migrate_tasks() uses _pick_next_task_rt() to get tasks from the
real-time runqueue to be migrated. When rt_rq is throttled
_pick_next_task_rt() won't return anything, in which case
migrate_tasks() can't move all threads over and gets stuck in an
infinite loop.
Instead unthrottle rt_rq before migrating tasks.
Signed-off-by: Peter Boonstoppel <[email protected]>
---
kernel/sched/core.c | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9236a48..b37e0b3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5159,6 +5159,12 @@ static void migrate_tasks(unsigned int dead_cpu)
/* Ensure any throttled groups are reachable by pick_next_task */
unthrottle_offline_cfs_rqs(rq);
+ /*
+ * Ensure rt_rq is not throttled so its threads can be migrated using
+ * pick_next_task_rt
+ */
+ rq->rt.rt_throttled = 0;
+
for ( ; ; ) {
/*
* There's this thread running, bail when that's the only
--
1.7.4.1
On Fri, 2012-05-18 at 11:56 -0700, Peter Boonstoppel wrote:
> migrate_tasks() uses _pick_next_task_rt() to get tasks from the
> real-time runqueue to be migrated. When rt_rq is throttled
> _pick_next_task_rt() won't return anything, in which case
> migrate_tasks() can't move all threads over and gets stuck in an
> infinite loop.
>
> Instead unthrottle rt_rq before migrating tasks.
>
> Signed-off-by: Peter Boonstoppel <[email protected]>
> ---
> kernel/sched/core.c | 6 ++++++
> 1 files changed, 6 insertions(+), 0 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 9236a48..b37e0b3 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5159,6 +5159,12 @@ static void migrate_tasks(unsigned int dead_cpu)
> /* Ensure any throttled groups are reachable by pick_next_task */
> unthrottle_offline_cfs_rqs(rq);
>
> + /*
> + * Ensure rt_rq is not throttled so its threads can be migrated using
> + * pick_next_task_rt
> + */
> + rq->rt.rt_throttled = 0;
> +
> for ( ; ; ) {
> /*
> * There's this thread running, bail when that's the only
OK, so there's two things:
- there's a set_rq_offline() call in CPU_DYING right before calling
migrate_tasks(). This would end up calling rq_offline_rt() which should
disable all the runtime muck.
- If the above doesn't unthrottle rqs (looks like it doesn't, should
it?) you still only unthrottle the root and 'forgot' to deal with
cgroups.
So I think I'm going to ask you to make rq_offline_rt() dtrt, and while
you're at it, move unthrottle_offline_cfs_rqs() to rq_offline_fair().
migrate_tasks() uses _pick_next_task_rt() to get tasks from the
real-time runqueues to be migrated. When rt_rq is throttled
_pick_next_task_rt() won't return anything, in which case
migrate_tasks() can't move all threads over and gets stuck in an
infinite loop.
Instead unthrottle rt runqueues before migrating tasks.
Additionally: move unthrottle_offline_cfs_rqs() to rq_offline_fair()
Signed-off-by: Peter Boonstoppel <[email protected]>
---
kernel/sched/core.c | 3 ---
kernel/sched/fair.c | 7 +++++--
kernel/sched/rt.c | 1 +
kernel/sched/sched.h | 1 -
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2df035a..2e7ecff 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5221,9 +5221,6 @@ static void migrate_tasks(unsigned int dead_cpu)
*/
rq->stop = NULL;
- /* Ensure any throttled groups are reachable by pick_next_task */
- unthrottle_offline_cfs_rqs(rq);
-
for ( ; ; ) {
/*
* There's this thread running, bail when that's the only
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3704ad3..dc8341b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2057,7 +2057,7 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
hrtimer_cancel(&cfs_b->slack_timer);
}
-void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void unthrottle_offline_cfs_rqs(struct rq *rq)
{
struct cfs_rq *cfs_rq;
@@ -2111,7 +2111,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
return NULL;
}
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
-void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
#endif /* CONFIG_CFS_BANDWIDTH */
@@ -5086,6 +5086,9 @@ static void rq_online_fair(struct rq *rq)
static void rq_offline_fair(struct rq *rq)
{
update_sysctl();
+
+ /* Ensure any throttled groups are reachable by pick_next_task */
+ unthrottle_offline_cfs_rqs(rq);
}
#endif /* CONFIG_SMP */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 573e1ca..b9a94fb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -691,6 +691,7 @@ balanced:
* runtime - in which case borrowing doesn't make sense.
*/
rt_rq->rt_runtime = RUNTIME_INF;
+ rt_rq->rt_throttled = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4134d37..5d9aabe 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1167,7 +1167,6 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
-extern void unthrottle_offline_cfs_rqs(struct rq *rq);
extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
--
1.7.0.4-