lkml.org 
[lkml]   [2008]   [Apr]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH 04/12] sched: Remove fixed NR_CPUS sized arrays in kernel_sched_c v2
 * Change fixed size arrays to per_cpu variables or dynamically allocated
arrays in sched_init() and sched_init_smp().

(1) static struct sched_entity *init_sched_entity_p[NR_CPUS];
(1) static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
(1) static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
(1) static struct rt_rq *init_rt_rq_p[NR_CPUS];
static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];

(1) - these arrays are allocated via alloc_bootmem_low()

* Change sched_domain_debug_one() to use cpulist_scnprintf instead of
cpumask_scnprintf. This reduces the output buffer required and improves
readability when large NR_CPU count machines arrive.

* In sched_create_group() we allocate new arrays based on nr_cpu_ids.

Based on:
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
+ x86/latest .../x86/linux-2.6-x86.git
+ sched-devel/latest .../mingo/linux-2.6-sched-devel.git

Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Travis <travis@sgi.com>
---
v2: Removed reference to cpumask_scnprintf_len().
---
kernel/sched.c | 80 +++++++++++++++++++++++++++++++++++++--------------------
1 file changed, 52 insertions(+), 28 deletions(-)
--- linux-2.6.x86.orig/kernel/sched.c
+++ linux-2.6.x86/kernel/sched.c
@@ -68,6 +68,7 @@
#include <linux/hrtimer.h>
#include <linux/ftrace.h>
#include <linux/tick.h>
+#include <linux/bootmem.h>

#include <asm/tlb.h>
#include <asm/irq_regs.h>
@@ -278,17 +279,11 @@ struct task_group {
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
-
-static struct sched_entity *init_sched_entity_p[NR_CPUS];
-static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
#endif

#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
-
-static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
-static struct rt_rq *init_rt_rq_p[NR_CPUS];
#endif

/* task_group_lock serializes add/remove of task groups and also changes to
@@ -312,17 +307,7 @@ static int init_task_group_load = INIT_T
/* Default task group.
* Every task in system belong to this group at bootup.
*/
-struct task_group init_task_group = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
- .se = init_sched_entity_p,
- .cfs_rq = init_cfs_rq_p,
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
- .rt_se = init_sched_rt_entity_p,
- .rt_rq = init_rt_rq_p,
-#endif
-};
+struct task_group init_task_group;

/* return group to which a task belongs */
static inline struct task_group *task_group(struct task_struct *p)
@@ -3754,7 +3739,7 @@ static inline void trigger_load_balance(
*/
int ilb = first_cpu(nohz.cpu_mask);

- if (ilb != NR_CPUS)
+ if (ilb < nr_cpu_ids)
resched_cpu(ilb);
}
}
@@ -5729,11 +5714,11 @@ static void move_task_off_dead_cpu(int d
dest_cpu = any_online_cpu(mask);

/* On any allowed CPU? */
- if (dest_cpu == NR_CPUS)
+ if (dest_cpu >= nr_cpu_ids)
dest_cpu = any_online_cpu(p->cpus_allowed);

/* No more Mr. Nice Guy. */
- if (dest_cpu == NR_CPUS) {
+ if (dest_cpu >= nr_cpu_ids) {
cpumask_t cpus_allowed = cpuset_cpus_allowed_locked(p);
/*
* Try to stay on the same cpuset, where the
@@ -6188,9 +6173,9 @@ static int sched_domain_debug_one(struct
{
struct sched_group *group = sd->groups;
cpumask_t groupmask;
- char str[NR_CPUS];
+ char str[256];

- cpumask_scnprintf(str, NR_CPUS, sd->span);
+ cpulist_scnprintf(str, sizeof(str), sd->span);
cpus_clear(groupmask);

printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@@ -6243,7 +6228,7 @@ static int sched_domain_debug_one(struct

cpus_or(groupmask, groupmask, group->cpumask);

- cpumask_scnprintf(str, NR_CPUS, group->cpumask);
+ cpulist_scnprintf(str, sizeof(str), group->cpumask);
printk(KERN_CONT " %s", str);

group = group->next;
@@ -6637,7 +6622,7 @@ cpu_to_phys_group(int cpu, const cpumask
* gets dynamically allocated.
*/
static DEFINE_PER_CPU(struct sched_domain, node_domains);
-static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
+static struct sched_group ***sched_group_nodes_bycpu;

static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_allnodes);
@@ -7280,6 +7265,11 @@ void __init sched_init_smp(void)
{
cpumask_t non_isolated_cpus;

+#if defined(CONFIG_NUMA)
+ sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
+ GFP_KERNEL);
+ BUG_ON(sched_group_nodes_bycpu == NULL);
+#endif
get_online_cpus();
arch_init_sched_domains(&cpu_online_map);
non_isolated_cpus = cpu_possible_map;
@@ -7297,6 +7287,11 @@ void __init sched_init_smp(void)
#else
void __init sched_init_smp(void)
{
+#if defined(CONFIG_NUMA)
+ sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
+ GFP_KERNEL);
+ BUG_ON(sched_group_nodes_bycpu == NULL);
+#endif
sched_init_granularity();
}
#endif /* CONFIG_SMP */
@@ -7393,6 +7388,35 @@ static void init_tg_rt_entry(struct rq *
void __init sched_init(void)
{
int i, j;
+ unsigned long alloc_size = 0, ptr;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+ alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+#endif
+ /*
+ * As sched_init() is called before page_alloc is setup,
+ * we use alloc_bootmem().
+ */
+ if (alloc_size) {
+ ptr = (unsigned long)alloc_bootmem_low(alloc_size);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ init_task_group.se = (struct sched_entity **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+
+ init_task_group.cfs_rq = (struct cfs_rq **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+ init_task_group.rt_se = (struct sched_rt_entity **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+
+ init_task_group.rt_rq = (struct rt_rq **)ptr;
+#endif
+ }

#ifdef CONFIG_SMP
init_defrootdomain();
@@ -7643,10 +7667,10 @@ static int alloc_fair_sched_group(struct
struct rq *rq;
int i;

- tg->cfs_rq = kzalloc(sizeof(cfs_rq) * NR_CPUS, GFP_KERNEL);
+ tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
if (!tg->cfs_rq)
goto err;
- tg->se = kzalloc(sizeof(se) * NR_CPUS, GFP_KERNEL);
+ tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
if (!tg->se)
goto err;

@@ -7728,10 +7752,10 @@ static int alloc_rt_sched_group(struct t
struct rq *rq;
int i;

- tg->rt_rq = kzalloc(sizeof(rt_rq) * NR_CPUS, GFP_KERNEL);
+ tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
if (!tg->rt_rq)
goto err;
- tg->rt_se = kzalloc(sizeof(rt_se) * NR_CPUS, GFP_KERNEL);
+ tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
if (!tg->rt_se)
goto err;

--


\
 
 \ /
  Last update: 2008-04-05 03:15    [from the cache]
©2003-2011 Jasper Spaans