[RFC PATCH v2 2/2] sched: loadbalancer hacks for forced packing of tasks

[Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>]

Pack more tasks in a group so as to reduce number of CPUs
used to run the work in the system.

Just for load balancing purpose, assume the group capacity
has been increased by group_capacity_bump()

Hacks:

o Make non-idle cpus also perform powersave balance so
  that we can pull more tasks into the group
o Increase group capacity for calculation
o Increase load-balancing threshold so that even if a
  group is overloaded by group_capacity_bump(), consider
  it balanced

Basically if we want to evacuate 2 cores, the group capacity
is increased by 2 (*SCHED_LOAD_SCALE) and the power save
balancer will accommodate the tasks after selecting the group
leader.

This will not work if the system is overloaded. Even
after pulling 2 extra tasks, there could be tasks to fill the
other package.  At this point we are not yet reducing the
group capacity of the other group.

*** RFC patch for discussion ***

Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
---

 kernel/sched.c |   28 +++++++++++++++++++++++++++-
 1 files changed, 27 insertions(+), 1 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index f22b9f6..186b0ec 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3234,6 +3234,7 @@ struct sd_lb_stats {
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
 	int power_savings_balance; /* Is powersave balance needed for this sd */
+	unsigned int group_capacity_bump; /* % increase in group capacity */
 	struct sched_group *group_min; /* Least loaded group in sd */
 	struct sched_group *group_leader; /* Group which relieves group_min */
 	unsigned long min_load_per_task; /* load_per_task in group_min */
@@ -3294,6 +3295,15 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 
 int sched_evacuate_cores; /* No of forced-idle cores */
 
+static inline unsigned int group_capacity_bump(struct sched_domain *sd)
+{
+
+	if (sd->flags & SD_POWERSAVINGS_BALANCE)
+		return sched_evacuate_cores;
+
+	return 0;
+}
+
 /**
  * init_sd_power_savings_stats - Initialize power savings statistics for
  * the given sched_domain, during load balancing.
@@ -3309,12 +3319,14 @@ static inline void init_sd_power_savings_stats(struct sched_domain *sd,
 	 * Busy processors will not participate in power savings
 	 * balance.
 	 */
-	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+	if ((idle == CPU_NOT_IDLE && !sched_evacuate_cores) ||
+		!(sd->flags & SD_POWERSAVINGS_BALANCE))
 		sds->power_savings_balance = 0;
 	else {
 		sds->power_savings_balance = 1;
 		sds->min_nr_running = ULONG_MAX;
 		sds->leader_nr_running = 0;
+		sds->group_capacity_bump = group_capacity_bump(sd);
 	}
 }
 
@@ -3436,6 +3448,12 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 {
 	return 0;
 }
+
+static inline unsigned int group_capacity_bump(struct sched_domain *sd)
+{
+	return 0;
+}
+
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
 
@@ -3568,6 +3586,8 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 
 		if (local_group && balance && !(*balance))
 			return;
+		/* Bump up group capacity for forced packing of tasks */
+		sgs.group_capacity += sds->group_capacity_bump;
 
 		sds->total_load += sgs.group_load;
 		sds->total_pwr += group->__cpu_power;
@@ -3768,6 +3788,12 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
 		goto out_balanced;
 
+	/* Push the upper limits for overload */
+	if (sds.max_load <= (sds.busiest->__cpu_power +
+				sds.group_capacity_bump * SCHED_LOAD_SCALE) /
+				sds.busiest->__cpu_power * SCHED_LOAD_SCALE)
+		goto out_balanced;
+
 	sds.busiest_load_per_task /= sds.busiest_nr_running;
 	if (sds.group_imb)
 		sds.busiest_load_per_task =