Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched

Version 10 of schedstats includes support for sched_domains, which

hit the mainline kernel in 2.6.7.  Some counters make more sense to be

per-runqueue; other to be per-domain.  Note that domains (and their associated

information) will only be pertinent and available on machines utilizing

CONFIG_SMP.

In version 10 of schedstat, there is at least one level of domain

Version 14 of schedstats includes support for sched_domains, which hit the

mainline kernel in 2.6.20 although it is identical to the stats from version

12 which was in the kernel from 2.6.13-2.6.19 (version 13 never saw a kernel

release).  Some counters make more sense to be per-runqueue; other to be

per-domain.  Note that domains (and their associated information) will only

be pertinent and available on machines utilizing CONFIG_SMP.

In version 14 of schedstat, there is at least one level of domain

statistics for each cpu listed, and there may well be more than one

domain.  Domains have no particular names in this implementation, but

the highest numbered one typically arbitrates balancing across all the

CPU statistics

--------------

cpu<N> 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28

cpu<N> 1 2 3 4 5 6 7 8 9 10 11 12

NOTE: In the sched_yield() statistics, the active queue is considered empty

    if it has only one process in it, since obviously the process calling

     3) # of times just the expired queue was empty

     4) # of times sched_yield() was called

Next four are schedule() statistics:

     5) # of times the active queue had at least one other process on it

     6) # of times we switched to the expired queue and reused it

     7) # of times schedule() was called

     8) # of times schedule() left the processor idle

Next four are active_load_balance() statistics:

     9) # of times active_load_balance() was called

    10) # of times active_load_balance() caused this cpu to gain a task

    11) # of times active_load_balance() caused this cpu to lose a task

    12) # of times active_load_balance() tried to move a task and failed

Next three are try_to_wake_up() statistics:

    13) # of times try_to_wake_up() was called

    14) # of times try_to_wake_up() successfully moved the awakening task

    15) # of times try_to_wake_up() attempted to move the awakening task

Next two are wake_up_new_task() statistics:

    16) # of times wake_up_new_task() was called

    17) # of times wake_up_new_task() successfully moved the new task

Next one is a sched_migrate_task() statistic:

    18) # of times sched_migrate_task() was called

Next three are schedule() statistics:

     5) # of times we switched to the expired queue and reused it

     6) # of times schedule() was called

     7) # of times schedule() left the processor idle

Next one is a sched_balance_exec() statistic:

    19) # of times sched_balance_exec() was called

Next two are try_to_wake_up() statistics:

     8) # of times try_to_wake_up() was called

     9) # of times try_to_wake_up() was called to wake up the local cpu

Next three are statistics describing scheduling latency:

    20) sum of all time spent running by tasks on this processor (in ms)

    21) sum of all time spent waiting to run by tasks on this processor (in ms)

    22) # of tasks (not necessarily unique) given to the processor

The last six are statistics dealing with pull_task():

    23) # of times pull_task() moved a task to this cpu when newly idle

    24) # of times pull_task() stole a task from this cpu when another cpu

	was newly idle

    25) # of times pull_task() moved a task to this cpu when idle

    26) # of times pull_task() stole a task from this cpu when another cpu

	was idle

    27) # of times pull_task() moved a task to this cpu when busy

    28) # of times pull_task() stole a task from this cpu when another cpu

	was busy

    10) sum of all time spent running by tasks on this processor (in jiffies)

    11) sum of all time spent waiting to run by tasks on this processor (in

        jiffies)

    12) # of timeslices run on this cpu

Domain statistics

CONFIG_SMP is not defined, *no* domains are utilized and these lines

will not appear in the output.)

domain<N> 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20

domain<N> <cpumask> 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36

The first field is a bit mask indicating what cpus this domain operates over.

The next fifteen are a variety of load_balance() statistics:

The next 24 are a variety of load_balance() statistics in grouped into types

of idleness (idle, busy, and newly idle):

     1) # of times in this domain load_balance() was called when the cpu

	was idle

     2) # of times in this domain load_balance() was called when the cpu

	was busy

     3) # of times in this domain load_balance() was called when the cpu

	was just becoming idle

     4) # of times in this domain load_balance() tried to move one or more

	tasks and failed, when the cpu was idle

     5) # of times in this domain load_balance() tried to move one or more

	tasks and failed, when the cpu was busy

     6) # of times in this domain load_balance() tried to move one or more

	tasks and failed, when the cpu was just becoming idle

     7) sum of imbalances discovered (if any) with each call to

     1) # of times in this domain load_balance() was called when the

        cpu was idle

     2) # of times in this domain load_balance() checked but found

        the load did not require balancing when the cpu was idle

     3) # of times in this domain load_balance() tried to move one or

        more tasks and failed, when the cpu was idle

     4) sum of imbalances discovered (if any) with each call to

        load_balance() in this domain when the cpu was idle

     8) sum of imbalances discovered (if any) with each call to

     5) # of times in this domain pull_task() was called when the cpu

        was idle

     6) # of times in this domain pull_task() was called even though

        the target task was cache-hot when idle

     7) # of times in this domain load_balance() was called but did

        not find a busier queue while the cpu was idle

     8) # of times in this domain a busier queue was found while the

        cpu was idle but no busier group was found

     9) # of times in this domain load_balance() was called when the

        cpu was busy

    10) # of times in this domain load_balance() checked but found the

        load did not require balancing when busy

    11) # of times in this domain load_balance() tried to move one or

        more tasks and failed, when the cpu was busy

    12) sum of imbalances discovered (if any) with each call to

        load_balance() in this domain when the cpu was busy

     9) sum of imbalances discovered (if any) with each call to

    13) # of times in this domain pull_task() was called when busy

    14) # of times in this domain pull_task() was called even though the

        target task was cache-hot when busy

    15) # of times in this domain load_balance() was called but did not

        find a busier queue while the cpu was busy

    16) # of times in this domain a busier queue was found while the cpu

        was busy but no busier group was found

    17) # of times in this domain load_balance() was called when the

        cpu was just becoming idle

    18) # of times in this domain load_balance() checked but found the

        load did not require balancing when the cpu was just becoming idle

    19) # of times in this domain load_balance() tried to move one or more

        tasks and failed, when the cpu was just becoming idle

    20) sum of imbalances discovered (if any) with each call to

        load_balance() in this domain when the cpu was just becoming idle

    10) # of times in this domain load_balance() was called but did not find

	a busier queue while the cpu was idle

    11) # of times in this domain load_balance() was called but did not find

	a busier queue while the cpu was busy

    12) # of times in this domain load_balance() was called but did not find

	a busier queue while the cpu was just becoming idle

    13) # of times in this domain a busier queue was found while the cpu was

	idle but no busier group was found

    14) # of times in this domain a busier queue was found while the cpu was

	busy but no busier group was found

    15) # of times in this domain a busier queue was found while the cpu was

	just becoming idle but no busier group was found

Next two are sched_balance_exec() statistics:

    17) # of times in this domain sched_balance_exec() successfully pushed

	a task to a new cpu

    18) # of times in this domain sched_balance_exec() tried but failed to

	push a task to a new cpu

Next two are try_to_wake_up() statistics:

    19) # of times in this domain try_to_wake_up() tried to move a task based

	on affinity and cache warmth

    20) # of times in this domain try_to_wake_up() tried to move a task based

	on load balancing

    21) # of times in this domain pull_task() was called when newly idle

    22) # of times in this domain pull_task() was called even though the

        target task was cache-hot when just becoming idle

    23) # of times in this domain load_balance() was called but did not

        find a busier queue while the cpu was just becoming idle

    24) # of times in this domain a busier queue was found while the cpu

        was just becoming idle but no busier group was found

   Next three are active_load_balance() statistics:

    25) # of times active_load_balance() was called

    26) # of times active_load_balance() tried to move a task and failed

    27) # of times active_load_balance() successfully moved a task

   Next three are sched_balance_exec() statistics:

    28) sbe_cnt is not used

    29) sbe_balanced is not used

    30) sbe_pushed is not used

   Next three are sched_balance_fork() statistics:

    31) sbf_cnt is not used

    32) sbf_balanced is not used

    33) sbf_pushed is not used

   Next three are try_to_wake_up() statistics:

    34) # of times in this domain try_to_wake_up() awoke a task that

        last ran on a different cpu in this domain

    35) # of times in this domain try_to_wake_up() moved a task to the

        waking cpu because it was cache-cold on its own cpu anyway

    36) # of times in this domain try_to_wake_up() started passive balancing

/proc/<pid>/schedstat

----------------

schedstats also adds a new /proc/<pid/schedstat file to include some of

the same information on a per-process level.  There are three fields in

this file correlating to fields 20, 21, and 22 in the CPU fields, but

they only apply for that process.

this file correlating for that process to:

     1) time spent on the cpu

     2) time spent waiting on a runqueue

     3) # of timeslices run on this cpu

A program could be easily written to make use of these extra fields to

report on how well a particular process or set of processes is faring

under the scheduler's policies.  A simple version of such a program is

available at

    http://eaglet.rain.com/rick/linux/schedstat/v10/latency.c

    http://eaglet.rain.com/rick/linux/schedstat/v12/latency.c

#include <linux/thread_info.h>

#include <linux/linkage.h>

#include <linux/list.h>

#ifdef CONFIG_DEBUG_PREEMPT

  extern void fastcall add_preempt_count(int val);

#endif

#ifdef CONFIG_PREEMPT_NOTIFIERS

struct preempt_notifier;

/**

 * preempt_ops - notifiers called when a task is preempted and rescheduled

 * @sched_in: we're about to be rescheduled:

 *    notifier: struct preempt_notifier for the task being scheduled

 *    cpu:  cpu we're scheduled on

 * @sched_out: we've just been preempted

 *    notifier: struct preempt_notifier for the task being preempted

 *    next: the task that's kicking us out

 */

struct preempt_ops {

	void (*sched_in)(struct preempt_notifier *notifier, int cpu);

	void (*sched_out)(struct preempt_notifier *notifier,

			  struct task_struct *next);

};

/**

 * preempt_notifier - key for installing preemption notifiers

 * @link: internal use

 * @ops: defines the notifier functions to be called

 *

 * Usually used in conjunction with container_of().

 */

struct preempt_notifier {

	struct hlist_node link;

	struct preempt_ops *ops;

};

void preempt_notifier_register(struct preempt_notifier *notifier);

void preempt_notifier_unregister(struct preempt_notifier *notifier);

static inline void preempt_notifier_init(struct preempt_notifier *notifier,

				     struct preempt_ops *ops)

{

	INIT_HLIST_NODE(&notifier->link);

	notifier->ops = ops;

}

#endif

#endif /* __LINUX_PREEMPT_H */

#define SCHED_LOAD_SHIFT	10

#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

#define SCHED_LOAD_SCALE_FUZZ	(SCHED_LOAD_SCALE >> 5)

#define SCHED_LOAD_SCALE_FUZZ	(SCHED_LOAD_SCALE >> 1)

#ifdef CONFIG_SMP

#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */

#endif	/* CONFIG_SMP */

/*

 * A runqueue laden with a single nice 0 task scores a weighted_cpuload of

 * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a

 * task of nice 0 or enough lower priority tasks to bring up the

 * weighted_cpuload

 */

static inline int above_background_load(void)

{

	unsigned long cpu;

	for_each_online_cpu(cpu) {

		if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)

			return 1;

	}

	return 0;

}

struct io_context;			/* See blkdev.h */

struct cpuset;

	struct sched_class *sched_class;

	struct sched_entity se;

#ifdef CONFIG_PREEMPT_NOTIFIERS

	/* list of struct preempt_notifier: */

	struct hlist_head preempt_notifiers;

#endif

	unsigned short ioprio;

#ifdef CONFIG_BLK_DEV_IO_TRACE

	unsigned int btrace_seq;

	  Say Y here if you are building a kernel for a desktop system.

	  Say N if you are unsure.

config PREEMPT_NOTIFIERS

	bool

#include <linux/percpu.h>

#include <linux/kthread.h>

#include <linux/seq_file.h>

#include <linux/sysctl.h>

#include <linux/syscalls.h>

#include <linux/times.h>

#include <linux/tsacct_kern.h>

	unsigned int clock_warps, clock_overflows;

	unsigned int clock_unstable_events;

	struct sched_class *load_balance_class;

	atomic_t nr_iowait;

#ifdef CONFIG_SMP

 */

unsigned long long cpu_clock(int cpu)

{

	struct rq *rq = cpu_rq(cpu);

	unsigned long long now;

	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);

	now = rq_clock(rq);

	spin_unlock_irqrestore(&rq->lock, flags);

	local_irq_save(flags);

	now = rq_clock(cpu_rq(cpu));

	local_irq_restore(flags);

	return now;

}

	INIT_LIST_HEAD(&p->run_list);

	p->se.on_rq = 0;

#ifdef CONFIG_PREEMPT_NOTIFIERS

	INIT_HLIST_HEAD(&p->preempt_notifiers);

#endif

	/*

	 * We mark the process as running here, but have not actually

	 * inserted it onto the runqueue yet. This guarantees that

	task_rq_unlock(rq, &flags);

}

#ifdef CONFIG_PREEMPT_NOTIFIERS

/**

 * preempt_notifier_register - tell me when current is being being preempted

 *                         and rescheduled

 */

void preempt_notifier_register(struct preempt_notifier *notifier)

{

	hlist_add_head(&notifier->link, &current->preempt_notifiers);

}

EXPORT_SYMBOL_GPL(preempt_notifier_register);

/**

 * preempt_notifier_unregister - no longer interested in preemption notifications

 *

 * This is safe to call from within a preemption notifier.

 */

void preempt_notifier_unregister(struct preempt_notifier *notifier)

{

	hlist_del(&notifier->link);

}

EXPORT_SYMBOL_GPL(preempt_notifier_unregister);

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)

{

	struct preempt_notifier *notifier;

	struct hlist_node *node;

	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)

		notifier->ops->sched_in(notifier, raw_smp_processor_id());

}

static void

fire_sched_out_preempt_notifiers(struct task_struct *curr,

				 struct task_struct *next)

{

	struct preempt_notifier *notifier;

	struct hlist_node *node;

	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)

		notifier->ops->sched_out(notifier, next);

}

#else

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)

{

}

static void

fire_sched_out_preempt_notifiers(struct task_struct *curr,

				 struct task_struct *next)

{

}

#endif

/**

 * prepare_task_switch - prepare to switch tasks

 * @rq: the runqueue preparing to switch

 * prepare_task_switch sets up locking and calls architecture specific

 * hooks.

 */

static inline void prepare_task_switch(struct rq *rq, struct task_struct *next)

static inline void

prepare_task_switch(struct rq *rq, struct task_struct *prev,

		    struct task_struct *next)

{

	fire_sched_out_preempt_notifiers(prev, next);

	prepare_lock_switch(rq, next);

	prepare_arch_switch(next);

}

	prev_state = prev->state;

	finish_arch_switch(prev);

	finish_lock_switch(rq, prev);

	fire_sched_in_preempt_notifiers(current);

	if (mm)

		mmdrop(mm);

	if (unlikely(prev_state == TASK_DEAD)) {

{

	struct mm_struct *mm, *oldmm;

	prepare_task_switch(rq, next);

	prepare_task_switch(rq, prev, next);

	mm = next->mm;

	oldmm = prev->active_mm;

	/*

		if (!next)

			break;

		migrate_dead(dead_cpu, next);

	}

}

#endif /* CONFIG_HOTPLUG_CPU */

#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)

static struct ctl_table sd_ctl_dir[] = {

	{CTL_UNNUMBERED, "sched_domain", NULL, 0, 0755, NULL, },

	{0,},

};

static struct ctl_table sd_ctl_root[] = {

	{CTL_UNNUMBERED, "kernel", NULL, 0, 0755, sd_ctl_dir, },

	{0,},

};

static struct ctl_table *sd_alloc_ctl_entry(int n)

{

	struct ctl_table *entry =

		kmalloc(n * sizeof(struct ctl_table), GFP_KERNEL);

	BUG_ON(!entry);

	memset(entry, 0, n * sizeof(struct ctl_table));

	return entry;

}

static void

set_table_entry(struct ctl_table *entry, int ctl_name,

		const char *procname, void *data, int maxlen,

		mode_t mode, proc_handler *proc_handler)

{

	entry->ctl_name = ctl_name;

	entry->procname = procname;

	entry->data = data;

	entry->maxlen = maxlen;

	entry->mode = mode;

	entry->proc_handler = proc_handler;

}

static struct ctl_table *

sd_alloc_ctl_domain_table(struct sched_domain *sd)

{

	struct ctl_table *table = sd_alloc_ctl_entry(14);

	set_table_entry(&table[0], 1, "min_interval", &sd->min_interval,

		sizeof(long), 0644, proc_doulongvec_minmax);

	set_table_entry(&table[1], 2, "max_interval", &sd->max_interval,

		sizeof(long), 0644, proc_doulongvec_minmax);

	set_table_entry(&table[2], 3, "busy_idx", &sd->busy_idx,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[3], 4, "idle_idx", &sd->idle_idx,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[4], 5, "newidle_idx", &sd->newidle_idx,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[5], 6, "wake_idx", &sd->wake_idx,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[6], 7, "forkexec_idx", &sd->forkexec_idx,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[7], 8, "busy_factor", &sd->busy_factor,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[8], 9, "imbalance_pct", &sd->imbalance_pct,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[9], 10, "cache_hot_time", &sd->cache_hot_time,

		sizeof(long long), 0644, proc_doulongvec_minmax);

	set_table_entry(&table[10], 11, "cache_nice_tries",

		&sd->cache_nice_tries,

		sizeof(int), 0644, proc_dointvec_minmax);

	set_table_entry(&table[12], 13, "flags", &sd->flags,

		sizeof(int), 0644, proc_dointvec_minmax);

	return table;

}

static ctl_table *sd_alloc_ctl_cpu_table(int cpu)

{

	struct ctl_table *entry, *table;

	struct sched_domain *sd;

	int domain_num = 0, i;

	char buf[32];

	for_each_domain(cpu, sd)

		domain_num++;

	entry = table = sd_alloc_ctl_entry(domain_num + 1);

	i = 0;

	for_each_domain(cpu, sd) {

		snprintf(buf, 32, "domain%d", i);

		entry->ctl_name = i + 1;

		entry->procname = kstrdup(buf, GFP_KERNEL);

		entry->mode = 0755;

		entry->child = sd_alloc_ctl_domain_table(sd);

		entry++;

		i++;

	}

	return table;

}

static struct ctl_table_header *sd_sysctl_header;

static void init_sched_domain_sysctl(void)

{

	int i, cpu_num = num_online_cpus();

	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);

	char buf[32];

	sd_ctl_dir[0].child = entry;

	for (i = 0; i < cpu_num; i++, entry++) {

		snprintf(buf, 32, "cpu%d", i);

		entry->ctl_name = i + 1;

		entry->procname = kstrdup(buf, GFP_KERNEL);

		entry->mode = 0755;

		entry->child = sd_alloc_ctl_cpu_table(i);

	}

	sd_sysctl_header = register_sysctl_table(sd_ctl_root);

}

#else

static void init_sched_domain_sysctl(void)

{

}

#endif

/*

 * migration_call - callback that gets triggered when a CPU is added.

 * Here we can start up the necessary migration thread for the new CPU.

	/* XXX: Theoretical race here - CPU may be hotplugged now */

	hotcpu_notifier(update_sched_domains, 0);

	init_sched_domain_sysctl();

	/* Move init over to a non-isolated CPU */

	if (set_cpus_allowed(current, non_isolated_cpus) < 0)

		BUG();

	set_load_weight(&init_task);

#ifdef CONFIG_PREEMPT_NOTIFIERS

	INIT_HLIST_HEAD(&init_task.preempt_notifiers);

#endif

#ifdef CONFIG_SMP

	nr_cpu_ids = highest_cpu + 1;

	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);