a4ac01c36e
There are two problems with balance_tasks() and how it used: 1. The variables best_prio and best_prio_seen (inherited from the old move_tasks()) were only required to handle problems caused by the active/expired arrays, the order in which they were processed and the possibility that the task with the highest priority could be on either. These issues are no longer present and the extra overhead associated with their use is unnecessary (and possibly wrong). 2. In the absence of CONFIG_FAIR_GROUP_SCHED being set, the same this_best_prio variable needs to be used by all scheduling classes or there is a risk of moving too much load. E.g. if the highest priority task on this at the beginning is a fairly low priority task and the rt class migrates a task (during its turn) then that moved task becomes the new highest priority task on this_rq but when the sched_fair class initializes its copy of this_best_prio it will get the priority of the original highest priority task as, due to the run queue locks being held, the reschedule triggered by pull_task() will not have taken place. This could result in inappropriate overriding of skip_for_load and excessive load being moved. The attached patch addresses these problems by deleting all reference to best_prio and best_prio_seen and making this_best_prio a reference parameter to the various functions involved. load_balance_fair() has also been modified so that this_best_prio is only reset (in the loop) if CONFIG_FAIR_GROUP_SCHED is set. This should preserve the effect of helping spread groups' higher priority tasks around the available CPUs while improving system performance when CONFIG_FAIR_GROUP_SCHED isn't set. Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
72 lines
1.7 KiB
C
72 lines
1.7 KiB
C
/*
|
|
* idle-task scheduling class.
|
|
*
|
|
* (NOTE: these are not related to SCHED_IDLE tasks which are
|
|
* handled in sched_fair.c)
|
|
*/
|
|
|
|
/*
|
|
* Idle tasks are unconditionally rescheduled:
|
|
*/
|
|
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p)
|
|
{
|
|
resched_task(rq->idle);
|
|
}
|
|
|
|
static struct task_struct *pick_next_task_idle(struct rq *rq, u64 now)
|
|
{
|
|
schedstat_inc(rq, sched_goidle);
|
|
|
|
return rq->idle;
|
|
}
|
|
|
|
/*
|
|
* It is not legal to sleep in the idle task - print a warning
|
|
* message if some code attempts to do it:
|
|
*/
|
|
static void
|
|
dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep, u64 now)
|
|
{
|
|
spin_unlock_irq(&rq->lock);
|
|
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
|
|
dump_stack();
|
|
spin_lock_irq(&rq->lock);
|
|
}
|
|
|
|
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, u64 now)
|
|
{
|
|
}
|
|
|
|
static unsigned long
|
|
load_balance_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
|
|
unsigned long max_nr_move, unsigned long max_load_move,
|
|
struct sched_domain *sd, enum cpu_idle_type idle,
|
|
int *all_pinned, int *this_best_prio)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void task_tick_idle(struct rq *rq, struct task_struct *curr)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* Simple, special scheduling class for the per-CPU idle tasks:
|
|
*/
|
|
static struct sched_class idle_sched_class __read_mostly = {
|
|
/* no enqueue/yield_task for idle tasks */
|
|
|
|
/* dequeue is not valid, we print a debug message there: */
|
|
.dequeue_task = dequeue_task_idle,
|
|
|
|
.check_preempt_curr = check_preempt_curr_idle,
|
|
|
|
.pick_next_task = pick_next_task_idle,
|
|
.put_prev_task = put_prev_task_idle,
|
|
|
|
.load_balance = load_balance_idle,
|
|
|
|
.task_tick = task_tick_idle,
|
|
/* no .task_new for idle tasks */
|
|
};
|