Re: [PATCH 3/3] sched: Optimize !CONFIG_NO_HZ_COMMON cpu load updates

[Peter Zijlstra]

On Fri, Apr 08, 2016 at 03:07:13AM +0200, Frederic Weisbecker wrote:
> index 4c522a7..59a2821 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -7327,8 +7327,9 @@ void __init sched_init(void)
>  
>  		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
>  			rq->cpu_load[j] = 0;
> -
> +#ifdef CONFIG_NO_HZ_COMMON
>  		rq->last_load_update_tick = jiffies;
> +#endif
>  
>  #ifdef CONFIG_SMP
>  		rq->sd = NULL;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 1dd864d..4618e5b 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4661,8 +4680,10 @@ static inline void cpu_load_update_nohz(struct rq *this_rq,
>  
>  static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load)
>  {
> +#ifdef CONFIG_NO_HZ_COMMON
>  	/* See the mess around cpu_load_update_nohz(). */
>  	this_rq->last_load_update_tick = READ_ONCE(jiffies);
> +#endif
>  	cpu_load_update(this_rq, load, 1);
>  }
>  

Here you do the simple #ifdef, while here you make a giant mess instead
of the relatively straight forward:

> @@ -4540,17 +4568,8 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
>  
>  		/* scale is effectively 1 << i now, and >> i divides by scale */
>  
> -		old_load = this_rq->cpu_load[i];
#ifdef CONFIG_NO_HZ_COMMON
> -		old_load = decay_load_missed(old_load, pending_updates - 1, i);
> -		if (tickless_load) {
> -			old_load -= decay_load_missed(tickless_load, pending_updates - 1, i);
> -			/*
> -			 * old_load can never be a negative value because a
> -			 * decayed tickless_load cannot be greater than the
> -			 * original tickless_load.
> -			 */
> -			old_load += tickless_load;
> -		}
#endif
>  		new_load = this_load;
>  		/*
>  		 * Round up the averaging division if load is increasing. This