Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit f6ee05f9 authored by Thara Gopinath's avatar Thara Gopinath Committed by Lingutla Chandrasekhar
Browse files

ANDROID: sched: Per-Sched-domain over utilization 



The current implementation of overutilization, aborts energy aware
scheduling if any cpu in the system is over-utilized. This patch introduces
over utilization flag per sched domain level instead of a single flag
system wide. Load balancing is done at the sched domain where any
of the cpu is over utilized. If energy aware scheduling is
enabled and no cpu in a sched domain is overuttilized,
load balancing is skipped for that sched domain and energy aware
scheduling continues at that level.

The implementation takes advantage of the shared sched_domain structure
that is common across all the sched domains at a level. The new flag
introduced is placed in this structure so that all the sched domains the
same level share the flag. In case of an overutilized cpu, the flag gets
set at level1 sched_domain. The flag at the parent sched_domain level gets
set in either of the two following scenarios.
 1. There is a misfit task in one of the cpu's in this sched_domain.
 2. The total utilization of the domain is greater than the domain capacity

The flag is cleared if no cpu in a sched domain is overutilized.

This implementation still can have corner scenarios with respect to
misfit tasks. For example consider a sched group with n cpus and
n+1 70%utilized tasks. Ideally this is a case for load balance to happen
in a parent sched domain. But neither the total group utilization is
high enough for the load balance to be triggered in the parent domain nor
there is a cpu with a single overutilized task so that aload balance is
triggered in a parent domain. But again this could be a purely academic
sceanrio, as during task wake up these tasks will be placed
more appropriately.

Signed-off-by: default avatarThara Gopinath <thara.gopinath@linaro.org>
Change-Id: I3f327cff4080096a3e58208dd72c9b7f7913cdb2
Signed-off-by: default avatarChris Redpath <chris.redpath@arm.com>
Git-commit: addef378
Git-repo: https://android.googlesource.com/kernel/common/


[clingutla@codeaurora.org: Resolved trivial merge conflicts]
Signed-off-by: default avatarLingutla Chandrasekhar <clingutla@codeaurora.org>
parent 54f3590a

include/linux/sched/topology.h

+2 −0
Original line number Diff line number Diff line
@@ -74,6 +74,8 @@ struct sched_domain_shared { 
	atomic_t	ref;

	atomic_t	nr_busy_cpus;

	int		has_idle_cores;



	bool            overutilized;

};



struct sched_domain {

kernel/sched/fair.c

+75 −13
Original line number Diff line number Diff line
@@ -5278,12 +5278,31 @@ bool cpu_overutilized(int cpu) 
	return __cpu_overutilized(cpu, 0);

}



static inline void update_overutilized_status(struct rq *rq)

static bool sd_overutilized(struct sched_domain *sd)

{

	if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) {

		WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);

		trace_sched_overutilized(1);

	return sd->shared->overutilized;

}



static void set_sd_overutilized(struct sched_domain *sd)

{

	sd->shared->overutilized = true;

}



static void clear_sd_overutilized(struct sched_domain *sd)

{

	sd->shared->overutilized = false;

}



static inline void update_overutilized_status(struct rq *rq)

{

	struct sched_domain *sd;



	rcu_read_lock();

	sd = rcu_dereference(rq->sd);

	if (sd && !sd_overutilized(sd) &&

	    cpu_overutilized(rq->cpu))

		set_sd_overutilized(sd);

	rcu_read_unlock();

}

#else

static inline void update_overutilized_status(struct rq *rq) { }
@@ -8410,7 +8429,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) 
	if (static_branch_unlikely(&sched_energy_present)) {

		struct root_domain *rd = env->dst_rq->rd;



		if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized) &&

		if ((rcu_dereference(rd->pd) && !sd_overutilized(env->sd)) &&

					env->idle == CPU_NEWLY_IDLE &&

					!task_in_related_thread_group(p)) {

			long util_cum_dst, util_cum_src;
@@ -8879,6 +8898,7 @@ struct sd_lb_stats { 
	unsigned long total_running;

	unsigned long total_load;	/* Total load of all groups in sd */

	unsigned long total_capacity;	/* Total capacity of all groups in sd */

	unsigned long total_util;	/* Total util of all groups in sd */

	unsigned long avg_load;	/* Average load across all groups in sd */



	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
@@ -8899,6 +8919,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) 
		.total_running = 0UL,

		.total_load = 0UL,

		.total_capacity = 0UL,

		.total_util = 0UL,

		.busiest_stat = {

			.avg_load = 0UL,

			.sum_nr_running = 0,
@@ -9298,9 +9319,13 @@ static inline void update_sg_lb_stats(struct lb_env *env, 
		if (nr_running > 1)

			*sg_status |= SG_OVERLOAD;



		if (cpu_overutilized(i))

		if (cpu_overutilized(i)) {

			*sg_status |= SG_OVERUTILIZED;



			if (rq->misfit_task_load)

				*sg_status |= SG_HAS_MISFIT_TASK;

		}



#ifdef CONFIG_NUMA_BALANCING

		sgs->nr_numa_running += rq->nr_numa_running;

		sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -9534,6 +9559,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd 
		sds->total_running += sgs->sum_nr_running;

		sds->total_load += sgs->group_load;

		sds->total_capacity += sgs->group_capacity;

		sds->total_util += sgs->group_util;



		trace_sched_load_balance_sg_stats(sg->cpumask[0],

				sgs->group_type, sgs->idle_cpus,
@@ -9565,14 +9591,47 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd 


		/* update overload indicator if we are at root domain */

		WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);

	}



		/* Update over-utilization (tipping point, U >= 0) indicator */

		WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);

		trace_sched_overutilized(!!(sg_status & SG_OVERUTILIZED));

	} else if (sg_status & SG_OVERUTILIZED) {

		WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);

		trace_sched_overutilized(1);

	if (sg_status & SG_OVERUTILIZED)

		set_sd_overutilized(env->sd);

	else

		clear_sd_overutilized(env->sd);



	/*

	 * If there is a misfit task in one cpu in this sched_domain

	 * it is likely that the imbalance cannot be sorted out among

	 * the cpu's in this sched_domain. In this case set the

	 * overutilized flag at the parent sched_domain.

	 */

	if (sg_status & SG_HAS_MISFIT_TASK) {

		struct sched_domain *sd = env->sd->parent;



		/*

		 * In case of a misfit task, load balance at the parent

		 * sched domain level will make sense only if the the cpus

		 * have a different capacity. If cpus at a domain level have

		 * the same capacity, the misfit task cannot be well

		 * accomodated	in any of the cpus and there in no point in

		 * trying a load balance at this level

		 */

		while (sd) {

			if (sd->flags & SD_ASYM_CPUCAPACITY) {

				set_sd_overutilized(sd);

				break;

			}

			sd = sd->parent;

		}

	}



	/*

	 * If the domain util is greater that domain capacity, load balancing

	 * needs to be done at the next sched domain level as well.

	 */

	if (env->sd->parent &&

	    sds->total_capacity * 1024 < sds->total_util *

			 sched_capacity_margin_up[group_first_cpu(sds->local)])

		set_sd_overutilized(env->sd->parent);



}
@@ -9867,7 +9926,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) 
	if (static_branch_unlikely(&sched_energy_present)) {

		struct root_domain *rd = env->dst_rq->rd;



		if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) {

		if (rcu_dereference(rd->pd) && !sd_overutilized(env->sd)) {

			int cpu_local, cpu_busiest;

			unsigned long capacity_local, capacity_busiest;
@@ -10711,6 +10770,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) 
		}

		max_cost += sd->max_newidle_lb_cost;



		if (!sd_overutilized(sd))

			continue;



		if (!(sd->flags & SD_LOAD_BALANCE))

			continue;

kernel/sched/sched.h

+1 −3
Original line number Diff line number Diff line
@@ -790,6 +790,7 @@ struct max_cpu_capacity { 
/* Scheduling group status flags */

#define SG_OVERLOAD		0x1 /* More than one runnable task on a CPU. */

#define SG_OVERUTILIZED		0x2 /* One or more CPUs are over-utilized. */

#define SG_HAS_MISFIT_TASK	0x4 /* Group has misfit task. */



/*

 * We add the notion of a root-domain which will be used to define per-domain
@@ -813,9 +814,6 @@ struct root_domain { 
	 */

	int			overload;



	/* Indicate one or more cpus over-utilized (tipping point) */

	int			overutilized;



	/*

	 * The bit corresponding to a CPU gets set here if such CPU has more

	 * than one runnable -deadline task (as it is below for RT tasks).

kernel/sched/topology.c

+4 −8
Original line number Diff line number Diff line
@@ -1380,15 +1380,11 @@ sd_init(struct sched_domain_topology_level *tl, 
		sd->idle_idx = 1;

	}



	/*

	 * For all levels sharing cache; connect a sched_domain_shared

	 * instance.

	 */

	if (sd->flags & SD_SHARE_PKG_RESOURCES) {

	sd->shared = *per_cpu_ptr(sdd->sds, sd_id);

	atomic_inc(&sd->shared->ref);



	if (sd->flags & SD_SHARE_PKG_RESOURCES)

		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);

	}



	sd->private = sdd;