Re: [PATCH v2 29/35] sched: handle preempt=voluntary under PREEMPT_AUTO

[Tianchen Ding <dtcccc@linux.alibaba.com>]

On 2024/5/28 08:35, Ankur Arora wrote:
> The default preemption policy for voluntary preemption under
> PREEMPT_AUTO is to schedule eagerly for tasks of higher scheduling
> class, and lazily for well-behaved, non-idle tasks.
> 
> This is the same policy as preempt=none, with an eager handling of
> higher priority scheduling classes.
> 
> Comparing a cyclictest workload with a background kernel load of
> 'stress-ng --mmap', shows that both the average and the maximum
> latencies improve:
> 
>   # stress-ng --mmap 0 &
>   # cyclictest --mlockall --smp --priority=80 --interval=200 --distance=0 -q -D 300
> 
>                                       Min     (  %stdev )    Act     (  %stdev )   Avg     (  %stdev )   Max      (  %stdev )
> 
>    PREEMPT_AUTO, preempt=voluntary    1.73  ( +-  25.43% )   62.16 ( +- 303.39% )  14.92 ( +-  17.96% )  2778.22 ( +-  15.04% )
>    PREEMPT_DYNAMIC, preempt=voluntary 1.83  ( +-  20.76% )  253.45 ( +- 233.21% )  18.70 ( +-  15.88% )  2992.45 ( +-  15.95% )
> 
> The table above shows the aggregated latencies across all CPUs.
> 
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Ziljstra <peterz@infradead.org>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Originally-by: Thomas Gleixner <tglx@linutronix.de>
> Link: https://lore.kernel.org/lkml/87jzshhexi.ffs@tglx/
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
> ---
>   kernel/sched/core.c  | 12 ++++++++----
>   kernel/sched/sched.h |  6 ++++++
>   2 files changed, 14 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index c25cccc09b65..2bc3ae21a9d0 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -1052,6 +1052,9 @@ static resched_t resched_opt_translate(struct task_struct *curr,
>   	if (preempt_model_preemptible())
>   		return RESCHED_NOW;
>   
> +	if (preempt_model_voluntary() && opt == RESCHED_PRIORITY)
> +		return RESCHED_NOW;
> +
>   	if (is_idle_task(curr))
>   		return RESCHED_NOW;
>   
> @@ -2289,7 +2292,7 @@ void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
>   	if (p->sched_class == rq->curr->sched_class)
>   		rq->curr->sched_class->wakeup_preempt(rq, p, flags);
>   	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
> -		resched_curr(rq);
> +		resched_curr_priority(rq);
>   
Besides the conditions about higher class, can we do resched_curr_priority() in the same class?
For example, in fair class, we can do it when SCHED_NORMAL vs SCHED_IDLE.

Maybe sth like

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 41b58387023d..eedb70234bdd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8352,6 +8352,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
  	struct sched_entity *se = &curr->se, *pse = &p->se;
  	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
  	int cse_is_idle, pse_is_idle;
+	enum resched_opt opt = RESCHED_PRIORITY;
  
  	if (unlikely(se == pse))
  		return;
@@ -8385,7 +8386,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
  	/* Idle tasks are by definition preempted by non-idle tasks. */
  	if (unlikely(task_has_idle_policy(curr)) &&
  	    likely(!task_has_idle_policy(p)))
-		goto preempt;
+		goto preempt; /* RESCHED_PRIORITY */
  
  	/*
  	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
@@ -8405,7 +8406,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
  	 * in the inverse case).
  	 */
  	if (cse_is_idle && !pse_is_idle)
-		goto preempt;
+		goto preempt; /* RESCHED_PRIORITY */
  	if (cse_is_idle != pse_is_idle)
  		return;
  
@@ -8415,13 +8416,15 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
  	/*
  	 * XXX pick_eevdf(cfs_rq) != se ?
  	 */
-	if (pick_eevdf(cfs_rq) == pse)
+	if (pick_eevdf(cfs_rq) == pse) {
+		opt = RESCHED_DEFAULT;
  		goto preempt;
+	}
  
  	return;
  
  preempt:
-	resched_curr(rq);
+	__resched_curr(rq, opt);
  }
  
  #ifdef CONFIG_SMP