[rhelv6-beta-list] Apache benchmark RHEL 5 vs. RHEL 6

[Marco Shaw]

> Multiple posters keep trying to blame this performance discrepancy on
> the virtualized environment.
>
> This makes no sense. The original poster has stated that both systems
> used the same virtualized environment, thereby eliminating that as a
> source of variability.

I haven't "blamed" the virtualized environment, but you simply cannot
make a simple comparison when you involve such external factors.

I think you would be surprised at the virtualization optimizations
that have been made once a product has been tested against Linux 2.2,
2.4 and 2.6.

A virtualization application layer is *not* one size fits all, and
any, even is small, changes in the kernel can have a major impact.

In the end, it may turn out to be not related to the virtualization at
all, but that is not a safe assumption to make upfront.