Date:	Fri, 29 Oct 2010 08:42:26 +0200
From:	Raistlin <raistlin@...ux.it>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	Ingo Molnar <mingo@...e.hu>, Thomas Gleixner <tglx@...utronix.de>,
	Steven Rostedt <rostedt@...dmis.org>,
	Chris Friesen <cfriesen@...tel.com>, oleg@...hat.com,
	Frederic Weisbecker <fweisbec@...il.com>,
	Darren Hart <darren@...art.com>,
	Johan Eker <johan.eker@...csson.com>,
	"p.faure" <p.faure@...tech.ch>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	Claudio Scordino <claudio@...dence.eu.com>,
	michael trimarchi <trimarchi@...is.sssup.it>,
	Fabio Checconi <fabio@...dalf.sssup.it>,
	Tommaso Cucinotta <cucinotta@...up.it>,
	Juri Lelli <juri.lelli@...il.com>,
	Nicola Manica <nicola.manica@...i.unitn.it>,
	Luca Abeni <luca.abeni@...tn.it>,
	Dhaval Giani <dhaval@...is.sssup.it>,
	Harald Gustafsson <hgu1972@...il.com>,
	paulmck <paulmck@...ux.vnet.ibm.com>
Subject: [RFC][PATCH 18/22] sched: add reclaiming logic to -deadline tasks

The bandwidth enforcing mechanism implemented inside the
SCHED_DEADLINE policy ensures that overrunning tasks are slowed
down without interfering with well behaving ones.
This, however, comes at the price of limiting the capability of
a task to exploit more bandwidth than it is asigned.

The current implementation always stops a task that is trying
to use more than its runtime (every deadline). Something else that
could be done is to let it continue running, but with a "decreased
priority". This way, we can exploit full CPU bandwidth and still
avoid interferences.

In order of "decreasing the priority" of a deadline task, we can:
 - let it stay SCHED_DEADLINE and postpone its deadline. This way it
   will always be scheduled before -rt and -other tasks but it
   won't affect other -deadline tasks;
 - put it in SCHED_FIFO with some priority. This way it will always
   be scheduled before -other tasks but it won't affect -deadline
   tasks, nor other -rt tasks with higher priority;
 - put it in SCHED_OTHER.

Notice also that this can be done on a per-task basis, e.g., each
task can specify what kind of reclaiming mechanism it wants to use
by means of the sched_flags field of sched_param_ex.

Therefore, this patch:
 - adds the flags for specyfing DEADLINE, RT or OTHER reclaiming
   behaviour;
 - adds the logic that changes the scheduling class of a task when
   it overruns, according to the requested policy.

Signed-off-by: Dario Faggioli <raistlin@...ux.it>
---
 include/linux/sched.h |   25 ++++++++++++++
 kernel/hrtimer.c      |    2 +-
 kernel/sched.c        |   86 ++++++++++++++++++++++++++++++++-----------------
 kernel/sched_debug.c  |    2 +-
 kernel/sched_dl.c     |   44 +++++++++++++++++++++++--
 5 files changed, 123 insertions(+), 36 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b729f83..8806c1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -172,10 +172,26 @@ struct sched_param_ex {
  *                      a runtime overrun occurs;
  *  @SF_SIG_DMISS       tells us the task wants to be notified whenever
  *                      a scheduling deadline is missed.
+ *  @SF_BWRECL_DL       tells us that the task doesn't stop when exhausting
+ *                      its runtime, and it remains a -deadline task, even
+ *                      though its deadline is postponed. This means it
+ *                      won't affect the scheduling of the other -deadline
+ *                      tasks, but if it is a CPU-hog, lower scheduling
+ *                      classes will starve!
+ *  @SF_BWRECL_RT       tells us that the task doesn't stop when exhausting
+ *                      its runtime, and it becomes a -rt task, with the
+ *                      priority specified in the sched_priority field of
+ *                      struct shced_param_ex.
+ *  @SF_BWRECL_OTH      tells us that the task doesn't stop when exhausting
+ *                      its runtime, and it becomes a normal task, with
+ *                      default priority.
  */
 #define SF_HEAD		1
 #define SF_SIG_RORUN	2
 #define SF_SIG_DMISS	4
+#define SF_BWRECL_DL	8
+#define SF_BWRECL_RT	16
+#define SF_BWRECL_NR	32
 
 struct exec_domain;
 struct futex_pi_state;
@@ -1694,6 +1710,15 @@ static inline int dl_task(struct task_struct *p)
 	return dl_prio(p->prio);
 }
 
+/*
+ * We might have temporarily dropped -deadline policy,
+ * but still be a -deadline task!
+ */
+static inline int __dl_task(struct task_struct *p)
+{
+	return dl_task(p) || p->policy == SCHED_DEADLINE;
+}
+
 static inline int rt_prio(int prio)
 {
 	if (unlikely(prio >= MAX_DL_PRIO && prio < MAX_RT_PRIO))
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9cd8564..54277be 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1574,7 +1574,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (dl_task(current) || rt_task(current))
+	if (__dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/sched.c b/kernel/sched.c
index 79cac6e..4d291e3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2235,7 +2235,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
-	if (unlikely(dl_task(p)))
+	if (unlikely(__dl_task(p)))
 		trace_sched_migrate_task_dl(p, task_rq(p)->clock,
 					    new_cpu, cpu_rq(new_cpu)->clock);
 
@@ -2983,6 +2983,16 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 			prev->sched_class->task_dead(prev);
 
 		/*
+		 * If we are a -deadline task, dieing while
+		 * hanging out in a different scheduling class
+		 * we need to manually call our own cleanup function,
+		 * at least to stop the bandwidth timer.
+		 */
+		if (unlikely(task_has_dl_policy(prev) &&
+		    prev->sched_class != &dl_sched_class))
+			dl_sched_class.task_dead(prev);
+
+		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
 		 */
@@ -3064,7 +3074,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 
 	prepare_task_switch(rq, prev, next);
 	trace_sched_switch(prev, next);
-	if (unlikely(dl_task(prev) || dl_task(next)))
+	if (unlikely(__dl_task(prev) || __dl_task(next)))
 		trace_sched_switch_dl(rq->clock, prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
@@ -4554,34 +4564,13 @@ long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
 }
 EXPORT_SYMBOL(sleep_on_timeout);
 
-#ifdef CONFIG_RT_MUTEXES
-
-/*
- * rt_mutex_setprio - set the current priority of a task
- * @p: task
- * @prio: prio value (kernel-internal form)
- *
- * This function changes the 'effective' priority of a task. It does
- * not touch ->normal_prio like __setscheduler().
- *
- * Used by the rt_mutex code to implement priority inheritance logic.
- */
-void rt_mutex_setprio(struct task_struct *p, int prio)
+static void __setprio(struct rq *rq, struct task_struct *p, int prio)
 {
-	unsigned long flags;
-	int oldprio, on_rq, running;
-	struct rq *rq;
-	const struct sched_class *prev_class;
-
-	BUG_ON(prio < 0 || prio > MAX_PRIO);
+	int oldprio = p->prio;
+	const struct sched_class *prev_class = p->sched_class;
+	int running = task_current(rq, p);
+	int on_rq = p->se.on_rq;
 
-	rq = task_rq_lock(p, &flags);
-
-	trace_sched_pi_setprio(p, prio);
-	oldprio = p->prio;
-	prev_class = p->sched_class;
-	on_rq = p->se.on_rq;
-	running = task_current(rq, p);
 	if (on_rq)
 		dequeue_task(rq, p, 0);
 	if (running)
@@ -4603,6 +4592,30 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}
+}
+
+#ifdef CONFIG_RT_MUTEXES
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task
+ * @prio: prio value (kernel-internal form)
+ *
+ * This function changes the 'effective' priority of a task. It does
+ * not touch ->normal_prio like __setscheduler().
+ *
+ * Used by the rt_mutex code to implement priority inheritance logic.
+ */
+void rt_mutex_setprio(struct task_struct *p, int prio)
+{
+	unsigned long flags;
+	struct rq *rq;
+
+	BUG_ON(prio < 0 || prio > MAX_PRIO);
+
+	rq = task_rq_lock(p, &flags);
+	trace_sched_pi_setprio(p, prio);
+	__setprio(rq, p, prio);
 	task_rq_unlock(rq, &flags);
 }
 
@@ -4909,19 +4922,32 @@ recheck:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
 		if (dl_policy(policy)) {
-			u64 rlim_dline, rlim_rtime;
+			u64 rlim_dline, rlim_rtime, rlim_rtprio;
 			u64 dline, rtime;
 
 			if (!lock_task_sighand(p, &flags))
 				return -ESRCH;
 			rlim_dline = p->signal->rlim[RLIMIT_DLDLINE].rlim_cur;
 			rlim_rtime = p->signal->rlim[RLIMIT_DLRTIME].rlim_cur;
+			rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
 			unlock_task_sighand(p, &flags);
 
 			/* can't set/change -deadline policy */
 			if (policy != p->policy && !rlim_rtime)
 				return -EPERM;
 
+			/* can't set/change reclaiming policy to -deadline */
+			if ((param_ex->sched_flags & SF_BWRECL_DL) !=
+			    (p->dl.flags & SF_BWRECL_DL))
+				return -EPERM;
+
+			/* can't set/increase -rt reclaiming priority */
+			if (param_ex->sched_flags & SF_BWRECL_RT &&
+			    (param_ex->sched_priority <= 0 ||
+			     (param_ex->sched_priority > p->rt_priority &&
+			      param_ex->sched_priority > rlim_rtprio)))
+				return -EPERM;
+
 			/* can't decrease the deadline */
 			rlim_dline *= NSEC_PER_USEC;
 			dline = timespec_to_ns(&param_ex->sched_deadline);
@@ -8596,7 +8622,7 @@ void normalize_rt_tasks(void)
 		p->se.statistics.block_start	= 0;
 #endif
 
-		if (!dl_task(p) && !rt_task(p)) {
+		if (!__dl_task(p) && !rt_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4949a21..2bf4e72 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -467,7 +467,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.statistics.nr_wakeups_affine_attempts);
 	P(se.statistics.nr_wakeups_passive);
 	P(se.statistics.nr_wakeups_idle);
-	if (dl_task(p)) {
+	if (__dl_task(p)) {
 		P(dl.stats.dmiss);
 		PN(dl.stats.last_dmiss);
 		PN(dl.stats.dmiss_max);
diff --git a/kernel/sched_dl.c b/kernel/sched_dl.c
index eff183a..4d24109 100644
--- a/kernel/sched_dl.c
+++ b/kernel/sched_dl.c
@@ -15,6 +15,8 @@
  *                    Fabio Checconi <fabio@...dalf.sssup.it>
  */
 
+static const struct sched_class dl_sched_class;
+
 static inline int dl_time_before(u64 a, u64 b)
 {
 	return (s64)(a - b) < 0;
@@ -382,6 +384,17 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	s64 delta;
 
 	/*
+	 * If the task wants to stay -deadline even if it exhausted
+	 * its runtime we allow that by not starting the timer.
+	 * update_curr_dl() will thus queue it back after replenishment
+	 * and deadline postponing.
+	 * This won't affect the other -deadline tasks, but if we are
+	 * a CPU-hog, lower scheduling classes will starve!
+	 */
+	if (dl_se->flags & SF_BWRECL_DL)
+		return 0;
+
+	/*
 	 * We want the timer to fire at the deadline, but considering
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
@@ -414,6 +427,8 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	return hrtimer_active(&dl_se->dl_timer);
 }
 
+static void __setprio(struct rq *rq, struct task_struct *p, int prio);
+
 /*
  * This is the bandwidth enforcement timer callback. If here, we know
  * a task is not on its dl_rq, since the fact that the timer was running
@@ -440,12 +455,18 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * We need to take care of a possible races here. In fact, the
 	 * task might have changed its scheduling policy to something
 	 * different from SCHED_DEADLINE (through sched_setscheduler()).
+	 * However, if we changed scheduling class for reclaiming, it
+	 * is correct to handle this replenishment, since this is what
+	 * will put us back into the -deadline scheduling class.
 	 */
-	if (!dl_task(p))
+	if (!__dl_task(p))
 		goto unlock;
 
 	trace_sched_timer_dl(p, rq->clock, p->se.on_rq, task_current(rq, p));
 
+	if (unlikely(p->sched_class != &dl_sched_class))
+		__setprio(rq, p, MAX_DL_PRIO-1);
+
 	dl_se->dl_throttled = 0;
 	if (p->se.on_rq) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
@@ -530,6 +551,16 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 	return 1;
 }
 
+static inline void throttle_curr_dl(struct rq *rq, struct task_struct *curr)
+{
+	curr->dl.dl_throttled = 1;
+
+	if (curr->dl.flags & SF_BWRECL_RT)
+		__setprio(rq, curr, MAX_RT_PRIO-1 - curr->rt_priority);
+	else if (curr->dl.flags & SF_BWRECL_NR)
+		__setprio(rq, curr, DEFAULT_PRIO);
+}
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -565,7 +596,7 @@ static void update_curr_dl(struct rq *rq)
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);
 		if (likely(start_dl_timer(dl_se)))
-			dl_se->dl_throttled = 1;
+			throttle_curr_dl(rq, curr);
 		else
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
@@ -765,8 +796,10 @@ static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_curr_dl(rq);
-	__dequeue_task_dl(rq, p, flags);
+	if (likely(!p->dl.dl_throttled)) {
+		update_curr_dl(rq);
+		__dequeue_task_dl(rq, p, flags);
+	}
 }
 
 /*
@@ -1000,6 +1033,9 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
+	if (unlikely(p->dl.dl_throttled))
+		return;
+
 	update_curr_dl(rq);
 	p->se.exec_start = 0;
 
-- 
1.7.2.3



-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
----------------------------------------------------------------------
Dario Faggioli, ReTiS Lab, Scuola Superiore Sant'Anna, Pisa  (Italy)

http://blog.linux.it/raistlin / raistlin@...ga.net /
dario.faggioli@...ber.org

Download attachment "signature.asc" of type "application/pgp-signature" (199 bytes)

Powered by blists - more mailing lists