Re: [squid-users] Benchmarks: ext3 vs. ReiserFS

On Saturday 13 July 2002 03.07, Steve Snyder wrote:
> Interesting benchmarks of ext3 vs. ReiserFS:
>
> http://www.gurulabs.com/ext3-reiserfs.html
>
> This makes me reconsider my use of ReiserFS for my Squid cache.

Does it? Why? The tests they have performed is totally inconclusive
regarding applicability on Squid caches..

To get anything that can be applied to how Squid may perform/benefit
you need a test using 2M files of an average filesize of 10KB... not
a test of only 4000 files with a size of up to 300K each.. the two
tests are verly likely to give considerably different results..

The first tests using very small filesets isn't really interesting as
the filesets is too small, and the third test isn't interesting due
to the size distribution of the files.

Regards
Henrik
Received on Fri Jul 12 2002 - 20:01:32 MDT