Skip to contentSkip to conversation

scheduler fix

GIT PULL Ingo Molnar 1 participant 1 message May 13, 2016 Scheduler

lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 53d3bc773eaa7ab1cf63585e76af7ee869d5e709 Revert "sched/fair: Fix fairness issue on migration"

This is a revert to fix an interactivity problem. The proper fixes for the problems that the reverted commit exposed are now in sched/core (consisting of 3 patches), but were too risky for v4.6 and will arrive in the v4.7 merge window.

Thanks,

Ingo

------------------>
Ingo Molnar (1):
Revert "sched/fair: Fix fairness issue on migration"

 kernel/sched/fair.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)
kernel/sched/fair.c +6 -14
index 40748dc8ea3e..e7dd0ec169be 100644
@@ -3188,25 +3188,17 @@ static inline void check_schedstat_required(void)
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING);
-	bool curr = cfs_rq->curr == se;
-
 	/*
-	 * If we're the current task, we must renormalise before calling
-	 * update_curr().
+	 * Update the normalized vruntime before updating min_vruntime
+	 * through calling update_curr().
 	 */
-	if (renorm && curr)
+	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;
 
-	update_curr(cfs_rq);
-
 	/*
-	 * Otherwise, renormalise after, such that we're placed at the current
-	 * moment in time, instead of some random moment in the past.
+	 * Update run-time statistics of the 'current'.
 	 */
-	if (renorm && !curr)
-		se->vruntime += cfs_rq->min_vruntime;
-
+	update_curr(cfs_rq);
 	enqueue_entity_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
@@ -3222,7 +3214,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		update_stats_enqueue(cfs_rq, se);
 		check_spread(cfs_rq, se);
 	}
-	if (!curr)
+	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;