On Wed, Jun 04, 2008 at 09:59:56AM -0500, Spencer Shepler wrote:
> 
> On Jun 3, 2008, at 11:26 PM, [EMAIL PROTECTED] wrote:
> 
> >On Tue, Jun 03, 2008 at 03:32:47PM -0700, eric kustarz wrote:
> >>
> >>On May 29, 2008, at 11:44 PM, [EMAIL PROTECTED] wrote:
> >>>[...]
> >>>
> >>>I remember another hardware arrays (yes, two arrays) test where
> >>>vdbench shows
> >>>that one array is a bit faster (more IOPS) then the other. While
> >>>filebench (which tries to simulate the real workloads) shows that  
> >>>that
> >>>the other aray is slightly faster. What is true ? I don't know.  
> >>>But I
> >>>wouldn't like to use just one tool. Both has its advantages and
> >>>disadvantages. And _both_ give much wider picture of how the storage
> >>>behaves in particular workload.
> >>
> >>So that's disturbing.  What workload were you running?
> >
> >OLTP
> >
> 
> Isn't this the case of an application (e.g. vdbench, filebench) having
> slightly differing behavior and the underlying storage being a better
> match to one or the other?  I am not surprised by this.  If you were
> to say the workload was something like sequential read, then it
> would be a surprise.
> 
> Then the question becomes: what benchmark most closely resembles the
> behavior of the applications of the most interest.  IMO, filebench
> has the greatest potential for providing the closest match
> when scaling across system types and attempting to simulate the
> complexities of application intra-dependence.

Hi Spencer,

I agree with you that filebench is closer to real life workloads than
vdbench. I mentioned vdbench because it sometimes allows to discover
(it happened in my case) some hidden picture of tested environments.

I have just tested vxfs vs zfs on fibre channel array and soon
(hopefully ...) will write about it on my blog. The tests were
using vdbench and filebench. There are some interesting observations
which couldn't be shown without vdbench.

What I am trying to say is that filebench _plus_ vdbench gives much more
information/data to analyze that just filebench alone.

Regards
przemol

-- 
http://przemol.blogspot.com/






















----------------------------------------------------------------------
Podbij Dziki Zachod!Gra strategiczna online
Sprawdz >>> http://link.interia.pl/f1dff

_______________________________________________
perf-discuss mailing list
perf-discuss@opensolaris.org

Reply via email to