> > The only other interesting fact is that during the 3.8 seconds
> > and 10E6 locks, 52 restarts were performed.  Not much statistical
> > variation either; suprisingly determinstic in fact.
> 
> Related in some way to the number of clock interrupts?  That's only
> 13-odd HZ, but the only thing that comes to mind...

I'd guess that it's roughly:

	       (cycle count of loop)
    HZ *  --------------------------------    
          (cycle count of critical region)

						- Bill