* increased. Here we update the fair scheduling stats and
* then put the task into the rbtree:
*/
-static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
* If there's an idle sibling in this domain, make that
* the wake_affine target instead of the current cpu.
*/
- if (tmp->flags & SD_PREFER_SIBLING)
+ if (tmp->flags & SD_SHARE_PKG_RESOURCES)
target = select_idle_sibling(p, tmp, target);
if (target >= 0) {
unsigned long max_load;
unsigned long busiest_load_per_task;
unsigned long busiest_nr_running;
+ unsigned long busiest_group_capacity;
int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
unsigned long load, max_cpu_load, min_cpu_load;
int i;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
- unsigned long sum_avg_load_per_task;
- unsigned long avg_load_per_task;
+ unsigned long avg_load_per_task = 0;
- if (local_group) {
+ if (local_group)
balance_cpu = group_first_cpu(group);
- if (balance_cpu == this_cpu)
- update_group_power(sd, this_cpu);
- }
/* Tally up the load of all CPUs in the group */
- sum_avg_load_per_task = avg_load_per_task = 0;
max_cpu_load = 0;
min_cpu_load = ~0UL;
sgs->sum_nr_running += rq->nr_running;
sgs->sum_weighted_load += weighted_cpuload(i);
- sum_avg_load_per_task += cpu_avg_load_per_task(i);
}
/*
* to do the newly idle load balance.
*/
if (idle != CPU_NEWLY_IDLE && local_group &&
- balance_cpu != this_cpu && balance) {
+ balance_cpu != this_cpu) {
*balance = 0;
return;
}
+ update_group_power(sd, this_cpu);
+
/* Adjust by relative CPU power of the group */
sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
-
/*
* Consider the group unbalanced when the imbalance is larger
* than the average weight of two tasks.
* normalized nr_running number somewhere that negates
* the hierarchy?
*/
- avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
- group->cpu_power;
+ if (sgs->sum_nr_running)
+ avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
sgs->group_imb = 1;
update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
local_group, cpus, balance, &sgs);
- if (local_group && balance && !(*balance))
+ if (local_group && !(*balance))
return;
sds->total_load += sgs.group_load;
sds->max_load = sgs.avg_load;
sds->busiest = group;
sds->busiest_nr_running = sgs.sum_nr_running;
+ sds->busiest_group_capacity = sgs.group_capacity;
sds->busiest_load_per_task = sgs.sum_weighted_load;
sds->group_imb = sgs.group_imb;
}
{
unsigned long tmp, pwr_now = 0, pwr_move = 0;
unsigned int imbn = 2;
+ unsigned long scaled_busy_load_per_task;
if (sds->this_nr_running) {
sds->this_load_per_task /= sds->this_nr_running;
sds->this_load_per_task =
cpu_avg_load_per_task(this_cpu);
- if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
- sds->busiest_load_per_task * imbn) {
+ scaled_busy_load_per_task = sds->busiest_load_per_task
+ * SCHED_LOAD_SCALE;
+ scaled_busy_load_per_task /= sds->busiest->cpu_power;
+
+ if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
+ (scaled_busy_load_per_task * imbn)) {
*imbalance = sds->busiest_load_per_task;
return;
}
static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
unsigned long *imbalance)
{
- unsigned long max_pull;
+ unsigned long max_pull, load_above_capacity = ~0UL;
+
+ sds->busiest_load_per_task /= sds->busiest_nr_running;
+ if (sds->group_imb) {
+ sds->busiest_load_per_task =
+ min(sds->busiest_load_per_task, sds->avg_load);
+ }
+
/*
* In the presence of smp nice balancing, certain scenarios can have
* max load less than avg load(as we skip the groups at or below
return fix_small_imbalance(sds, this_cpu, imbalance);
}
- /* Don't want to pull so many tasks that a group would go idle */
- max_pull = min(sds->max_load - sds->avg_load,
- sds->max_load - sds->busiest_load_per_task);
+ if (!sds->group_imb) {
+ /*
+ * Don't want to pull so many tasks that a group would go idle.
+ */
+ load_above_capacity = (sds->busiest_nr_running -
+ sds->busiest_group_capacity);
+
+ load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+
+ load_above_capacity /= sds->busiest->cpu_power;
+ }
+
+ /*
+ * We're trying to get all the cpus to the average_load, so we don't
+ * want to push ourselves above the average load, nor do we wish to
+ * reduce the max loaded cpu below the average load. At the same time,
+ * we also don't want to reduce the group load below the group capacity
+ * (so that we can implement power-savings policies etc). Thus we look
+ * for the minimum possible imbalance.
+ * Be careful of negative numbers as they'll appear as very large values
+ * with unsigned longs.
+ */
+ max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
/* How much load to actually move to equalise the imbalance */
*imbalance = min(max_pull * sds->busiest->cpu_power,
* 4) This group is more busy than the avg busieness at this
* sched_domain.
* 5) The imbalance is within the specified limit.
- * 6) Any rebalance would lead to ping-pong
*/
- if (balance && !(*balance))
+ if (!(*balance))
goto ret;
if (!sds.busiest || sds.busiest_nr_running == 0)
if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
goto out_balanced;
- sds.busiest_load_per_task /= sds.busiest_nr_running;
- if (sds.group_imb)
- sds.busiest_load_per_task =
- min(sds.busiest_load_per_task, sds.avg_load);
-
- /*
- * We're trying to get all the cpus to the average_load, so we don't
- * want to push ourselves above the average load, nor do we wish to
- * reduce the max loaded cpu below the average load, as either of these
- * actions would just result in more rebalancing later, and ping-pong
- * tasks around. Thus we look for the minimum possible imbalance.
- * Negative imbalances (*we* are more loaded than anyone else) will
- * be counted as no imbalance for these purposes -- we can't fix that
- * by pulling tasks to us. Be careful of negative numbers as they'll
- * appear as very large values with unsigned longs.
- */
- if (sds.max_load <= sds.busiest_load_per_task)
- goto out_balanced;
-
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(&sds, this_cpu, imbalance);
return sds.busiest;
continue;
rq = cpu_rq(i);
- wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
- wl /= power;
+ wl = weighted_cpuload(i);
+ /*
+ * When comparing with imbalance, use weighted_cpuload()
+ * which is not scaled with the cpu power.
+ */
if (capacity && rq->nr_running == 1 && wl > imbalance)
continue;
+ /*
+ * For the load comparisons with the other cpu's, consider
+ * the weighted_cpuload() scaled with the cpu power, so that
+ * the load can be moved away from the cpu that is potentially
+ * running at a lower capacity.
+ */
+ wl = (wl * SCHED_LOAD_SCALE) / power;
+
if (wl > max_load) {
max_load = wl;
busiest = rq;
}
/*
- * Check this_cpu to ensure it is balanced within domain. Attempt to move
- * tasks if there is an imbalance.
- *
- * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
- * this_rq is locked.
- */
-static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
-{
- struct sched_group *group;
- struct rq *busiest = NULL;
- unsigned long imbalance;
- int ld_moved = 0;
- int sd_idle = 0;
- int all_pinned = 0;
- struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
- cpumask_copy(cpus, cpu_active_mask);
-
- /*
- * When power savings policy is enabled for the parent domain, idle
- * sibling can pick up load irrespective of busy siblings. In this case,
- * let the state of idle sibling percolate up as IDLE, instead of
- * portraying it as CPU_NOT_IDLE.
- */
- if (sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- sd_idle = 1;
-
- schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
-redo:
- update_shares_locked(this_rq, sd);
- group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
- &sd_idle, cpus, NULL);
- if (!group) {
- schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
- goto out_balanced;
- }
-
- busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
- if (!busiest) {
- schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
- goto out_balanced;
- }
-
- BUG_ON(busiest == this_rq);
-
- schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
-
- ld_moved = 0;
- if (busiest->nr_running > 1) {
- /* Attempt to move tasks */
- double_lock_balance(this_rq, busiest);
- /* this_rq->clock is already updated */
- update_rq_clock(busiest);
- ld_moved = move_tasks(this_rq, this_cpu, busiest,
- imbalance, sd, CPU_NEWLY_IDLE,
- &all_pinned);
- double_unlock_balance(this_rq, busiest);
-
- if (unlikely(all_pinned)) {
- cpumask_clear_cpu(cpu_of(busiest), cpus);
- if (!cpumask_empty(cpus))
- goto redo;
- }
- }
-
- if (!ld_moved) {
- int active_balance = 0;
-
- schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
- sd->nr_balance_failed++;
-
- if (need_active_balance(sd, sd_idle, CPU_NEWLY_IDLE)) {
- double_lock_balance(this_rq, busiest);
-
- /*
- * don't kick the migration_thread, if the curr
- * task on busiest cpu can't be moved to this_cpu
- */
- if (!cpumask_test_cpu(this_cpu,
- &busiest->curr->cpus_allowed)) {
- double_unlock_balance(this_rq, busiest);
- all_pinned = 1;
- return ld_moved;
- }
-
- if (!busiest->active_balance) {
- busiest->active_balance = 1;
- busiest->push_cpu = this_cpu;
- active_balance = 1;
- }
-
- double_unlock_balance(this_rq, busiest);
- /*
- * Should not call ttwu while holding a rq->lock
- */
- raw_spin_unlock(&this_rq->lock);
- if (active_balance)
- wake_up_process(busiest->migration_thread);
- raw_spin_lock(&this_rq->lock);
- }
- } else
- sd->nr_balance_failed = 0;
-
- update_shares_locked(this_rq, sd);
- return ld_moved;
-
-out_balanced:
- schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return -1;
- sd->nr_balance_failed = 0;
-
- return 0;
-}
-
-/*
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
if (this_rq->avg_idle < sysctl_sched_migration_cost)
return;
+ /*
+ * Drop the rq->lock, but keep IRQ/preempt disabled.
+ */
+ raw_spin_unlock(&this_rq->lock);
+
for_each_domain(this_cpu, sd) {
unsigned long interval;
+ int balance = 1;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
- if (sd->flags & SD_BALANCE_NEWIDLE)
+ if (sd->flags & SD_BALANCE_NEWIDLE) {
/* If we've pulled tasks over stop searching: */
- pulled_task = load_balance_newidle(this_cpu, this_rq,
- sd);
+ pulled_task = load_balance(this_cpu, this_rq,
+ sd, CPU_NEWLY_IDLE, &balance);
+ }
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
break;
}
}
+
+ raw_spin_lock(&this_rq->lock);
+
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
* We are going idle. next_balance may be set based on
static inline int on_null_domain(int cpu)
{
- return !rcu_dereference(cpu_rq(cpu)->sd);
+ return !rcu_dereference_sched(cpu_rq(cpu)->sd);
}
/*