mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-06 00:36:40 +07:00
ef477183d0
Playing with SCHED_DEADLINE and cpusets, I found that I was unable to create new SCHED_DEADLINE tasks, with the error of EBUSY as if the bandwidth was already used up. I then realized there wa no way to see what bandwidth is used by the runqueues to debug the issue. By adding the dl_bw->bw and dl_bw->total_bw to the output of the deadline info in /proc/sched_debug, this allows us to see what bandwidth has been reserved and where a problem may exist. For example, before the issue we see the ratio of the bandwidth: # cat /proc/sys/kernel/sched_rt_runtime_us 950000 # cat /proc/sys/kernel/sched_rt_period_us 1000000 # grep dl /proc/sched_debug dl_rq[0]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[1]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[2]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[3]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[4]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[5]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[6]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 dl_rq[7]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 0 Note: (950000 / 1000000) << 20 == 996147 After I played with cpusets and hit the issue, the result is now: # grep dl /proc/sched_debug dl_rq[0]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : -104857 dl_rq[1]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 104857 dl_rq[2]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 104857 dl_rq[3]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : 104857 dl_rq[4]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : -104857 dl_rq[5]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : -104857 dl_rq[6]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : -104857 dl_rq[7]: .dl_nr_running : 0 .dl_bw->bw : 996147 .dl_bw->total_bw : -104857 This shows that there is definitely a problem as we should never have a negative total bandwidth. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Clark Williams <williams@redhat.com> Cc: Juri Lelli <juri.lelli@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20160222212825.756849091@goodmis.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
981 lines
22 KiB
C
981 lines
22 KiB
C
/*
|
|
* kernel/sched/debug.c
|
|
*
|
|
* Print the CFS rbtree
|
|
*
|
|
* Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/debugfs.h>
|
|
|
|
#include "sched.h"
|
|
|
|
static DEFINE_SPINLOCK(sched_debug_lock);
|
|
|
|
/*
|
|
* This allows printing both to /proc/sched_debug and
|
|
* to the console
|
|
*/
|
|
#define SEQ_printf(m, x...) \
|
|
do { \
|
|
if (m) \
|
|
seq_printf(m, x); \
|
|
else \
|
|
printk(x); \
|
|
} while (0)
|
|
|
|
/*
|
|
* Ease the printing of nsec fields:
|
|
*/
|
|
static long long nsec_high(unsigned long long nsec)
|
|
{
|
|
if ((long long)nsec < 0) {
|
|
nsec = -nsec;
|
|
do_div(nsec, 1000000);
|
|
return -nsec;
|
|
}
|
|
do_div(nsec, 1000000);
|
|
|
|
return nsec;
|
|
}
|
|
|
|
static unsigned long nsec_low(unsigned long long nsec)
|
|
{
|
|
if ((long long)nsec < 0)
|
|
nsec = -nsec;
|
|
|
|
return do_div(nsec, 1000000);
|
|
}
|
|
|
|
#define SPLIT_NS(x) nsec_high(x), nsec_low(x)
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
#name ,
|
|
|
|
static const char * const sched_feat_names[] = {
|
|
#include "features.h"
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
static int sched_feat_show(struct seq_file *m, void *v)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < __SCHED_FEAT_NR; i++) {
|
|
if (!(sysctl_sched_features & (1UL << i)))
|
|
seq_puts(m, "NO_");
|
|
seq_printf(m, "%s ", sched_feat_names[i]);
|
|
}
|
|
seq_puts(m, "\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
|
|
#define jump_label_key__true STATIC_KEY_INIT_TRUE
|
|
#define jump_label_key__false STATIC_KEY_INIT_FALSE
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
jump_label_key__##enabled ,
|
|
|
|
struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
|
|
#include "features.h"
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
static void sched_feat_disable(int i)
|
|
{
|
|
static_key_disable(&sched_feat_keys[i]);
|
|
}
|
|
|
|
static void sched_feat_enable(int i)
|
|
{
|
|
static_key_enable(&sched_feat_keys[i]);
|
|
}
|
|
#else
|
|
static void sched_feat_disable(int i) { };
|
|
static void sched_feat_enable(int i) { };
|
|
#endif /* HAVE_JUMP_LABEL */
|
|
|
|
static int sched_feat_set(char *cmp)
|
|
{
|
|
int i;
|
|
int neg = 0;
|
|
|
|
if (strncmp(cmp, "NO_", 3) == 0) {
|
|
neg = 1;
|
|
cmp += 3;
|
|
}
|
|
|
|
for (i = 0; i < __SCHED_FEAT_NR; i++) {
|
|
if (strcmp(cmp, sched_feat_names[i]) == 0) {
|
|
if (neg) {
|
|
sysctl_sched_features &= ~(1UL << i);
|
|
sched_feat_disable(i);
|
|
} else {
|
|
sysctl_sched_features |= (1UL << i);
|
|
sched_feat_enable(i);
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
return i;
|
|
}
|
|
|
|
static ssize_t
|
|
sched_feat_write(struct file *filp, const char __user *ubuf,
|
|
size_t cnt, loff_t *ppos)
|
|
{
|
|
char buf[64];
|
|
char *cmp;
|
|
int i;
|
|
struct inode *inode;
|
|
|
|
if (cnt > 63)
|
|
cnt = 63;
|
|
|
|
if (copy_from_user(&buf, ubuf, cnt))
|
|
return -EFAULT;
|
|
|
|
buf[cnt] = 0;
|
|
cmp = strstrip(buf);
|
|
|
|
/* Ensure the static_key remains in a consistent state */
|
|
inode = file_inode(filp);
|
|
inode_lock(inode);
|
|
i = sched_feat_set(cmp);
|
|
inode_unlock(inode);
|
|
if (i == __SCHED_FEAT_NR)
|
|
return -EINVAL;
|
|
|
|
*ppos += cnt;
|
|
|
|
return cnt;
|
|
}
|
|
|
|
static int sched_feat_open(struct inode *inode, struct file *filp)
|
|
{
|
|
return single_open(filp, sched_feat_show, NULL);
|
|
}
|
|
|
|
static const struct file_operations sched_feat_fops = {
|
|
.open = sched_feat_open,
|
|
.write = sched_feat_write,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
static __init int sched_init_debug(void)
|
|
{
|
|
debugfs_create_file("sched_features", 0644, NULL, NULL,
|
|
&sched_feat_fops);
|
|
|
|
return 0;
|
|
}
|
|
late_initcall(sched_init_debug);
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
static struct ctl_table sd_ctl_dir[] = {
|
|
{
|
|
.procname = "sched_domain",
|
|
.mode = 0555,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table sd_ctl_root[] = {
|
|
{
|
|
.procname = "kernel",
|
|
.mode = 0555,
|
|
.child = sd_ctl_dir,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table *sd_alloc_ctl_entry(int n)
|
|
{
|
|
struct ctl_table *entry =
|
|
kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
|
|
|
|
return entry;
|
|
}
|
|
|
|
static void sd_free_ctl_entry(struct ctl_table **tablep)
|
|
{
|
|
struct ctl_table *entry;
|
|
|
|
/*
|
|
* In the intermediate directories, both the child directory and
|
|
* procname are dynamically allocated and could fail but the mode
|
|
* will always be set. In the lowest directory the names are
|
|
* static strings and all have proc handlers.
|
|
*/
|
|
for (entry = *tablep; entry->mode; entry++) {
|
|
if (entry->child)
|
|
sd_free_ctl_entry(&entry->child);
|
|
if (entry->proc_handler == NULL)
|
|
kfree(entry->procname);
|
|
}
|
|
|
|
kfree(*tablep);
|
|
*tablep = NULL;
|
|
}
|
|
|
|
static int min_load_idx = 0;
|
|
static int max_load_idx = CPU_LOAD_IDX_MAX-1;
|
|
|
|
static void
|
|
set_table_entry(struct ctl_table *entry,
|
|
const char *procname, void *data, int maxlen,
|
|
umode_t mode, proc_handler *proc_handler,
|
|
bool load_idx)
|
|
{
|
|
entry->procname = procname;
|
|
entry->data = data;
|
|
entry->maxlen = maxlen;
|
|
entry->mode = mode;
|
|
entry->proc_handler = proc_handler;
|
|
|
|
if (load_idx) {
|
|
entry->extra1 = &min_load_idx;
|
|
entry->extra2 = &max_load_idx;
|
|
}
|
|
}
|
|
|
|
static struct ctl_table *
|
|
sd_alloc_ctl_domain_table(struct sched_domain *sd)
|
|
{
|
|
struct ctl_table *table = sd_alloc_ctl_entry(14);
|
|
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
set_table_entry(&table[0], "min_interval", &sd->min_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax, false);
|
|
set_table_entry(&table[1], "max_interval", &sd->max_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax, false);
|
|
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[9], "cache_nice_tries",
|
|
&sd->cache_nice_tries,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[10], "flags", &sd->flags,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[11], "max_newidle_lb_cost",
|
|
&sd->max_newidle_lb_cost,
|
|
sizeof(long), 0644, proc_doulongvec_minmax, false);
|
|
set_table_entry(&table[12], "name", sd->name,
|
|
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
|
|
/* &table[13] is terminator */
|
|
|
|
return table;
|
|
}
|
|
|
|
static struct 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);
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
i = 0;
|
|
for_each_domain(cpu, sd) {
|
|
snprintf(buf, 32, "domain%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_domain_table(sd);
|
|
entry++;
|
|
i++;
|
|
}
|
|
return table;
|
|
}
|
|
|
|
static struct ctl_table_header *sd_sysctl_header;
|
|
void register_sched_domain_sysctl(void)
|
|
{
|
|
int i, cpu_num = num_possible_cpus();
|
|
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
|
|
char buf[32];
|
|
|
|
WARN_ON(sd_ctl_dir[0].child);
|
|
sd_ctl_dir[0].child = entry;
|
|
|
|
if (entry == NULL)
|
|
return;
|
|
|
|
for_each_possible_cpu(i) {
|
|
snprintf(buf, 32, "cpu%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_cpu_table(i);
|
|
entry++;
|
|
}
|
|
|
|
WARN_ON(sd_sysctl_header);
|
|
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
|
|
}
|
|
|
|
/* may be called multiple times per register */
|
|
void unregister_sched_domain_sysctl(void)
|
|
{
|
|
unregister_sysctl_table(sd_sysctl_header);
|
|
sd_sysctl_header = NULL;
|
|
if (sd_ctl_dir[0].child)
|
|
sd_free_ctl_entry(&sd_ctl_dir[0].child);
|
|
}
|
|
#endif /* CONFIG_SYSCTL */
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
|
|
{
|
|
struct sched_entity *se = tg->se[cpu];
|
|
|
|
#define P(F) \
|
|
SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F)
|
|
#define PN(F) \
|
|
SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
|
|
|
|
if (!se)
|
|
return;
|
|
|
|
PN(se->exec_start);
|
|
PN(se->vruntime);
|
|
PN(se->sum_exec_runtime);
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
if (schedstat_enabled()) {
|
|
PN(se->statistics.wait_start);
|
|
PN(se->statistics.sleep_start);
|
|
PN(se->statistics.block_start);
|
|
PN(se->statistics.sleep_max);
|
|
PN(se->statistics.block_max);
|
|
PN(se->statistics.exec_max);
|
|
PN(se->statistics.slice_max);
|
|
PN(se->statistics.wait_max);
|
|
PN(se->statistics.wait_sum);
|
|
P(se->statistics.wait_count);
|
|
}
|
|
#endif
|
|
P(se->load.weight);
|
|
#ifdef CONFIG_SMP
|
|
P(se->avg.load_avg);
|
|
P(se->avg.util_avg);
|
|
#endif
|
|
#undef PN
|
|
#undef P
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
static char group_path[PATH_MAX];
|
|
|
|
static char *task_group_path(struct task_group *tg)
|
|
{
|
|
if (autogroup_path(tg, group_path, PATH_MAX))
|
|
return group_path;
|
|
|
|
return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
|
|
}
|
|
#endif
|
|
|
|
static void
|
|
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
|
|
{
|
|
if (rq->curr == p)
|
|
SEQ_printf(m, "R");
|
|
else
|
|
SEQ_printf(m, " ");
|
|
|
|
SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
|
|
p->comm, task_pid_nr(p),
|
|
SPLIT_NS(p->se.vruntime),
|
|
(long long)(p->nvcsw + p->nivcsw),
|
|
p->prio);
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
if (schedstat_enabled()) {
|
|
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
|
|
SPLIT_NS(p->se.statistics.wait_sum),
|
|
SPLIT_NS(p->se.sum_exec_runtime),
|
|
SPLIT_NS(p->se.statistics.sum_sleep_runtime));
|
|
}
|
|
#else
|
|
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
|
|
0LL, 0L,
|
|
SPLIT_NS(p->se.sum_exec_runtime),
|
|
0LL, 0L);
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
|
|
#endif
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
SEQ_printf(m, " %s", task_group_path(task_group(p)));
|
|
#endif
|
|
|
|
SEQ_printf(m, "\n");
|
|
}
|
|
|
|
static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
SEQ_printf(m,
|
|
"\nrunnable tasks:\n"
|
|
" task PID tree-key switches prio"
|
|
" wait-time sum-exec sum-sleep\n"
|
|
"------------------------------------------------------"
|
|
"----------------------------------------------------\n");
|
|
|
|
rcu_read_lock();
|
|
for_each_process_thread(g, p) {
|
|
if (task_cpu(p) != rq_cpu)
|
|
continue;
|
|
|
|
print_task(m, rq, p);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
|
|
{
|
|
s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
|
|
spread, rq0_min_vruntime, spread0;
|
|
struct rq *rq = cpu_rq(cpu);
|
|
struct sched_entity *last;
|
|
unsigned long flags;
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
|
|
#else
|
|
SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
|
|
#endif
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
|
|
SPLIT_NS(cfs_rq->exec_clock));
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (cfs_rq->rb_leftmost)
|
|
MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
|
|
last = __pick_last_entity(cfs_rq);
|
|
if (last)
|
|
max_vruntime = last->vruntime;
|
|
min_vruntime = cfs_rq->min_vruntime;
|
|
rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
|
|
SPLIT_NS(MIN_vruntime));
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
|
|
SPLIT_NS(min_vruntime));
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime",
|
|
SPLIT_NS(max_vruntime));
|
|
spread = max_vruntime - MIN_vruntime;
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread",
|
|
SPLIT_NS(spread));
|
|
spread0 = min_vruntime - rq0_min_vruntime;
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0",
|
|
SPLIT_NS(spread0));
|
|
SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over",
|
|
cfs_rq->nr_spread_over);
|
|
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
|
|
#ifdef CONFIG_SMP
|
|
SEQ_printf(m, " .%-30s: %lu\n", "load_avg",
|
|
cfs_rq->avg.load_avg);
|
|
SEQ_printf(m, " .%-30s: %lu\n", "runnable_load_avg",
|
|
cfs_rq->runnable_load_avg);
|
|
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
|
|
cfs_rq->avg.util_avg);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "removed_load_avg",
|
|
atomic_long_read(&cfs_rq->removed_load_avg));
|
|
SEQ_printf(m, " .%-30s: %ld\n", "removed_util_avg",
|
|
atomic_long_read(&cfs_rq->removed_util_avg));
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib",
|
|
cfs_rq->tg_load_avg_contrib);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg",
|
|
atomic_long_read(&cfs_rq->tg->load_avg));
|
|
#endif
|
|
#endif
|
|
#ifdef CONFIG_CFS_BANDWIDTH
|
|
SEQ_printf(m, " .%-30s: %d\n", "throttled",
|
|
cfs_rq->throttled);
|
|
SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
|
|
cfs_rq->throttle_count);
|
|
#endif
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
print_cfs_group_stats(m, cpu, cfs_rq->tg);
|
|
#endif
|
|
}
|
|
|
|
void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
|
|
{
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
|
|
#else
|
|
SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
|
|
#endif
|
|
|
|
#define P(x) \
|
|
SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
|
|
#define PN(x) \
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
|
|
|
|
P(rt_nr_running);
|
|
P(rt_throttled);
|
|
PN(rt_time);
|
|
PN(rt_runtime);
|
|
|
|
#undef PN
|
|
#undef P
|
|
}
|
|
|
|
void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
|
|
{
|
|
struct dl_bw *dl_bw;
|
|
|
|
SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
|
|
#ifdef CONFIG_SMP
|
|
dl_bw = &cpu_rq(cpu)->rd->dl_bw;
|
|
#else
|
|
dl_bw = &dl_rq->dl_bw;
|
|
#endif
|
|
SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
|
|
SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
|
|
}
|
|
|
|
extern __read_mostly int sched_clock_running;
|
|
|
|
static void print_cpu(struct seq_file *m, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long flags;
|
|
|
|
#ifdef CONFIG_X86
|
|
{
|
|
unsigned int freq = cpu_khz ? : 1;
|
|
|
|
SEQ_printf(m, "cpu#%d, %u.%03u MHz\n",
|
|
cpu, freq / 1000, (freq % 1000));
|
|
}
|
|
#else
|
|
SEQ_printf(m, "cpu#%d\n", cpu);
|
|
#endif
|
|
|
|
#define P(x) \
|
|
do { \
|
|
if (sizeof(rq->x) == 4) \
|
|
SEQ_printf(m, " .%-30s: %ld\n", #x, (long)(rq->x)); \
|
|
else \
|
|
SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x));\
|
|
} while (0)
|
|
|
|
#define PN(x) \
|
|
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
|
|
|
|
P(nr_running);
|
|
SEQ_printf(m, " .%-30s: %lu\n", "load",
|
|
rq->load.weight);
|
|
P(nr_switches);
|
|
P(nr_load_updates);
|
|
P(nr_uninterruptible);
|
|
PN(next_balance);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
|
|
PN(clock);
|
|
PN(clock_task);
|
|
P(cpu_load[0]);
|
|
P(cpu_load[1]);
|
|
P(cpu_load[2]);
|
|
P(cpu_load[3]);
|
|
P(cpu_load[4]);
|
|
#undef P
|
|
#undef PN
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n);
|
|
#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n);
|
|
|
|
#ifdef CONFIG_SMP
|
|
P64(avg_idle);
|
|
P64(max_idle_balance_cost);
|
|
#endif
|
|
|
|
if (schedstat_enabled()) {
|
|
P(yld_count);
|
|
P(sched_count);
|
|
P(sched_goidle);
|
|
P(ttwu_count);
|
|
P(ttwu_local);
|
|
}
|
|
|
|
#undef P
|
|
#undef P64
|
|
#endif
|
|
spin_lock_irqsave(&sched_debug_lock, flags);
|
|
print_cfs_stats(m, cpu);
|
|
print_rt_stats(m, cpu);
|
|
print_dl_stats(m, cpu);
|
|
|
|
print_rq(m, rq, cpu);
|
|
spin_unlock_irqrestore(&sched_debug_lock, flags);
|
|
SEQ_printf(m, "\n");
|
|
}
|
|
|
|
static const char *sched_tunable_scaling_names[] = {
|
|
"none",
|
|
"logaritmic",
|
|
"linear"
|
|
};
|
|
|
|
static void sched_debug_header(struct seq_file *m)
|
|
{
|
|
u64 ktime, sched_clk, cpu_clk;
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
ktime = ktime_to_ns(ktime_get());
|
|
sched_clk = sched_clock();
|
|
cpu_clk = local_clock();
|
|
local_irq_restore(flags);
|
|
|
|
SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
|
|
init_utsname()->release,
|
|
(int)strcspn(init_utsname()->version, " "),
|
|
init_utsname()->version);
|
|
|
|
#define P(x) \
|
|
SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x))
|
|
#define PN(x) \
|
|
SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
|
|
PN(ktime);
|
|
PN(sched_clk);
|
|
PN(cpu_clk);
|
|
P(jiffies);
|
|
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
|
|
P(sched_clock_stable());
|
|
#endif
|
|
#undef PN
|
|
#undef P
|
|
|
|
SEQ_printf(m, "\n");
|
|
SEQ_printf(m, "sysctl_sched\n");
|
|
|
|
#define P(x) \
|
|
SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x))
|
|
#define PN(x) \
|
|
SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
|
|
PN(sysctl_sched_latency);
|
|
PN(sysctl_sched_min_granularity);
|
|
PN(sysctl_sched_wakeup_granularity);
|
|
P(sysctl_sched_child_runs_first);
|
|
P(sysctl_sched_features);
|
|
#undef PN
|
|
#undef P
|
|
|
|
SEQ_printf(m, " .%-40s: %d (%s)\n",
|
|
"sysctl_sched_tunable_scaling",
|
|
sysctl_sched_tunable_scaling,
|
|
sched_tunable_scaling_names[sysctl_sched_tunable_scaling]);
|
|
SEQ_printf(m, "\n");
|
|
}
|
|
|
|
static int sched_debug_show(struct seq_file *m, void *v)
|
|
{
|
|
int cpu = (unsigned long)(v - 2);
|
|
|
|
if (cpu != -1)
|
|
print_cpu(m, cpu);
|
|
else
|
|
sched_debug_header(m);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void sysrq_sched_debug_show(void)
|
|
{
|
|
int cpu;
|
|
|
|
sched_debug_header(NULL);
|
|
for_each_online_cpu(cpu)
|
|
print_cpu(NULL, cpu);
|
|
|
|
}
|
|
|
|
/*
|
|
* This itererator needs some explanation.
|
|
* It returns 1 for the header position.
|
|
* This means 2 is cpu 0.
|
|
* In a hotplugged system some cpus, including cpu 0, may be missing so we have
|
|
* to use cpumask_* to iterate over the cpus.
|
|
*/
|
|
static void *sched_debug_start(struct seq_file *file, loff_t *offset)
|
|
{
|
|
unsigned long n = *offset;
|
|
|
|
if (n == 0)
|
|
return (void *) 1;
|
|
|
|
n--;
|
|
|
|
if (n > 0)
|
|
n = cpumask_next(n - 1, cpu_online_mask);
|
|
else
|
|
n = cpumask_first(cpu_online_mask);
|
|
|
|
*offset = n + 1;
|
|
|
|
if (n < nr_cpu_ids)
|
|
return (void *)(unsigned long)(n + 2);
|
|
return NULL;
|
|
}
|
|
|
|
static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset)
|
|
{
|
|
(*offset)++;
|
|
return sched_debug_start(file, offset);
|
|
}
|
|
|
|
static void sched_debug_stop(struct seq_file *file, void *data)
|
|
{
|
|
}
|
|
|
|
static const struct seq_operations sched_debug_sops = {
|
|
.start = sched_debug_start,
|
|
.next = sched_debug_next,
|
|
.stop = sched_debug_stop,
|
|
.show = sched_debug_show,
|
|
};
|
|
|
|
static int sched_debug_release(struct inode *inode, struct file *file)
|
|
{
|
|
seq_release(inode, file);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int sched_debug_open(struct inode *inode, struct file *filp)
|
|
{
|
|
int ret = 0;
|
|
|
|
ret = seq_open(filp, &sched_debug_sops);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static const struct file_operations sched_debug_fops = {
|
|
.open = sched_debug_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = sched_debug_release,
|
|
};
|
|
|
|
static int __init init_sched_debug_procfs(void)
|
|
{
|
|
struct proc_dir_entry *pe;
|
|
|
|
pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
|
|
if (!pe)
|
|
return -ENOMEM;
|
|
return 0;
|
|
}
|
|
|
|
__initcall(init_sched_debug_procfs);
|
|
|
|
#define __P(F) \
|
|
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
|
|
#define P(F) \
|
|
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
|
|
#define __PN(F) \
|
|
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
|
|
#define PN(F) \
|
|
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
|
|
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
|
|
unsigned long tpf, unsigned long gsf, unsigned long gpf)
|
|
{
|
|
SEQ_printf(m, "numa_faults node=%d ", node);
|
|
SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
|
|
SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
|
|
}
|
|
#endif
|
|
|
|
|
|
static void sched_show_numa(struct task_struct *p, struct seq_file *m)
|
|
{
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
struct mempolicy *pol;
|
|
|
|
if (p->mm)
|
|
P(mm->numa_scan_seq);
|
|
|
|
task_lock(p);
|
|
pol = p->mempolicy;
|
|
if (pol && !(pol->flags & MPOL_F_MORON))
|
|
pol = NULL;
|
|
mpol_get(pol);
|
|
task_unlock(p);
|
|
|
|
P(numa_pages_migrated);
|
|
P(numa_preferred_nid);
|
|
P(total_numa_faults);
|
|
SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
|
|
task_node(p), task_numa_group_id(p));
|
|
show_numa_stats(p, m);
|
|
mpol_put(pol);
|
|
#endif
|
|
}
|
|
|
|
void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
|
|
{
|
|
unsigned long nr_switches;
|
|
|
|
SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
|
|
get_nr_threads(p));
|
|
SEQ_printf(m,
|
|
"---------------------------------------------------------"
|
|
"----------\n");
|
|
#define __P(F) \
|
|
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
|
|
#define P(F) \
|
|
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
|
|
#define __PN(F) \
|
|
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
|
|
#define PN(F) \
|
|
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
|
|
|
|
PN(se.exec_start);
|
|
PN(se.vruntime);
|
|
PN(se.sum_exec_runtime);
|
|
|
|
nr_switches = p->nvcsw + p->nivcsw;
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
P(se.nr_migrations);
|
|
|
|
if (schedstat_enabled()) {
|
|
u64 avg_atom, avg_per_cpu;
|
|
|
|
PN(se.statistics.sum_sleep_runtime);
|
|
PN(se.statistics.wait_start);
|
|
PN(se.statistics.sleep_start);
|
|
PN(se.statistics.block_start);
|
|
PN(se.statistics.sleep_max);
|
|
PN(se.statistics.block_max);
|
|
PN(se.statistics.exec_max);
|
|
PN(se.statistics.slice_max);
|
|
PN(se.statistics.wait_max);
|
|
PN(se.statistics.wait_sum);
|
|
P(se.statistics.wait_count);
|
|
PN(se.statistics.iowait_sum);
|
|
P(se.statistics.iowait_count);
|
|
P(se.statistics.nr_migrations_cold);
|
|
P(se.statistics.nr_failed_migrations_affine);
|
|
P(se.statistics.nr_failed_migrations_running);
|
|
P(se.statistics.nr_failed_migrations_hot);
|
|
P(se.statistics.nr_forced_migrations);
|
|
P(se.statistics.nr_wakeups);
|
|
P(se.statistics.nr_wakeups_sync);
|
|
P(se.statistics.nr_wakeups_migrate);
|
|
P(se.statistics.nr_wakeups_local);
|
|
P(se.statistics.nr_wakeups_remote);
|
|
P(se.statistics.nr_wakeups_affine);
|
|
P(se.statistics.nr_wakeups_affine_attempts);
|
|
P(se.statistics.nr_wakeups_passive);
|
|
P(se.statistics.nr_wakeups_idle);
|
|
|
|
avg_atom = p->se.sum_exec_runtime;
|
|
if (nr_switches)
|
|
avg_atom = div64_ul(avg_atom, nr_switches);
|
|
else
|
|
avg_atom = -1LL;
|
|
|
|
avg_per_cpu = p->se.sum_exec_runtime;
|
|
if (p->se.nr_migrations) {
|
|
avg_per_cpu = div64_u64(avg_per_cpu,
|
|
p->se.nr_migrations);
|
|
} else {
|
|
avg_per_cpu = -1LL;
|
|
}
|
|
|
|
__PN(avg_atom);
|
|
__PN(avg_per_cpu);
|
|
}
|
|
#endif
|
|
__P(nr_switches);
|
|
SEQ_printf(m, "%-45s:%21Ld\n",
|
|
"nr_voluntary_switches", (long long)p->nvcsw);
|
|
SEQ_printf(m, "%-45s:%21Ld\n",
|
|
"nr_involuntary_switches", (long long)p->nivcsw);
|
|
|
|
P(se.load.weight);
|
|
#ifdef CONFIG_SMP
|
|
P(se.avg.load_sum);
|
|
P(se.avg.util_sum);
|
|
P(se.avg.load_avg);
|
|
P(se.avg.util_avg);
|
|
P(se.avg.last_update_time);
|
|
#endif
|
|
P(policy);
|
|
P(prio);
|
|
#undef PN
|
|
#undef __PN
|
|
#undef P
|
|
#undef __P
|
|
|
|
{
|
|
unsigned int this_cpu = raw_smp_processor_id();
|
|
u64 t0, t1;
|
|
|
|
t0 = cpu_clock(this_cpu);
|
|
t1 = cpu_clock(this_cpu);
|
|
SEQ_printf(m, "%-45s:%21Ld\n",
|
|
"clock-delta", (long long)(t1-t0));
|
|
}
|
|
|
|
sched_show_numa(p, m);
|
|
}
|
|
|
|
void proc_sched_set_task(struct task_struct *p)
|
|
{
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
|
|
#endif
|
|
}
|