Re: [PATCH 06/18] sched: set initial load avg of new forked task as its load weight

[Namhyung Kim <namhyung@kernel.org>]

On Mon, 10 Dec 2012 16:22:22 +0800, Alex Shi wrote:
> New task has no runnable sum at its first runnable time, that make
> burst forking just select few idle cpus to put tasks.
> Set initial load avg of new forked task as its load weight to resolve
> this issue.
>
> Signed-off-by: Alex Shi <alex.shi@intel.com>
> ---
>  include/linux/sched.h |    1 +
>  kernel/sched/core.c   |    2 +-
>  kernel/sched/fair.c   |   13 +++++++++++--
>  3 files changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 5dafac3..093f9cd 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1058,6 +1058,7 @@ struct sched_domain;
>  #else
>  #define ENQUEUE_WAKING		0
>  #endif
> +#define ENQUEUE_NEWTASK		8
>  
>  #define DEQUEUE_SLEEP		1
>  
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index e6533e1..96fa5f1 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -1648,7 +1648,7 @@ void wake_up_new_task(struct task_struct *p)
>  #endif
>  
>  	rq = __task_rq_lock(p);
> -	activate_task(rq, p, 0);
> +	activate_task(rq, p, ENQUEUE_NEWTASK);
>  	p->on_rq = 1;
>  	trace_sched_wakeup_new(p, true);
>  	check_preempt_curr(rq, p, WF_FORK);
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 1faf89f..61c8d24 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1277,8 +1277,9 @@ static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
>  /* Add the load generated by se into cfs_rq's child load-average */
>  static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
>  						  struct sched_entity *se,
> -						  int wakeup)
> +						  int flags)
>  {
> +	int wakeup = flags & ENQUEUE_WAKEUP;
>  	/*
>  	 * We track migrations using entity decay_count <= 0, on a wake-up
>  	 * migration we use a negative decay count to track the remote decays
> @@ -1312,6 +1313,12 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
>  		update_entity_load_avg(se, 0);
>  	}
>  
> +	/*
> +	 * set the initial load avg of new task same as its load
> +	 * in order to avoid brust fork make few cpu too heavier
> +	 */
> +	if (flags & ENQUEUE_NEWTASK)
> +		se->avg.load_avg_contrib = se->load.weight;
>  	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
>  	/* we force update consideration on load-balancer moves */
>  	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
> @@ -1476,7 +1483,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>  	 */
>  	update_curr(cfs_rq);
>  	account_entity_enqueue(cfs_rq, se);
> -	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
> +	enqueue_entity_load_avg(cfs_rq, se, flags &
> +				(ENQUEUE_WAKEUP | ENQUEUE_NEWTASK));

It seems that just passing 'flags' is enough.

>  
>  	if (flags & ENQUEUE_WAKEUP) {
>  		place_entity(cfs_rq, se, 0);
> @@ -2586,6 +2594,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>  		cfs_rq->h_nr_running++;
>  
>  		flags = ENQUEUE_WAKEUP;
> +		flags &= ~ENQUEUE_NEWTASK;

Why is this needed?

Thanks,
Namhyung


>  	}
>  
>  	for_each_sched_entity(se) {