Re: [PATCH] instrument softirq raising

* Frank Ch. Eigler ([email protected]) wrote:
> 
> >> This will allow the measuring of softirq latencies, and will make it easier to
> >> follow critical paths from irq arrival to process wakeup. 
> >> [...]
> >>  inline fastcall void raise_softirq_irqoff(unsigned int nr)
> >>  {
> >> +	trace_mark(kernel_softirq_raise, "softirq %u", nr);
> >> +
> >>  	__raise_softirq_irqoff(nr);
> 
> It would probably be better to have instrumentation that marks both
> the beginning and the end of a soft/hard irq handler.
> 

We already have this. It's only the "raise" that we didn't have.

> - FChE
> _______________________________________________
> Ltt-dev mailing list
> [email protected]
> http://listserv.shafik.org/mailman/listinfo/ltt-dev
> 

-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68