[RESEND PATCH 0/3] sched/fair: some fixes for asym_packing

[RESEND PATCH 0/3] sched/fair: some fixes for asym_packing

[Vincent Guittot]

During the review of misfit task patchset, Morten and Valentin raised some
problems with the use of SD_ASYM_PACKING flag on asymmetric system like
hikey960 arm64 big/LITTLE platform. The study of the use cases has shown
some problems that can happen for every systems that use the flag.

The 3 patches fixes the problems raised for lmbench and the rt-app UC that
creates 2 tasks that start as small tasks and then become suddenly always
running tasks. (I can provide the rt-app json is needed)

- Rebase on latest tip/sched/core

Vincent Guittot (3):
  sched/fair: fix rounding issue for asym packing
  sched/fair: trigger asym_packing during idle load balance
  sched/fair: fix unnecessary increase of balance interval

 kernel/sched/fair.c | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

-- 
2.7.4

[RESEND PATCH 1/3] sched/fair: fix rounding issue for asym packing

[Vincent Guittot]

When check_asym_packing() is triggered, the imbalance is set to :
busiest_stat.avg_load * busiest_stat.group_capacity / SCHED_CAPACITY_SCALE
busiest_stat.avg_load also comes from a division and the final rounding
can make imbalance slightly lower than the weighted load of the cfs_rq.
But this is enough to skip the rq in find_busiest_queue and prevents asym
migration to happen.

Add 1 to the avg_load to make sure that the targeted cpu will not be
skipped unexpectidly.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6bd142d..0ed99ad2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7824,6 +7824,12 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	/* Adjust by relative CPU capacity of the group */
 	sgs->group_capacity = group->sgc->capacity;
 	sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
+	/*
+	 * Prevent division rounding to make the computation of imbalance
+	 * slightly less than original value and to prevent the rq to be then
+	 * selected as busiest queue
+	 */
+	sgs->avg_load += 1;
 
 	if (sgs->sum_nr_running)
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
-- 
2.7.4

[RESEND PATCH 2/3] sched/fair: trigger asym_packing during idle load balance

[Vincent Guittot]

newly idle load balance is not always triggered when a cpu becomes idle.
This prevent the scheduler to get a chance to migrate task for asym packing.
Enable active migration because of asym packing during idle load balance too.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0ed99ad2..00f2171 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8460,7 +8460,7 @@ static int need_active_balance(struct lb_env *env)
 {
 	struct sched_domain *sd = env->sd;
 
-	if (env->idle == CPU_NEWLY_IDLE) {
+	if (env->idle != CPU_NOT_IDLE) {
 
 		/*
 		 * ASYM_PACKING needs to force migrate tasks from busy but
-- 
2.7.4

[RESEND PATCH 3/3] sched/fair: fix unnecessary increase of balance interval

[Vincent Guittot]

In case of active balance, we increase the balance interval to cover
pinned tasks cases not covered by all_pinned logic. Neverthless, the active
migration triggered by asym packing should be treated as the normal
unbalanced case and reset the interval to default value otherwise active
migration for asym_packing can be easily delayed for hundreds of ms
because of this all_pinned detection mecanism.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 00f2171..4b6a226 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8456,22 +8456,32 @@ static struct rq *find_busiest_queue(struct lb_env *env,
  */
 #define MAX_PINNED_INTERVAL	512
 
-static int need_active_balance(struct lb_env *env)
+static inline bool
+asym_active_balance(enum cpu_idle_type idle, unsigned int flags, int dst, int src)
 {
-	struct sched_domain *sd = env->sd;
-
-	if (env->idle != CPU_NOT_IDLE) {
+	if (idle != CPU_NOT_IDLE) {
 
 		/*
 		 * ASYM_PACKING needs to force migrate tasks from busy but
 		 * lower priority CPUs in order to pack all tasks in the
 		 * highest priority CPUs.
 		 */
-		if ((sd->flags & SD_ASYM_PACKING) &&
-		    sched_asym_prefer(env->dst_cpu, env->src_cpu))
-			return 1;
+		if ((flags & SD_ASYM_PACKING) &&
+		    sched_asym_prefer(dst, src))
+			return true;
 	}
 
+	return false;
+}
+
+static int need_active_balance(struct lb_env *env)
+{
+	struct sched_domain *sd = env->sd;
+
+
+	if (asym_active_balance(env->idle, sd->flags, env->dst_cpu, env->src_cpu))
+		return 1;
+
 	/*
 	 * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
 	 * It's worth migrating the task if the src_cpu's capacity is reduced
@@ -8749,7 +8759,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	} else
 		sd->nr_balance_failed = 0;
 
-	if (likely(!active_balance)) {
+	if (likely(!active_balance) ||
+	    asym_active_balance(env.idle, sd->flags, env.dst_cpu, env.src_cpu)) {
 		/* We were unbalanced, so reset the balancing interval */
 		sd->balance_interval = sd->min_interval;
 	} else {
-- 
2.7.4