[PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Mel Gorman]

Changelog since V2
o Print stats that are not related to schedstat
o Reintroduce a static inline for update_stats_dequeue

Changelog since V1
o Introduce schedstat_enabled and address Ingo's feedback
o More schedstat-only paths eliminated, particularly ttwu_stat

schedstats is very useful during debugging and performance tuning but it
incurs overhead. As such, even though it can be disabled at build time,
it is often enabled as the information is useful.  This patch adds a
kernel command-line and sysctl tunable to enable or disable schedstats on
demand. It is disabled by default as someone who knows they need it can
also learn to enable it when necessary.

The benefits are workload-dependent but when it gets down to it, the
difference will be whether cache misses are incurred updating the shared
stats or not. These measurements were taken from a 48-core 2-socket machine
with Xeon(R) E5-2670 v3 cpus although they were also tested on a single
socket machine 8-core machine with Intel i7-3770 processors.

netperf-tcp
                           4.5.0-rc1             4.5.0-rc1
                             vanilla          nostats-v3r1
Hmean    64         560.45 (  0.00%)      575.98 (  2.77%)
Hmean    128        766.66 (  0.00%)      795.79 (  3.80%)
Hmean    256        950.51 (  0.00%)      981.50 (  3.26%)
Hmean    1024      1433.25 (  0.00%)     1466.51 (  2.32%)
Hmean    2048      2810.54 (  0.00%)     2879.75 (  2.46%)
Hmean    3312      4618.18 (  0.00%)     4682.09 (  1.38%)
Hmean    4096      5306.42 (  0.00%)     5346.39 (  0.75%)
Hmean    8192     10581.44 (  0.00%)    10698.15 (  1.10%)
Hmean    16384    18857.70 (  0.00%)    18937.61 (  0.42%)

Small gains here, UDP_STREAM showed nothing intresting and neither did
the TCP_RR tests. The gains on the 8-core machine were very similar.

tbench4
                                 4.5.0-rc1             4.5.0-rc1
                                   vanilla          nostats-v3r1
Hmean    mb/sec-1         500.85 (  0.00%)      522.43 (  4.31%)
Hmean    mb/sec-2         984.66 (  0.00%)     1018.19 (  3.41%)
Hmean    mb/sec-4        1827.91 (  0.00%)     1847.78 (  1.09%)
Hmean    mb/sec-8        3561.36 (  0.00%)     3611.28 (  1.40%)
Hmean    mb/sec-16       5824.52 (  0.00%)     5929.03 (  1.79%)
Hmean    mb/sec-32      10943.10 (  0.00%)    10802.83 ( -1.28%)
Hmean    mb/sec-64      15950.81 (  0.00%)    16211.31 (  1.63%)
Hmean    mb/sec-128     15302.17 (  0.00%)    15445.11 (  0.93%)
Hmean    mb/sec-256     14866.18 (  0.00%)    15088.73 (  1.50%)
Hmean    mb/sec-512     15223.31 (  0.00%)    15373.69 (  0.99%)
Hmean    mb/sec-1024    14574.25 (  0.00%)    14598.02 (  0.16%)
Hmean    mb/sec-2048    13569.02 (  0.00%)    13733.86 (  1.21%)
Hmean    mb/sec-3072    12865.98 (  0.00%)    13209.23 (  2.67%)

Small gains of 2-4% at low thread counts and otherwise flat.  The
gains on the 8-core machine were slightly different

tbench4 on 8-core i7-3770 single socket machine
Hmean    mb/sec-1        442.59 (  0.00%)      448.73 (  1.39%)
Hmean    mb/sec-2        796.68 (  0.00%)      794.39 ( -0.29%)
Hmean    mb/sec-4       1322.52 (  0.00%)     1343.66 (  1.60%)
Hmean    mb/sec-8       2611.65 (  0.00%)     2694.86 (  3.19%)
Hmean    mb/sec-16      2537.07 (  0.00%)     2609.34 (  2.85%)
Hmean    mb/sec-32      2506.02 (  0.00%)     2578.18 (  2.88%)
Hmean    mb/sec-64      2511.06 (  0.00%)     2569.16 (  2.31%)
Hmean    mb/sec-128     2313.38 (  0.00%)     2395.50 (  3.55%)
Hmean    mb/sec-256     2110.04 (  0.00%)     2177.45 (  3.19%)
Hmean    mb/sec-512     2072.51 (  0.00%)     2053.97 ( -0.89%)

In constract, this shows a relatively steady 2-3% gain at higher thread
counts. Due to the nature of the patch and the type of workload, it's
not a surprise that the result will depend on the CPU used.

hackbench-pipes
                         4.5.0-rc1             4.5.0-rc1
                           vanilla          nostats-v3r1
Amean    1        0.0637 (  0.00%)      0.0660 ( -3.59%)
Amean    4        0.1229 (  0.00%)      0.1181 (  3.84%)
Amean    7        0.1921 (  0.00%)      0.1911 (  0.52%)
Amean    12       0.3117 (  0.00%)      0.2923 (  6.23%)
Amean    21       0.4050 (  0.00%)      0.3899 (  3.74%)
Amean    30       0.4586 (  0.00%)      0.4433 (  3.33%)
Amean    48       0.5910 (  0.00%)      0.5694 (  3.65%)
Amean    79       0.8663 (  0.00%)      0.8626 (  0.43%)
Amean    110      1.1543 (  0.00%)      1.1517 (  0.22%)
Amean    141      1.4457 (  0.00%)      1.4290 (  1.16%)
Amean    172      1.7090 (  0.00%)      1.6924 (  0.97%)
Amean    192      1.9126 (  0.00%)      1.9089 (  0.19%)

Some small gains and losses and while the variance data is not included,
it's close to the noise. The UMA machine did not show anything particularly
different

pipetest
                             4.5.0-rc1             4.5.0-rc1
                               vanilla          nostats-v2r2
Min         Time        4.13 (  0.00%)        3.99 (  3.39%)
1st-qrtle   Time        4.38 (  0.00%)        4.27 (  2.51%)
2nd-qrtle   Time        4.46 (  0.00%)        4.39 (  1.57%)
3rd-qrtle   Time        4.56 (  0.00%)        4.51 (  1.10%)
Max-90%     Time        4.67 (  0.00%)        4.60 (  1.50%)
Max-93%     Time        4.71 (  0.00%)        4.65 (  1.27%)
Max-95%     Time        4.74 (  0.00%)        4.71 (  0.63%)
Max-99%     Time        4.88 (  0.00%)        4.79 (  1.84%)
Max         Time        4.93 (  0.00%)        4.83 (  2.03%)
Mean        Time        4.48 (  0.00%)        4.39 (  1.91%)
Best99%Mean Time        4.47 (  0.00%)        4.39 (  1.91%)
Best95%Mean Time        4.46 (  0.00%)        4.38 (  1.93%)
Best90%Mean Time        4.45 (  0.00%)        4.36 (  1.98%)
Best50%Mean Time        4.36 (  0.00%)        4.25 (  2.49%)
Best10%Mean Time        4.23 (  0.00%)        4.10 (  3.13%)
Best5%Mean  Time        4.19 (  0.00%)        4.06 (  3.20%)
Best1%Mean  Time        4.13 (  0.00%)        4.00 (  3.39%)

Small improvement and similar gains were seen on the UMA machine.

The gain is small but it'll depend on the CPU and the workload whether
this patch makes a different.  However, it stands to reason that doing
less work in the scheduler is a good thing. The downside is that the
lack of schedstats and tracepoints will be surprising to experts doing
performance analysis until they find the existance of the schedstats=
parameter or schedstats sysctl.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 Documentation/kernel-parameters.txt |   5 ++
 Documentation/sysctl/kernel.txt     |   8 +++
 include/linux/sched/sysctl.h        |   4 ++
 kernel/sched/core.c                 |  62 +++++++++++++++++++++-
 kernel/sched/debug.c                | 102 +++++++++++++++++++-----------------
 kernel/sched/fair.c                 |  90 +++++++++++++++++++------------
 kernel/sched/sched.h                |   1 +
 kernel/sched/stats.h                |   8 +--
 kernel/sysctl.c                     |  11 ++++
 9 files changed, 204 insertions(+), 87 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 87d40a72f6a1..846956abfe85 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3523,6 +3523,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	sched_debug	[KNL] Enables verbose scheduler debug messages.
 
+	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
+			Allowed values are enable and disable. This feature
+			incurs a small amount of overhead in the scheduler
+			but is useful for debugging and performance tuning.
+
 	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index a93b414672a7..be7c3b720adf 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -760,6 +760,14 @@ rtsig-nr shows the number of RT signals currently queued.
 
 ==============================================================
 
+schedstats:
+
+Enables/disables scheduler statistics. Enabling this feature
+incurs a small amount of overhead in the scheduler but is
+useful for debugging and performance tuning.
+
+==============================================================
+
 sg-big-buff:
 
 This file shows the size of the generic SCSI (sg) buffer.
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c9e4731cf10b..4f080ab4f2cd 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -95,4 +95,8 @@ extern int sysctl_numa_balancing(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos);
 
+extern int sysctl_schedstats(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 63d3a24e081a..1a816ebaa7da 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2093,7 +2093,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	ttwu_queue(p, cpu);
 stat:
-	ttwu_stat(p, cpu, wake_flags);
+	if (schedstat_enabled())
+		ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -2141,7 +2142,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0);
-	ttwu_stat(p, smp_processor_id(), 0);
+	if (schedstat_enabled())
+		ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }
@@ -2210,6 +2212,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SCHEDSTATS
+	/* Even if schedstat is disabled, there should not be garbage */
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
@@ -2281,6 +2284,61 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+
+#ifdef CONFIG_SCHEDSTATS
+static void set_schedstats(bool enabled)
+{
+	if (enabled)
+		static_branch_enable(&sched_schedstats);
+	else
+		static_branch_disable(&sched_schedstats);
+}
+
+static int __init setup_schedstats(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+
+	if (!strcmp(str, "enable")) {
+		set_schedstats(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_schedstats(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		pr_warn("Unable to parse schedstats=\n");
+
+	return ret;
+}
+__setup("schedstats=", setup_schedstats);
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_schedstats(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = static_branch_likely(&sched_schedstats);
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_schedstats(state);
+	return err;
+}
+#endif
+#endif
+
 /*
  * fork()/clone()-time setup:
  */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 641511771ae6..7cfa87bd8b89 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -75,16 +75,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->statistics.wait_start);
-	PN(se->statistics.sleep_start);
-	PN(se->statistics.block_start);
-	PN(se->statistics.sleep_max);
-	PN(se->statistics.block_max);
-	PN(se->statistics.exec_max);
-	PN(se->statistics.slice_max);
-	PN(se->statistics.wait_max);
-	PN(se->statistics.wait_sum);
-	P(se->statistics.wait_count);
+	if (schedstat_enabled()) {
+		PN(se->statistics.wait_start);
+		PN(se->statistics.sleep_start);
+		PN(se->statistics.block_start);
+		PN(se->statistics.sleep_max);
+		PN(se->statistics.block_max);
+		PN(se->statistics.exec_max);
+		PN(se->statistics.slice_max);
+		PN(se->statistics.wait_max);
+		PN(se->statistics.wait_sum);
+		P(se->statistics.wait_count);
+	}
 #endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
@@ -122,10 +124,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 #ifdef CONFIG_SCHEDSTATS
-	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(p->se.statistics.wait_sum),
-		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	if (schedstat_enabled()) {
+		SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+			SPLIT_NS(p->se.statistics.wait_sum),
+			SPLIT_NS(p->se.sum_exec_runtime),
+			SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	}
 #else
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		0LL, 0L,
@@ -313,17 +317,18 @@ do {									\
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
 #define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
-	P(yld_count);
-
-	P(sched_count);
-	P(sched_goidle);
 #ifdef CONFIG_SMP
 	P64(avg_idle);
 	P64(max_idle_balance_cost);
 #endif
 
-	P(ttwu_count);
-	P(ttwu_local);
+	if (schedstat_enabled()) {
+		P(yld_count);
+		P(sched_count);
+		P(sched_goidle);
+		P(ttwu_count);
+		P(ttwu_local);
+	}
 
 #undef P
 #undef P64
@@ -569,38 +574,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-	PN(se.statistics.sum_sleep_runtime);
-	PN(se.statistics.wait_start);
-	PN(se.statistics.sleep_start);
-	PN(se.statistics.block_start);
-	PN(se.statistics.sleep_max);
-	PN(se.statistics.block_max);
-	PN(se.statistics.exec_max);
-	PN(se.statistics.slice_max);
-	PN(se.statistics.wait_max);
-	PN(se.statistics.wait_sum);
-	P(se.statistics.wait_count);
-	PN(se.statistics.iowait_sum);
-	P(se.statistics.iowait_count);
 	P(se.nr_migrations);
-	P(se.statistics.nr_migrations_cold);
-	P(se.statistics.nr_failed_migrations_affine);
-	P(se.statistics.nr_failed_migrations_running);
-	P(se.statistics.nr_failed_migrations_hot);
-	P(se.statistics.nr_forced_migrations);
-	P(se.statistics.nr_wakeups);
-	P(se.statistics.nr_wakeups_sync);
-	P(se.statistics.nr_wakeups_migrate);
-	P(se.statistics.nr_wakeups_local);
-	P(se.statistics.nr_wakeups_remote);
-	P(se.statistics.nr_wakeups_affine);
-	P(se.statistics.nr_wakeups_affine_attempts);
-	P(se.statistics.nr_wakeups_passive);
-	P(se.statistics.nr_wakeups_idle);
 
-	{
+	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
+		PN(se.statistics.sum_sleep_runtime);
+		PN(se.statistics.wait_start);
+		PN(se.statistics.sleep_start);
+		PN(se.statistics.block_start);
+		PN(se.statistics.sleep_max);
+		PN(se.statistics.block_max);
+		PN(se.statistics.exec_max);
+		PN(se.statistics.slice_max);
+		PN(se.statistics.wait_max);
+		PN(se.statistics.wait_sum);
+		P(se.statistics.wait_count);
+		PN(se.statistics.iowait_sum);
+		P(se.statistics.iowait_count);
+		P(se.statistics.nr_migrations_cold);
+		P(se.statistics.nr_failed_migrations_affine);
+		P(se.statistics.nr_failed_migrations_running);
+		P(se.statistics.nr_failed_migrations_hot);
+		P(se.statistics.nr_forced_migrations);
+		P(se.statistics.nr_wakeups);
+		P(se.statistics.nr_wakeups_sync);
+		P(se.statistics.nr_wakeups_migrate);
+		P(se.statistics.nr_wakeups_local);
+		P(se.statistics.nr_wakeups_remote);
+		P(se.statistics.nr_wakeups_affine);
+		P(se.statistics.nr_wakeups_affine_attempts);
+		P(se.statistics.nr_wakeups_passive);
+		P(se.statistics.nr_wakeups_idle);
+
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
 			avg_atom = div64_ul(avg_atom, nr_switches);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1926606ece80..7fe6e713c881 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -755,7 +755,9 @@ static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct task_struct *p;
-	u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+	u64 delta;
+
+	delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
 
 	if (entity_is_task(se)) {
 		p = task_of(se);
@@ -776,22 +778,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->statistics.wait_sum += delta;
 	se->statistics.wait_start = 0;
 }
-#else
-static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-
-static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-#endif
 
 /*
  * Task is being enqueued - update stats:
  */
-static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	/*
 	 * Are we enqueueing a waiting task? (for current tasks
@@ -802,7 +794,7 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Mark the end of the wait period if dequeueing a
@@ -810,8 +802,41 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	if (se != cfs_rq->curr)
 		update_stats_wait_end(cfs_rq, se);
+
+	if (flags & DEQUEUE_SLEEP) {
+		if (entity_is_task(se)) {
+			struct task_struct *tsk = task_of(se);
+
+			if (tsk->state & TASK_INTERRUPTIBLE)
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
+			if (tsk->state & TASK_UNINTERRUPTIBLE)
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
+		}
+	}
+
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
 }
 
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+}
+#endif
+
 /*
  * We are picking a new current task - update its stats:
  */
@@ -3106,11 +3131,14 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
-		enqueue_sleeper(cfs_rq, se);
+		if (schedstat_enabled())
+			enqueue_sleeper(cfs_rq, se);
 	}
 
-	update_stats_enqueue(cfs_rq, se);
-	check_spread(cfs_rq, se);
+	if (schedstat_enabled()) {
+		update_stats_enqueue(cfs_rq, se);
+		check_spread(cfs_rq, se);
+	}
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
@@ -3177,19 +3205,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_curr(cfs_rq);
 	dequeue_entity_load_avg(cfs_rq, se);
 
-	update_stats_dequeue(cfs_rq, se);
-	if (flags & DEQUEUE_SLEEP) {
-#ifdef CONFIG_SCHEDSTATS
-		if (entity_is_task(se)) {
-			struct task_struct *tsk = task_of(se);
-
-			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
-			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
-		}
-#endif
-	}
+	if (schedstat_enabled())
+		update_stats_dequeue(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -3263,7 +3280,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		update_stats_wait_end(cfs_rq, se);
+		if (schedstat_enabled())
+			update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(se, 1);
 	}
@@ -3276,7 +3294,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * least twice that of our own weight (i.e. dont track it
 	 * when there are only lesser-weight tasks around):
 	 */
-	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
+	if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
 		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
@@ -3359,9 +3377,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	/* throttle cfs_rqs exceeding runtime */
 	check_cfs_rq_runtime(cfs_rq);
 
-	check_spread(cfs_rq, prev);
+	if (schedstat_enabled()) {
+		check_spread(cfs_rq, prev);
+		if (prev->on_rq)
+			update_stats_wait_start(cfs_rq, prev);
+	}
+
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f16374df7f..1d583870e1a6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1022,6 +1022,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
 extern struct static_key_false sched_numa_balancing;
+extern struct static_key_false sched_schedstats;
 
 static inline u64 global_rt_period(void)
 {
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index b0fbc7632de5..70b3b6a20fb0 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 	if (rq)
 		rq->rq_sched_info.run_delay += delta;
 }
-# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
-# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
-# define schedstat_set(var, val)	do { var = (val); } while (0)
+# define schedstat_enabled()		static_branch_unlikely(&sched_schedstats)
+# define schedstat_inc(rq, field)	do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
+# define schedstat_add(rq, field, amt)	do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
+# define schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
 #else /* !CONFIG_SCHEDSTATS */
 static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {}
+# define schedstat_enabled()		0
 # define schedstat_inc(rq, field)	do { } while (0)
 # define schedstat_add(rq, field, amt)	do { } while (0)
 # define schedstat_set(var, val)	do { } while (0)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 97715fd9e790..6fe70ccdf2ac 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SCHEDSTATS
+	{
+		.procname	= "sched_schedstats",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_schedstats,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif /* CONFIG_SCHEDSTATS */
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_NUMA_BALANCING
 	{
-- 
2.6.4

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Matt Fleming]

On Mon, 01 Feb, at 09:37:06AM, Mel Gorman wrote:
> Changelog since V2
> o Print stats that are not related to schedstat
> o Reintroduce a static inline for update_stats_dequeue
> 
> Changelog since V1
> o Introduce schedstat_enabled and address Ingo's feedback
> o More schedstat-only paths eliminated, particularly ttwu_stat
> 
> schedstats is very useful during debugging and performance tuning but it
> incurs overhead. As such, even though it can be disabled at build time,
> it is often enabled as the information is useful.  This patch adds a
> kernel command-line and sysctl tunable to enable or disable schedstats on
> demand. It is disabled by default as someone who knows they need it can
> also learn to enable it when necessary.
> 
> The benefits are workload-dependent but when it gets down to it, the
> difference will be whether cache misses are incurred updating the shared
> stats or not. These measurements were taken from a 48-core 2-socket machine
> with Xeon(R) E5-2670 v3 cpus although they were also tested on a single
> socket machine 8-core machine with Intel i7-3770 processors.
 
[...]
 
> The gain is small but it'll depend on the CPU and the workload whether
> this patch makes a different.  However, it stands to reason that doing
> less work in the scheduler is a good thing. The downside is that the
> lack of schedstats and tracepoints will be surprising to experts doing
> performance analysis until they find the existance of the schedstats=
> parameter or schedstats sysctl.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> ---
>  Documentation/kernel-parameters.txt |   5 ++
>  Documentation/sysctl/kernel.txt     |   8 +++
>  include/linux/sched/sysctl.h        |   4 ++
>  kernel/sched/core.c                 |  62 +++++++++++++++++++++-
>  kernel/sched/debug.c                | 102 +++++++++++++++++++-----------------
>  kernel/sched/fair.c                 |  90 +++++++++++++++++++------------
>  kernel/sched/sched.h                |   1 +
>  kernel/sched/stats.h                |   8 +--
>  kernel/sysctl.c                     |  11 ++++
>  9 files changed, 204 insertions(+), 87 deletions(-)

Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk>

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Srikar Dronamraju]

Dont we need changes for sched_info_on()?

If we disable schedstats dynamically but CONFIG_TASK_DELAY_ACCT is not
set, then sched_info_on will return true, This could impact guest steal
time stats as well as data read from /proc/<PID>/schedstat

Also when schedstats is dynamically disabled, and user tries to enable
kernel sleep profiling profile_setup(), the kernel may not be able to do
the right profiling since enqueue_sleeper() may not get called. Should
we alert the user saying kernel sleep profiling is disabled?

-- 
Thanks and Regards
Srikar Dronamraju

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Mel Gorman]

On Tue, Feb 02, 2016 at 03:02:07PM +0530, Srikar Dronamraju wrote:
> 
> Dont we need changes for sched_info_on()?
> 
> If we disable schedstats dynamically but CONFIG_TASK_DELAY_ACCT is not
> set, then sched_info_on will return true,

Is this really a problem?

sched_info_on() guards sched_info_dequeued(), sched_info_queued(),
__sched_info_switch(). These update fields in the sched_info struct with
the exception of rq->rq_cpu_time. In the case of rq_cpu_time, the values
it's updated depend on sched_info.

I'm not spotting the case where the current information for delayacct is
inaccurate. Where is it? Granted, there is some scope for also disabling
the delayacct information unless explicitly enabled.

> This could impact guest steal
> time stats as well as data read from /proc/<PID>/schedstat
> 
> Also when schedstats is dynamically disabled, and user tries to enable
> kernel sleep profiling profile_setup(), the kernel may not be able to do
> the right profiling since enqueue_sleeper() may not get called. Should
> we alert the user saying kernel sleep profiling is disabled?
> 

Yes. This on top? It's not completely bullet proof as a user could both
force schedstat disabled and enable sleep profiling but it's a waste of
memory to guard against it

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a10494a94cc3..5c2cd37c42e9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -920,6 +920,14 @@ static inline int sched_info_on(void)
 #endif
 }
 
+#ifdef CONFIG_SCHEDSTATS
+void force_schedstat_enabled(void);
+#else
+static inline void force_schedstat_enabled(void)
+{
+}
+#endif
+
 enum cpu_idle_type {
 	CPU_IDLE,
 	CPU_NOT_IDLE,
diff --git a/kernel/profile.c b/kernel/profile.c
index 99513e1160e5..51369697466e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -59,6 +59,7 @@ int profile_setup(char *str)
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
 #ifdef CONFIG_SCHEDSTATS
+		force_schedstat_enabled();
 		prof_on = SLEEP_PROFILING;
 		if (str[strlen(sleepstr)] == ',')
 			str += strlen(sleepstr) + 1;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1a816ebaa7da..f7aff8386c3f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2295,6 +2295,14 @@ static void set_schedstats(bool enabled)
 		static_branch_disable(&sched_schedstats);
 }
 
+void force_schedstat_enabled(void)
+{
+	if (!schedstat_enabled()) {
+		pr_info("kernel sleep profiling force enabled sched_schedstats\n");
+		static_branch_enable(&sched_schedstats);
+	}
+}
+
 static int __init setup_schedstats(char *str)
 {
 	int ret = 0;

-- 
Mel Gorman
SUSE Labs

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Srikar Dronamraju]

> > If we disable schedstats dynamically but CONFIG_TASK_DELAY_ACCT is not
> > set, then sched_info_on will return true,
> 
> Is this really a problem?
> 
> sched_info_on() guards sched_info_dequeued(), sched_info_queued(),
> __sched_info_switch(). These update fields in the sched_info struct with
> the exception of rq->rq_cpu_time. In the case of rq_cpu_time, the values
> it's updated depend on sched_info.
> 
> I'm not spotting the case where the current information for delayacct is
> inaccurate. Where is it? Granted, there is some scope for also disabling
> the delayacct information unless explicitly enabled.

ah, the run_delay gets updated. So yes its not a problem.

> 
> > This could impact guest steal
> > time stats as well as data read from /proc/<PID>/schedstat
> > 
> > Also when schedstats is dynamically disabled, and user tries to enable
> > kernel sleep profiling profile_setup(), the kernel may not be able to do
> > the right profiling since enqueue_sleeper() may not get called. Should
> > we alert the user saying kernel sleep profiling is disabled?
> > 
> 
> Yes. This on top? It's not completely bullet proof as a user could both
> force schedstat disabled and enable sleep profiling but it's a waste of
> memory to guard against it
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index a10494a94cc3..5c2cd37c42e9 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -920,6 +920,14 @@ static inline int sched_info_on(void)
>  #endif
>  }
> 
> +#ifdef CONFIG_SCHEDSTATS
> +void force_schedstat_enabled(void);
> +#else
> +static inline void force_schedstat_enabled(void)
> +{
> +}
> +#endif

One nit:
Since force_schedstat_enabled is called under CONFIG_SCHEDSTATS
we may not want the static define.

> +
>  enum cpu_idle_type {
>  	CPU_IDLE,
>  	CPU_NOT_IDLE,
> diff --git a/kernel/profile.c b/kernel/profile.c
> index 99513e1160e5..51369697466e 100644
> --- a/kernel/profile.c
> +++ b/kernel/profile.c
> @@ -59,6 +59,7 @@ int profile_setup(char *str)
> 
>  	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
>  #ifdef CONFIG_SCHEDSTATS
> +		force_schedstat_enabled();
>  		prof_on = SLEEP_PROFILING;
>  		if (str[strlen(sleepstr)] == ',')
>  			str += strlen(sleepstr) + 1;

-- 
Thanks and Regards
Srikar Dronamraju

Re: [PATCH 1/1] sched: Make schedstats a runtime tunable that is disabled by default v3

[Mel Gorman]

On Tue, Feb 02, 2016 at 08:15:14PM +0530, Srikar Dronamraju wrote:
> > Yes. This on top? It's not completely bullet proof as a user could both
> > force schedstat disabled and enable sleep profiling but it's a waste of
> > memory to guard against it
> > 
> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index a10494a94cc3..5c2cd37c42e9 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -920,6 +920,14 @@ static inline int sched_info_on(void)
> >  #endif
> >  }
> > 
> > +#ifdef CONFIG_SCHEDSTATS
> > +void force_schedstat_enabled(void);
> > +#else
> > +static inline void force_schedstat_enabled(void)
> > +{
> > +}
> > +#endif
> 
> One nit:
> Since force_schedstat_enabled is called under CONFIG_SCHEDSTATS
> we may not want the static define.
> 

I'm not sure I get this either :(. It is a static inline that does
nothing under !CONFIG_SCHEDSTAT because tehre is nothing to do.
Otherwise it needs to be available for profiling and I just spotted it's
needed by latencytop too.

-- 
Mel Gorman
SUSE Labs