[RFC tg_shares_up improvements - v1 11/12] sched: update tg->shares after cpu.shares write

[pjt]

Formerly sched_group_set_shares would force a rebalance by overflowing domain
share sums.  Now that per-cpu averages are maintained we can set the true value
by issuing an update_cfs_shares() following a tg->shares update.

Also initialize tg se->load to 0 for consistency since we'll now set correct
weights on enqueue.

Signed-off-by: Paul Turner <pjt@xxxxxxxxxx?>

---
 kernel/sched.c |   42 +++++++++++-------------------------------
 1 file changed, 11 insertions(+), 31 deletions(-)

Index: kernel/sched.c
===================================================================
--- kernel/sched.c.orig
+++ kernel/sched.c
@@ -7575,7 +7575,7 @@ static void init_tg_cfs_entry(struct tas
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	update_load_set(&se->load, tg->shares);
+	update_load_set(&se->load, 0);
 	se->parent = parent;
 }
 #endif
@@ -8194,37 +8194,12 @@ void sched_move_task(struct task_struct 
 #endif /* CONFIG_CGROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void __set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-	struct cfs_rq *cfs_rq = se->cfs_rq;
-	int on_rq;
-
-	on_rq = se->on_rq;
-	if (on_rq)
-		dequeue_entity(cfs_rq, se, 0);
-
-	update_load_set(&se->load, shares);
-
-	if (on_rq)
-		enqueue_entity(cfs_rq, se, 0);
-}
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-	struct cfs_rq *cfs_rq = se->cfs_rq;
-	struct rq *rq = cfs_rq->rq;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	__set_se_shares(se, shares);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
 static DEFINE_MUTEX(shares_mutex);
 
 int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 {
 	int i;
+	unsigned long flags;
 
 	/*
 	 * We can't change the weight of the root cgroup.
@@ -8243,10 +8218,15 @@ int sched_group_set_shares(struct task_g
 
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
-		/*
-		 * force a rebalance
-		 */
-		set_se_shares(tg->se[i], shares);
+		struct rq *rq = cpu_rq(i);
+		struct sched_entity *se;
+
+		se = tg->se[i];
+		/* Propagate contribution to hierarchy */
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		for_each_sched_entity(se)
+			update_cfs_shares(group_cfs_rq(se), 0);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
 done:

-- 

--
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/