Hi Peter,

On 10/23/2013 03:53 AM, Peter Zijlstra wrote:

On Mon, Oct 21, 2013 at 05:15:02PM +0530, Vaidyanathan Srinivasan wrote:

quoted

 kernel/sched/fair.c |   18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 828ed97..bbcd96b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -5165,6 +5165,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
 	struct sched_group *group;
+	struct sched_domain *child;
+	int share_pkg_res = 0;
 	struct rq *busiest;
 	unsigned long flags;
 	struct cpumask *cpus = __get_cpu_var(load_balance_mask);

@@ -5190,6 +5192,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 
 	schedstat_inc(sd, lb_count[idle]);
 
+	child = sd->child;
+	if (child && child->flags & SD_SHARE_PKG_RESOURCES)
+		share_pkg_res = 1;
+
 redo:
 	if (!should_we_balance(&env)) {
 		*continue_balancing = 0;

@@ -5202,6 +5208,7 @@ redo:
 		goto out_balanced;
 	}
 
+redo_grp:
 	busiest = find_busiest_queue(&env, group);
 	if (!busiest) {
 		schedstat_inc(sd, lb_nobusyq[idle]);

@@ -5292,6 +5299,11 @@ more_balance:
 			if (!cpumask_empty(cpus)) {
 				env.loop = 0;
 				env.loop_break = sched_nr_migrate_break;
+				if (share_pkg_res &&
+					cpumask_intersects(cpus,
+						to_cpumask(group->cpumask)))

sched_group_cpus()

quoted

+					goto redo_grp;
+
 				goto redo;
 			}
 			goto out_balanced;

@@ -5318,9 +5330,15 @@ more_balance:
 			 */
 			if (!cpumask_test_cpu(this_cpu,
 					tsk_cpus_allowed(busiest->curr))) {
+				cpumask_clear_cpu(cpu_of(busiest), cpus);
 				raw_spin_unlock_irqrestore(&busiest->lock,
 							    flags);
 				env.flags |= LBF_ALL_PINNED;
+				if (share_pkg_res &&
+					cpumask_intersects(cpus,
+						to_cpumask(group->cpumask)))
+					goto redo_grp;
+
 				goto out_one_pinned;
 			}

Man this retry logic is getting annoying.. isn't there anything saner we
can do?

Let me give this a thought and get back.

Regards
Preeti U Murthy