[LinuxPPS] So far, so good

[Bernhard Schiffner]

...
> > Of course we can do little more than speculate on this since we don't
> > have any way to measure the interrupt handler latency.  About the only
> > way to test this would be to use a machine with a temperature controlled
> > oscillator as a test bed.  If loading such a machine causes significant
> > changes to the offset then that affect can probably be attributed to
> > latency rather than temperatures. But I don't have a machine like this
> > to test with.
> 
> It should be also possible to get an upper bound by flipping a bit on
> parallel port in the interrupt handler and measuring the delay on a
> scope.

Do it in the serial pps driver itself (changing an serial output pin). It's 
very "hacky" but  less distant from the interrupt-handling soft- and hardware 
itself.

Sorry for not having the code at hand here.

Bernhard
PS:
If you get results, can you post your delays please?

IIRR I got about 100µs and "big" jitter.
( I'am goin to repeat this with recent software. Not guaranteed.)