On 15 September 2016 at 16:43, Peter Zijlstra <pet...@infradead.org> wrote:
> On Mon, Sep 12, 2016 at 09:47:49AM +0200, Vincent Guittot wrote:
>> +static inline void
>> +update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
>> +{
>> + struct cfs_rq *gcfs_rq = group_cfs_rq(se);
>> + long delta, load = gcfs_rq->avg.load_avg;
>> +
>> + /* If the load of group cfs_rq is null, the load of the
>> + * sched_entity will also be null so we can skip the formula
>> + */
>> + if (load) {
>> + long tg_load;
>> +
>> + /* Get tg's load and ensure tg_load > 0 */
>> + tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
>> +
>> + /* Ensure tg_load >= load and updated with current load*/
>> + tg_load -= gcfs_rq->tg_load_avg_contrib;
>> + tg_load += load;
>> +
>> + /* scale gcfs_rq's load into tg's shares*/
>> + load *= scale_load_down(gcfs_rq->tg->shares);
>> + load /= tg_load;
>> +
>> + /*
>> + * we need to compute a correction term in the case that the
>> + * task group is consuming <1 cpu so that we would contribute
>> + * the same load as a task of equal weight.
>> + */
>> + if (tg_load < scale_load_down(gcfs_rq->tg->shares)) {
>> + load *= tg_load;
>> + load /= scale_load_down(gcfs_rq->tg->shares);
>> + }
>
> Note that you're reversing the exact scaling you just applied.
Yes, Indeed
>
> That is:
> shares tg_load
> load * ------- * ------- == load
> tg_load shares
>
>> + }
>
> So something like:
>
> shares = scale_load_down(gcfs_rq->tg->shares);
>
> if (tg_load >= shares) {
> load *= shares;
> load /= tg_load;
> }
>
> should be the same as the above and saves a bunch of math, no?
Yes
