(from https://patchwork.kernel.org/patch/9895261/) This patch adds a parameter to select_task_rq, sibling_count_hint allowing the caller, where it has this information, to inform the sched_class the number of tasks that are being woken up as part of the same event. The wake_q mechanism is one case where this information is available. select_task_rq_fair can then use the information to detect that it needs to widen the search space for task placement in order to avoid overloading the last-level cache domain's CPUs. * * * The reason I am investigating this change is the following use case on ARM big.LITTLE (asymmetrical CPU capacity): 1 task per CPU, which all repeatedly do X amount of work then pthread_barrier_wait (i.e. sleep until the last task finishes its X and hits the barrier). On big.LITTLE, the tasks which get a "big" CPU finish faster, and then those CPUs pull over the tasks that are still running: v CPU v ->time-> ------------- 0 (big) 11111 /333 ------------- 1 (big) 22222 /444| ------------- 2 (LITTLE) 333333/ ------------- 3 (LITTLE) 444444/ ------------- Now when task 4 hits the barrier (at |) and wakes the others up, there are 4 tasks with prev_cpu=<big> and 0 tasks with prev_cpu=<little>. want_affine therefore means that we'll only look in CPUs 0 and 1 (sd_llc), so tasks will be unnecessarily coscheduled on the bigs until the next load balance, something like this: v CPU v ->time-> ------------------------ 0 (big) 11111 /333 31313\33333 ------------------------ 1 (big) 22222 /444|424\4444444 ------------------------ 2 (LITTLE) 333333/ \222222 ------------------------ 3 (LITTLE) 444444/ \1111 ------------------------ ^^^ underutilization So, I'm trying to get want_affine = 0 for these tasks. I don't _think_ any incarnation of the wakee_flips mechanism can help us here because which task is waker and which tasks are wakees generally changes with each iteration. However pthread_barrier_wait (or more accurately FUTEX_WAKE) has the nice property that we know exactly how many tasks are being woken, so we can cheat. It might be a disadvantage that we "widen" _every_ task that's woken in an event, while select_idle_sibling would work fine for the first sd_llc_size - 1 tasks. IIUC, if wake_affine() behaves correctly this trick wouldn't be necessary on SMP systems, so it might be best guarded by the presence of SD_ASYM_CPUCAPACITY? * * * Final note.. In order to observe "perfect" behaviour for this use case, I also had to disable the TTWU_QUEUE sched feature. Suppose during the wakeup above we are working through the work queue and have placed tasks 3 and 2, and are about to place task 1: v CPU v ->time-> -------------- 0 (big) 11111 /333 3 -------------- 1 (big) 22222 /444|4 -------------- 2 (LITTLE) 333333/ 2 -------------- 3 (LITTLE) 444444/ <- Task 1 should go here -------------- If TTWU_QUEUE is enabled, we will not yet have enqueued task 2 (having instead sent a reschedule IPI) or attached its load to CPU 2. So we are likely to also place task 1 on cpu 2. Disabling TTWU_QUEUE means that we enqueue task 2 before placing task 1, solving this issue. TTWU_QUEUE is there to minimise rq lock contention, and I guess that this contention is less of an issue on big.LITTLE systems since they have relatively few CPUs, which suggests the trade-off makes sense here. Change-Id: I2080302839a263e0841a89efea8589ea53bbda9c Signed-off-by: Brendan Jackman <brendan.jackman@arm.com> Signed-off-by: Chris Redpath <chris.redpath@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Joel Fernandes <joelaf@google.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Matt Fleming <matt@codeblueprint.co.uk>
112 lines
2.3 KiB
C
112 lines
2.3 KiB
C
#include "sched.h"
|
|
|
|
/*
|
|
* idle-task scheduling class.
|
|
*
|
|
* (NOTE: these are not related to SCHED_IDLE tasks which are
|
|
* handled in sched/fair.c)
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
static int
|
|
select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags,
|
|
int sibling_count_hint)
|
|
{
|
|
return task_cpu(p); /* IDLE tasks as never migrated */
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/*
|
|
* Idle tasks are unconditionally rescheduled:
|
|
*/
|
|
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
resched_curr(rq);
|
|
}
|
|
|
|
static struct task_struct *
|
|
pick_next_task_idle(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
put_prev_task(rq, prev);
|
|
|
|
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 flags)
|
|
{
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
|
|
dump_stack();
|
|
raw_spin_lock_irq(&rq->lock);
|
|
}
|
|
|
|
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
idle_exit_fair(rq);
|
|
rq_last_tick_reset(rq);
|
|
}
|
|
|
|
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
|
|
{
|
|
}
|
|
|
|
static void set_curr_task_idle(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
static void switched_to_idle(struct rq *rq, struct task_struct *p)
|
|
{
|
|
BUG();
|
|
}
|
|
|
|
static void
|
|
prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
|
|
{
|
|
BUG();
|
|
}
|
|
|
|
static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void update_curr_idle(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* Simple, special scheduling class for the per-CPU idle tasks:
|
|
*/
|
|
const struct sched_class idle_sched_class = {
|
|
/* .next is NULL */
|
|
/* 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,
|
|
|
|
#ifdef CONFIG_SMP
|
|
.select_task_rq = select_task_rq_idle,
|
|
.set_cpus_allowed = set_cpus_allowed_common,
|
|
#endif
|
|
|
|
.set_curr_task = set_curr_task_idle,
|
|
.task_tick = task_tick_idle,
|
|
|
|
.get_rr_interval = get_rr_interval_idle,
|
|
|
|
.prio_changed = prio_changed_idle,
|
|
.switched_to = switched_to_idle,
|
|
.update_curr = update_curr_idle,
|
|
};
|