We kill rq->rd on the CPU_DOWN_PREPARE stage:
cpuset_cpu_inactive -> cpuset_update_active_cpus ->
partition_sched_domains ->
-> cpu_attach_domain -> rq_attach_root -> set_rq_offline
This unthrottles all throttled cfs_rqs.
But the cpu is still able to call schedule() till
take_cpu_down->__cpu_disable()
is called from stop_machine.
This case the tasks from just unthrottled cfs_rqs are pickable
in a standard scheduler way, and they are picked by dying cpu.
The cfs_rqs becomes throttled again, and migrate_tasks()
in migration_call skips their tasks (one more unthrottle
in migrate_tasks()->CPU_DYING does not happen, because rq->rd
is already NULL).
Patch sets runtime_enabled to zero. This guarantees, the runtime
is not accounted, and the cfs_rqs won't exceed given
cfs_rq->runtime_remaining = 1, and tasks will be pickable
in migrate_tasks(). runtime_enabled is recalculated again
when rq becomes online again.
Signed-off-by: Kirill Tkhai <[email protected]>
CC: Srikar Dronamraju <[email protected]>
CC: Mike Galbraith <[email protected]>
CC: Peter Zijlstra <[email protected]>
CC: Ingo Molnar <[email protected]>
---
kernel/sched/fair.c | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fea7d33..f120525 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3775,6 +3775,19 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth
*cfs_b)
hrtimer_cancel(&cfs_b->slack_timer);
}
+static void __maybe_unused update_runtime_enabled(struct rq *rq)
+{
+ struct cfs_rq *cfs_rq;
+
+ for_each_leaf_cfs_rq(rq, cfs_rq) {
+ struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+
+ raw_spin_lock(&cfs_b->lock);
+ cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
+ raw_spin_unlock(&cfs_b->lock);
+ }
+}
+
static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
{
struct cfs_rq *cfs_rq;
@@ -3790,6 +3803,12 @@ static void __maybe_unused
unthrottle_offline_cfs_rqs(struct rq *rq)
cfs_rq->runtime_remaining = 1;
if (cfs_rq_throttled(cfs_rq))
unthrottle_cfs_rq(cfs_rq);
+
+ /*
+ * Offline rq is schedulable till cpu is completely disabled
+ * in take_cpu_down(), so we prevent new cfs throttling here.
+ */
+ cfs_rq->runtime_enabled = 0;
}
}
@@ -3831,6 +3850,7 @@ 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) {}
+static inline void update_runtime_enabled(struct rq *rq) {}
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
#endif /* CONFIG_CFS_BANDWIDTH */
@@ -7325,6 +7345,8 @@ void trigger_load_balance(struct rq *rq)
static void rq_online_fair(struct rq *rq)
{
update_sysctl();
+
+ update_runtime_enabled(rq);
}
static void rq_offline_fair(struct rq *rq)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
