linux/kernel/sched_stats.h

337 lines
9.3 KiB
C
Raw Normal View History

#ifdef CONFIG_SCHEDSTATS
/*
* bump this up when changing the output format or the meaning of an existing
* format, so that tools can adapt (or abort)
*/
#define SCHEDSTAT_VERSION 15
static int show_schedstat(struct seq_file *seq, void *v)
{
int cpu;
int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
char *mask_str = kmalloc(mask_len, GFP_KERNEL);
if (mask_str == NULL)
return -ENOMEM;
seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
seq_printf(seq, "timestamp %lu\n", jiffies);
for_each_online_cpu(cpu) {
struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
struct sched_domain *sd;
int dcount = 0;
#endif
/* runqueue-specific stats */
seq_printf(seq,
"cpu%d %u %u %u %u %u %u %llu %llu %lu",
cpu, rq->yld_count,
rq->sched_switch, rq->sched_count, rq->sched_goidle,
rq->ttwu_count, rq->ttwu_local,
rq->rq_cpu_time,
rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
seq_printf(seq, "\n");
#ifdef CONFIG_SMP
/* domain-specific stats */
rcu_read_lock();
for_each_domain(cpu, sd) {
enum cpu_idle_type itype;
cpumask_scnprintf(mask_str, mask_len,
sched_domain_span(sd));
seq_printf(seq, "domain%d %s", dcount++, mask_str);
for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
itype++) {
seq_printf(seq, " %u %u %u %u %u %u %u %u",
sd->lb_count[itype],
sd->lb_balanced[itype],
sd->lb_failed[itype],
sd->lb_imbalance[itype],
sd->lb_gained[itype],
sd->lb_hot_gained[itype],
sd->lb_nobusyq[itype],
sd->lb_nobusyg[itype]);
}
seq_printf(seq,
" %u %u %u %u %u %u %u %u %u %u %u %u\n",
sd->alb_count, sd->alb_failed, sd->alb_pushed,
sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed,
sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
sd->ttwu_wake_remote, sd->ttwu_move_affine,
sd->ttwu_move_balance);
}
rcu_read_unlock();
#endif
}
kfree(mask_str);
return 0;
}
static int schedstat_open(struct inode *inode, struct file *file)
{
unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
char *buf = kmalloc(size, GFP_KERNEL);
struct seq_file *m;
int res;
if (!buf)
return -ENOMEM;
res = single_open(file, show_schedstat, NULL);
if (!res) {
m = file->private_data;
m->buf = buf;
m->size = size;
} else
kfree(buf);
return res;
}
static const struct file_operations proc_schedstat_operations = {
.open = schedstat_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init proc_schedstat_init(void)
{
proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
return 0;
}
module_init(proc_schedstat_init);
/*
* Expects runqueue lock to be held for atomicity of update
*/
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
{
if (rq) {
rq->rq_sched_info.run_delay += delta;
rq->rq_sched_info.pcount++;
}
}
/*
* Expects runqueue lock to be held for atomicity of update
*/
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{
if (rq)
rq->rq_cpu_time += delta;
}
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
static inline void
rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
{
if (rq)
rq->rq_sched_info.run_delay += delta;
}
# define schedstat_inc(rq, field) do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0)
# define schedstat_set(var, val) do { var = (val); } while (0)
#else /* !CONFIG_SCHEDSTATS */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
{}
static inline void
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
{}
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{}
# define schedstat_inc(rq, field) do { } while (0)
# define schedstat_add(rq, field, amt) do { } while (0)
# define schedstat_set(var, val) do { } while (0)
#endif
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
t->sched_info.last_queued = 0;
}
/*
* We are interested in knowing how long it was from the *first* time a
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
* task was queued to the time that it finally hit a cpu, we call this routine
* from dequeue_task() to account for possible rq->clock skew across cpus. The
* delta taken on each cpu would annul the skew.
*/
static inline void sched_info_dequeued(struct task_struct *t)
{
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
unsigned long long now = task_rq(t)->clock, delta = 0;
if (unlikely(sched_info_on()))
if (t->sched_info.last_queued)
delta = now - t->sched_info.last_queued;
sched_info_reset_dequeued(t);
t->sched_info.run_delay += delta;
rq_sched_info_dequeued(task_rq(t), delta);
}
/*
* Called when a task finally hits the cpu. We can now calculate how
* long it was waiting to run. We also note when it began so that we
* can keep stats on how long its timeslice is.
*/
static void sched_info_arrive(struct task_struct *t)
{
unsigned long long now = task_rq(t)->clock, delta = 0;
if (t->sched_info.last_queued)
delta = now - t->sched_info.last_queued;
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
sched_info_reset_dequeued(t);
t->sched_info.run_delay += delta;
t->sched_info.last_arrival = now;
t->sched_info.pcount++;
rq_sched_info_arrive(task_rq(t), delta);
}
/*
* This function is only called from enqueue_task(), but also only updates
* the timestamp if it is already not set. It's assumed that
* sched_info_dequeued() will clear that stamp when appropriate.
*/
static inline void sched_info_queued(struct task_struct *t)
{
if (unlikely(sched_info_on()))
if (!t->sched_info.last_queued)
t->sched_info.last_queued = task_rq(t)->clock;
}
/*
* Called when a process ceases being the active-running process, either
* voluntarily or involuntarily. Now we can calculate how long we ran.
* Also, if the process is still in the TASK_RUNNING state, call
* sched_info_queued() to mark that it has now again started waiting on
* the runqueue.
*/
static inline void sched_info_depart(struct task_struct *t)
{
unsigned long long delta = task_rq(t)->clock -
t->sched_info.last_arrival;
rq_sched_info_depart(task_rq(t), delta);
if (t->state == TASK_RUNNING)
sched_info_queued(t);
}
/*
* Called when tasks are switched involuntarily due, typically, to expiring
* their time slice. (This may also be called when switching to or from
* the idle task.) We are only called when prev != next.
*/
static inline void
__sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
struct rq *rq = task_rq(prev);
/*
* prev now departs the cpu. It's not interesting to record
* stats about how efficient we were at scheduling the idle
* process, however.
*/
if (prev != rq->idle)
sched_info_depart(prev);
if (next != rq->idle)
sched_info_arrive(next);
}
static inline void
sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
if (unlikely(sched_info_on()))
__sched_info_switch(prev, next);
}
#else
sched: fix accounting in task delay accounting & migration On Thu, Jun 19, 2008 at 12:27:14PM +0200, Peter Zijlstra wrote: > On Thu, 2008-06-05 at 10:50 +0530, Ankita Garg wrote: > > > Thanks Peter for the explanation... > > > > I agree with the above and that is the reason why I did not see weird > > values with cpu_time. But, run_delay still would suffer skews as the end > > points for delta could be taken on different cpus due to migration (more > > so on RT kernel due to the push-pull operations). With the below patch, > > I could not reproduce the issue I had seen earlier. After every dequeue, > > we take the delta and start wait measurements from zero when moved to a > > different rq. > > OK, so task delay delay accounting is broken because it doesn't take > migration into account. > > What you've done is make it symmetric wrt enqueue, and account it like > > cpu0 cpu1 > > enqueue > <wait-d1> > dequeue > enqueue > <wait-d2> > run > > Where you add both d1 and d2 to the run_delay,.. right? > Thanks for reviewing the patch. The above is exactly what I have done. > This seems like a good fix, however it looks like the patch will break > compilation in !CONFIG_SCHEDSTATS && !CONFIG_TASK_DELAY_ACCT, of it > failing to provide a stub for sched_info_dequeue() in that case. Fixed. Pl. find the new patch below. Signed-off-by: Ankita Garg <ankita@in.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: rostedt@goodmis.org Cc: suresh.b.siddha@intel.com Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dhaval@linux.vnet.ibm.com Cc: vatsa@linux.vnet.ibm.com Cc: David Bahi <DBahi@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-01 11:00:06 +02:00
#define sched_info_queued(t) do { } while (0)
#define sched_info_reset_dequeued(t) do { } while (0)
#define sched_info_dequeued(t) do { } while (0)
#define sched_info_switch(t, next) do { } while (0)
#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
/*
* The following are functions that support scheduler-internal time accounting.
* These functions are generally called at the timer tick. None of this depends
* on CONFIG_SCHEDSTATS.
*/
/**
* account_group_user_time - Maintain utime for a thread group.
*
* @tsk: Pointer to task structure.
* @cputime: Time value by which to increment the utime field of the
* thread_group_cputime structure.
*
* If thread group time is being maintained, get the structure for the
* running CPU and update the utime field there.
*/
static inline void account_group_user_time(struct task_struct *tsk,
cputime_t cputime)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
if (!cputimer->running)
return;
raw_spin_lock(&cputimer->lock);
cputimer->cputime.utime =
cputime_add(cputimer->cputime.utime, cputime);
raw_spin_unlock(&cputimer->lock);
}
/**
* account_group_system_time - Maintain stime for a thread group.
*
* @tsk: Pointer to task structure.
* @cputime: Time value by which to increment the stime field of the
* thread_group_cputime structure.
*
* If thread group time is being maintained, get the structure for the
* running CPU and update the stime field there.
*/
static inline void account_group_system_time(struct task_struct *tsk,
cputime_t cputime)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
if (!cputimer->running)
return;
raw_spin_lock(&cputimer->lock);
cputimer->cputime.stime =
cputime_add(cputimer->cputime.stime, cputime);
raw_spin_unlock(&cputimer->lock);
}
/**
* account_group_exec_runtime - Maintain exec runtime for a thread group.
*
* @tsk: Pointer to task structure.
* @ns: Time value by which to increment the sum_exec_runtime field
* of the thread_group_cputime structure.
*
* If thread group time is being maintained, get the structure for the
* running CPU and update the sum_exec_runtime field there.
*/
static inline void account_group_exec_runtime(struct task_struct *tsk,
unsigned long long ns)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
if (!cputimer->running)
return;
raw_spin_lock(&cputimer->lock);
cputimer->cputime.sum_exec_runtime += ns;
raw_spin_unlock(&cputimer->lock);
}