Re: [RFC PATCH] sched: START_NICE feature (temporarily niced forks) (v3)

[Peter Zijlstra <peterz@infradead.org>]

On Tue, 2010-09-14 at 16:25 -0400, Mathieu Desnoyers wrote:


> Index: linux-2.6-lttng.git/include/linux/sched.h
> ===================================================================
> --- linux-2.6-lttng.git.orig/include/linux/sched.h
> +++ linux-2.6-lttng.git/include/linux/sched.h
> @@ -1132,6 +1132,8 @@ struct sched_entity {
>  	u64			prev_sum_exec_runtime;
>  
>  	u64			nr_migrations;
> +	u64			fork_nice_timeout;
> +	unsigned int		fork_nice_penality;
>  
>  #ifdef CONFIG_SCHEDSTATS
>  	struct sched_statistics statistics;
> Index: linux-2.6-lttng.git/kernel/sched.c
> ===================================================================
> --- linux-2.6-lttng.git.orig/kernel/sched.c
> +++ linux-2.6-lttng.git/kernel/sched.c
> @@ -2421,6 +2421,8 @@ static void __sched_fork(struct task_str
>  	p->se.sum_exec_runtime		= 0;
>  	p->se.prev_sum_exec_runtime	= 0;
>  	p->se.nr_migrations		= 0;
> +	p->se.fork_nice_timeout		= 0;
> +	p->se.fork_nice_penality	= 0;
>  
>  #ifdef CONFIG_SCHEDSTATS
>  	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
> Index: linux-2.6-lttng.git/kernel/sched_fair.c
> ===================================================================
> --- linux-2.6-lttng.git.orig/kernel/sched_fair.c
> +++ linux-2.6-lttng.git/kernel/sched_fair.c
> @@ -433,6 +433,14 @@ calc_delta_fair(unsigned long delta, str
>  	if (unlikely(se->load.weight != NICE_0_LOAD))
>  		delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
>  
> +	if (se->fork_nice_penality) {
> +		delta <<= se->fork_nice_penality;
> +		if ((s64)(se->sum_exec_runtime - se->fork_nice_timeout) > 0) {
> +			se->fork_nice_penality = 0;
> +			se->fork_nice_timeout = 0;
> +		}
> +	}
> +
>  	return delta;
>  }

Something like this ought to live at every place where you use se->load,
including sched_slice(), possibly wakeup_gran(), although that's more
heuristic, so you could possibly leave it out there.

> @@ -832,6 +840,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, st
>  	 */
>  	if (!(flags & DEQUEUE_SLEEP))
>  		se->vruntime -= cfs_rq->min_vruntime;
> +
> +	if (se->fork_nice_penality) {
> +		se->fork_nice_penality = 0;
> +		se->fork_nice_timeout = 0;
> +	}
>  }
>  
>  /*

So you want to reset this penalty on each de-schedule, not only sleep
(but also preemptions)?

> @@ -3544,8 +3557,27 @@ static void task_fork_fair(struct task_s
>  
>  	update_curr(cfs_rq);
>  
> -	if (curr)
> +	if (curr) {
>  		se->vruntime = curr->vruntime;
> +		if (sched_feat(START_NICE)) {
> +			if (curr->fork_nice_penality &&
> +			    (s64)(curr->sum_exec_runtime
> +				  - curr->fork_nice_timeout) > 0) {
> +				curr->fork_nice_penality = 0;
> +				curr->fork_nice_timeout = 0;
> +			}
> +
> +			if (!curr->fork_nice_timeout)
> +				curr->fork_nice_timeout =
> +					curr->sum_exec_runtime;
> +			curr->fork_nice_timeout += sched_slice(cfs_rq, curr);
> +			curr->fork_nice_penality = min_t(unsigned int,
> +							 curr->fork_nice_penality + 1, 8);
> +			se->fork_nice_timeout = curr->fork_nice_timeout
> +						- curr->sum_exec_runtime;
> +			se->fork_nice_penality = curr->fork_nice_penality;
> +		}
> +	}
>  	place_entity(cfs_rq, se, 1);
>  
>  	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {

If you stick than in a separate function you can loose 2 indent levels,
which would help with readability.