Linux-rt-users Archive on lore.kernel.org
 help / color / Atom feed
From: Yafang Shao <laoar.shao@gmail.com>
To: mgorman@suse.de, mingo@redhat.com, peterz@infradead.org,
	juri.lelli@redhat.com, vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com, rostedt@goodmis.org,
	bsegall@google.com, bristot@redhat.com
Cc: linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org,
	Yafang Shao <laoar.shao@gmail.com>,
	kernel test robot <lkp@intel.com>
Subject: [PATCH v2 3/6] sched: make schedstats helpers independent of fair sched class
Date: Sat, 27 Mar 2021 18:12:50 +0800
Message-ID: <20210327101254.56872-4-laoar.shao@gmail.com> (raw)
In-Reply-To: <20210327101254.56872-1-laoar.shao@gmail.com>

The original prototype of the schedstats helpers are

update_stats_wait_*(struct cfs_rq *cfs_rq, struct sched_entity *se)

The cfs_rq in these helpers is used to get the rq_clock, and the se is
used to get the struct sched_statistics and the struct task_struct. In
order to make these helpers available by all sched classes, we can pass
the rq, sched_statistics and task_struct directly.

Then the new helpers are

update_stats_wait_*(struct rq *rq, struct task_struct *p,
                    struct sched_statistics *stats)

which are independent of fair sched class.

To avoid vmlinux growing too large or introducing ovehead when
!schedstat_enabled(), some new helpers after schedstat_enabled() are also
introduced, Suggested by Mel. These helpers are in sched/stats.c,

__update_stats_wait_*(struct rq *rq, struct task_struct *p,
                      struct sched_statistics *stats)

The size of vmlinux as follows,
                      Before          After
  Size of vmlinux     826308552       826304640
The size is a litte smaller as some functions are not inlined again after
the change.

I also compared the sched performance with 'perf bench sched pipe',
suggested by Mel. The result as follows,
                             Before               After
  kernel.sched_schedstats=0  6.0~6.1              6.0~6.1
  kernel.sched_schedstats=1  6.2~6.4              6.2~6.4
No obvious difference after the change.

No functional change.

[lkp@intel.com: reported build failure in prev version]

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: kernel test robot <lkp@intel.com>
---
 kernel/sched/fair.c  | 133 +++++++------------------------------------
 kernel/sched/stats.c | 103 +++++++++++++++++++++++++++++++++
 kernel/sched/stats.h |  34 +++++++++++
 3 files changed, 156 insertions(+), 114 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5f72fef1cc0a..77a615b6310d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -904,32 +904,28 @@ static void update_curr_fair(struct rq *rq)
 }
 
 static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_start_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct sched_statistics *stats = NULL;
-	u64 wait_start, prev_wait_start;
+	struct task_struct *p = NULL;
 
 	if (!schedstat_enabled())
 		return;
 
 	__schedstats_from_sched_entity(se, &stats);
 
-	wait_start = rq_clock(rq_of(cfs_rq));
-	prev_wait_start = schedstat_val(stats->wait_start);
+	if (entity_is_task(se))
+		p = task_of(se);
 
-	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
-	    likely(wait_start > prev_wait_start))
-		wait_start -= prev_wait_start;
+	__update_stats_wait_start(rq_of(cfs_rq), p, stats);
 
-	__schedstat_set(stats->wait_start, wait_start);
 }
 
 static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct sched_statistics *stats = NULL;
 	struct task_struct *p = NULL;
-	u64 delta;
 
 	if (!schedstat_enabled())
 		return;
@@ -945,105 +941,34 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (unlikely(!schedstat_val(stats->wait_start)))
 		return;
 
-	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(stats->wait_start);
-
-	if (entity_is_task(se)) {
+	if (entity_is_task(se))
 		p = task_of(se);
-		if (task_on_rq_migrating(p)) {
-			/*
-			 * Preserve migrating task's wait time so wait_start
-			 * time stamp can be adjusted to accumulate wait time
-			 * prior to migration.
-			 */
-			__schedstat_set(stats->wait_start, delta);
-			return;
-		}
-		trace_sched_stat_wait(p, delta);
-	}
 
-	__schedstat_set(stats->wait_max,
-		      max(schedstat_val(stats->wait_max), delta));
-	__schedstat_inc(stats->wait_count);
-	__schedstat_add(stats->wait_sum, delta);
-	__schedstat_set(stats->wait_start, 0);
+	__update_stats_wait_end(rq_of(cfs_rq), p, stats);
 }
 
 static inline void
-update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_enqueue_sleeper_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct sched_statistics *stats = NULL;
 	struct task_struct *tsk = NULL;
-	u64 sleep_start, block_start;
 
 	if (!schedstat_enabled())
 		return;
 
 	__schedstats_from_sched_entity(se, &stats);
 
-	sleep_start = schedstat_val(stats->sleep_start);
-	block_start = schedstat_val(stats->block_start);
-
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (sleep_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(stats->sleep_max)))
-			__schedstat_set(stats->sleep_max, delta);
-
-		__schedstat_set(stats->sleep_start, 0);
-		__schedstat_add(stats->sum_sleep_runtime, delta);
-
-		if (tsk) {
-			account_scheduler_latency(tsk, delta >> 10, 1);
-			trace_sched_stat_sleep(tsk, delta);
-		}
-	}
-	if (block_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(stats->block_max)))
-			__schedstat_set(stats->block_max, delta);
-
-		__schedstat_set(stats->block_start, 0);
-		__schedstat_add(stats->sum_sleep_runtime, delta);
-
-		if (tsk) {
-			if (tsk->in_iowait) {
-				__schedstat_add(stats->iowait_sum, delta);
-				__schedstat_inc(stats->iowait_count);
-				trace_sched_stat_iowait(tsk, delta);
-			}
-
-			trace_sched_stat_blocked(tsk, delta);
-
-			/*
-			 * Blocking time is in units of nanosecs, so shift by
-			 * 20 to get a milliseconds-range estimation of the
-			 * amount of time that the task spent sleeping:
-			 */
-			if (unlikely(prof_on == SLEEP_PROFILING)) {
-				profile_hits(SLEEP_PROFILING,
-						(void *)get_wchan(tsk),
-						delta >> 20);
-			}
-			account_scheduler_latency(tsk, delta >> 10, 0);
-		}
-	}
+	__update_stats_enqueue_sleeper(rq_of(cfs_rq), tsk, stats);
 }
 
 /*
  * Task is being enqueued - update stats:
  */
 static inline void
-update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	if (!schedstat_enabled())
 		return;
@@ -1053,14 +978,14 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * a dequeue/enqueue event is a NOP)
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_start(cfs_rq, se);
+		update_stats_wait_start_fair(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
-		update_stats_enqueue_sleeper(cfs_rq, se);
+		update_stats_enqueue_sleeper_fair(cfs_rq, se);
 }
 
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 
 	if (!schedstat_enabled())
@@ -1071,7 +996,7 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * waiting task:
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end_fair(cfs_rq, se);
 
 	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
 		struct task_struct *tsk = task_of(se);
@@ -4202,26 +4127,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
-static inline void check_schedstat_required(void)
-{
-#ifdef CONFIG_SCHEDSTATS
-	if (schedstat_enabled())
-		return;
-
-	/* Force schedstat enabled if a dependent tracepoint is active */
-	if (trace_sched_stat_wait_enabled()    ||
-			trace_sched_stat_sleep_enabled()   ||
-			trace_sched_stat_iowait_enabled()  ||
-			trace_sched_stat_blocked_enabled() ||
-			trace_sched_stat_runtime_enabled())  {
-		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
-			     "stat_blocked and stat_runtime require the "
-			     "kernel parameter schedstats=enable or "
-			     "kernel.sched_schedstats=1\n");
-	}
-#endif
-}
-
 static inline bool cfs_bandwidth_used(void);
 
 /*
@@ -4295,7 +4200,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		place_entity(cfs_rq, se, 0);
 
 	check_schedstat_required();
-	update_stats_enqueue(cfs_rq, se, flags);
+	update_stats_enqueue_fair(cfs_rq, se, flags);
 	check_spread(cfs_rq, se);
 	if (!curr)
 		__enqueue_entity(cfs_rq, se);
@@ -4379,7 +4284,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_load_avg(cfs_rq, se, UPDATE_TG);
 	se_update_runnable(se);
 
-	update_stats_dequeue(cfs_rq, se, flags);
+	update_stats_dequeue_fair(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -4464,7 +4369,7 @@ 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);
+		update_stats_wait_end_fair(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 	}
@@ -4566,7 +4471,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	check_spread(cfs_rq, prev);
 
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
+		update_stats_wait_start_fair(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/stats.c b/kernel/sched/stats.c
index 3f93fc3b5648..b2542f4d3192 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -4,6 +4,109 @@
  */
 #include "sched.h"
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats)
+{
+u64 wait_start, prev_wait_start;
+
+	wait_start = rq_clock(rq);
+	prev_wait_start = schedstat_val(stats->wait_start);
+
+	if (p && likely(wait_start > prev_wait_start))
+		wait_start -= prev_wait_start;
+
+	__schedstat_set(stats->wait_start, wait_start);
+}
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats)
+{
+	u64 delta = rq_clock(rq) - schedstat_val(stats->wait_start);
+
+	if (p) {
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			__schedstat_set(stats->wait_start, delta);
+
+			return;
+		}
+
+		trace_sched_stat_wait(p, delta);
+	}
+
+	__schedstat_set(stats->wait_max,
+			max(schedstat_val(stats->wait_max), delta));
+	__schedstat_inc(stats->wait_count);
+	__schedstat_add(stats->wait_sum, delta);
+	__schedstat_set(stats->wait_start, 0);
+}
+
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats)
+{
+	u64 sleep_start, block_start;
+
+	sleep_start = schedstat_val(stats->sleep_start);
+	block_start = schedstat_val(stats->block_start);
+
+	if (sleep_start) {
+		u64 delta = rq_clock(rq) - sleep_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->sleep_max)))
+			__schedstat_set(stats->sleep_max, delta);
+
+		__schedstat_set(stats->sleep_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+
+		if (p) {
+			account_scheduler_latency(p, delta >> 10, 1);
+			trace_sched_stat_sleep(p, delta);
+		}
+	}
+
+	if (block_start) {
+		u64 delta = rq_clock(rq) - block_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->block_max)))
+			__schedstat_set(stats->block_max, delta);
+
+		__schedstat_set(stats->block_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+
+		if (p) {
+			if (p->in_iowait) {
+				__schedstat_add(stats->iowait_sum, delta);
+				__schedstat_inc(stats->iowait_count);
+				trace_sched_stat_iowait(p, delta);
+			}
+
+			trace_sched_stat_blocked(p, delta);
+
+			/*
+			 * Blocking time is in units of nanosecs, so shift by
+			 * 20 to get a milliseconds-range estimation of the
+			 * amount of time that the task spent sleeping:
+			 */
+			if (unlikely(prof_on == SLEEP_PROFILING)) {
+				profile_hits(SLEEP_PROFILING,
+					     (void *)get_wchan(p),
+					     delta >> 20);
+			}
+			account_scheduler_latency(p, delta >> 10, 0);
+		}
+	}
+}
+
 /*
  * Current schedstat API version.
  *
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 6c810388a897..3671857c70c6 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -2,6 +2,8 @@
 
 #ifdef CONFIG_SCHEDSTATS
 
+extern struct static_key_false sched_schedstats;
+
 /*
  * Expects runqueue lock to be held for atomicity of update
  */
@@ -40,6 +42,33 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 #define   schedstat_val(var)		(var)
 #define   schedstat_val_or_zero(var)	((schedstat_enabled()) ? (var) : 0)
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats);
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats);
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats);
+
+static inline void
+check_schedstat_required(void)
+{
+	if (schedstat_enabled())
+		return;
+
+	/* Force schedstat enabled if a dependent tracepoint is active */
+	if (trace_sched_stat_wait_enabled()    ||
+		trace_sched_stat_sleep_enabled()   ||
+		trace_sched_stat_iowait_enabled()  ||
+		trace_sched_stat_blocked_enabled() ||
+		trace_sched_stat_runtime_enabled())  {
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+					"stat_blocked and stat_runtime require the "
+					"kernel parameter schedstats=enable or "
+					"kernel.sched_schedstats=1\n");
+	}
+}
+
 #else /* !CONFIG_SCHEDSTATS: */
 
 static inline void rq_sched_info_arrive  (struct rq *rq, unsigned long long delta) { }
@@ -55,6 +84,11 @@ static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delt
 # define   schedstat_val(var)		0
 # define   schedstat_val_or_zero(var)	0
 
+# define __update_stats_wait_start(rq, p, stats)       do { } while (0)
+# define __update_stats_wait_end(rq, p, stats)         do { } while (0)
+# define __update_stats_enqueue_sleeper(rq, p, stats)  do { } while (0)
+# define check_schedstat_required()                    do { } while (0)
+
 #endif /* CONFIG_SCHEDSTATS */
 
 #if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SCHEDSTATS)
-- 
2.18.2


  parent reply index

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-27 10:12 [PATCH v2 0/6] sched: support schedstats for RT " Yafang Shao
2021-03-27 10:12 ` [PATCH v2 1/6] sched, fair: use __schedstat_set() in set_next_entity() Yafang Shao
2021-03-27 10:12 ` [PATCH v2 2/6] sched: make struct sched_statistics independent of fair sched class Yafang Shao
2021-03-27 10:12 ` Yafang Shao [this message]
2021-03-27 10:12 ` [PATCH v2 4/6] sched: introduce task block time in schedstats Yafang Shao
2021-03-27 10:12 ` [PATCH v2 5/6] sched, rt: support sched_stat_runtime tracepoint for RT sched class Yafang Shao
2021-03-27 10:12 ` [PATCH v2 6/6] sched, rt: support schedstats " Yafang Shao
2021-04-06 10:41 ` [PATCH v2 0/6] sched: " Yafang Shao

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210327101254.56872-4-laoar.shao@gmail.com \
    --to=laoar.shao@gmail.com \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=lkp@intel.com \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-rt-users Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rt-users/0 linux-rt-users/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rt-users linux-rt-users/ https://lore.kernel.org/linux-rt-users \
		linux-rt-users@vger.kernel.org
	public-inbox-index linux-rt-users

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rt-users


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git