> Now I look at the diff and see that the memory used is reasonably
quoted text
> small. But still, if multiple copies of your cp are run together on a
> machine where available physical mem is low I might end up with a
> machine swapping. That is certainly not going to speed up cp.

If multiple copies of anything are run on a machine with low phys,
you'll end up swapping.

Again, if you're really focusing on being able to run the maximum
number of cp's on a memory starved machine we can do it as a one byte
read and write loop. come on, this is not the typical or even the
extreme case.

You could always check avm rather than physmen and base it on what was free.