[Benchmarking] Last minute vote: shall we switch to 6600 requests run?

[Andrea Aime]

Hi,
during today's meeting it was discussed that some servers
are being disk bound during the tests, whilst others
are not.

I can't speak for others, but for GeoServer the difference
between a disk bound run and one that is not is 5 to 10
times (in terms of req/sec).

So it was suggested that we adopt a setup that has
6600 different requests instead (see the other thread
about it).

What shall we do? Vote please.
If we don't reach a consensus by the end of tomorrow
we'll just stick with what we have (as it's late).

+0 for me (meaning, I think it's a good idea but also
that it's too late)

Cheers
Andrea

-- 
Andrea Aime
OpenGeo - http://opengeo.org
Expert service straight from the developers.