[Tinyos-host-mote-wg] Re: [Tinyos-2.0wg] TinyOS Telecon Notes 8/31/05

[Philip Levis]

On Sep 1, 2005, at 4:28 AM, Joe Polastre wrote:


>
> Note about Phil's comment:
>
> This won't work if you're using a DMA or other such device that relies
> on other hardware components.  It makes setting the "dirty" bit very
> difficult.
>
>

Why? The notion of a dirty bit is merely a way for any component to  
tell the power manager that something --- anything --- involving  
power has changed, and so it should recompute the desired low power  
state. It may be that it can go into the same state next time around,  
but it should check to make sure. Rob came up with this idea after a  
bit of discussion on whether power states generally change rapidly  
enough to warrant recomputing every time.


> Besides, 60-80 cycles is at most 20us of computation.  Considering it
> takes longer than that for the Atmel to wake up, I don't see a problem
> doing the computation.
>
>

This code runs every time the system handles an interrupt. Think of  
it as adding an overhead in that regard. Given that it is in an  
atomic section, this means that it is part of the critical path that  
defines the maximum interrupt handling rate. This is the most  
fundamental OS primitive (the task scheduler): we should make it as  
efficient as possible without making it too complex. Doesn't the  
msp430 wake up in something like 6us?

Phil

-------

"We shall not cease from exploration
And the end of all our exploring
Will be to arrive where we started
And know the place for the first time."

- T. S. Eliot,  'Little Gidding'


_______________________________________________
Tinyos-2.0wg mailing list
Tinyos-2.0wg at Mail.Millennium.Berkeley.EDU
https://mail.millennium.berkeley.edu/cgi-bin/mailman/listinfo/tinyos-2.0wg