[PATCH v2] sched/fair: Sync task util before slow-path wakeup

[PATCH v2] sched/fair: Sync task util before slow-path wakeup

[Brendan Jackman]

We use task_util in find_idlest_group via capacity_spare_wake. This
task_util is updated in wake_cap. However wake_cap is not the only
reason for ending up in find_idlest_group - we could have been sent
there by wake_wide. So explicitly sync the task util with prev_cpu
when we are about to head to find_idlest_group.

We could simply do this at the beginning of
select_task_rq_fair (i.e. irrespective of whether we're heading to
select_idle_sibling or find_idlest_group & co), but I didn't want to
slow down the select_idle_sibling path more than necessary.

Don't do this during fork balancing, we won't need the task_util and
we'd just clobber the last_update_time, which is supposed to be 0.

Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
---

changes v1 -> v2: Just cosmetic

 kernel/sched/fair.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c95880e216f6..20275178604d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5913,8 +5913,17 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			new_cpu = cpu;
 	}

+	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
+		/*
+		 * We're going to need the task's util for capacity_spare_wake
+		 * in find_idlest_group. Sync it up to prev_cpu's
+		 * last_update_time.
+		 */
+		sync_entity_load_avg(&p->se);
+	}
+
 	if (!sd) {
- pick_cpu:
+pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);

--
2.13.0

Re: [PATCH v2] sched/fair: Sync task util before slow-path wakeup

[Brendan Jackman]

Hi Peter,

Ping.

Log of previous discussion: https://patchwork.kernel.org/patch/9876769/

Cheers,
Brendan

On Tue, Aug 08 2017 at 09:55, Brendan Jackman wrote:
> We use task_util in find_idlest_group via capacity_spare_wake. This
> task_util is updated in wake_cap. However wake_cap is not the only
> reason for ending up in find_idlest_group - we could have been sent
> there by wake_wide. So explicitly sync the task util with prev_cpu
> when we are about to head to find_idlest_group.
>
> We could simply do this at the beginning of
> select_task_rq_fair (i.e. irrespective of whether we're heading to
> select_idle_sibling or find_idlest_group & co), but I didn't want to
> slow down the select_idle_sibling path more than necessary.
>
> Don't do this during fork balancing, we won't need the task_util and
> we'd just clobber the last_update_time, which is supposed to be 0.
>
> Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Cc: Josef Bacik <josef@toxicpanda.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Morten Rasmussen <morten.rasmussen@arm.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> ---
>
> changes v1 -> v2: Just cosmetic
>
>  kernel/sched/fair.c | 11 ++++++++++-
>  1 file changed, 10 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index c95880e216f6..20275178604d 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5913,8 +5913,17 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
>  			new_cpu = cpu;
>  	}
>
> +	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
> +		/*
> +		 * We're going to need the task's util for capacity_spare_wake
> +		 * in find_idlest_group. Sync it up to prev_cpu's
> +		 * last_update_time.
> +		 */
> +		sync_entity_load_avg(&p->se);
> +	}
> +
>  	if (!sd) {
> - pick_cpu:
> +pick_cpu:
>  		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
>  			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);

[tip:sched/core] sched/fair: Sync task util before slow-path wakeup

[tip-bot for Brendan Jackman]

Commit-ID:  ea16f0ea6c3dc9e1aa083bd3d1792ba02860526e
Gitweb:     https://git.kernel.org/tip/ea16f0ea6c3dc9e1aa083bd3d1792ba02860526e
Author:     Brendan Jackman <brendan.jackman@arm.com>
AuthorDate: Thu, 5 Oct 2017 11:55:51 +0100
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 10 Oct 2017 11:45:31 +0200

sched/fair: Sync task util before slow-path wakeup

We use task_util() in find_idlest_group() via capacity_spare_wake().
This task_util() updated in wake_cap(). However wake_cap() is not the
only reason for ending up in find_idlest_group() - we could have been sent
there by wake_wide(). So explicitly sync the task util with prev_cpu
when we are about to head to find_idlest_group().

We could simply do this at the beginning of
select_task_rq_fair() (i.e. irrespective of whether we're heading to
select_idle_sibling() or find_idlest_group() & co), but I didn't want to
slow down the select_idle_sibling() path more than necessary.

Don't do this during fork balancing, we won't need the task_util and
we'd just clobber the last_update_time, which is supposed to be 0.

Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andres Oportus <andresoportus@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/20170808095519.10077-1-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cc0bfb0..c04a425 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6263,8 +6263,17 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			new_cpu = cpu;
 	}
 
+	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
+		/*
+		 * We're going to need the task's util for capacity_spare_wake
+		 * in find_idlest_group. Sync it up to prev_cpu's
+		 * last_update_time.
+		 */
+		sync_entity_load_avg(&p->se);
+	}
+
 	if (!sd) {
- pick_cpu:
+pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);