Re: PREEMPT_RT vs ADEOS: the numbers, part 1

[Ingo Molnar <mingo@elte.hu>]

* Karim Yaghmour <karim@opersys.com> wrote:

> Ingo Molnar wrote:
> > ok, this method should work fine. I suspect you increased the parport 
> > IRQ's priority to the maximum on the PREEMPT_RT kernel, correct? Was 
> > there any userspace thread on the target system (receiving the parport 
> > request and sending the reply), or was it all done in a kernelspace 
> > parport driver?
> 
> This is all done in kernelspace. I'll check with Kristian for the 
> rest. In the mean time, let me know if you have any recommendations 
> based on the fact that it's indeed in the kernel.

if you want to measure hw-interrupt delays then under PREEMPT_RT you'll 
need to use an SA_NODELAY interrupt handler. (which is a PREEMPT_RT 
specific flag) If you use normal request_irq() or some parport driver 
then the driver function will run in an interrupt thread and what you 
are measuring is not interrupt latency but rescheduling latency.

	Ingo