>Somehow I thought the os-x scheduler snatchs control away for 1/60 
>of a second, but that doesn't jive

Ah, thats because there is a lower limit for the 
interruptCheckCounter counter (1000). So it just happens running 1000 
*interesting* bytecodes interspersed with usleep() takes 16ms or so.

mmmm I wonder if you set the lower limit to 25 or so would that allow 
you to forgo the check in ioRelinquishProcessorForMicroseconds. I'll 
let someone else decide tonight. Maybe you need to adjust the decay 
value from 12 to a much bigger number too? mmm maybe this won't 
work...

-- 
--
===========================================================================
John M. McIntosh <johnmci at smalltalkconsulting.com> 1-800-477-2659
Corporate Smalltalk Consulting Ltd.  http://www.smalltalkconsulting.com
===========================================================================