LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yafang Shao <laoar.shao@gmail.com>
To: mingo@redhat.com, peterz@infradead.org, mgorman@suse.de,
	juri.lelli@redhat.com, vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com, rostedt@goodmis.org,
	bsegall@google.com, bristot@redhat.com, achaiken@aurora.tech
Cc: lkp@intel.com, linux-kernel@vger.kernel.org,
	linux-rt-users@vger.kernel.org,
	Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCH v3 7/7] sched, rt: support schedstats for RT sched class
Date: Tue, 24 Aug 2021 11:29:46 +0000	[thread overview]
Message-ID: <20210824112946.9324-8-laoar.shao@gmail.com> (raw)
In-Reply-To: <20210824112946.9324-1-laoar.shao@gmail.com>

We want to measure the latency of RT tasks in our production
environment with schedstats facility, but currently schedstats is only
supported for fair sched class. This patch enable it for RT sched class
as well.

After we make the struct sched_statistics and the helpers of it
independent of fair sched class, we can easily use the schedstats
facility for RT sched class.

The schedstat usage in RT sched class is similar with fair sched class,
for example,
                fair                        RT
enqueue         update_stats_enqueue_fair   update_stats_enqueue_rt
dequeue         update_stats_dequeue_fair   update_stats_dequeue_rt
put_prev_task   update_stats_wait_start     update_stats_wait_start_rt
set_next_task   update_stats_wait_end       update_stats_wait_end_rt

The user can get the schedstats information in the same way in fair sched
class. For example,
       fair                            RT
       /proc/[pid]/sched               /proc/[pid]/sched

The output of a RT task's schedstats as follows,
$ cat /proc/227408/sched
...
se.statistics.sum_sleep_runtime              :        402284.476088
se.statistics.sum_block_runtime              :        402272.475254
se.statistics.wait_start                     :             0.000000
se.statistics.sleep_start                    :             0.000000
se.statistics.block_start                    :      46903176.965093
se.statistics.sleep_max                      :            12.000834
se.statistics.block_max                      :          1446.963040
se.statistics.exec_max                       :             0.463806
se.statistics.slice_max                      :             0.000000
se.statistics.wait_max                       :           146.656326
se.statistics.wait_sum                       :         81741.944704
se.statistics.wait_count                     :                 1004
se.statistics.iowait_sum                     :         77875.399958
se.statistics.iowait_count                   :                  142
se.statistics.nr_migrations_cold             :                    0
se.statistics.nr_failed_migrations_affine    :                    0
se.statistics.nr_failed_migrations_running   :                    0
se.statistics.nr_failed_migrations_hot       :                    0
se.statistics.nr_forced_migrations           :                    0
se.statistics.nr_wakeups                     :                 1003
se.statistics.nr_wakeups_sync                :                    0
se.statistics.nr_wakeups_migrate             :                    0
se.statistics.nr_wakeups_local               :                  351
se.statistics.nr_wakeups_remote              :                  652
se.statistics.nr_wakeups_affine              :                    0
se.statistics.nr_wakeups_affine_attempts     :                    0
se.statistics.nr_wakeups_passive             :                    0
se.statistics.nr_wakeups_idle                :                    0
...

The sched:sched_stat_{wait, sleep, iowait, blocked} tracepoints can
be used to trace RT tasks as well. The output of these tracepoints for a
RT tasks as follows,

- blocked
  kworker/u113:0-230817  [000] d... 47197.452940: sched_stat_blocked: comm=stress pid=227408 delay=4096 [ns]

- iowait
     kworker/3:1-222921  [003] d... 47492.211521: sched_stat_iowait: comm=stress pid=227408 delay=905187613 [ns]

- wait
          stress-227400  [003] d... 47202.283021: sched_stat_wait: comm=stress pid=227408 delay=67958890 [ns]

- runtime
          stress-227408  [003] d... 47202.283027: sched_stat_runtime: comm=stress pid=227408 runtime=7815 [ns] vruntime=0 [ns]

- sleep
           sleep-244868  [022] dN.. 50070.614833: sched_stat_sleep: comm=sleep.sh pid=244300 delay=1001131165 [ns]
           sleep-244869  [022] dN.. 50071.616222: sched_stat_sleep: comm=sleep.sh pid=244300 delay=1001100486 [ns]
           sleep-244879  [022] dN.. 50072.617628: sched_stat_sleep: comm=sleep.sh pid=244300 delay=1001137198 [ns]
           [ In sleep.sh, it sleeps 1 sec each time. ]

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

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Alison Chaiken <achaiken@aurora.tech>
---
 kernel/sched/rt.c | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 5d251112e51c..446164597232 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1273,6 +1273,129 @@ static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_arr
 	rt_se->on_list = 0;
 }
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline void
+__schedstats_from_sched_rt_entity(struct sched_rt_entity *rt_se,
+				  struct sched_statistics **stats)
+{
+	struct task_struct *p;
+	struct task_group *tg;
+	struct rt_rq *rt_rq;
+	int cpu;
+
+	if (rt_entity_is_task(rt_se)) {
+		p = rt_task_of(rt_se);
+		*stats = &p->stats;
+	} else {
+		rt_rq = group_rt_rq(rt_se);
+		tg = rt_rq->tg;
+		cpu = cpu_of(rq_of_rt_rq(rt_rq));
+		*stats = tg->stats[cpu];
+	}
+}
+
+#else
+
+static inline void
+__schedstats_from_sched_rt_entity(struct sched_rt_entity *rt_se,
+				  struct sched_statistics **stats)
+{
+	struct task_struct *p;
+
+	p = rt_task_of(rt_se);
+	*stats = &p->stats;
+}
+
+#endif
+
+static inline void
+update_stats_wait_start_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats = NULL;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	__schedstats_from_sched_rt_entity(rt_se, &stats);
+
+	__update_stats_wait_start(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_enqueue_sleeper_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats = NULL;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	__schedstats_from_sched_rt_entity(rt_se, &stats);
+
+	__update_stats_enqueue_sleeper(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_enqueue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
+			int flags)
+{
+	if (!schedstat_enabled())
+		return;
+
+	if (flags & ENQUEUE_WAKEUP)
+		update_stats_enqueue_sleeper_rt(rt_rq, rt_se);
+}
+
+static inline void
+update_stats_wait_end_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+{
+	struct sched_statistics *stats = NULL;
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	__schedstats_from_sched_rt_entity(rt_se, &stats);
+
+	__update_stats_wait_end(rq_of_rt_rq(rt_rq), p, stats);
+}
+
+static inline void
+update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
+			int flags)
+{
+	struct task_struct *p = NULL;
+
+	if (!schedstat_enabled())
+		return;
+
+	if (rt_entity_is_task(rt_se))
+		p = rt_task_of(rt_se);
+
+	if ((flags & DEQUEUE_SLEEP) && p) {
+		unsigned int state;
+
+		state = READ_ONCE(p->__state);
+		if (state & TASK_INTERRUPTIBLE)
+			__schedstat_set(p->stats.sleep_start,
+					rq_clock(rq_of_rt_rq(rt_rq)));
+
+		if (state & TASK_UNINTERRUPTIBLE)
+			__schedstat_set(p->stats.block_start,
+					rq_clock(rq_of_rt_rq(rt_rq)));
+	}
+}
+
 static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
@@ -1346,6 +1469,8 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
+	update_stats_enqueue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+
 	dequeue_rt_stack(rt_se, flags);
 	for_each_sched_rt_entity(rt_se)
 		__enqueue_rt_entity(rt_se, flags);
@@ -1356,6 +1481,8 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
+	update_stats_dequeue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+
 	dequeue_rt_stack(rt_se, flags);
 
 	for_each_sched_rt_entity(rt_se) {
@@ -1378,6 +1505,9 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
+	check_schedstat_required();
+	update_stats_wait_start_rt(rt_rq_of_se(rt_se), rt_se);
+
 	enqueue_rt_entity(rt_se, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
@@ -1578,7 +1708,12 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 
 static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = &rq->rt;
+
 	p->se.exec_start = rq_clock_task(rq);
+	if (on_rt_rq(&p->rt))
+		update_stats_wait_end_rt(rt_rq, rt_se);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
@@ -1652,6 +1787,12 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 
 static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (on_rt_rq(&p->rt))
+		update_stats_wait_start_rt(rt_rq, rt_se);
+
 	update_curr_rt(rq);
 
 	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
-- 
2.18.2


  parent reply	other threads:[~2021-08-24 11:30 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-24 11:29 [PATCH v3 0/7] sched: " Yafang Shao
2021-08-24 11:29 ` [PATCH v3 1/7] sched, fair: use __schedstat_set() in set_next_entity() Yafang Shao
2021-08-24 11:29 ` [PATCH v3 2/7] sched: make struct sched_statistics independent of fair sched class Yafang Shao
2021-08-31 10:14   ` Peter Zijlstra
2021-08-31 13:25     ` Yafang Shao
2021-08-31 10:19   ` Peter Zijlstra
2021-08-31 13:25     ` Yafang Shao
2021-08-24 11:29 ` [PATCH v3 3/7] sched: make schedstats helpers " Yafang Shao
2021-08-31 11:07   ` Peter Zijlstra
2021-08-31 13:27     ` Yafang Shao
2021-08-24 11:29 ` [PATCH v3 4/7] sched: make the output of schedstats " Yafang Shao
2021-08-31 11:08   ` Peter Zijlstra
2021-08-31 13:27     ` Yafang Shao
2021-08-24 11:29 ` [PATCH v3 5/7] sched: introduce task block time in schedstats Yafang Shao
2021-08-24 11:29 ` [PATCH v3 6/7] sched, rt: support sched_stat_runtime tracepoint for RT sched class Yafang Shao
2021-08-24 11:29 ` Yafang Shao [this message]
2021-08-31 10:08 ` [PATCH v3 0/7] sched: support schedstats " Peter Zijlstra
2021-08-31 10:44   ` Peter Zijlstra
2021-08-31 13:21     ` Yafang Shao
2021-08-31 12:57   ` 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=20210824112946.9324-8-laoar.shao@gmail.com \
    --to=laoar.shao@gmail.com \
    --cc=achaiken@aurora.tech \
    --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 \
    --subject='Re: [PATCH v3 7/7] sched, rt: support schedstats for RT sched class' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).