[PATCH v2] sched: reduce contention on tg's load_avg & runnable_avg

[Waiman Long <Waiman.Long@hp.com>]

It was found that with a perf profile of a compute workload (at 1500
users) of the AIM7 benchmark running on a glueless 4-socket 40-core
Westmere-EX system (HT on) on a 3.13-rc8 kernel that the scheduling
tick related functions account for quite a significant portion of
the total kernel cpu cycles.

  0.62%  reaim  [kernel.kallsyms]  [k] update_cfs_rq_blocked_load
  0.47%  reaim  [kernel.kallsyms]  [k] entity_tick
  0.10%  reaim  [kernel.kallsyms]  [k] update_cfs_shares
  0.03%  reaim  [kernel.kallsyms]  [k] update_curr

The scheduling tick functions account for about 1.22% of the total
CPU cycles. Of the top 2 function in the above list, the reading
and writing of the tg->load_avg variable account for over 90% of the
CPU cycles:

  atomic_long_add(tg_contrib, &tg->load_avg);
  atomic_long_read(&tg->load_avg) + 1);

This patch reduces the contention on the load_avg variable (and
secondarily on the runnable_avg variable) by the following 2 measures:

1. Make the load_avg and runnable_avg fields of the task_group
   structure sit in their own cacheline without sharing it with others.
   This only applies if the kernel is built for NUMA systems with
   multiple sockets.

2. Use atomic_long_add_return() to update the fields and save the
   returned value in a temporary location in the cfs structure to
   be used later instead of reading the fields directly.

The second change does require some changes in the ordering of how
some of the average counts are being computed and hence may have a
slight effect on their behavior.

With these 2 changes, the perf profile becomes:

  0.42%   reaim  [kernel.kallsyms]  [k] update_cfs_rq_blocked_load
  0.05%   reaim  [kernel.kallsyms]  [k] update_cfs_shares
  0.04%   reaim  [kernel.kallsyms]  [k] update_curr
  0.04%   reaim  [kernel.kallsyms]  [k] entity_tick

The %CPU cycle is reduced to about 0.55%. It is not a big change,
but it did improve the compute benchmark slightly from 398509 JPM
(Jobs/Minute) to 405803 JPM which is about 2% improvement and reduced
the reported systime from 50.03s to 48.37s.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
 kernel/sched/fair.c  |   29 ++++++++++++++++++++++-------
 kernel/sched/sched.h |   14 ++++++++++++--
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c7395d9..c4aa86d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1868,7 +1868,10 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	 * to gain a more accurate current total weight. See
 	 * update_cfs_rq_load_contribution().
 	 */
-	tg_weight = atomic_long_read(&tg->load_avg);
+	/* Use the saved version of tg's load_avg, if available */
+	tg_weight = cfs_rq->tg_load_save;
+	if (!tg_weight)
+		tg_weight = atomic_long_read(&tg->load_avg);
 	tg_weight -= cfs_rq->tg_load_contrib;
 	tg_weight += cfs_rq->load.weight;
 
@@ -2155,7 +2158,8 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 	tg_contrib -= cfs_rq->tg_load_contrib;
 
 	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
-		atomic_long_add(tg_contrib, &tg->load_avg);
+		cfs_rq->tg_load_save =
+			atomic_long_add_return(tg_contrib, &tg->load_avg);
 		cfs_rq->tg_load_contrib += tg_contrib;
 	}
 }
@@ -2176,7 +2180,8 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 	contrib -= cfs_rq->tg_runnable_contrib;
 
 	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
-		atomic_add(contrib, &tg->runnable_avg);
+		cfs_rq->tg_runnable_save =
+			atomic_add_return(contrib, &tg->runnable_avg);
 		cfs_rq->tg_runnable_contrib += contrib;
 	}
 }
@@ -2186,12 +2191,19 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 	struct cfs_rq *cfs_rq = group_cfs_rq(se);
 	struct task_group *tg = cfs_rq->tg;
 	int runnable_avg;
+	long load_avg;
 
 	u64 contrib;
 
 	contrib = cfs_rq->tg_load_contrib * tg->shares;
-	se->avg.load_avg_contrib = div_u64(contrib,
-				     atomic_long_read(&tg->load_avg) + 1);
+	/*
+	 * Retrieve & clear the saved tg's load_avg and use it if not 0
+	 */
+	load_avg = cfs_rq->tg_load_save;
+	cfs_rq->tg_load_save = 0;
+	if (unlikely(!load_avg))
+		load_avg = atomic_long_read(&tg->load_avg);
+	se->avg.load_avg_contrib = div_u64(contrib, load_avg + 1);
 
 	/*
 	 * For group entities we need to compute a correction term in the case
@@ -2216,7 +2228,10 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 	 * of consequential size guaranteed to see n_i*w_i quickly converge to
 	 * our upper bound of 1-cpu.
 	 */
-	runnable_avg = atomic_read(&tg->runnable_avg);
+	runnable_avg = cfs_rq->tg_runnable_save;
+	cfs_rq->tg_runnable_save = 0;
+	if (unlikely(!runnable_avg))
+		runnable_avg = atomic_read(&tg->runnable_avg);
 	if (runnable_avg < NICE_0_LOAD) {
 		se->avg.load_avg_contrib *= runnable_avg;
 		se->avg.load_avg_contrib >>= NICE_0_SHIFT;
@@ -2823,9 +2838,9 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	/*
 	 * Ensure that runnable average is periodically updated.
 	 */
-	update_entity_load_avg(curr, 1);
 	update_cfs_rq_blocked_load(cfs_rq, 1);
 	update_cfs_shares(cfs_rq);
+	update_entity_load_avg(curr, 1);
 
 #ifdef CONFIG_SCHED_HRTICK
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b2..f425630 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -11,6 +11,14 @@
 #include "cpupri.h"
 #include "cpuacct.h"
 
+#ifndef ____cacheline_aligned_in_numa
+#ifdef CONFIG_NUMA
+#define ____cacheline_aligned_in_numa	____cacheline_aligned
+#else
+#define ____cacheline_aligned_in_numa
+#endif
+#endif
+
 struct rq;
 
 extern __read_mostly int scheduler_running;
@@ -150,8 +158,8 @@ struct task_group {
 	unsigned long shares;
 
 #ifdef	CONFIG_SMP
-	atomic_long_t load_avg;
-	atomic_t runnable_avg;
+	atomic_long_t load_avg ____cacheline_aligned_in_numa;
+	atomic_t runnable_avg ____cacheline_aligned_in_numa;
 #endif
 #endif
 
@@ -285,7 +293,9 @@ struct cfs_rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* Required to track per-cpu representation of a task_group */
 	u32 tg_runnable_contrib;
+	int tg_runnable_save;
 	unsigned long tg_load_contrib;
+	long tg_load_save;
 
 	/*
 	 *   h_load = weight * f(tg)
-- 
1.7.1