sched: Rewrite tg_shares_up)

By tracking a per-cpu load-avg for each cfs_rq and folding it into a
global task_group load on each tick we can rework tg_shares_up to be
strictly per-cpu.

This should improve cpu-cgroup performance for smp systems
significantly.

[ Paul: changed to use queueing cfs_rq + bug fixes ]

Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20101115234937.580480400@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 2e1b0d1..e6590e7 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -202,15 +202,22 @@
 	spread0 = min_vruntime - rq0_min_vruntime;
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
 			SPLIT_NS(spread0));
-	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
-	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
-
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
+	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
+			SPLIT_NS(cfs_rq->load_avg));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
+			SPLIT_NS(cfs_rq->load_period));
+	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
+			cfs_rq->load_contribution);
+	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
+			atomic_read(&tg->load_weight));
 #endif
+
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif
 }