Re: [PATCH 2/3] posix_timers: Defer per process timer stop after timers processing

[Frederic Weisbecker <fweisbec@gmail.com>]

On Tue, Apr 30, 2013 at 01:51:58PM -0400, Olivier Langlois wrote:
> 
> > 
> > > Maybe the condition around the posix_cpu_timer_schedule() block inside
> > > cpu_timer_fire() could even be a good candidate for 'unlikely'
> > > qualifier.
> > 
> > Well, cpu_timer_fire() is probably not a fast path. So helping branch
> > prediction there probably won't have much measurable effect in practice.
> > 
> Frederic, I'm totally sure that you are right on the measurable effect.
> When I did propose the 'unlikely' qualifier, please note, that I also
> had a documentary purpose in mind.
> 
> Would you have searched the 'likely' path that does
> posix_cpu_timer_schedule() when you did modify the code if the
> 'unlikely' tag would have been present?

It's indeed sometimes a good indicator.

But here it's in the end of a batch of conditional blocks, so it sort
of already suggests itself as an unlikely event.

But if you feel the comment can be improved, don't hesitate to send a patch.



> 
> Greetings,
> Olivier
> 
> 
>