[tip:sched/balancing] sched: Remove reciprocal for cpu_power

From: tip-bot for Peter Zijlstra
Date: Fri Sep 04 2009 - 04:57:33 EST

Next message: Nick Craig-Wood: "Re: Reading /proc/kcore causes a BUG()"
Previous message: tip-bot for Peter Zijlstra: "[tip:sched/balancing] sched: Try to deal with low capacity"
In reply to: Andreas Herrmann: "Re: [RFC][PATCH 8/8] sched: remove reciprocal for cpu_power"
Next in thread: Peter Zijlstra: "[RFC][PATCH 4/8] sched: add smt_gain"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Commit-ID: 18a3885fc1ffa92c2212ff0afdf033403d5b0fa0
Gitweb: http://git.kernel.org/tip/18a3885fc1ffa92c2212ff0afdf033403d5b0fa0
Author: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
AuthorDate: Tue, 1 Sep 2009 10:34:39 +0200
Committer: Ingo Molnar <mingo@xxxxxxx>
CommitDate: Fri, 4 Sep 2009 10:09:56 +0200

sched: Remove reciprocal for cpu_power

Its a source of fail, also, now that cpu_power is dynamical,
its a waste of time.

before:
<idle>-0 [000] 132.877936: find_busiest_group: avg_load: 0 group_load: 8241 power: 1

after:
bash-1689 [001] 137.862151: find_busiest_group: avg_load: 10636288 group_load: 10387 power: 1

[ v2: build fix from From: Andreas Herrmann ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Tested-by: Andreas Herrmann <andreas.herrmann3@xxxxxxx>
Acked-by: Andreas Herrmann <andreas.herrmann3@xxxxxxx>
Acked-by: Gautham R Shenoy <ego@xxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
LKML-Reference: <20090901083826.425896304@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>

---
include/linux/sched.h | 10 +----
kernel/sched.c | 101 ++++++++++++++++--------------------------------
2 files changed, 36 insertions(+), 75 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c67ddf3..3b7f43e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -860,15 +860,9 @@ struct sched_group {

/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
- * single CPU. This is read only (except for setup, hotplug CPU).
- * Note : Never change cpu_power without recompute its reciprocal
+ * single CPU.
*/
- unsigned int __cpu_power;
- /*
- * reciprocal value of cpu_power to avoid expensive divides
- * (see include/linux/reciprocal_div.h)
- */
- u32 reciprocal_cpu_power;
+ unsigned int cpu_power;

/*
* The CPUs this group covers.
diff --git a/kernel/sched.c b/kernel/sched.c
index e1ebf9b..b537853 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -64,7 +64,6 @@
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
@@ -120,30 +119,8 @@
*/
#define RUNTIME_INF ((u64)~0ULL)

-#ifdef CONFIG_SMP
-
static void double_rq_lock(struct rq *rq1, struct rq *rq2);

-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
- return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
- sg->__cpu_power += val;
- sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
static inline int rt_policy(int policy)
{
if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
@@ -2335,8 +2312,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
}

/* Adjust by relative CPU power of the group */
- avg_load = sg_div_cpu_power(group,
- avg_load * SCHED_LOAD_SCALE);
+ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

if (local_group) {
this_load = avg_load;
@@ -3768,7 +3744,6 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
unsigned long weight = cpumask_weight(sched_domain_span(sd));
unsigned long power = SCHED_LOAD_SCALE;
struct sched_group *sdg = sd->groups;
- unsigned long old = sdg->__cpu_power;

/* here we could scale based on cpufreq */

@@ -3783,33 +3758,26 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
if (!power)
power = 1;

- if (power != old) {
- sdg->__cpu_power = power;
- sdg->reciprocal_cpu_power = reciprocal_value(power);
- }
+ sdg->cpu_power = power;
}

static void update_group_power(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long power = sdg->__cpu_power;

if (!child) {
update_cpu_power(sd, cpu);
return;
}

- sdg->__cpu_power = 0;
+ sdg->cpu_power = 0;

group = child->groups;
do {
- sdg->__cpu_power += group->__cpu_power;
+ sdg->cpu_power += group->cpu_power;
group = group->next;
} while (group != child->groups);
-
- if (power != sdg->__cpu_power)
- sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
}

/**
@@ -3889,8 +3857,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
}

/* Adjust by relative CPU power of the group */
- sgs->avg_load = sg_div_cpu_power(group,
- sgs->group_load * SCHED_LOAD_SCALE);
+ sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;

/*
@@ -3902,14 +3869,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
* normalized nr_running number somewhere that negates
* the hierarchy?
*/
- avg_load_per_task = sg_div_cpu_power(group,
- sum_avg_load_per_task * SCHED_LOAD_SCALE);
+ avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+ group->cpu_power;

if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
sgs->group_imb = 1;

sgs->group_capacity =
- DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
+ DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
}

/**
@@ -3951,7 +3918,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
return;

sds->total_load += sgs.group_load;
- sds->total_pwr += group->__cpu_power;
+ sds->total_pwr += group->cpu_power;

/*
* In case the child domain prefers tasks go to siblings
@@ -4016,28 +3983,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
* moving them.
*/

- pwr_now += sds->busiest->__cpu_power *
+ pwr_now += sds->busiest->cpu_power *
min(sds->busiest_load_per_task, sds->max_load);
- pwr_now += sds->this->__cpu_power *
+ pwr_now += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load);
pwr_now /= SCHED_LOAD_SCALE;

/* Amount of load we'd subtract */
- tmp = sg_div_cpu_power(sds->busiest,
- sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+ tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ sds->busiest->cpu_power;
if (sds->max_load > tmp)
- pwr_move += sds->busiest->__cpu_power *
+ pwr_move += sds->busiest->cpu_power *
min(sds->busiest_load_per_task, sds->max_load - tmp);

/* Amount of load we'd add */
- if (sds->max_load * sds->busiest->__cpu_power <
+ if (sds->max_load * sds->busiest->cpu_power <
sds->busiest_load_per_task * SCHED_LOAD_SCALE)
- tmp = sg_div_cpu_power(sds->this,
- sds->max_load * sds->busiest->__cpu_power);
+ tmp = (sds->max_load * sds->busiest->cpu_power) /
+ sds->this->cpu_power;
else
- tmp = sg_div_cpu_power(sds->this,
- sds->busiest_load_per_task * SCHED_LOAD_SCALE);
- pwr_move += sds->this->__cpu_power *
+ tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ sds->this->cpu_power;
+ pwr_move += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load + tmp);
pwr_move /= SCHED_LOAD_SCALE;

@@ -4072,8 +4039,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
sds->max_load - sds->busiest_load_per_task);

/* How much load to actually move to equalise the imbalance */
- *imbalance = min(max_pull * sds->busiest->__cpu_power,
- (sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+ *imbalance = min(max_pull * sds->busiest->cpu_power,
+ (sds->avg_load - sds->this_load) * sds->this->cpu_power)
/ SCHED_LOAD_SCALE;

/*
@@ -4208,7 +4175,7 @@ static unsigned long power_of(int cpu)
if (!group)
return SCHED_LOAD_SCALE;

- return group->__cpu_power;
+ return group->cpu_power;
}

/*
@@ -7922,7 +7889,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
break;
}

- if (!group->__cpu_power) {
+ if (!group->cpu_power) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
@@ -7946,9 +7913,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));

printk(KERN_CONT " %s", str);
- if (group->__cpu_power != SCHED_LOAD_SCALE) {
- printk(KERN_CONT " (__cpu_power = %d)",
- group->__cpu_power);
+ if (group->cpu_power != SCHED_LOAD_SCALE) {
+ printk(KERN_CONT " (cpu_power = %d)",
+ group->cpu_power);
}

group = group->next;
@@ -8233,7 +8200,7 @@ init_sched_build_groups(const struct cpumask *span,
continue;

cpumask_clear(sched_group_cpus(sg));
- sg->__cpu_power = 0;
+ sg->cpu_power = 0;

for_each_cpu(j, span) {
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
@@ -8491,7 +8458,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
continue;
}

- sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+ sg->cpu_power += sd->groups->cpu_power;
}
sg = sg->next;
} while (sg != group_head);
@@ -8528,7 +8495,7 @@ static int build_numa_sched_groups(struct s_data *d,
sd->groups = sg;
}

- sg->__cpu_power = 0;
+ sg->cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), d->nodemask);
sg->next = sg;
cpumask_or(d->covered, d->covered, d->nodemask);
@@ -8551,7 +8518,7 @@ static int build_numa_sched_groups(struct s_data *d,
"Can not alloc domain group for node %d\n", j);
return -ENOMEM;
}
- sg->__cpu_power = 0;
+ sg->cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), d->tmpmask);
sg->next = prev->next;
cpumask_or(d->covered, d->covered, d->tmpmask);
@@ -8629,7 +8596,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)

child = sd->child;

- sd->groups->__cpu_power = 0;
+ sd->groups->cpu_power = 0;

if (!child) {
power = SCHED_LOAD_SCALE;
@@ -8645,7 +8612,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
power /= weight;
power >>= SCHED_LOAD_SHIFT;
}
- sg_inc_cpu_power(sd->groups, power);
+ sd->groups->cpu_power += power;
return;
}

@@ -8654,7 +8621,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
*/
group = child->groups;
do {
- sg_inc_cpu_power(sd->groups, group->__cpu_power);
+ sd->groups->cpu_power += group->cpu_power;
group = group->next;
} while (group != child->groups);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Nick Craig-Wood: "Re: Reading /proc/kcore causes a BUG()"
Previous message: tip-bot for Peter Zijlstra: "[tip:sched/balancing] sched: Try to deal with low capacity"
In reply to: Andreas Herrmann: "Re: [RFC][PATCH 8/8] sched: remove reciprocal for cpu_power"
Next in thread: Peter Zijlstra: "[RFC][PATCH 4/8] sched: add smt_gain"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]