linux-kernel - [RFC PATCH 11/13] sched: Modify 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]

Date:	Thu, 25 Oct 2012 15:56:06 +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 11/13] sched: Modify find_idlest_group to use PJT's
 metric

Additional parameters introduced to perform this function which are
calculated using PJT's metrics and its helpers.

Signed-off-by: Preeti U Murthy <preeti@...ux.vnet.ibm.com>
---
 kernel/sched/fair.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a5affbc..c64be1c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3173,11 +3173,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		  int this_cpu, int load_idx)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
-	unsigned long min_load = ULONG_MAX, this_load = 0;
+	unsigned long this_load = 0;
+	u64 min_sg_load = ~0ULL, this_sg_load = 0;/* Helpers for PJT's metrics */
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
 	do {
 		unsigned long load, avg_load;
+		u64 avg_sg_load;/* Helpers for PJT's metrics */
 		int local_group;
 		int i;
 
@@ -3191,6 +3193,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
 		/* Tally up the load of all CPUs in the group */
 		avg_load = 0;
+		avg_sg_load = 0;
 
 		for_each_cpu(i, sched_group_cpus(group)) {
 			/* Bias balancing toward cpus of our domain */
@@ -3200,20 +3203,23 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 				load = target_load(i, load_idx);
 
 			avg_load += load;
+			avg_sg_load += cpu_rq(i)->cfs.runnable_load_avg;
 		}
 
 		/* Adjust by relative CPU power of the group */
 		avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
+		avg_sg_load = (avg_sg_load * SCHED_POWER_SCALE) / group->sgp->power;
 
 		if (local_group) {
 			this_load = avg_load;
-		} else if (avg_load < min_load) {
-			min_load = avg_load;
+			this_sg_load = avg_sg_load;
+		} else if (avg_sg_load < min_sg_load) {/* Decision changed to suit PJT's metric */
+			min_sg_load = avg_sg_load;
 			idlest = group;
 		}
 	} while (group = group->next, group != sd->groups);
 
-	if (!idlest || 100*this_load < imbalance*min_load)
+	if (!idlest || 100*this_sg_load < imbalance*min_sg_load)
 		return NULL;
 	return idlest;
 }

--
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/