lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Fri, 12 Nov 2021 15:55:27 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Vincent Guittot <vincent.guittot@...aro.org>
Cc:     mingo@...hat.com, juri.lelli@...hat.com, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, linux-kernel@...r.kernel.org,
        tim.c.chen@...ux.intel.com, joel@...lfernandes.org
Subject: Re: [PATCH 1/2] sched/fair: skip newidle update stats


Subject: sched/fair: Reflow newidle_balance()
From: Peter Zijlstra <peterz@...radead.org>
Date: Fri Nov 12 15:46:08 CET 2021

The control flow in newidle_balance() is a little convoluted, attempt
simplification.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 kernel/sched/fair.c |   21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10858,10 +10858,10 @@ static inline void nohz_newidle_balance(
 static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
+	int pulled_task = 0, timeout = 0;
 	int this_cpu = this_rq->cpu;
 	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
-	int pulled_task = 0, early_stop = 0;
 
 	update_misfit_status(NULL, this_rq);
 
@@ -10889,17 +10889,9 @@ static int newidle_balance(struct rq *th
 	if (!READ_ONCE(this_rq->rd->overload) ||
 	    (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
 
-		if (sd) {
+		if (sd)
 			update_next_balance(sd, &next_balance);
 
-			/*
-			 * We skip new idle LB because there is not enough
-			 * time before next wake up. Make sure that we will
-			 * not kick NOHZ_NEWILB_KICK
-			 */
-			early_stop = 1;
-		}
-
 		goto out;
 	}
 
@@ -10922,7 +10914,7 @@ static int newidle_balance(struct rq *th
 		update_next_balance(sd, &next_balance);
 
 		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
-			early_stop = 1;
+			timeout = 1;
 			break;
 		}
 
@@ -10967,6 +10959,11 @@ static int newidle_balance(struct rq *th
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
 
+	if (pulled_task || timeout)
+		goto out;
+
+	nohz_newidle_balance(this_rq);
+
 out:
 	/* Move the next balance forward */
 	if (time_after(this_rq->next_balance, next_balance))
@@ -10974,8 +10971,6 @@ static int newidle_balance(struct rq *th
 
 	if (pulled_task)
 		this_rq->idle_stamp = 0;
-	else if (!early_stop)
-		nohz_newidle_balance(this_rq);
 
 	return pulled_task;
 }

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ