On Wed, May 04, 2016 at 12:37:01PM +0200, Peter Zijlstra wrote: > +static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, > int target) > +{ > + struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); > + u64 time, cost; > + s64 delta; > + int cpu, wrap; > + > + if (sched_feat(AVG_CPU)) { > + u64 avg_idle = this_rq()->avg_idle; > + u64 avg_cost = this_sd->avg_scan_cost; > + > + if (sched_feat(PRINT_AVG)) > + trace_printk("idle: %Ld cost: %Ld\n", avg_idle, > avg_cost); > + > + if (avg_idle / 32 < avg_cost)
s/32/512/ + IDLE_SMT fixes a hackbench regression hackbench, like tbench, doesn't like IDLE_CPU to trigger, but apparently needs IDLE_SMT. Bah, I could sort of explain 32 away, but 512 is firmly in the magic value range :/ > + return -1; > + } > + > + time = local_clock(); > + > + for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { > + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) > + continue; > + if (idle_cpu(cpu)) > + break; > + } > + > + time = local_clock() - time; > + cost = this_sd->avg_scan_cost; > + delta = (s64)(time - cost) / 8; > + /* trace_printk("time: %Ld cost: %Ld delta: %Ld\n", time, cost, delta); > */ > + this_sd->avg_scan_cost += delta; > + > + return cpu; > +}