Just a week after launch of new Workstation 6.0, VMware published a valuable 34-pages whitepaper detailing performance tuning best practices and recommended benchmarking approaches:
There are some areas in which the best-performing configurations of VMware Workstation virtual machines vary slightly from the configurations of native machines. One of the goals of this book is to provide guidance about these variations. To this end, we discuss configuration of the host, the VMware Workstation software, and the operating systems and applications in the individual virtual machines.
The benchmarking guidelines in this book are intended to assist in the acquisition of meaningful, accurate, and repeatable benchmarking results. These guidelines are useful when you perform comparisons between VMware Workstation and either native systems or other virtualization products, as well as when you run benchmarks in virtual machines in general. The guidelines should not, however, be considered VMware best practices in all cases. Among other reasons, this is because benchmarking sometimes involves saturating one resource while overprovisioning others, something that would not be desirable in a production environment.
Some point, mainly about benchmarking, are particularly interesting:
We don’t recommend use of the following benchmarks, as our experience has shown that they can produce unexpected results in virtual machines:
- Sisoft Sandra
- LMbench
while others seems pretty odd:
Try not to overcommit CPU resources:
- …
- Avoid running two or more single-processor virtual machines on a single-processor host system, even if the single-processor host has hyper-threading.
- …
Is VMware trying to say now desktop virtualization is no more good for running concurrent virtual machines at once?
Read the whole whtepaper at source.