[tip: sched/core] sched: Allow newidle balancing to bail out of load_balance

[tip-bot2 for Josh Don]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     792b9f65a568f48c50b3175536db9cde5a1edcc0
Gitweb:        https://git.kernel.org/tip/792b9f65a568f48c50b3175536db9cde5a1edcc0
Author:        Josh Don <joshdon@xxxxxxxxxx>
AuthorDate:    Wed, 08 Jun 2022 19:55:15 -07:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Mon, 13 Jun 2022 10:30:01 +02:00

sched: Allow newidle balancing to bail out of load_balance

While doing newidle load balancing, it is possible for new tasks to
arrive, such as with pending wakeups. newidle_balance() already accounts
for this by exiting the sched_domain load_balance() iteration if it
detects these cases. This is very important for minimizing wakeup
latency.

However, if we are already in load_balance(), we may stay there for a
while before returning back to newidle_balance(). This is most
exacerbated if we enter a 'goto redo' loop in the LBF_ALL_PINNED case. A
very straightforward workaround to this is to adjust should_we_balance()
to bail out if we're doing a CPU_NEWLY_IDLE balance and new tasks are
detected.

This was tested with the following reproduction:
- two threads that take turns sleeping and waking each other up are
  affined to two cores
- a large number of threads with 100% utilization are pinned to all
  other cores

Without this patch, wakeup latency was ~120us for the pair of threads,
almost entirely spent in load_balance(). With this patch, wakeup latency
is ~6us.

Signed-off-by: Josh Don <joshdon@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20220609025515.2086253-1-joshdon@xxxxxxxxxx
---
 kernel/sched/fair.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7d8ef01..8bed757 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9824,9 +9824,15 @@ static int should_we_balance(struct lb_env *env)
 	/*
 	 * In the newly idle case, we will allow all the CPUs
 	 * to do the newly idle load balance.
+	 *
+	 * However, we bail out if we already have tasks or a wakeup pending,
+	 * to optimize wakeup latency.
 	 */
-	if (env->idle == CPU_NEWLY_IDLE)
+	if (env->idle == CPU_NEWLY_IDLE) {
+		if (env->dst_rq->nr_running > 0 || env->dst_rq->ttwu_pending)
+			return 0;
 		return 1;
+	}
 
 	/* Try to find first idle CPU */
 	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {