On Thursday 06 January 2005 04:07 pm, death rince <[EMAIL PROTECTED]> 
wrote:
> Hi,
>
> I was browsing through benchmarks of Reiserfs and
> other filesystem when I came across this,
>
> http://linuxgazette.net/102/piszcz.html
>
> Can anyone please give an insight, behind the
> rationale of such tests and what exactly it signifies
> in terms of working of the kernel with respect to
> different filesystems. I am not too knowledgeable with
> working of OS and kernel to be able to understand it

Well, I think the conclusion at the bottom is fairly concise.

Depending on your needs, you'll want to choose XFS, ReiserFS, or JFS.  Just 
stay away from ext3.  The "total time" graph reflects this.  Looks like 
XFS is the big winner on large files, whereas ReiserFS is the winner on 
large numbers of files (except for deleting).

Also, ReiserFS will perform better on the small file tests if notail is 
turned on, but will minimize disk usage if notail is turned off.  [notail 
is a mount option that changes how reiserfs packs small files.]

In fact, in the tests that reiserfs and ext3 performed most poorly, there 
are already "fixes" available.  notail for reiserfs and the new directory 
handling code for ext3.  (I forget exactly what they called their 
modification.)  There are probably fixes for JFS and XFS on their problem 
areas, too.

It should be noted that reiser4 has better benchmarks than reiserfs in 
pretty much everything, sometimes drastically so.  However, last time I 
tried it (which is pretty recently) it doesn't support resizing the 
filesystem, a show-stopper for many people (including me).

-- 
Boyd Stephen Smith Jr.
[EMAIL PROTECTED]
ICQ: 514984 YM/AIM: DaTwinkDaddy

--
[email protected] mailing list

Reply via email to