Re: questions on calc_delta_mine() in sched.c

[Joel Schopp <jschopp@austin.ibm.com>]

> This one builds and... boots

I'll try to test in on my end.

> +	struct load_weight lw_cache[4];
> +	int lw_cache_idx;
> +
>  	struct cfs_rq cfs;
>  	struct rt_rq rt;
>  
> @@ -1438,8 +1441,24 @@ calc_delta_mine(unsigned long delta_exec
>  {
>  	u64 tmp;
>  
> -	if (unlikely(!lw->inv_weight))
> -		lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
> +	if (!lw->inv_weight) {

Yep, got to get rid of unlikely.

> +		struct rq *rq = cpu_rq(smp_processor_id());
> +		unsigned long weight = lw->weight;
> +		int i;
> +
> +		for (i = 0; i < ARRAY_SIZE(rq->lw_cache); i++) {
> +			if (rq->lw_cache[i].weight == weight)
> +				lw->inv_weight = rq->lw_cache[i].inv_weight;
> +			goto got_inv;
> +		}
> +		if (unlikely(!weight))
> +			weight++;
> +		lw->inv_weight = 1 + (WMULT_CONST - weight/2) / weight;

I bet just dividing by weight + 1 unconditionally would be cheaper than 
doing the test and shouldn't skew results too badly.

> +		rq->lw_cache[rq->lw_cache_idx] = *lw;
> +		rq->lw_cache_idx++;
> +		rq->lw_cache_idx %= ARRAY_SIZE(rq->lw_cache);
> +	}
> + got_inv:

Doctor, I think the cure is worse than the disease.   I'd expect that even 
if all these extra loads hit cache they should together be more expensive 
than the divide they save.   Not that I have any better solutions myself.

>  
>  	tmp = (u64)delta_exec * weight;
>  	/*
> @@ -8025,7 +8044,7 @@ static void init_tg_cfs_entry(struct tas
>  
>  	se->my_q = cfs_rq;
>  	se->load.weight = tg->shares;
> -	se->load.inv_weight = div64_64(1ULL<<32, se->load.weight);
> +	se->load.inv_weight = 0;
>  	se->parent = parent;
>  }
>  #endif
> @@ -8692,7 +8711,7 @@ static void __set_se_shares(struct sched
>  		dequeue_entity(cfs_rq, se, 0);
>  
>  	se->load.weight = shares;
> -	se->load.inv_weight = div64_64((1ULL<<32), shares);
> +	se->load.inv_weight = 0;
>  
>  	if (on_rq)
>  		enqueue_entity(cfs_rq, se, 0);
> 
> 

I think a patch to get rid of unlikely and to change these two div64_64 to 
0s should be pushed up.  Not sure what we do about the divide.