linux-kernel - [PATCH v3 10/10] sched/fair: optimize find_idlest

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: <1568878421-12301-11-git-send-email-vincent.guittot@linaro.org>
Date:   Thu, 19 Sep 2019 09:33:41 +0200
From:   Vincent Guittot <vincent.guittot@...aro.org>
To:     linux-kernel@...r.kernel.org, mingo@...hat.com,
        peterz@...radead.org
Cc:     pauld@...hat.com, valentin.schneider@....com,
        srikar@...ux.vnet.ibm.com, quentin.perret@....com,
        dietmar.eggemann@....com, Morten.Rasmussen@....com,
        hdanton@...a.com, Vincent Guittot <vincent.guittot@...aro.org>
Subject: [PATCH v3 10/10] sched/fair: optimize find_idlest_group

find_idlest_group() now loads CPU's load_avg in 2 different ways.
Consolidate the function to read and use load_avg only once and simplify
the algorithm to only look for the group with lowest load_avg.

Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
---
 kernel/sched/fair.c | 52 +++++++++++-----------------------------------------
 1 file changed, 11 insertions(+), 41 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 39a37ae..1fac444 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5560,16 +5560,14 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	struct sched_group *most_spare_sg = NULL;
-	unsigned long min_runnable_load = ULONG_MAX;
-	unsigned long this_runnable_load = ULONG_MAX;
-	unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
+	unsigned long min_load = ULONG_MAX, this_load = ULONG_MAX;
 	unsigned long most_spare = 0, this_spare = 0;
 	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
 	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
 				(sd->imbalance_pct-100) / 100;
 
 	do {
-		unsigned long load, avg_load, runnable_load;
+		unsigned long load;
 		unsigned long spare_cap, max_spare_cap;
 		int local_group;
 		int i;
@@ -5586,15 +5584,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		 * Tally up the load of all CPUs in the group and find
 		 * the group containing the CPU with most spare capacity.
 		 */
-		avg_load = 0;
-		runnable_load = 0;
+		load = 0;
 		max_spare_cap = 0;
 
 		for_each_cpu(i, sched_group_span(group)) {
-			load = cpu_load(cpu_rq(i));
-			runnable_load += load;
-
-			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
+			load += cpu_load(cpu_rq(i));
 
 			spare_cap = capacity_spare_without(i, p);
 
@@ -5603,31 +5597,15 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		}
 
 		/* Adjust by relative CPU capacity of the group */
-		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
-					group->sgc->capacity;
-		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
+		load = (load * SCHED_CAPACITY_SCALE) /
 					group->sgc->capacity;
 
 		if (local_group) {
-			this_runnable_load = runnable_load;
-			this_avg_load = avg_load;
+			this_load = load;
 			this_spare = max_spare_cap;
 		} else {
-			if (min_runnable_load > (runnable_load + imbalance)) {
-				/*
-				 * The runnable load is significantly smaller
-				 * so we can pick this new CPU:
-				 */
-				min_runnable_load = runnable_load;
-				min_avg_load = avg_load;
-				idlest = group;
-			} else if ((runnable_load < (min_runnable_load + imbalance)) &&
-				   (100*min_avg_load > imbalance_scale*avg_load)) {
-				/*
-				 * The runnable loads are close so take the
-				 * blocked load into account through avg_load:
-				 */
-				min_avg_load = avg_load;
+			if (load < min_load) {
+				min_load = load;
 				idlest = group;
 			}
 
@@ -5668,18 +5646,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 	 * local domain to be very lightly loaded relative to the remote
 	 * domains but "imbalance" skews the comparison making remote CPUs
 	 * look much more favourable. When considering cross-domain, add
-	 * imbalance to the runnable load on the remote node and consider
-	 * staying local.
+	 * imbalance to the load on the remote node and consider staying
+	 * local.
 	 */
-	if ((sd->flags & SD_NUMA) &&
-	    min_runnable_load + imbalance >= this_runnable_load)
-		return NULL;
-
-	if (min_runnable_load > (this_runnable_load + imbalance))
-		return NULL;
-
-	if ((this_runnable_load < (min_runnable_load + imbalance)) &&
-	     (100*this_avg_load < imbalance_scale*min_avg_load))
+	if (min_load + imbalance >= this_load)
 		return NULL;
 
 	return idlest;
-- 
2.7.4