From: Steven Rostedt <rostedt@goodmis.org>
To: Xunlei Pang <xlpang@126.com>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@gmail.com>,
Xunlei Pang <pang.xunlei@linaro.org>
Subject: Re: [PATCH RESEND v4 2/3] sched/rt: Fix wrong SMP scheduler behavior for equal prio cases
Date: Fri, 27 Mar 2015 11:28:04 -0400 [thread overview]
Message-ID: <20150327112804.048ba405@gandalf.local.home> (raw)
In-Reply-To: <1425886348-3191-2-git-send-email-xlpang@126.com>
On Mon, 9 Mar 2015 15:32:27 +0800
Xunlei Pang <xlpang@126.com> wrote:
> From: Xunlei Pang <pang.xunlei@linaro.org>
>
> Currently, SMP RT scheduler has some trouble in dealing with
> equal prio cases.
>
> For example, in check_preempt_equal_prio():
> When RT1(current task) gets preempted by RT2, if there is a
> migratable RT3 with same prio, RT3 will be pushed away instead
> of RT1 afterwards, because RT1 will be enqueued to the tail of
> the pushable list when going through succeeding put_prev_task_rt()
> triggered by resched. This broke FIFO.
>
> Furthermore, this is also problematic for normal preempted cases
> if there're some rt tasks queued with the same prio as current.
> Because current will be put behind these tasks in the pushable
> queue.
>
> So, if a task is running and gets preempted by a higher priority
> task (or even with same priority for migrating), this patch ensures
> that it is put ahead of any existing task with the same priority in
> the pushable queue.
>
> Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
> ---
> kernel/sched/rt.c | 23 ++++++++++++++++-------
> 1 file changed, 16 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index f4d4b07..86cd79f 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -347,11 +347,15 @@ static inline void set_post_schedule(struct rq *rq)
> rq->post_schedule = has_pushable_tasks(rq);
> }
>
> -static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
> +static void enqueue_pushable_task(struct rq *rq,
> + struct task_struct *p, bool head)
Nit.
static void
enqueue_pushable_task(struct rq *rq, struct task_struct *p, bool head)
Is a better breaking of the line.
> {
> plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
> plist_node_init(&p->pushable_tasks, p->prio);
> - plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
> + if (head)
> + plist_add_head(&p->pushable_tasks, &rq->rt.pushable_tasks);
> + else
> + plist_add_tail(&p->pushable_tasks, &rq->rt.pushable_tasks);
>
> /* Update the highest prio pushable task */
> if (p->prio < rq->rt.highest_prio.next)
> @@ -373,7 +377,8 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
>
> #else
>
> -static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
> +static inline void enqueue_pushable_task(struct rq *rq,
> + struct task_struct *p, bool head)
Same here.
> {
> }
>
> @@ -1248,7 +1253,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
> enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
>
> if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
> - enqueue_pushable_task(rq, p);
> + enqueue_pushable_task(rq, p, false);
> }
>
> static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
> @@ -1494,8 +1499,12 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
> * The previous task needs to be made eligible for pushing
> * if it is still active
> */
> - if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
> - enqueue_pushable_task(rq, p);
> + if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) {
> + if (task_running(rq, p) && (preempt_count() & PREEMPT_ACTIVE))
put_prev_task_rt() is called by put_prev_task() which is called by
several functions: rt_mutex_setprio(), __sched_setscheduler(),
sched_setnuma(), migrate_tasks(), and sched_move_task(). It's not part
of being preempted.
Now it is also called by pick_next_task_rt() which I'm assuming is what
you want it to affect.
The above definitely needs a comment about what it is doing. Also, I'm
not so sure we care about testing task_running(). I'm thinking the
check for PREEMPT_ACTIVE is good enough, as that would only be set from
being called within preempt_schedule().
Also, we could get rid of the if statement and do:
enqueue_pushable_task(rq, p, !!(preempt_count() & PREEMPT_ACTIVE));
-- Steve
> + enqueue_pushable_task(rq, p, true);
> + else
> + enqueue_pushable_task(rq, p, false);
> + }
> }
>
> #ifdef CONFIG_SMP
> @@ -1914,7 +1923,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
> rq->rt.rt_nr_migratory--;
> } else {
> if (!task_current(rq, p))
> - enqueue_pushable_task(rq, p);
> + enqueue_pushable_task(rq, p, false);
> rq->rt.rt_nr_migratory++;
> }
>
next prev parent reply other threads:[~2015-03-27 15:28 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-09 7:32 [PATCH RESEND v4 1/3] lib/plist: Provide plist_add_head() for nodes with the same prio Xunlei Pang
2015-03-09 7:32 ` [PATCH RESEND v4 2/3] sched/rt: Fix wrong SMP scheduler behavior for equal prio cases Xunlei Pang
2015-03-27 14:39 ` Xunlei Pang
2015-03-27 15:28 ` Steven Rostedt [this message]
2015-04-01 2:41 ` Xunlei Pang
2015-03-09 7:32 ` [PATCH RESEND v4 3/3] sched/rt: Check to push the task when changing its affinity Xunlei Pang
2015-03-11 1:27 ` [PATCH RESEND v4 1/3] lib/plist: Provide plist_add_head() for nodes with the same prio Dan Streetman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20150327112804.048ba405@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=juri.lelli@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pang.xunlei@linaro.org \
--cc=peterz@infradead.org \
--cc=xlpang@126.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®