Re: A strange behavior of sched_fair

[Kei Tokunaga]

Ingo Molnar wrote, (2008/02/29 14:42):
> * Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> wrote:
>
> > > Seems the vruntime doesn't get re-set if you move tasks between 
> > > groups. sched_move_task() should call place_entity() in the context 
> > > of the new cfs_rq.
> > This should do I guess - uncompiled, untested
>
> if someone tests it and if it solves the problem i'll apply it to the 
> scheduler tree.

Hi Ingo, Peter,

Thanks for the patch, Peter.  I modified it a bit to compile and
confirmed the issue did not occur on my ia64 box.  I am attaching
the revised patch below.

Thanks,
Kei


Subject: sched: fair-group: fixup tasks on group move

Tasks would retain their old vruntime when moved between groups, this
can cause funny lags. Re-set the vruntime on group move to fit within
the new tree.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>


---

 linux-2.6.25-rc3-cgroup-kei/include/linux/sched.h |    4 ++++
 linux-2.6.25-rc3-cgroup-kei/kernel/sched.c        |    3 +++
 linux-2.6.25-rc3-cgroup-kei/kernel/sched_fair.c   |   14 ++++++++++++++
 3 files changed, 21 insertions(+)

diff -puN include/linux/sched.h~sched_fair include/linux/sched.h
--- linux-2.6.25-rc3-cgroup/include/linux/sched.h~sched_fair	2008-02-29 12:26:47.000000000 -0500
+++ linux-2.6.25-rc3-cgroup-kei/include/linux/sched.h	2008-02-29 12:26:47.000000000 -0500
@@ -898,6 +898,10 @@ struct sched_class {
 			     int running);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
 			     int oldprio, int running);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	void (*moved_group) (struct task_struct *p);
+#endif
 };

 struct load_weight {
diff -puN kernel/sched.c~sched_fair kernel/sched.c
--- linux-2.6.25-rc3-cgroup/kernel/sched.c~sched_fair	2008-02-29 12:26:47.000000000 -0500
+++ linux-2.6.25-rc3-cgroup-kei/kernel/sched.c	2008-02-29 12:26:47.000000000 -0500
@@ -7825,6 +7825,9 @@ void sched_move_task(struct task_struct

 	set_task_rq(tsk, task_cpu(tsk));

+	if (tsk->sched_class->moved_group)
+		tsk->sched_class->moved_group(tsk);
+
 	if (on_rq) {
 		if (unlikely(running))
 			tsk->sched_class->set_curr_task(rq);
diff -puN kernel/sched_fair.c~sched_fair kernel/sched_fair.c
--- linux-2.6.25-rc3-cgroup/kernel/sched_fair.c~sched_fair	2008-02-29 12:26:47.000000000 -0500
+++ linux-2.6.25-rc3-cgroup-kei/kernel/sched_fair.c	2008-02-29 13:49:15.000000000 -0500
@@ -1403,6 +1403,16 @@ static void set_curr_task_fair(struct rq
 		set_next_entity(cfs_rq_of(se), se);
 }

+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void moved_group_fair(struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+	update_curr(cfs_rq);
+	place_entity(cfs_rq, &p->se, 1);
+}
+#endif
+
 /*
  * All the scheduling class methods:
  */
@@ -1431,6 +1441,10 @@ static const struct sched_class fair_sch

 	.prio_changed		= prio_changed_fair,
 	.switched_to		= switched_to_fair,
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	.moved_group		= moved_group_fair,
+#endif
 };

 #ifdef CONFIG_SCHED_DEBUG

_



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/