[PATCH 5.12 112/178] sched/fair: Correctly insert cfs_rqs to list on unthrottle

From: Greg Kroah-Hartman
Date: Mon Jun 21 2021 - 12:48:00 EST


From: Odin Ugedal <odin@xxxxxxx>

[ Upstream commit a7b359fc6a37faaf472125867c8dc5a068c90982 ]

Fix an issue where fairness is decreased since cfs_rq's can end up not
being decayed properly. For two sibling control groups with the same
priority, this can often lead to a load ratio of 99/1 (!!).

This happens because when a cfs_rq is throttled, all the descendant
cfs_rq's will be removed from the leaf list. When they initial cfs_rq
is unthrottled, it will currently only re add descendant cfs_rq's if
they have one or more entities enqueued. This is not a perfect
heuristic.

Instead, we insert all cfs_rq's that contain one or more enqueued
entities, or it its load is not completely decayed.

Can often lead to situations like this for equally weighted control
groups:

$ ps u -C stress
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 10009 88.8 0.0 3676 100 pts/1 R+ 11:04 0:13 stress --cpu 1
root 10023 3.0 0.0 3676 104 pts/1 R+ 11:04 0:00 stress --cpu 1

Fixes: 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()")
[vingo: !SMP build fix]
Signed-off-by: Odin Ugedal <odin@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20210612112815.61678-1-odin@xxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
kernel/sched/fair.c | 44 +++++++++++++++++++++++++-------------------
1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 47fcc3fe9dc5..56e2334fe66b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3293,6 +3293,24 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)

#ifdef CONFIG_SMP
#ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+ if (cfs_rq->load.weight)
+ return false;
+
+ if (cfs_rq->avg.load_sum)
+ return false;
+
+ if (cfs_rq->avg.util_sum)
+ return false;
+
+ if (cfs_rq->avg.runnable_sum)
+ return false;
+
+ return true;
+}
+
/**
* update_tg_load_avg - update the tg's load avg
* @cfs_rq: the cfs_rq whose avg changed
@@ -4086,6 +4104,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)

#else /* CONFIG_SMP */

+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+ return true;
+}
+
#define UPDATE_TG 0x0
#define SKIP_AGE_LOAD 0x0
#define DO_ATTACH 0x0
@@ -4744,8 +4767,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
cfs_rq->throttled_clock_task;

- /* Add cfs_rq with already running entity in the list */
- if (cfs_rq->nr_running >= 1)
+ /* Add cfs_rq with load or one or more already running entities to the list */
+ if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
list_add_leaf_cfs_rq(cfs_rq);
}

@@ -7972,23 +7995,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)

#ifdef CONFIG_FAIR_GROUP_SCHED

-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
- if (cfs_rq->load.weight)
- return false;
-
- if (cfs_rq->avg.load_sum)
- return false;
-
- if (cfs_rq->avg.util_sum)
- return false;
-
- if (cfs_rq->avg.runnable_sum)
- return false;
-
- return true;
-}
-
static bool __update_blocked_fair(struct rq *rq, bool *done)
{
struct cfs_rq *cfs_rq, *pos;
--
2.30.2