing similar to each other.

The URL of results using the mongo.pl script comparing ReiserFS, XFS and
ext2 to each other is

<http://www.informatik.uni-frankfurt.de/~loizides/reiserfs/ext2-reiserfs-xfs.html>

The XFS developers raised the issue, however, of this test using default
RPMs of release 1.0 of XFS which had a lot of options enabled which
ReiserFS doesn't do, hence making the playing field uneven. Included are
debugging stuff (which when enabled for ReiserFS kills performance, too)
and ACLs (which ReiserFS doesn't have). Also, the latest CVS of XFS which
runs on Linux kernel 2.4.4 has a lot of performance improvements (not to
mention bugfixes).

I think one of the biggest benefits of XFS over ReiserFS is the maturity
of its on-disk format. With ReiserFS there is that uncertainty of not
knowing when something wrong will be discovered with the current hash,
hence needing an upgrade of the hash which in turn requires the filesystem
to be re-made.

Anyway, here it is. :-)

(BTW, cross-posted to PLUG because this isn't really newbie stuff, is it?)

 --> Jijo

--
Linux, MS-DOS, and Windows NT ...
... also known as the Good, the Bad, and the Ugly

_
Philippine Linux Users Group. Web site and archives at http://plug.linux.org.ph
To leave: send "unsubscribe" in the body to [EMAIL PROTECTED]

To subscribe to the Linux Newbies' List: send "subscribe" in the body to 
[EMAIL PROTECTED]

Reply via email to