Add accounting to track cases that runtime isn't running
out, and export the information in "/proc/<pid>/sched".
Specifically, the patch adds three members "nr_underrun_sched",
"nr_underrun_block", and "nr_underrun_yield" in sched_dl_entity:
-@nr_underrun_sched hints some scheduling issue.
-@nr_underrun_block hints some block reason. E.g. long sleep.
-@nr_underrun_yield hints the yield reason.
This is helpful to spot/debug deadline issues, for example,
I launched three 50% dl tasks on my dual-core machine, plus
several buggy contrained dl tasks that Daniel is trying to
address in "sched/deadline: Use the revised wakeup rule for
suspending constrained dl tasks", then I observed one 50%
deadline task's proc sched output:
$ cat /proc/3389/sched |grep underrun
dl.nr_underrun_sched : 981
dl.nr_underrun_block : 0
dl.nr_underrun_yield : 0
Very large "dl.nr_underrun_sched" hints it's very likely that
there is some underlying scheduling issue.
Note that we don't use CONFIG_SCHED_DEBUG as the accounting
added has little overhead(also happens infrequently).
Suggested-by: Steven Rostedt <rost...@goodmis.org>
Signed-off-by: Xunlei Pang <xlp...@redhat.com>
---
include/linux/sched.h | 10 ++++++++++
kernel/sched/core.c | 3 +++
kernel/sched/deadline.c | 12 +++++++++---
kernel/sched/debug.c | 3 +++
4 files changed, 25 insertions(+), 3 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ba080e5..e17928f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -455,6 +455,16 @@ struct sched_dl_entity {
* own bandwidth to be enforced, thus we need one timer per task.
*/
struct hrtimer dl_timer;
+
+ /*
+ * Accounting for periods that run less than @dl_runtime:
+ * @nr_underrun_sched hints some scheduling issue.
+ * @nr_underrun_block hints some block reason. E.g. long sleep.
+ * @nr_underrun_yield hints the yield reason.
+ */
+ u64 nr_underrun_sched;
+ u64 nr_underrun_block;
+ u64 nr_underrun_yield;
};
union rcu_special {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bccd819..6214ada 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4004,6 +4004,9 @@ static struct task_struct *find_process_by_pid(pid_t pid)
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
dl_se->flags = attr->sched_flags;
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->nr_underrun_sched = 0;
+ dl_se->nr_underrun_block = 0;
+ dl_se->nr_underrun_yield = 0;
/*
* Changing the parameters of a task is 'tricky' and we're not doing
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5691149..a7ddc03 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -394,8 +394,10 @@ static void replenish_dl_entity(struct sched_dl_entity
*dl_se,
dl_se->runtime = pi_se->dl_runtime;
}
- if (dl_se->dl_yielded && dl_se->runtime > 0)
+ if (dl_se->dl_yielded && dl_se->runtime > 0) {
dl_se->runtime = 0;
+ ++dl_se->nr_underrun_yield;
+ }
/*
* We keep moving the deadline away until we get some
@@ -723,8 +725,10 @@ static inline void dl_check_constrained_dl(struct
sched_dl_entity *dl_se)
if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
return;
dl_se->dl_throttled = 1;
- if (dl_se->runtime > 0)
+ if (dl_se->runtime > 0) {
dl_se->runtime = 0;
+ ++dl_se->nr_underrun_block;
+ }
}
}
@@ -733,8 +737,10 @@ int dl_runtime_exceeded(struct rq *rq, struct
sched_dl_entity *dl_se)
{
bool dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
- if (dmiss && dl_se->runtime > 0)
+ if (dmiss && dl_se->runtime > 0) {
dl_se->runtime = 0;
+ ++dl_se->nr_underrun_sched;
+ }
return (dl_se->runtime <= 0);
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 38f0193..904b43f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -957,6 +957,9 @@ void proc_sched_show_task(struct task_struct *p, struct
seq_file *m)
if (p->policy == SCHED_DEADLINE) {
P(dl.runtime);
P(dl.deadline);
+ P(dl.nr_underrun_sched);
+ P(dl.nr_underrun_block);
+ P(dl.nr_underrun_yield);
}
#undef PN_SCHEDSTAT
#undef PN
--
1.8.3.1
