Re: [patch] smpnice: don't consider sched groups which are lightly loaded for balancing

["Siddha, Suresh B" <suresh.b.siddha@intel.com>]

updated patch appended. thanks.

--
with smpnice, sched groups with highest priority tasks can mask the
imbalance between the other sched groups with in the same domain.
This patch fixes some of the listed down scenarios by not considering
the sched groups which are lightly loaded.

a) on a simple 4-way MP system, if we have one high priority and 4 normal
priority tasks, with smpnice we would like to see the high priority task
scheduled on one cpu, two other cpus getting one normal task each and the
fourth cpu getting the remaining two normal tasks. but with current smpnice
extra normal priority task keeps jumping from one cpu to another cpu having
the normal priority task.  This is because of the busiest_has_loaded_cpus,
nr_loaded_cpus logic.. We are not including the cpu with high priority
task in max_load calculations but including that in total and avg_load
calcuations.. leading to max_load < avg_load and load balance between
cpus running normal priority tasks(2 Vs 1) will always show imbalanace
as one normal priority and the extra normal priority task will keep moving
from one cpu to another cpu having normal priority task..

b) 4-way system with HT (8 logical processors). Package-P0 T0 has a highest
priority task, T1 is idle. Package-P1 Both T0 and T1 have 1 normal priority
task each..  P2 and P3 are idle.  With this patch, one of the normal priority
tasks on P1 will be moved to P2 or P3..

c) With the current weighted smp nice calculations, it doesn't always make
sense to look at the highest weighted runqueue in the busy group..
Consider a load balance scenario on a DP with HT system, with Package-0
containing one high priority and one low priority, Package-1 containing
one low priority(with other thread being idle)..  Package-1 thinks that it
need to take the low priority thread from Package-0. And find_busiest_queue()
returns the cpu thread with highest priority task.. And ultimately(with help
of active load balance) we move high priority task to Package-1. And same
continues with Package-0 now, moving high priority task from package-1 to
package-0..  Even without the presence of active load balance, load balance
will fail to balance the above scenario..  Fix find_busiest_queue to use
"imbalance" when it is lightly loaded.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>

--- linux-2.6.17-rc1/kernel/sched.c	2006-04-13 11:38:16.897333112 -0700
+++ linux~/kernel/sched.c	2006-04-20 07:52:31.974898888 -0700
@@ -2145,7 +2145,6 @@ find_busiest_group(struct sched_domain *
 	unsigned long max_pull;
 	unsigned long busiest_load_per_task, busiest_nr_running;
 	unsigned long this_load_per_task, this_nr_running;
-	unsigned int busiest_has_loaded_cpus = idle == NEWLY_IDLE;
 	int load_idx;
 
 	max_load = this_load = total_load = total_pwr = 0;
@@ -2200,15 +2199,8 @@ find_busiest_group(struct sched_domain *
 			this = group;
 			this_nr_running = sum_nr_running;
 			this_load_per_task = sum_weighted_load;
-		} else if (nr_loaded_cpus) {
-			if (avg_load > max_load || !busiest_has_loaded_cpus) {
-				max_load = avg_load;
-				busiest = group;
-				busiest_nr_running = sum_nr_running;
-				busiest_load_per_task = sum_weighted_load;
-				busiest_has_loaded_cpus = 1;
-			}
-		} else if (!busiest_has_loaded_cpus && avg_load > max_load) {
+		} else if (avg_load > max_load &&
+			   sum_nr_running > group->cpu_power / SCHED_LOAD_SCALE) {
 			max_load = avg_load;
 			busiest = group;
 			busiest_nr_running = sum_nr_running;
@@ -2241,6 +2233,16 @@ find_busiest_group(struct sched_domain *
 	if (max_load <= busiest_load_per_task)
 		goto out_balanced;
 
+	/*
+	 * In the presence of smp nice balancing, certain scenarios can have
+	 * max load less than avg load(as we skip the groups at or below
+	 * its cpu_power, while calculating max_load..)
+	 */
+	if (max_load < avg_load) {
+		*imbalance = 0;
+		goto small_imbalance;
+	}
+
 	/* Don't want to pull so many tasks that a group would go idle */
 	max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
 
@@ -2256,6 +2258,7 @@ find_busiest_group(struct sched_domain *
 	 * moved
 	 */
 	if (*imbalance < busiest_load_per_task) {
+small_imbalance:
 		unsigned long pwr_now = 0, pwr_move = 0;
 		unsigned long tmp;
 		unsigned int imbn = 2;
@@ -2318,23 +2321,19 @@ out_balanced:
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
 static runqueue_t *find_busiest_queue(struct sched_group *group,
-	enum idle_type idle)
+	enum idle_type idle, unsigned long imbalance)
 {
 	unsigned long max_load = 0;
 	runqueue_t *busiest = NULL, *rqi;
-	unsigned int busiest_is_loaded = idle == NEWLY_IDLE;
 	int i;
 
 	for_each_cpu_mask(i, group->cpumask) {
 		rqi = cpu_rq(i);
 
-		if (rqi->nr_running > 1) {
-			if (rqi->raw_weighted_load > max_load || !busiest_is_loaded) {
-				max_load = rqi->raw_weighted_load;
-				busiest = rqi;
-				busiest_is_loaded = 1;
-			}
-		} else if (!busiest_is_loaded && rqi->raw_weighted_load > max_load) {
+		if (rqi->nr_running == 1 && rqi->raw_weighted_load > imbalance)
+			continue;
+
+		if (rqi->raw_weighted_load > max_load) {
 			max_load = rqi->raw_weighted_load;
 			busiest = rqi;
 		}
@@ -2377,7 +2376,7 @@ static int load_balance(int this_cpu, ru
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(group, idle);
+	busiest = find_busiest_queue(group, idle, imbalance);
 	if (!busiest) {
 		schedstat_inc(sd, lb_nobusyq[idle]);
 		goto out_balanced;
@@ -2501,7 +2500,7 @@ static int load_balance_newidle(int this
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(group, NEWLY_IDLE);
+	busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance);
 	if (!busiest) {
 		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
 		goto out_balanced;