[patch 13/16] sched: update_cfs_shares at period edge

From: pjt
Date: Thu Aug 23 2012 - 10:16:52 EST


From: Paul Turner <pjt@xxxxxxxxxx>

Now that our measurement intervals are small (~1ms) we can amortize the posting
of update_shares() to be about each period overflow. This is a large cost
saving for frequently switching tasks.

Signed-off-by: Paul Turner <pjt@xxxxxxxxxx>
Reviewed-by: Ben Segall <bsegall@xxxxxxxxxx>
---
kernel/sched/fair.c | 18 ++++++++++--------
1 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 44cd4be..12e9ae5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1181,6 +1181,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
}

__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
+ update_cfs_shares(cfs_rq);
}

static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
@@ -1390,9 +1391,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
- enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
account_entity_enqueue(cfs_rq, se);
- update_cfs_shares(cfs_rq);
+ enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);

if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
@@ -1465,7 +1465,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
- dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);

update_stats_dequeue(cfs_rq, se);
if (flags & DEQUEUE_SLEEP) {
@@ -1485,8 +1484,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
- se->on_rq = 0;
account_entity_dequeue(cfs_rq, se);
+ dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);

/*
* Normalize the entity after updating the min_vruntime because the
@@ -1500,7 +1499,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
return_cfs_rq_runtime(cfs_rq);

update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq);
+ se->on_rq = 0;
}

/*
@@ -2512,8 +2511,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;

- update_cfs_shares(cfs_rq);
update_entity_load_avg(se, 1);
+ update_cfs_rq_blocked_load(cfs_rq, 0);
}

if (!se) {
@@ -2573,8 +2572,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;

- update_cfs_shares(cfs_rq);
update_entity_load_avg(se, 1);
+ update_cfs_rq_blocked_load(cfs_rq, 0);
}

if (!se) {
@@ -5620,8 +5619,11 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
se = tg->se[i];
/* Propagate contribution to hierarchy */
raw_spin_lock_irqsave(&rq->lock, flags);
- for_each_sched_entity(se)
+ for_each_sched_entity(se) {
update_cfs_shares(group_cfs_rq(se));
+ /* update contribution to parent */
+ update_entity_load_avg(se, 1);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}



--
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/