Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1580012
| From | Daniel Bristot de Oliveira <bristot@redhat.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline |
| Date | 2017-02-13 20:10 +0100 |
| Message-ID | <tauaD-7Oj-41@gated-at.bofh.it> (permalink) |
| References | <tauaC-7Oj-13@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
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 <bristot@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: linux-kernel@vger.kernel.org
---
kernel/sched/deadline.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 45 insertions(+)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3c94d85..3a88def 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -694,6 +694,37 @@ 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)
+{
+ 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)))
+ return;
+ dl_se->dl_throttled = 1;
+ }
+}
+
static
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
@@ -927,6 +958,11 @@ 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_deadline < 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 +989,15 @@ 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
--
2.9.3
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH V2 0/2] sched/deadline: Fixes for constrained deadline tasks Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
[PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it> - 2017-02-14 18:00 +0100
Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-14 18:40 +0100
Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline Steven Rostedt <rostedt@goodmis.org> - 2017-02-14 20:40 +0100
[PATCH V2 1/2] sched/deadline: Replenishment timer should fire in the next period Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
[PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow "Steven Rostedt (VMware)" <rostedt@goodmis.org> - 2017-02-14 20:30 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow luca abeni <luca.abeni@santannapisa.it> - 2017-02-14 23:50 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-15 01:20 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 08:50 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 11:30 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Peter Zijlstra <peterz@infradead.org> - 2017-02-15 12:40 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 13:40 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 14:00 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 14:20 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 15:20 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-15 14:40 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-15 14:50 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-15 15:10 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 15:20 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it> - 2017-02-16 17:40 +0100
Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-16 17:50 +0100
csiph-web