At 7:40 PM -0600 11/18/02, Frederick Bruckman wrote:
>On Mon, 18 Nov 2002, RAParker wrote:
>  > Under a load, the time loss can be in the neighborhood of several 
>minutes or
>>  more.
>
>It's a well known problem, having to do with the clock chip on the
>Macs not being wired to the highest priority interrupt on the m68k
>chip, as it is on every other make of computer.

I'll second that.  The hardware is just not what it should be.  The 
problem is probably even in the FAQ somewhere.

Some models (II-FX, 650?) have an "alternate" interrupt scheme which 
might even be supported now.  I know there was some work done to 
support it, but I don't know if it fizzled or made it into the tree.
-- 
The opinions expressed in this message are mine,
not those of Caltech, JPL, NASA, or the US Government.
Henry.B.Hotz@jpl.nasa.gov, or hbhotz@oxy.edu