Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 17 May 2023 18:34:13 -0700
Mime-Version: 1.0
Message-ID: <20230518013414.3053254-1-joshdon@google.com>
Subject: [PATCH 1/2] sched: don't account throttle time for empty groups
From:   Josh Don <joshdon@google.com>
To:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>
Cc:     Tejun Heo <tj@kernel.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        linux-kernel@vger.kernel.org,
        Xiangling Kong <xiangling@google.com>,
        Josh Don <joshdon@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

It is easy for a cfs_rq to become throttled even when it has no enqueued
entities (for example, if we have just put_prev()'d the last runnable
task of the cfs_rq, and the cfs_rq is out of quota).

Avoid accounting this time towards total throttle time, since it
otherwise falsely inflates the stats.

Signed-off-by: Josh Don <joshdon@google.com>
---
 kernel/sched/fair.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f4b8b906d30a..85c2c0c3cab6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4768,6 +4768,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED);
 	bool curr = cfs_rq->curr == se;
+	struct rq *rq = rq_of(cfs_rq);
 
 	/*
 	 * If we're the current task, we must renormalise before calling
@@ -4816,8 +4817,12 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (cfs_rq->nr_running == 1) {
 		check_enqueue_throttle(cfs_rq);
-		if (!throttled_hierarchy(cfs_rq))
+		if (!throttled_hierarchy(cfs_rq)) {
 			list_add_leaf_cfs_rq(cfs_rq);
+		} else {
+			if (!cfs_rq->throttled_clock)
+				cfs_rq->throttled_clock = rq_clock(rq);
+		}
 	}
 }
 
@@ -5423,7 +5428,9 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	 * throttled-list.  rq->lock protects completion.
 	 */
 	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq_clock(rq);
+	SCHED_WARN_ON(cfs_rq->throttled_clock);
+	if (cfs_rq->nr_running)
+		cfs_rq->throttled_clock = rq_clock(rq);
 	return true;
 }
 
@@ -5441,7 +5448,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	update_rq_clock(rq);
 
 	raw_spin_lock(&cfs_b->lock);
-	cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
+	if (cfs_rq->throttled_clock) {
+		cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
+		cfs_rq->throttled_clock = 0;
+	}
 	list_del_rcu(&cfs_rq->throttled_list);
 	raw_spin_unlock(&cfs_b->lock);
 
-- 
2.40.1.606.ga4b1b128d6-goog