Re: [PATCH v2] sched/fair: Sync se's load_avg with cfs_rq in reweight_task

From: Chengming Zhou
Date: Mon Jul 22 2024 - 02:41:11 EST


On 2024/7/22 13:17, K Prateek Nayak wrote:
(+ Qais)

Hello Chuyi,

On 7/20/2024 10:42 AM, Chuyi Zhou wrote:
In reweight_task(), there are two situations:

1. The task was on_rq, then the task's load_avg is accurate because we
synchronized it with cfs_rq through update_load_avg() in dequeue_task().

2. The task is sleeping, its load_avg might not have been updated for some
time, which can result in inaccurate dequeue_load_avg() in
reweight_entity().

This patch solves this by using update_load_avg() to synchronize the
load_avg of se with cfs_rq. For tasks were on_rq, since we already update
load_avg to accurate values in dequeue_task(), this change will not have
other effects due to the short time interval between the two updates.

Signed-off-by: Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx>
---
Changes in v2:
- change the description in commit log.
- use update_load_avg() in reweight_task() rather than in reweight_entity
suggested by chengming.
- Link to v1: https://lore.kernel.org/lkml/20240716150840.23061-1-zhouchuyi@xxxxxxxxxxxxx/
---
  kernel/sched/fair.c | 3 +++
  1 file changed, 3 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9057584ec06d..b1e07ce90284 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3835,12 +3835,15 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
      }
  }
+static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);
+
  void reweight_task(struct task_struct *p, const struct load_weight *lw)
  {
      struct sched_entity *se = &p->se;
      struct cfs_rq *cfs_rq = cfs_rq_of(se);
      struct load_weight *load = &se->load;
+    update_load_avg(cfs_rq, se, 0);

Seems to be necessary when we reach here from __setscheduler_params() or
set_user_nice() for a sleeping task. Please feel free to add:

Reviewed-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>

But since we are on the subject of accurate PELT accounting, one question
I have here is whether a reweight_task() for a sleeping task race with
its wakeup? Something like the following scenario:

These two paths are impossible to race, since we have the task->pi_lock.

Thanks.


CPU0                                        CPU1
====                                        ====
/* No rq locks held until ttwu_queue() */
try_to_wake_up(p) {
    ...
    /* Migrating task */
    set_task_cpu(p, cpu) {
        /* p->sched_class->migrate_task_rq(p, new_cpu); */        /* Called with task_cpu(p)'s rq lock held */
        migrate_task_rq_fair() {                    reweight_task(p) {
            /* p is still sleeping */                    ...
            if (!task_on_rq_migrating(p)) { dequeue_load_avg(cfs_rq, se);
                        remove_entity_load_avg(se); update_load_set(&se->load, weight);
                ...                            enqueue_load_avg(cfs_rq, se);
            }                                ...
        }                                }
        /* task_cpu() is updated here */
        __set_task_cpu(p, new_cpu);
    }
    ttwu_queue();
}

In theory, the remove_entity_load_avg() could record stale value of
"load_avg" that gets removed at the next dequeue if I'm not mistaken?
But I believe these small inaccuracies are tolerable since they'll decay
in a while anyways?

      reweight_entity(cfs_rq, se, lw->weight);
      load->inv_weight = lw->inv_weight;
  }