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

On Friday 12 July 2002 09:50 pm, Henrik Nordstrom wrote:
> 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..

Well, I wouldn't take any single set of benchmarks as gospel, but that first
set (http://www.gurulabs.com/ext3-reiserfs-3.html) does give me pause.
Files in the range of 1000 to 9000 bytes? Sounds like a Web cache dataset
to me.

Anyway, I thought it was interesting.
Received on Fri Jul 12 2002 - 20:37:34 MDT