Stan writes in response to a memory question:

>  However, on the chance that you aren't really interested in the memory
>  manager so much as in overall performance...

Although I've edited out most of Stan's response here, it should be retrieved
and saved somewhere on your PC, if not outrightly committed to memory. What he
wrote is worth its weight in gold (however much it might weigh).

However, there is a small addendum that should be added. Stan wrote:

> Ok...what's the value?  My rule of thumb is that if the value is about
>  70% or so, you can benefit from a faster CPU.  If it's below 70%, then
>  you *might* benefit from more memory.  Why the doubt?  Well, we started
>  with the proposition that the machine was busy ... so why isn't it fully
>  utilizing the CPU?  Because processes are waiting for something(s).

There are exceptions to Stan's 70% rule, especially in situations such as a
report writer running in the middle of the night, in batch, as a process
absent of any other competiting jobs. In this circumstance, if the people who
wrote the report writer don't drive your CPU utilization to 100%, they didn't
do their jobs correctly.

The ideal situation for a report writer is to find and isolate the appropriate
records and get them into main memory as quickly and as compactly as it can --
and then never touch the disc again. Under this (highly) idealized situation,
CPU utilization will rise to 100%, regardless of how fast your processor is.

The only thing a faster processor can do under such a situation is simply make
your report run faster (but of course, that's not a bad proposition in and of
itself).

Wirt Atmar