Re: [PATCH 3/4] sched: Optimize tick periodic cpu load updates

[Frederic Weisbecker <fweisbec@gmail.com>]

On Sat, Apr 02, 2016 at 09:23:37AM +0200, Peter Zijlstra wrote:
> On Fri, Apr 01, 2016 at 03:23:06PM +0200, Frederic Weisbecker wrote:
> > Don't bother with the whole pending tickless cpu load machinery if
> > we run a tick periodic kernel. That's less job for the CPU on ticks.
> 
> Again, the changelog really could use help. Is this a pure optimization
> patch? If so, do you have numbers?

Well until now we have always tried to keep the nohz code under ifdef.
For optimizations and kernel size. I haven't measured it though, I guess
the gain is hardly visible.

> 
> > +++ b/kernel/sched/sched.h
> > @@ -585,8 +585,10 @@ struct rq {
> >  #endif
> >  	#define CPU_LOAD_IDX_MAX 5
> >  	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
> > +#ifdef CONFIG_NO_HZ_COMMON
> > +# ifdef CONFIG_SMP
> 
> I'm not a fan of this #ifdef indenting and nothing near there uses this
> style, so please don't introduce it here.

Ok.

Thanks.

> 
> >  	unsigned long last_load_update_tick;
> > -#ifdef CONFIG_NO_HZ_COMMON
> > +# endif
> >  	u64 nohz_stamp;
> >  	unsigned long nohz_flags;
> >  #endif
> > -- 
> > 2.7.0
> >