> As a relative measure between the zSeries platforms, > it is an indication of relative speed.
I'm not convinced it's even valid there, if there is any type of virtualization (LPAR or VM) active and there are shared resources. It's a bogus measure because it depends on the resources available at the precise instant the timer loop executes, and that doesn't really reflect anything about the capabilities of the hardware. > The performance literature for Linux is way behind > what its real capabilites are today. Only 3 years in, the fact that we have any performance literature at all is a step in the right direction. It took decades to get to this point with the mainstream Unix variants. -- db
