Re: [PATCH 09/16] sched: normalize tg load contributions against runnable time

[Namhyung Kim <namhyung@kernel.org>]

On Wed, 27 Jun 2012 19:24:14 -0700, Paul Turner wrote:
> Entities of equal weight should receive equitable distribution of cpu time.
> This is challenging in the case of a task_group's shares as execution may be
> occurring on multiple cpus simultaneously.
>
> To handle this we divide up the shares into weights proportionate with the load
> on each cfs_rq.  This does not however, account for the fact that the sum of
> the parts may be less than one cpu and so we need to normalize:
>   load(tg) = min(runnable_avg(tg), 1) * tg->shares
> Where runnable_avg is the aggregate time in which the task_group had runnable
> children.
>
> Signed-off-by: Paul Turner <pjt@google.com>
> Signed-off-by: Ben Segall <bsegall@google.com>.
> ---
>  kernel/sched/debug.c |    4 ++++
>  kernel/sched/fair.c  |   39 +++++++++++++++++++++++++++++++++++++++
>  kernel/sched/sched.h |    2 ++
>  3 files changed, 45 insertions(+), 0 deletions(-)
>
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index 9268fb7..9334c68 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -237,6 +237,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
>  			atomic64_read(&cfs_rq->tg->load_avg));
>  	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
>  			cfs_rq->tg_load_contrib);
> +	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
> +			cfs_rq->tg_runnable_contrib);
> +	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
> +			atomic_read(&cfs_rq->tg->runnable_avg));
>  #endif
>  
>  	print_cfs_group_stats(m, cpu, cfs_rq->tg);
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index a416296..91d0b21 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1117,19 +1117,56 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
>  	}
>  }
>  
> +/*
> + * Aggregate cfs_rq runnable averages into an equivalent task_group
> + * representation for computing load contributions.
> + */
> +static inline void __update_tg_runnable_avg(struct sched_avg *sa,
> +						  struct cfs_rq *cfs_rq)
> +{
> +	struct task_group *tg = cfs_rq->tg;
> +	long contrib;
> +
> +	contrib = div_u64(sa->runnable_avg_sum << 12,
> +			  sa->runnable_avg_period + 1);
> +	contrib -= cfs_rq->tg_runnable_contrib;
> +
> +	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
> +		atomic_add(contrib, &tg->runnable_avg);
> +		cfs_rq->tg_runnable_contrib += contrib;
> +	}
> +}
> +
>  static inline void __update_group_entity_contrib(struct sched_entity *se)
>  {
>  	struct cfs_rq *cfs_rq = group_cfs_rq(se);
>  	struct task_group *tg = cfs_rq->tg;
> +	int runnable_avg;
> +
>  	u64 contrib;
>  
>  	contrib = cfs_rq->tg_load_contrib * tg->shares;
>  	se->avg.load_avg_contrib = div64_u64(contrib,
>  					     atomic64_read(&tg->load_avg) + 1);
> +
> +	/*
> +	 * Unlike a task-entity, a group entity may be using >=1 cpu globally.
> +	 * However, in the case that it's using <1 cpu we need to form a
> +	 * correction term so that we contribute the same load as a task of
> +	 * equal weight. (Global runnable time is taken as a fraction over
> +	 * 2^12.)

Wouldn't it be better using a symbolic name rather than the magic number?


> +	 */
> +	runnable_avg = atomic_read(&tg->runnable_avg);
> +	if (runnable_avg < (1<<12)) {
> +		se->avg.load_avg_contrib *= runnable_avg;
> +		se->avg.load_avg_contrib /= (1<<12);

Ditto.

Thanks,
Namhyung


> +	}
>  }
>  #else
>  static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
>  						 int force_update) {}
> +static inline void __update_tg_runnable_avg(struct sched_avg *sa,
> +						  struct cfs_rq *cfs_rq) {}
>  static inline void __update_group_entity_contrib(struct sched_entity *se) {}
>  #endif
>  
> @@ -1151,6 +1188,7 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
>  	if (entity_is_task(se)) {
>  		__update_task_entity_contrib(se);
>  	} else {
> +		__update_tg_runnable_avg(&se->avg, group_cfs_rq(se));
>  		__update_group_entity_contrib(se);
>  	}
>  
> @@ -1219,6 +1257,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
>  static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
>  {
>  	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
> +	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
>  }
>  
>  /* Add the load generated by se into cfs_rq's child load-average */
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 4d3b3ad..b48bbd7 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -113,6 +113,7 @@ struct task_group {
>  
>  	atomic_t load_weight;
>  	atomic64_t load_avg;
> +	atomic_t runnable_avg;
>  #endif
>  
>  #ifdef CONFIG_RT_GROUP_SCHED
> @@ -234,6 +235,7 @@ struct cfs_rq {
>  	atomic64_t decay_counter, removed_load;
>  	u64 last_decay;
>  #ifdef CONFIG_FAIR_GROUP_SCHED
> +	u32 tg_runnable_contrib;
>  	u64 tg_load_contrib;
>  #endif
>  #endif