Received-SPF: pass (google.com: domain of linux-kernel+bounces-112534-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Qais Yousef <qyousef@layalina.io>
To: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: linux-kernel@vger.kernel.org,
	"Pierre Gondois" <Pierre.Gondois@arm.com>,
	Qais Yousef <qyousef@layalina.io>
Subject: [PATCH v8 4/4] sched/fair: Don't double balance_interval for migrate_misfit
Date: Sun, 24 Mar 2024 00:45:52 +0000
Message-Id: <20240324004552.999936-5-qyousef@layalina.io>
In-Reply-To: <20240324004552.999936-1-qyousef@layalina.io>
References: <20240324004552.999936-1-qyousef@layalina.io>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

It is not necessarily an indication of the system being busy and
requires a backoff of the load balancer activities. But pushing it high
could mean generally delaying other misfit activities or other type of
imbalances.

Also don't pollute nr_balance_failed because of misfit failures. The
value is used for enabling cache hot migration and in migrate_util/load
types. None of which should be impacted (skewed) by misfit failures.

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Qais Yousef <qyousef@layalina.io>
---
 kernel/sched/fair.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3b88cf58fb45..18da54da48a5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11443,8 +11443,12 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 		 * We do not want newidle balance, which can be very
 		 * frequent, pollute the failure counter causing
 		 * excessive cache_hot migrations and active balances.
+		 *
+		 * Similarly for migration_misfit which is not related to
+		 * load/util migration, don't pollute nr_balance_failed.
 		 */
-		if (idle != CPU_NEWLY_IDLE)
+		if (idle != CPU_NEWLY_IDLE &&
+		    env.migration_type != migrate_misfit)
 			sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
@@ -11527,8 +11531,13 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 	 * repeatedly reach this code, which would lead to balance_interval
 	 * skyrocketing in a short amount of time. Skip the balance_interval
 	 * increase logic to avoid that.
+	 *
+	 * Similarly misfit migration which is not necessarily an indication of
+	 * the system being busy and requires lb to backoff to let it settle
+	 * down.
 	 */
-	if (env.idle == CPU_NEWLY_IDLE)
+	if (env.idle == CPU_NEWLY_IDLE ||
+	    env.migration_type == migrate_misfit)
 		goto out;
 
 	/* tune up the balancing interval */
-- 
2.34.1