my next "spare time" project....

Huw Powell one@humanspeakers.com
Fri, 11 May 2001 16:59:33 -0700


> > Agreed.  If the engine is running at 6000 rpms, that's one revolution of the
> > crank every 1/100th of a second.  The severity of the CPU running kernel
> > interrupts would depend on the duration of the interrupt.  As far as I know
> > on a bare bones kernel that should only account for a few thousandths of a
> > second at the worst.. if this is the case then there isn't too much to worry
> > about.  As you say though.. probably best to run a real-time OS just to be
> > "safe...er".

I was gonna reply in a similar vein... but my head started to hurt, and
I try to keep my car free of kernels, even though the squirrels and mice
stay ahead.

The tough part is this - starting with that 100 Hz type assumption - the
computer is running 2 sets of 5 things at the same time - sparkers,
which I guess are reasonaby simple, and injectors, which are more
complex than a 100 Hz square wave ("on"/"off"), in that 10 ms window
they must be turned on, have some calculated duration, and be turned
off.  To have a gradation of of 1% accuracy in the "duty cycle" range,
now you need at least 10 ms/100 = 100 us "attention" from the CPU.  And
it has to run five of them with overlapping functions.

My initial thought was, hey, CPUs run at 100s of MHz these days, one
"clock click" is in the range of .01 ms so it should be ok - but then I
realised I didn't understand the subject matter so I deleted the reply
:-)

> 
> A little looking around and it seems that some tests have shown kernel
> blocking times for interrupts (ie. when the kernel can't service any
> interrupts) on the order of 150us if things are done smartly. This goes
> down to around 100us or so for RAM-based filesystems.

that would seem to just about barely meet the criterion I wildly guessed
at above - and 1% accuracy may not be that important for the injector
duty cycle?  I not know....

> As do some of the comments on the list :
>... now what was it that Huw was
> saying about waxing rotors? :)

Rotor wax, very important to the proper parking attitude, as in "that
car looks fast!"

I'm thinking that during that 100 ms CPU "daydream" (is that what they
do?) it could be monitoring rotor temps and applying/reducing brake
pressure to keep the wax at the temperature required for that "perfect
shine" after shutdown.

-- 
Huw Powell

http://www.humanspeakers.com/audi/

http://www.humanthoughts.org/