sched/deadline: Fixes for constrained deadline tasks

Currently, the replenishment timer is set to fire at the deadline of a task. Although that works for implicit deadline tasks because the deadline is equals to the begin of the next period, that is not correct for constrained deadline tasks (deadline < period).

For instance:

f.c:
--------------- %< ---------------
int main (void)

{
	for(;;);
}

--------------- >% ---------------

  # gcc -o f f.c

  # trace-cmd record -e sched:sched_switch                              \
   				   -e syscalls:sys_exit_sched_setattr   \
   chrt -d --sched-runtime  490000000 					\
           --sched-deadline 500000000 					\
	   --sched-period  1000000000 0 ./f

  # trace-cmd report | grep "{pid of ./f}"

After setting parameters, the task is replenished and continue running until being throttled.

         f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0

The task is throttled after running 492318 ms, as expected.

         f-11295 [003] 13322.606094: sched_switch:   f:11295 [-1] R ==> \
						   watchdog/3:32 [0]

But then, the task is replenished 500719 ms after the first replenishment:

    <idle>-0     [003] 13322.614495: sched_switch:   swapper/3:0 [120] R \
						   ==> f:11295 [-1]  

Running for 490277 ms:

         f-11295 [003] 13323.104772: sched_switch:   f:11295 [-1] R ==>  \
						   swapper/3:0 [120]

Hence, in the first period, the task runs 2 * runtime, and that is a bug.

During the first replenishment, the next deadline is set one period away. So the runtime/period starts to be respected. However, as the second replenishment took place in the wrong instant, the next replenishment will also be held in a wrong instant of time. Rather than occurring in the nth period away from the first activation, it is taking place in the (nth period - relative deadline).

Signed-off-by Daniel Bristot de Oliveira <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Juri Lelli <[email protected]>

Cc Tommaso Cucinotta <[email protected]>

Cc Luca Abeni <[email protected]>

Cc Steven Rostedt <[email protected]>

Cc [email protected]

---
 kernel/sched/deadline.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

kernel/sched/deadline.c +7 -2

index 70ef2b1..3c94d85 100644
@@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	}
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer

@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);

kernel/sched/deadline.c +5 -1

index 70ef2b1..3c94d85 100644
@@ -505,10 +505,15 @@ static void update_dl_entity(struct
 sched_dl_entity *dl_se, }
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline +
 dl_se->dl_period; +}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer

kernel/sched/deadline.c +0 -0

 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);

Hi Daniel,

On Fri, 10 Feb 2017 20:48:10 +0100
Daniel Bristot de Oliveira <[email protected]> wrote:

[...]

Quoted 22 lines

kernel/sched/deadline.c +5 -1

index 70ef2b1..3c94d85 100644
@@ -505,10 +505,15 @@ static void update_dl_entity(struct
 sched_dl_entity *dl_se, }
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline +
 dl_se->dl_period; +}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer

@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)

kernel/sched/deadline.c static int start_dl_timer(struct task_struct *p) · line 538

Quoted 5 lines

kernel/sched/deadline.c +1 -1

 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));

Looks like there is a real bug in the code, and your fix looks correct to me. I think it should be committed.

I've interpreted this as:

Reviewed-by Luca Abeni <[email protected]>

Holler if you disagree.

Quoted 2 lines · On Mon, 13 Feb 2017 12:10:25 +0100 Peter Zijlstra <[email protected]> wrote:

I've interpreted this as:

Quoted 3 lines

Reviewed-by Luca Abeni <[email protected]>

Holler if you disagree.

You can add mine too. I put in a lot of trace_printk()s and it all appears to be exactly as Daniel describes.

Reviewed-by Steven Rostedt (VMware) <[email protected]>

During the activation, CBS checks if it can reuse the current task's runtime and period. If the deadline of the task is in the past, CBS cannot use the runtime, and so it replenishes the task. This rule works fine for implicit deadline tasks (deadline == period), and the CBS was designed for implicit deadline tasks. However, a task with constrained deadline (deadine < period) might be awakened after the deadline, but before the next period. In this case, replenishing the task would allow it to run for runtime / deadline. As in this case deadline < period, CBS enables a task to run for more than the runtime/period. In a very load system, this can cause the domino effect, making other tasks to miss their deadlines.

To avoid this problem, in the activation of a constrained deadline task after the deadline but before the next period, throttle the task and set the replenishing timer to the begin of the next period, unless it is boosted.

Reproducer:

--------------- %< ---------------
int main (int argc, char **argv)

  {
	int ret;
	int flags = 0;
	unsigned long l = 0;
	struct timespec ts;
	struct sched_attr attr;

	memset(&attr, 0, sizeof(attr));
	attr.size = sizeof(attr);

	attr.sched_policy   = SCHED_DEADLINE;
	attr.sched_runtime  = 2 * 1000 * 1000;		/* 2 ms
*/ attr.sched_deadline = 2 * 1000 * 1000;		/* 2 ms */
	attr.sched_period   = 2 * 1000 * 1000 * 1000;	/* 2 s */

	ts.tv_sec = 0;
	ts.tv_nsec = 2000 * 1000;			/* 2 ms */

	ret = sched_setattr(0, &attr, flags);

	if (ret < 0) {
		perror("sched_setattr");
		exit(-1);
	}

	for(;;) {
		/* XXX: you may need to adjust the loop */
		for (l = 0; l < 150000; l++);
		/*
		 * The ideia is to go to sleep right before the
deadline
		 * and then wake up before the next period to receive
		 * a new replenishment.
		 */
		nanosleep(&ts, NULL);
	}

	exit(0);

}
--------------- >% ---------------

On my box, this reproducer uses almost 50% of the CPU time, which is obviously wrong for a task with 2/2000 reservation.

Signed-off-by Daniel Bristot de Oliveira <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Juri Lelli <[email protected]>

Cc Tommaso Cucinotta <[email protected]>

Cc Luca Abeni <[email protected]>

Cc Steven Rostedt <[email protected]>

Cc [email protected]

---
 kernel/sched/deadline.c | 44

++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+)

kernel/sched/deadline.c +1 -0

index 3c94d85..b74d40e 100644
@@ -694,6 +694,36 @@ void init_dl_task_timer(struct sched_dl_entity
 *dl_se) timer->function = dl_task_timer;
 }
 
+/* During the activation, CBS checks if it can reuse the current

task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very load system, this can cause the domino
+ * effect, making other tasks to miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) +{

kernel/sched/deadline.c +6 -0

+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+		if (unlikely(dl_se->dl_boosted

|| !start_dl_timer(p)))

kernel/sched/deadline.c +19 -0

+			return;
+		dl_se->dl_throttled = 1;
+	}
+}
+
 static
 int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 {

@@ -927,6 +957,11 @@ static void dequeue_dl_entity(struct
 sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se);
 }
 
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_runtime < dl_se->dl_period;
+}
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p,
 int flags) {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);

@@ -953,6 +988,15 @@ static void enqueue_task_dl(struct rq *rq,
 struct task_struct *p, int flags) }
 
 	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!pi_se->dl_throttled && dl_is_constrained(pi_se))
+		dl_check_constrained_dl(pi_se);
+
+	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is

on
* its rq, the bandwidth timer callback (which clearly has
not

Hi Daniel,

Quoted 6 lines · On Fri, 10 Feb 2017 20:48:11 +0100 Daniel Bristot de Oliveira…

During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS cannot use the runtime, and so it replenishes the task. This rule works fine for implicit deadline tasks (deadline == period), and the

Quoted 8 lines

CBS was designed for implicit deadline tasks. However, a task with constrained deadline (deadine < period) might be awakened after the deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case deadline < period, CBS enables a task to run for more than the runtime/period. In a very load system, this can cause the domino effect, making other tasks to miss their deadlines.

I think you are right: SCHED_DEADLINE implements the original CBS algorithm here, but uses relative deadlines different from periods in other places (while the original algorithm only considered relative deadlines equal to periods).
An this mix is dangerous... I think your fix is correct, and cures a real problem.

Both of these should be tagged for stable as well, or?

Hi Daniel,

Quoted 11 lines · On Fri, 10 Feb 2017 20:48:11 +0100 Daniel Bristot de Oliveira…

During the activation, CBS checks if it can reuse the current task's runtime and period. If the deadline of the task is in the past, CBS cannot use the runtime, and so it replenishes the task. This rule works fine for implicit deadline tasks (deadline == period), and the CBS was designed for implicit deadline tasks. However, a task with constrained deadline (deadine < period) might be awakened after the deadline, but before the next period. In this case, replenishing the task would allow it to run for runtime / deadline. As in this case deadline < period, CBS enables a task to run for more than the runtime/period. In a very load system, this can cause the domino effect, making other tasks to miss their deadlines.

I think you are right: SCHED_DEADLINE implements the original CBS algorithm here, but uses relative deadlines different from periods in other places (while the original algorithm only considered relative deadlines equal to periods).
An this mix is dangerous... I think your fix is correct, and cures a real problem.

+/* During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS

Quoted 2 lines · Daniel Bristot de Oliveira

+/* During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS

Broken comment style, fixed that for you.

kernel/sched/deadline.c static void dequeue_dl_entity(struct sched_dl_entity *dl_se) · line 964

Quoted 5 lines

kernel/sched/deadline.c +5 -0

+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_runtime < dl_se->dl_period;
+}
+

Is it ever appropriate for a dl task to have runtime == period? What purpose would that serve? Just run the task as FIFO higher than everything else.

Or was this suppose to be dl_deadline < dl_period?

Quoted 9 lines · Steven Rostedt

kernel/sched/deadline.c static void dequeue_dl_entity(struct sched_dl_entity *dl_se) · line 964

Quoted 5 lines

kernel/sched/deadline.c +5 -0

+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_runtime < dl_se->dl_period;
+}
+

Is it ever appropriate for a dl task to have runtime == period? What purpose would that serve? Just run the task as FIFO higher than everything else.

Quoted 1 line

Or was this suppose to be dl_deadline < dl_period?

Oooooops, my bad :-(, this was supposed to be dl_deadline < dl_period.