linux-kernel - [RFC PATCH 06/13] sched: Changing find_busiest

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]

Message-ID: <20121025102537.21022.522.stgit@preeti.in.ibm.com>
Date:	Thu, 25 Oct 2012 15:55:38 +0530
From:	Preeti U Murthy <preeti@...ux.vnet.ibm.com>
To:	svaidy@...ux.vnet.ibm.com, linux-kernel@...r.kernel.org
Cc:	mingo@...nel.org, venki@...gle.com, robin.randhawa@....com,
	linaro-dev@...ts.linaro.org, a.p.zijlstra@...llo.nl,
	mjg59@...f.ucam.org, viresh.kumar@...aro.org,
	akpm@...ux-foundation.org, amit.kucheria@...aro.org,
	deepthi@...ux.vnet.ibm.com, paul.mckenney@...aro.org,
	arjan@...ux.intel.com, paulmck@...ux.vnet.ibm.com,
	srivatsa.bhat@...ux.vnet.ibm.com, vincent.guittot@...aro.org,
	tglx@...utronix.de, Arvind.Chauhan@....com, pjt@...gle.com,
	Morten.Rasmussen@....com, linux-arm-kernel@...ts.infradead.org,
	suresh.b.siddha@...el.com
Subject: [RFC PATCH 06/13] sched: Changing find_busiest_queue to use PJT's
 metric

Additional parameters which decide the busiest cpu in the chosen sched group
calculated using PJT's metric are used

Signed-off-by: Preeti U Murthy <preeti@...ux.vnet.ibm.com>
---
 kernel/sched/fair.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fca6606..bb1c71b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5085,7 +5085,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
-	unsigned long max_load = 0;
+	u64 max_cpu_load = 0;
 	int i;
 
 	for_each_cpu(i, sched_group_cpus(group)) {
@@ -5093,6 +5093,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		unsigned long capacity = DIV_ROUND_CLOSEST(power,
 							   SCHED_POWER_SCALE);
 		unsigned long wl;
+		u64 runnable_load;/* Equivalent of wl,calculated using PJT's metric */
 
 		if (!capacity)
 			capacity = fix_small_capacity(env->sd, group);
@@ -5102,12 +5103,14 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 
 		rq = cpu_rq(i);
 		wl = weighted_cpuload(i);
+		runnable_load = cpu_rq(i)->cfs.runnable_load_avg;
 
 		/*
 		 * When comparing with imbalance, use weighted_cpuload()
 		 * which is not scaled with the cpu power.
+		 * The below decision is based on PJT's metric
 		 */
-		if (capacity && rq->nr_running == 1 && wl > env->imbalance)
+		if (capacity && rq->nr_running == 1 && runnable_load > env->load_imbalance)
 			continue;
 
 		/*
@@ -5117,9 +5120,11 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 * running at a lower capacity.
 		 */
 		wl = (wl * SCHED_POWER_SCALE) / power;
+		runnable_load = (runnable_load * SCHED_POWER_SCALE) / power;
 
-		if (wl > max_load) {
-			max_load = wl;
+		/* Below decision has been changed to use PJT's metric */
+		if (runnable_load > max_cpu_load) {
+			max_cpu_load = runnable_load;
 			busiest = rq;
 		}
 	}

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/