When enable sched_stat_wait trace_point, some rt tasks sched latency so long, like this,
sched_stat_wait: comm=rcu_preempt pid=14 delay=4936139545261 [ns]
Rt task has low latency, it must have a bug. When rt task balance off source cpu,
dequeue operation not update the sched_statistics, so follow update_stats_wait_end_fair
update method, so do dl tasks.
Fixes: 57a5c2dafca8 ("sched/rt: Support schedstats for RT sched class")
Fixes: b5eb4a5f6521 ("sched/dl: Support schedstats for deadline sched class")
Signed-off-by: Junwen Wu <[email protected]>
---
kernel/sched/deadline.c | 8 +++++++-
kernel/sched/rt.c | 7 +++++++
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b28114478b82..29223163ee22 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1558,10 +1558,16 @@ update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
int flags)
{
struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
if (!schedstat_enabled())
return;
-
+ /*
+ * Mark the end of the wait period
+ * if dequeueing a waiting task.
+ */
+ if (p && (p != rq->curr))
+ update_stats_wait_end_dl(dl_rq, dl_se);
if ((flags & DEQUEUE_SLEEP)) {
unsigned int state;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6aaf0a3d6081..6a2600213991 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1360,12 +1360,19 @@ update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
int flags)
{
struct task_struct *p = NULL;
+ struct rq *rq = rq_of_rt_se(rt_se);
if (!schedstat_enabled())
return;
if (rt_entity_is_task(rt_se))
p = rt_task_of(rt_se);
+ /*
+ * Mark the end of the wait period
+ * if dequeueing a waiting task.
+ */
+ if (p && (p != rq->curr))
+ update_stats_wait_end_rt(rt_rq, rt_se);
if ((flags & DEQUEUE_SLEEP) && p) {
unsigned int state;
--
2.34.1
Hi Junwen
s/trace_point/tracepoint/g
On 1/1/24 04:17, Junwen Wu wrote:
> When enable sched_stat_wait trace_point, some rt tasks sched latency so long, like this,
> sched_stat_wait: comm=rcu_preempt pid=14 delay=4936139545261 [ns]
> Rt task has low latency, it must have a bug. When rt task balance off source cpu,
> dequeue operation not update the sched_statistics, so follow update_stats_wait_end_fair
> update method, so do dl tasks.
This is a little bit hard to read, how about something like this?
The sched_stat_wait tracepoint is showing unreasonably long
latencies for real-time tasks. For example:
sched_stat_wait: comm=rcu_preempt pid=14 delay=4936139545261 [ns]
This error happens when the rt task balances off the source CPU because
the dequeue operation is not updating the sched_statistics. So, follow
update_stats_wait_end_fair() and update the stats. Do the same for
SCHED_DEADLINE.
[ feel free to change ]
>
> Fixes: 57a5c2dafca8 ("sched/rt: Support schedstats for RT sched class")
> Fixes: b5eb4a5f6521 ("sched/dl: Support schedstats for deadline sched class")
> Signed-off-by: Junwen Wu <[email protected]>
> ---
> kernel/sched/deadline.c | 8 +++++++-
> kernel/sched/rt.c | 7 +++++++
> 2 files changed, 14 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index b28114478b82..29223163ee22 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1558,10 +1558,16 @@ update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
> int flags)
> {
> struct task_struct *p = dl_task_of(dl_se);
> + struct rq *rq = rq_of_dl_rq(dl_rq);
>
> if (!schedstat_enabled())
> return;
> -
> + /*
> + * Mark the end of the wait period
> + * if dequeueing a waiting task.
> + */
make this a single line comment.
> + if (p && (p != rq->curr))
> + update_stats_wait_end_dl(dl_rq, dl_se);
> if ((flags & DEQUEUE_SLEEP)) {
> unsigned int state;
>
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 6aaf0a3d6081..6a2600213991 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -1360,12 +1360,19 @@ update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
> int flags)
> {
> struct task_struct *p = NULL;
> + struct rq *rq = rq_of_rt_se(rt_se);
>
> if (!schedstat_enabled())
> return;
>
> if (rt_entity_is_task(rt_se))
> p = rt_task_of(rt_se);
> + /*
> + * Mark the end of the wait period
> + * if dequeueing a waiting task.
> + */
ditto
-- Daniel
>This error happens when the rt task balances off the source CPU because
>the dequeue operation is not updating the sched_statistics. So, follow
>update_stats_wait_end_fair() and update the stats. Do the same for
>SCHED_DEADLINE.
>[ feel free to change ]
ok
>> + /*
>> + * Mark the end of the wait period
>> + * if dequeueing a waiting task.
>> + */
>make this a single line comment.
ok
--
Best regards