summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2016-03-09 13:04:03 +0100
committerIngo Molnar <mingo@kernel.org>2016-03-21 10:49:23 +0100
commit3a47d5124a957358274e9ca7b115b2f3a914f56d (patch)
treeb657610dfb56fde7cd808981068bdeb0d3322eb7 /kernel
parent2f5177f0fd7e531b26d54633be62d1d4cb94621c (diff)
downloadlinux-3a47d5124a957358274e9ca7b115b2f3a914f56d.tar.bz2
sched/fair: Fix fairness issue on migration
Pavan reported that in the presence of very light tasks (or cgroups) the placement of migrated tasks can cause severe fairness issues. The problem is that enqueue_entity() places the task before it updates time, thereby it can place the task far in the past (remember that light tasks will shoot virtual time forward at a high speed, so in relation to the pre-existing light task, we can land far in the past). This is done because update_curr() needs the current task, and we might be placing the current task. The obvious solution is to differentiate between the current and any other task; placing the current before we update time, and placing any other task after, such that !curr tasks end up at the current moment in time, and not in the past. Reported-by: Pavan Kondeti <pkondeti@codeaurora.org> Tested-by: Pavan Kondeti <pkondeti@codeaurora.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ben Segall <bsegall@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: byungchul.park@lge.com Link: http://lkml.kernel.org/r/20160309120403.GK6344@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/fair.c20
1 files changed, 14 insertions, 6 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 33130529e9b5..3c114d971d84 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3157,17 +3157,25 @@ 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;
+
/*
- * Update the normalized vruntime before updating min_vruntime
- * through calling update_curr().
+ * If we're the current task, we must renormalise before calling
+ * update_curr().
*/
- if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
+ if (renorm && curr)
se->vruntime += cfs_rq->min_vruntime;
+ update_curr(cfs_rq);
+
/*
- * Update run-time statistics of the 'current'.
+ * Otherwise, renormalise after, such that we're placed at the current
+ * moment in time, instead of some random moment in the past.
*/
- update_curr(cfs_rq);
+ if (renorm && !curr)
+ se->vruntime += cfs_rq->min_vruntime;
+
enqueue_entity_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
update_cfs_shares(cfs_rq);
@@ -3183,7 +3191,7 @@ 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 (se != cfs_rq->curr)
+ if (!curr)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;