On Wed, Sep 27, 2017 at 01:58:20PM -0400, Rik van Riel wrote: > @@ -5359,10 +5378,14 @@ wake_affine_llc(struct sched_domain *sd, struct task_struct *p, > unsigned long current_load = task_h_load(current); > > /* in this case load hits 0 and this LLC is considered 'idle' */ > - if (current_load > this_stats.load) > + if (current_load > this_stats.max_load) > + return true; > + > + /* allow if the CPU would go idle, regardless of LLC load */ > + if (current_load >= target_load(this_cpu, sd->wake_idx)) > return true; > > - this_stats.load -= current_load; > + this_stats.max_load -= current_load; > } > > /* > @@ -5375,10 +5398,6 @@ wake_affine_llc(struct sched_domain *sd, struct task_struct *p, > if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) > return false; > > - /* if this cache has capacity, come here */ > - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) > - return true; > - > /* > * Check to see if we can move the load without causing too much > * imbalance. > @@ -5391,8 +5410,8 @@ wake_affine_llc(struct sched_domain *sd, struct task_struct *p, > prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; > prev_eff_load *= this_stats.capacity; > > - this_eff_load *= this_stats.load + task_load; > - prev_eff_load *= prev_stats.load - task_load; > + this_eff_load *= this_stats.max_load + task_load; > + prev_eff_load *= prev_stats.min_load - task_load; > > return this_eff_load <= prev_eff_load; > } So I would really like a workload that needs this LLC/NUMA stuff. Because I much prefer the simpler: 'on which of these two CPUs can I run soonest' approach.
