From a47a00dbf7793db63404d2b1569d0b40fa3ae21a Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Fri, 18 Oct 2019 15:26:33 +0200
Subject: [PATCH] sched/fair: Use load instead of runnable load in
load_balance()
References: bnc#1155798 (CPU scheduler functional and performance backports)
Patch-mainline: v5.5-rc1
Git-commit: b0fb1eb4f04ae4768231b9731efb1134e22053a4
'runnable load' was originally introduced to take into account the case
where blocked load biases the load balance decision which was selecting
underutilized groups with huge blocked load whereas other groups were
overloaded.
The load is now only used when groups are overloaded. In this case,
it's worth being conservative and taking into account the sleeping
tasks that might wake up on the CPU.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: hdanton@sina.com
Cc: parth@linux.ibm.com
Cc: pauld@redhat.com
Cc: quentin.perret@arm.com
Cc: riel@surriel.com
Cc: srikar@linux.vnet.ibm.com
Cc: valentin.schneider@arm.com
Link: https://lkml.kernel.org/r/1571405198-27570-7-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/fair.c | 24 ++++++++++++++----------
1 file changed, 14 insertions(+), 10 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b8d4c755b8c5..c00c19b4790d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5391,6 +5391,11 @@ static unsigned long cpu_runnable_load(struct rq *rq)
return cfs_rq_runnable_load_avg(&rq->cfs);
}
+static unsigned long cpu_load(struct rq *rq)
+{
+ return cfs_rq_load_avg(&rq->cfs);
+}
+
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
@@ -8074,7 +8079,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false))
env->flags |= LBF_NOHZ_AGAIN;
- sgs->group_load += cpu_runnable_load(rq);
+ sgs->group_load += cpu_load(rq);
sgs->group_util += cpu_util(i);
sgs->sum_h_nr_running += rq->cfs.h_nr_running;
@@ -8532,7 +8537,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
init_sd_lb_stats(&sds);
/*
- * Compute the various statistics relavent for load balancing at
+ * Compute the various statistics relevant for load balancing at
* this level.
*/
update_sd_lb_stats(env, &sds);
@@ -8692,11 +8697,10 @@ static struct rq *find_busiest_queue(struct lb_env *env,
switch (env->migration_type) {
case migrate_load:
/*
- * When comparing with load imbalance, use
- * cpu_runnable_load() which is not scaled with the CPU
- * capacity.
+ * When comparing with load imbalance, use cpu_load()
+ * which is not scaled with the CPU capacity.
*/
- load = cpu_runnable_load(rq);
+ load = cpu_load(rq);
if (nr_running == 1 && load > env->imbalance &&
!check_cpu_capacity(rq, env->sd))
@@ -8704,10 +8708,10 @@ static struct rq *find_busiest_queue(struct lb_env *env,
/*
* For the load comparisons with the other CPUs,
- * consider the cpu_runnable_load() scaled with the CPU
- * capacity, so that the load can be moved away from
- * the CPU that is potentially running at a lower
- * capacity.
+ * consider the cpu_load() scaled with the CPU
+ * capacity, so that the load can be moved away
+ * from the CPU that is potentially running at a
+ * lower capacity.
*
* Thus we're looking for max(load_i / capacity_i),
* crosswise multiplication to rid ourselves of the