multitasking question

norume at young.usask.ca norume at young.usask.ca
Tue Feb 12 02:24:15 UTC 2002


Quoting "Michael P. Collins on korat" <mcollins at anchor.sps.mot.com>:

> 
>   To provide some real-world info, I have been using the following
> parameters on a 25MHz MC68331 board over the past few days:
> 
>       #define CONFIGURE_MICROSECONDS_PER_TICK   122
> 
>       /*
>        * Timeslice interval is approx. 20ms.
>        */
>       #define CONFIGURE_TICKS_PER_TIMESLICE 164
> 
>   I've had as many as four tasks running simultaneously, three of
> which
> can be pretty busy for short intervals, and have not apparently run
> out
> of bandwidth.  Now I can't say that my configuration is optimal; the
> numbers chosen were simply first guesses, however I would expect
> Stan's
> configuration should work at 16MHz.
> 

It's good to have some hard numbers to work with.  I should have preceded my comments with some qualifiers, the most important being, ``Maximum clock rates depend heavily on the presence of other interrupt sources and the priority of those interrupts''.  Your example shows that very high clock rates can be tolerated by RTEMS.  Did you have any other interrupts enabled during your tests?  If so, what were the relative priorities of the other interrupts and the clock interrupt?  I would think that other interrupts at equal or higher priority might cause some missed clock ticks, or at least some pretty bad jitter on the clock interrupt latency at this exceptionally high clock rate.



More information about the users mailing list