[Phoronix] Ubuntu 9.04 vs. Fedora 11 Performance

[Thorsten Leemhuis]

On 12.06.2009 13:33, Christoph Höger wrote:
> Am Freitag, den 12.06.2009, 19:55 +1000 schrieb Eric Springer:
>> 2009/6/12 Christoph Höger <choeger at cs.tu-berlin.de>:
>>> Could you explain why mp3 (or ogg) encoding is not a "real world"
>>> benchmark? I do this quite often.
>> Because they are comparing file system on what is a CPU bound test. Notice
>> how all the file systems perform the same.
> 
> That was their conclusion, too: Anyone who wants fastest possible
> encoding can use any filesystem.  But it has to be measured, as the
> difference in ogg encoding shows. 
> That's what makes up "Real World" tests IMO: To test even side effects
> no one would ever really think of. As in "real world" you will probably
> store your encoded files on your filesystem it is good to see that there
> are no regressions.

Doing such "Real World" test to find unexpected side effects is a good
thing in a lot of cases. But you don't have to publish the results on
hundreds of pages if the results are as expected and hence uninteresting.

IOW: a lot of those phoronix articles that contain benchmarks could be
half as long or even shorter if you rip out the results that are of no
value and replace them by "No unexpected side effects could be found
when running tests foo, bar, baz, foobar, ...; We thus didn't publish
the results to not confuse and bore you".

Professional, printed computer magazine do things like that -- they have
to, because their space is quite limited. But that's not the case on the
web, where the methods to raise money make things even worse.

Cu
knurd