Skip to contentSkip to conversation

wait_task_inactive() spend too much time on system startup

PATCH Superseded [email protected] 2 participants 3 messages Mar 5, 2020 Scheduler

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

v2 cover wait_task_inactive() spend too much time on system startup

From: Liang Chen <[email protected]>

Changelog:
v1: wait_task_inactive() frequently call schedule_hrtimeout() and spend a lot of time, i am trying to optimize it on rockchip platform.
v2: Use atomic_flags(PFA) instead of TIF flag, and add some comments.

Liang Chen (1):
sched/fair: do not preempt current task if it is going to call
schedule()

 include/linux/sched.h |  5 +++++
 kernel/kthread.c      |  4 ++++
 kernel/sched/fair.c   | 13 +++++++++++++
 3 files changed, 22 insertions(+)
Signature · 1 line
2.17.1
#1 lore raw

PATCH v2 1/1 sched/fair: do not preempt current task if it is going to call schedule()

From: Liang Chen <[email protected]>

when we create a kthread with ktrhead_create_on_cpu(),the child thread entry is ktread.c:ktrhead() which will be preempted by the parent after call complete(done) while schedule() is not called yet,then the parent will call wait_task_inactive(child) but the child is still on the runqueue, so the parent will schedule_hrtimeout() for 1 jiffy,it will waste a lot of time,especially on startup.

parent child
ktrhead_create_on_cpu()
wait_fo_completion(&done) -----> ktread.c:ktrhead()
|----- complete(done);--wakeup and preempted by parent

 kthread_bind() <------------|  |-> schedule();--dequeue here
  wait_task_inactive(child)     |
   schedule_hrtimeout(1 jiffy) -|

So we hope the child just wakeup parent but not preempted by parent, and the child is going to call schedule() soon,then the parent will not call schedule_hrtimeout(1 jiffy) as the child is already dequeue.

The same issue for ktrhead_park()&&kthread_parkme(). This patch can save 120ms on rk312x startup with CONFIG_HZ=300.

---
 include/linux/sched.h |  5 +++++
 kernel/kthread.c      |  4 ++++
 kernel/sched/fair.c   | 13 +++++++++++++
 3 files changed, 22 insertions(+)
include/linux/sched.h +5 -0
index 04278493bf15..54bf336f5790 100644
@@ -1533,6 +1533,7 @@ static inline bool is_percpu_thread(void)
 #define PFA_SPEC_IB_DISABLE		5	/* Indirect branch speculation restricted */
 #define PFA_SPEC_IB_FORCE_DISABLE	6	/* Indirect branch speculation permanently restricted */
 #define PFA_SPEC_SSB_NOEXEC		7	/* Speculative Store Bypass clear on execve() */
+#define PFA_GOING_TO_SCHED		8	/* task is going to call schedule() */
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1575,6 +1576,10 @@ TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)
 TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
 TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
 
+TASK_PFA_TEST(GOING_TO_SCHED, going_to_sched)
+TASK_PFA_SET(GOING_TO_SCHED, going_to_sched)
+TASK_PFA_CLEAR(GOING_TO_SCHED, going_to_sched)
+
 static inline void
 current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {
kernel/kthread.c +4 -0
index b262f47046ca..bc96de2648f6 100644
@@ -199,8 +199,10 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
+		task_set_going_to_sched(current);
 		complete(&self->parked);
 		schedule();
+		task_clear_going_to_sched(current);
 	}
 	__set_current_state(TASK_RUNNING);
 }
@@ -245,8 +247,10 @@ static int kthread(void *_create)
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
+	task_set_going_to_sched(current);
 	complete(done);
 	schedule();
+	task_clear_going_to_sched(current);
 
 	ret = -EINTR;
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
kernel/sched/fair.c +13 -0
index 3c8a379c357e..78666cec794a 100644
@@ -4330,6 +4330,12 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
 		return;
 #endif
+	/*
+	 * current task is going to call schedule(), do not preempt it or
+	 * it will casue more useless contex_switch().
+	 */
+	if (task_going_to_sched(rq_of(cfs_rq)->curr))
+		return;
 
 	if (cfs_rq->nr_running > 1)
 		check_preempt_tick(cfs_rq, curr);
@@ -6634,6 +6640,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (test_tsk_need_resched(curr))
 		return;
 
+	/*
+	 * current task is going to call schedule(), do not preempt it or
+	 * it will casue more useless contex_switch().
+	 */
+	if (task_going_to_sched(curr))
+		return;
+
 	/* Idle tasks are by definition preempted by non-idle tasks. */
 	if (unlikely(task_has_idle_policy(curr)) &&
 	    likely(!task_has_idle_policy(p)))
Signature · 1 line
2.17.1
Reviewed-by on v2 1/1
#2 lore raw

Re: [PATCH v2 1/1] sched/fair: do not preempt current task if it is going to call schedule()

Quoted 17 lines · On Thu, Mar 05, 2020 at 05:59:48PM +0800, [email protected] wrote:

From: Liang Chen <[email protected]>

when we create a kthread with ktrhead_create_on_cpu(),the child thread entry is ktread.c:ktrhead() which will be preempted by the parent after call complete(done) while schedule() is not called yet,then the parent will call wait_task_inactive(child) but the child is still on the runqueue, so the parent will schedule_hrtimeout() for 1 jiffy,it will waste a lot of time,especially on startup.

parent child
ktrhead_create_on_cpu()
wait_fo_completion(&done) -----> ktread.c:ktrhead()
|----- complete(done);--wakeup and preempted by parent

 kthread_bind() <------------|  |-> schedule();--dequeue here
  wait_task_inactive(child)     |
   schedule_hrtimeout(1 jiffy) -|
Quoted 8 lines

So we hope the child just wakeup parent but not preempted by parent, and the child is going to call schedule() soon,then the parent will not call schedule_hrtimeout(1 jiffy) as the child is already dequeue.

The same issue for ktrhead_park()&&kthread_parkme(). This patch can save 120ms on rk312x startup with CONFIG_HZ=300.

I'm not familiar with the subtleties of scheduler internals (e.g. is there a race between the end of "schedule();" and calling "task_clear_going_to_sched();" that effects the preemption test logic?), so I'll leave that review to the others. But speaking to the PFA change, it looks sane to me:

-Kees

Quoted 91 lines
---
 include/linux/sched.h |  5 +++++
 kernel/kthread.c      |  4 ++++
 kernel/sched/fair.c   | 13 +++++++++++++
 3 files changed, 22 insertions(+)
include/linux/sched.h +5 -0
index 04278493bf15..54bf336f5790 100644
@@ -1533,6 +1533,7 @@ static inline bool is_percpu_thread(void)
 #define PFA_SPEC_IB_DISABLE		5	/* Indirect branch speculation restricted */
 #define PFA_SPEC_IB_FORCE_DISABLE	6	/* Indirect branch speculation permanently restricted */
 #define PFA_SPEC_SSB_NOEXEC		7	/* Speculative Store Bypass clear on execve() */
+#define PFA_GOING_TO_SCHED		8	/* task is going to call schedule() */
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1575,6 +1576,10 @@ TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)
 TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
 TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
 
+TASK_PFA_TEST(GOING_TO_SCHED, going_to_sched)
+TASK_PFA_SET(GOING_TO_SCHED, going_to_sched)
+TASK_PFA_CLEAR(GOING_TO_SCHED, going_to_sched)
+
 static inline void
 current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {
kernel/kthread.c +4 -0
index b262f47046ca..bc96de2648f6 100644
@@ -199,8 +199,10 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
+		task_set_going_to_sched(current);
 		complete(&self->parked);
 		schedule();
+		task_clear_going_to_sched(current);
 	}
 	__set_current_state(TASK_RUNNING);
 }
@@ -245,8 +247,10 @@ static int kthread(void *_create)
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
+	task_set_going_to_sched(current);
 	complete(done);
 	schedule();
+	task_clear_going_to_sched(current);
 
 	ret = -EINTR;
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
kernel/sched/fair.c +13 -0
index 3c8a379c357e..78666cec794a 100644
@@ -4330,6 +4330,12 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
 		return;
 #endif
+	/*
+	 * current task is going to call schedule(), do not preempt it or
+	 * it will casue more useless contex_switch().
+	 */
+	if (task_going_to_sched(rq_of(cfs_rq)->curr))
+		return;
 
 	if (cfs_rq->nr_running > 1)
 		check_preempt_tick(cfs_rq, curr);
@@ -6634,6 +6640,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (test_tsk_need_resched(curr))
 		return;
 
+	/*
+	 * current task is going to call schedule(), do not preempt it or
+	 * it will casue more useless contex_switch().
+	 */
+	if (task_going_to_sched(curr))
+		return;
+
 	/* Idle tasks are by definition preempted by non-idle tasks. */
 	if (unlikely(task_has_idle_policy(curr)) &&
 	    likely(!task_has_idle_policy(p)))
Signature · 1 line
2.17.1
Signature · 1 line
Kees Cook