Jan Kiszka wrote:
 > Gregory CLEMENT wrote:
 > > Here, they are the last latency we get on AT91SAM9261-EK. As just now
 > > I haven't the board at home, I send the last result we stored. The
 > > prority of dbgu should be set to 6 instead of 7, but I can't assure
 > > it, for Xenomai.
 > Hmm, hardware interrupt priorities must not impact the worst-case
 > latency if I-pipe acks and mask them appropriately (the worst case is
 > when multiple interrupts happen in a row, not at the same time). But
 > this statement is not based on knowledge about potential pitfalls of
 > this arch. Are there specialities that require this tweaking?

During the port to AT91RM9200, I observed that under ping flood, the
ethernet driver interrupt was delaying the timer interrupt for unbounded
period of times, this because it had a higher priority. Changing the
interrupt priorities solved the issue. That said, I understand what you
mean, the interrupt should be masked when acked and should no longer
bother us until the I-pipe gives control to Linux to handle it.

 > > first Xenomai:
 > > 
 > > #insmod 
 > > /lib/modules/
 > > #cd /usr/xenomai/bin/
 > Which versions were you using for both tests? Do you still have the
 > involved .configs?
 > > #./latency -t 2 -p 150 -h -H 500

Why not -p 500 ? Since RTAI was tested with a 500 us period, the same
period should be use for Xenomai. I do not think this will change
anything, but who knows.


                                            Gilles Chanteperdrix.

Xenomai-core mailing list

Reply via email to