[RFC][PATCH 1/6] sched: restore __cpu_power to a straight sum of power

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

[-- Attachment #1: sched-lb-1.patch --]
[-- Type: text/plain, Size: 3387 bytes --]

cpu_power is supposed to be a representation of the process capacity
of the cpu, not a value to randomly tweak in order to affect
placement.

Remove the placement hacks and add SMT gain.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
---
 include/linux/sched.h    |    1 +
 include/linux/topology.h |    1 +
 kernel/sched.c           |   34 ++++++++++++++++++----------------
 3 files changed, 20 insertions(+), 16 deletions(-)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -930,6 +930,7 @@ struct sched_domain {
 	unsigned int newidle_idx;
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
+	unsigned int smt_gain;
 	int flags;			/* See SD_* */
 	enum sched_domain_level level;
 
Index: linux-2.6/include/linux/topology.h
===================================================================
--- linux-2.6.orig/include/linux/topology.h
+++ linux-2.6/include/linux/topology.h
@@ -99,6 +99,7 @@ int arch_update_cpu_topology(void);
 				| SD_SHARE_CPUPOWER,	\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
+	.smt_gain		= 1178,	/* 15% */	\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -8468,15 +8468,13 @@ static void free_sched_groups(const stru
  * there are asymmetries in the topology. If there are asymmetries, group
  * having more cpu_power will pickup more load compared to the group having
  * less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_domain *child;
 	struct sched_group *group;
+	long power;
+	int weight;
 
 	WARN_ON(!sd || !sd->groups);
 
@@ -8487,22 +8485,26 @@ static void init_sched_groups_power(int 
 
 	sd->groups->__cpu_power = 0;
 
-	/*
-	 * For perf policy, if the groups in child domain share resources
-	 * (for example cores sharing some portions of the cache hierarchy
-	 * or SMT), then set this domain groups cpu_power such that each group
-	 * can handle only one task, when there are other idle groups in the
-	 * same sched domain.
-	 */
-	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
-		       (child->flags &
-			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
-		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+	if (!child) {
+		power = SCHED_LOAD_SCALE;
+		weight = cpumask_weight(sched_domain_span(sd));
+		/*
+		 * SMT siblings share the power of a single core.
+		 * Usually multiple threads get a better yield out of
+		 * that one core than a single thread would have,
+		 * reflect that in sd->smt_gain.
+		 */
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
+			power *= sd->smt_gain;
+			power /= weight;
+			power >>= SCHED_LOAD_SHIFT;
+		}
+		sg_inc_cpu_power(sd->groups, power);
 		return;
 	}
 
 	/*
-	 * add cpu_power of each child group to this groups cpu_power
+	 * Add cpu_power of each child group to this groups cpu_power.
 	 */
 	group = child->groups;
 	do {

--