From: dino@in.ibm.com
To: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org,
John Stultz <johnstul@us.ibm.com>,
Darren Hart <dvhltc@us.ibm.com>, John Kacur <jkacur@redhat.com>
Subject: [patch -rt 08/17] sched: remove reciprocal for cpu_power
Date: Thu, 22 Oct 2009 18:07:51 +0530 [thread overview]
Message-ID: <20091022124111.383069928@spinlock.in.ibm.com> (raw)
In-Reply-To: 20091022123743.506956796@spinlock.in.ibm.com
[-- Attachment #1: sched-lb-7.patch --]
[-- Type: text/plain, Size: 8756 bytes --]
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
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[andreas.herrmann3@amd.com: remove include]
Signed-off-by: Dinakar Guniguntala <dino@in.ibm.com>
---
include/linux/sched.h | 10 +----
kernel/sched.c | 100 +++++++++++++++++---------------------------------
2 files changed, 36 insertions(+), 74 deletions(-)
Index: linux-2.6.31.4-rt14/kernel/sched.c
===================================================================
--- linux-2.6.31.4-rt14.orig/kernel/sched.c 2009-10-16 09:15:37.000000000 -0400
+++ linux-2.6.31.4-rt14/kernel/sched.c 2009-10-16 09:15:38.000000000 -0400
@@ -137,30 +137,8 @@
*/
#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
-
#define TASK_PREEMPTS_CURR(p, rq) \
((p)->prio < (rq)->curr->prio)
@@ -2401,8 +2379,7 @@
}
/* 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;
@@ -3849,7 +3826,6 @@
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 */
@@ -3864,33 +3840,26 @@
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);
}
/**
@@ -3970,8 +3939,7 @@
}
/* 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;
/*
@@ -3983,14 +3951,14 @@
* 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);
}
/**
@@ -4032,7 +4000,7 @@
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
@@ -4097,28 +4065,28 @@
* 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;
@@ -4153,8 +4121,8 @@
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;
/*
@@ -4289,7 +4257,7 @@
if (!group)
return SCHED_LOAD_SCALE;
- return group->__cpu_power;
+ return group->cpu_power;
}
/*
@@ -8226,7 +8194,7 @@
break;
}
- if (!group->__cpu_power) {
+ if (!group->cpu_power) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
@@ -8250,9 +8218,9 @@
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;
@@ -8537,7 +8505,7 @@
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)
@@ -8762,7 +8730,7 @@
continue;
}
- sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+ sg->cpu_power += sd->groups->cpu_power;
}
sg = sg->next;
} while (sg != group_head);
@@ -8835,7 +8803,7 @@
child = sd->child;
- sd->groups->__cpu_power = 0;
+ sd->groups->cpu_power = 0;
if (!child) {
power = SCHED_LOAD_SCALE;
@@ -8851,7 +8819,7 @@
power /= weight;
power >>= SCHED_LOAD_SHIFT;
}
- sg_inc_cpu_power(sd->groups, power);
+ sd->groups->cpu_power += power;
return;
}
@@ -8860,7 +8828,7 @@
*/
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);
}
@@ -9133,7 +9101,7 @@
sd = &per_cpu(node_domains, j).sd;
sd->groups = sg;
}
- sg->__cpu_power = 0;
+ sg->cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), nodemask);
sg->next = sg;
cpumask_or(covered, covered, nodemask);
@@ -9160,7 +9128,7 @@
"Can not alloc domain group for node %d\n", j);
goto error;
}
- sg->__cpu_power = 0;
+ sg->cpu_power = 0;
cpumask_copy(sched_group_cpus(sg), tmpmask);
sg->next = prev->next;
cpumask_or(covered, covered, tmpmask);
Index: linux-2.6.31.4-rt14/include/linux/sched.h
===================================================================
--- linux-2.6.31.4-rt14.orig/include/linux/sched.h 2009-10-16 09:15:36.000000000 -0400
+++ linux-2.6.31.4-rt14/include/linux/sched.h 2009-10-16 09:15:38.000000000 -0400
@@ -905,15 +905,9 @@
/*
* 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.
--
next prev parent reply other threads:[~2009-10-22 12:42 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-22 12:37 [patch -rt 00/17] [patch -rt] Sched load balance backport dino
2009-10-22 12:37 ` [patch -rt 01/17] sched: restore __cpu_power to a straight sum of power dino
2009-10-22 12:37 ` [patch -rt 02/17] sched: SD_PREFER_SIBLING dino
2009-10-22 12:37 ` [patch -rt 03/17] sched: update the cpu_power sum during load-balance dino
2009-10-22 12:37 ` [patch -rt 04/17] sched: add smt_gain dino
2009-10-22 12:37 ` [patch -rt 05/17] sched: dynamic cpu_power dino
2009-10-22 12:37 ` [patch -rt 06/17] sched: scale down cpu_power due to RT tasks dino
2009-10-22 12:37 ` [patch -rt 07/17] sched: try to deal with low capacity dino
2009-10-22 12:37 ` dino [this message]
2009-10-22 12:37 ` [patch -rt 09/17] x86: move APERF/MPERF into a X86_FEATURE dino
2009-10-22 12:37 ` [patch -rt 10/17] x86: Add generic aperf/mperf code dino
2009-10-22 12:37 ` [patch -rt 11/17] Provide an arch specific hook for cpufreq based scaling of cpu_power dino
2009-10-22 12:37 ` [patch -rt 12/17] x86: sched: provide arch implementations using aperf/mperf dino
2009-10-22 12:37 ` [patch -rt 13/17] sched: cleanup wake_idle power saving dino
2009-10-22 12:37 ` [patch -rt 14/17] sched: cleanup wake_idle dino
2009-10-22 12:37 ` [patch -rt 15/17] sched: Add a missing = dino
2009-10-22 12:37 ` [patch -rt 16/17] sched: Deal with low-load in wake_affine() dino
2009-10-22 12:38 ` [patch -rt 17/17] sched: Fix dynamic power-balancing crash dino
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20091022124111.383069928@spinlock.in.ibm.com \
--to=dino@in.ibm.com \
--cc=a.p.zijlstra@chello.nl \
--cc=dvhltc@us.ibm.com \
--cc=jkacur@redhat.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox