sched/fair: Remove meaningless imbalance calculation

Clean up load_balance() and remove meaningless calculation and fields before
adding a new algorithm.

Signed-off-by: Vincent Guittot <[email protected]>
Acked-by: Rik van Riel <[email protected]>
Cc: Ben Segall <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: [email protected]
Cc: Peter Zijlstra <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: vingu-linaro

kernel/sched/fair.c

@@ -5380,18 +5380,6 @@ static unsigned long capacity_of(int cpu)
 	return cpu_rq(cpu)->cpu_capacity;
 }
 
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
-	unsigned long load_avg = cpu_runnable_load(rq);
-
-	if (nr_running)
-		return load_avg / nr_running;
-
-	return 0;
-}
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
@@ -7657,7 +7645,6 @@ static unsigned long task_h_load(struct task_struct *p)
 struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
-	unsigned long load_per_task;
 	unsigned long group_capacity;
 	unsigned long group_util; /* Total utilization of the group */
 	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
@@ -8039,9 +8026,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_capacity = group->sgc->capacity;
 	sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
 
-	if (sgs->sum_h_nr_running)
-		sgs->load_per_task = sgs->group_load / sgs->sum_h_nr_running;
-
 	sgs->group_weight = group->group_weight;
 
 	sgs->group_no_capacity = group_is_overloaded(env, sgs);
@@ -8271,76 +8255,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	}
 }
 
-/**
- * fix_small_imbalance - Calculate the minor imbalance that exists
- *			amongst the groups of a sched_domain, during
- *			load balancing.
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- */
-static inline
-void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
-{
-	unsigned long tmp, capa_now = 0, capa_move = 0;
-	unsigned int imbn = 2;
-	unsigned long scaled_busy_load_per_task;
-	struct sg_lb_stats *local, *busiest;
-
-	local = &sds->local_stat;
-	busiest = &sds->busiest_stat;
-
-	if (!local->sum_h_nr_running)
-		local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
-	else if (busiest->load_per_task > local->load_per_task)
-		imbn = 1;
-
-	scaled_busy_load_per_task =
-		(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		busiest->group_capacity;
-
-	if (busiest->avg_load + scaled_busy_load_per_task >=
-	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
-		env->imbalance = busiest->load_per_task;
-		return;
-	}
-
-	/*
-	 * OK, we don't have enough imbalance to justify moving tasks,
-	 * however we may be able to increase total CPU capacity used by
-	 * moving them.
-	 */
-
-	capa_now += busiest->group_capacity *
-			min(busiest->load_per_task, busiest->avg_load);
-	capa_now += local->group_capacity *
-			min(local->load_per_task, local->avg_load);
-	capa_now /= SCHED_CAPACITY_SCALE;
-
-	/* Amount of load we'd subtract */
-	if (busiest->avg_load > scaled_busy_load_per_task) {
-		capa_move += busiest->group_capacity *
-			    min(busiest->load_per_task,
-				busiest->avg_load - scaled_busy_load_per_task);
-	}
-
-	/* Amount of load we'd add */
-	if (busiest->avg_load * busiest->group_capacity <
-	    busiest->load_per_task * SCHED_CAPACITY_SCALE) {
-		tmp = (busiest->avg_load * busiest->group_capacity) /
-		      local->group_capacity;
-	} else {
-		tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		      local->group_capacity;
-	}
-	capa_move += local->group_capacity *
-		    min(local->load_per_task, local->avg_load + tmp);
-	capa_move /= SCHED_CAPACITY_SCALE;
-
-	/* Move if we gain throughput */
-	if (capa_move > capa_now)
-		env->imbalance = busiest->load_per_task;
-}
-
 /**
  * calculate_imbalance - Calculate the amount of imbalance present within the
  *			 groups of a given sched_domain during load balance.
@@ -8360,15 +8274,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		return;
 	}
 
-	if (busiest->group_type == group_imbalanced) {
-		/*
-		 * In the group_imb case we cannot rely on group-wide averages
-		 * to ensure CPU-load equilibrium, look at wider averages. XXX
-		 */
-		busiest->load_per_task =
-			min(busiest->load_per_task, sds->avg_load);
-	}
-
 	/*
 	 * Avg load of busiest sg can be less and avg load of local sg can
 	 * be greater than avg load across all sgs of sd because avg load
@@ -8379,7 +8284,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	    (busiest->avg_load <= sds->avg_load ||
 	     local->avg_load >= sds->avg_load)) {
 		env->imbalance = 0;
-		return fix_small_imbalance(env, sds);
+		return;
 	}
 
 	/*
@@ -8417,14 +8322,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 				       busiest->group_misfit_task_load);
 	}
 
-	/*
-	 * if *imbalance is less than the average load per runnable task
-	 * there is no guarantee that any tasks will be moved so we'll have
-	 * a think about bumping its value to force at least one task to be
-	 * moved
-	 */
-	if (env->imbalance < busiest->load_per_task)
-		return fix_small_imbalance(env, sds);
 }
 
 /******* find_busiest_group() helpers end here *********************/