sched/core: Address more wake_affine() regressions

The trivial wake_affine_idle() implementation is very good for a
number of workloads, but it comes apart at the moment there are no
idle CPUs left, IOW. the overloaded case.

hackbench:

		NO_WA_WEIGHT		WA_WEIGHT

hackbench-20  : 7.362717561 seconds	6.450509391 seconds

(win)

netperf:

		  NO_WA_WEIGHT		WA_WEIGHT

TCP_SENDFILE-1	: Avg: 54524.6		Avg: 52224.3
TCP_SENDFILE-10	: Avg: 48185.2          Avg: 46504.3
TCP_SENDFILE-20	: Avg: 29031.2          Avg: 28610.3
TCP_SENDFILE-40	: Avg: 9819.72          Avg: 9253.12
TCP_SENDFILE-80	: Avg: 5355.3           Avg: 4687.4

TCP_STREAM-1	: Avg: 41448.3          Avg: 42254
TCP_STREAM-10	: Avg: 24123.2          Avg: 25847.9
TCP_STREAM-20	: Avg: 15834.5          Avg: 18374.4
TCP_STREAM-40	: Avg: 5583.91          Avg: 5599.57
TCP_STREAM-80	: Avg: 2329.66          Avg: 2726.41

TCP_RR-1	: Avg: 80473.5          Avg: 82638.8
TCP_RR-10	: Avg: 72660.5          Avg: 73265.1
TCP_RR-20	: Avg: 52607.1          Avg: 52634.5
TCP_RR-40	: Avg: 57199.2          Avg: 56302.3
TCP_RR-80	: Avg: 25330.3          Avg: 26867.9

UDP_RR-1	: Avg: 108266           Avg: 107844
UDP_RR-10	: Avg: 95480            Avg: 95245.2
UDP_RR-20	: Avg: 68770.8          Avg: 68673.7
UDP_RR-40	: Avg: 76231            Avg: 75419.1
UDP_RR-80	: Avg: 34578.3          Avg: 35639.1

UDP_STREAM-1	: Avg: 64684.3          Avg: 66606
UDP_STREAM-10	: Avg: 52701.2          Avg: 52959.5
UDP_STREAM-20	: Avg: 30376.4          Avg: 29704
UDP_STREAM-40	: Avg: 15685.8          Avg: 15266.5
UDP_STREAM-80	: Avg: 8415.13          Avg: 7388.97

(wins and losses)

sysbench:

		    NO_WA_WEIGHT		WA_WEIGHT

sysbench-mysql-2  :  2135.17 per sec.		 2142.51 per sec.
sysbench-mysql-5  :  4809.68 per sec.            4800.19 per sec.
sysbench-mysql-10 :  9158.59 per sec.            9157.05 per sec.
sysbench-mysql-20 : 14570.70 per sec.           14543.55 per sec.
sysbench-mysql-40 : 22130.56 per sec.           22184.82 per sec.
sysbench-mysql-80 : 20995.56 per sec.           21904.18 per sec.

sysbench-psql-2   :  1679.58 per sec.            1705.06 per sec.
sysbench-psql-5   :  3797.69 per sec.            3879.93 per sec.
sysbench-psql-10  :  7253.22 per sec.            7258.06 per sec.
sysbench-psql-20  : 11166.75 per sec.           11220.00 per sec.
sysbench-psql-40  : 17277.28 per sec.           17359.78 per sec.
sysbench-psql-80  : 17112.44 per sec.           17221.16 per sec.

(increase on the top end)

tbench:

NO_WA_WEIGHT

Throughput 685.211 MB/sec   2 clients   2 procs  max_latency=0.123 ms
Throughput 1596.64 MB/sec   5 clients   5 procs  max_latency=0.119 ms
Throughput 2985.47 MB/sec  10 clients  10 procs  max_latency=0.262 ms
Throughput 4521.15 MB/sec  20 clients  20 procs  max_latency=0.506 ms
Throughput 9438.1  MB/sec  40 clients  40 procs  max_latency=2.052 ms
Throughput 8210.5  MB/sec  80 clients  80 procs  max_latency=8.310 ms

WA_WEIGHT

Throughput 697.292 MB/sec   2 clients   2 procs  max_latency=0.127 ms
Throughput 1596.48 MB/sec   5 clients   5 procs  max_latency=0.080 ms
Throughput 2975.22 MB/sec  10 clients  10 procs  max_latency=0.254 ms
Throughput 4575.14 MB/sec  20 clients  20 procs  max_latency=0.502 ms
Throughput 9468.65 MB/sec  40 clients  40 procs  max_latency=2.069 ms
Throughput 8631.73 MB/sec  80 clients  80 procs  max_latency=8.605 ms

(increase on the top end)
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -5363,6 +5363,10 @@ static int wake_wide(struct task_struct *p)
  *
  * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or
  *			will be) idle.
+ *
+ * wake_affine_weight() - considers the weight to reflect the average
+ *			  scheduling latency of the CPUs. This seems to work
+ *			  for the overloaded case.
  */
 
 static bool
@@ -5378,6 +5382,40 @@ wake_affine_idle(struct sched_domain *sd, struct task_struct *p,
 	return false;
 }
 
+static bool
+wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
+		   int this_cpu, int prev_cpu, int sync)
+{
+	s64 this_eff_load, prev_eff_load;
+	unsigned long task_load;
+
+	this_eff_load = target_load(this_cpu, sd->wake_idx);
+	prev_eff_load = source_load(prev_cpu, sd->wake_idx);
+
+	if (sync) {
+		unsigned long current_load = task_h_load(current);
+
+		if (current_load > this_eff_load)
+			return true;
+
+		this_eff_load -= current_load;
+	}
+
+	task_load = task_h_load(p);
+
+	this_eff_load += task_load;
+	if (sched_feat(WA_BIAS))
+		this_eff_load *= 100;
+	this_eff_load *= capacity_of(prev_cpu);
+
+	prev_eff_load -= task_load;
+	if (sched_feat(WA_BIAS))
+		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
+	prev_eff_load *= capacity_of(this_cpu);
+
+	return this_eff_load <= prev_eff_load;
+}
+
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
@@ -5387,6 +5425,9 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	if (sched_feat(WA_IDLE) && !affine)
 		affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync);
 
+	if (sched_feat(WA_WEIGHT) && !affine)
+		affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
+
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
 	if (affine) {
 		schedstat_inc(sd->ttwu_move_affine);

kernel/sched/features.h

@@ -82,3 +82,5 @@ SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
 SCHED_FEAT(WA_IDLE, true)
+SCHED_FEAT(WA_WEIGHT, true)
+SCHED_FEAT(WA_BIAS, true)