On Friday 07 January 2005 07:07, death rince wrote:
> Hi,

Hi. I figured that you might need another response as most of this thread just 
turned into a flame war. ;)

> 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

The rational of the test? I can kind of explain that as I have previously made 
the same false assumptions - not that I'm am enlightened enough to be able to 
identify all of them.

The biggest false assumption is that benchmarking serial activity to a 
filesystem is a relevant benchmark for desktop purposes. In fact, I'm not 
sure it's really relevant to any activity, except backups perhaps. Second 
false assumption...

001] Create 10,000 files with touch in a directory.
004] Create 10,000 directories with mkdir in a directory.

The rationale is to measure which fs is faster at what atomic operation, but 
the benchmark has assumed that creating a directory and creating a file 
should take the same amount of time.

Hmm.. I really have nothing else to say. I have this terrible urge to tell you 
about my experiences with various file system, but I won't yield to them. ;)

I guess all you can really do is try a few out and come to your own 
conclusions.

Regards,
Jason Stubbs

--
[email protected] mailing list

Reply via email to