mirror of
https://github.com/torvalds/linux
synced 2024-10-06 03:16:02 +00:00
cb2517653f
schedstats is very useful during debugging and performance tuning but it incurs overhead to calculate the stats. As such, even though it can be disabled at build time, it is often enabled as the information is useful. This patch adds a kernel command-line and sysctl tunable to enable or disable schedstats on demand (when it's built in). It is disabled by default as someone who knows they need it can also learn to enable it when necessary. The benefits are dependent on how scheduler-intensive the workload is. If it is then the patch reduces the number of cycles spent calculating the stats with a small benefit from reducing the cache footprint of the scheduler. These measurements were taken from a 48-core 2-socket machine with Xeon(R) E5-2670 v3 cpus although they were also tested on a single socket machine 8-core machine with Intel i7-3770 processors. netperf-tcp 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Hmean 64 560.45 ( 0.00%) 575.98 ( 2.77%) Hmean 128 766.66 ( 0.00%) 795.79 ( 3.80%) Hmean 256 950.51 ( 0.00%) 981.50 ( 3.26%) Hmean 1024 1433.25 ( 0.00%) 1466.51 ( 2.32%) Hmean 2048 2810.54 ( 0.00%) 2879.75 ( 2.46%) Hmean 3312 4618.18 ( 0.00%) 4682.09 ( 1.38%) Hmean 4096 5306.42 ( 0.00%) 5346.39 ( 0.75%) Hmean 8192 10581.44 ( 0.00%) 10698.15 ( 1.10%) Hmean 16384 18857.70 ( 0.00%) 18937.61 ( 0.42%) Small gains here, UDP_STREAM showed nothing intresting and neither did the TCP_RR tests. The gains on the 8-core machine were very similar. tbench4 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Hmean mb/sec-1 500.85 ( 0.00%) 522.43 ( 4.31%) Hmean mb/sec-2 984.66 ( 0.00%) 1018.19 ( 3.41%) Hmean mb/sec-4 1827.91 ( 0.00%) 1847.78 ( 1.09%) Hmean mb/sec-8 3561.36 ( 0.00%) 3611.28 ( 1.40%) Hmean mb/sec-16 5824.52 ( 0.00%) 5929.03 ( 1.79%) Hmean mb/sec-32 10943.10 ( 0.00%) 10802.83 ( -1.28%) Hmean mb/sec-64 15950.81 ( 0.00%) 16211.31 ( 1.63%) Hmean mb/sec-128 15302.17 ( 0.00%) 15445.11 ( 0.93%) Hmean mb/sec-256 14866.18 ( 0.00%) 15088.73 ( 1.50%) Hmean mb/sec-512 15223.31 ( 0.00%) 15373.69 ( 0.99%) Hmean mb/sec-1024 14574.25 ( 0.00%) 14598.02 ( 0.16%) Hmean mb/sec-2048 13569.02 ( 0.00%) 13733.86 ( 1.21%) Hmean mb/sec-3072 12865.98 ( 0.00%) 13209.23 ( 2.67%) Small gains of 2-4% at low thread counts and otherwise flat. The gains on the 8-core machine were slightly different tbench4 on 8-core i7-3770 single socket machine Hmean mb/sec-1 442.59 ( 0.00%) 448.73 ( 1.39%) Hmean mb/sec-2 796.68 ( 0.00%) 794.39 ( -0.29%) Hmean mb/sec-4 1322.52 ( 0.00%) 1343.66 ( 1.60%) Hmean mb/sec-8 2611.65 ( 0.00%) 2694.86 ( 3.19%) Hmean mb/sec-16 2537.07 ( 0.00%) 2609.34 ( 2.85%) Hmean mb/sec-32 2506.02 ( 0.00%) 2578.18 ( 2.88%) Hmean mb/sec-64 2511.06 ( 0.00%) 2569.16 ( 2.31%) Hmean mb/sec-128 2313.38 ( 0.00%) 2395.50 ( 3.55%) Hmean mb/sec-256 2110.04 ( 0.00%) 2177.45 ( 3.19%) Hmean mb/sec-512 2072.51 ( 0.00%) 2053.97 ( -0.89%) In constract, this shows a relatively steady 2-3% gain at higher thread counts. Due to the nature of the patch and the type of workload, it's not a surprise that the result will depend on the CPU used. hackbench-pipes 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Amean 1 0.0637 ( 0.00%) 0.0660 ( -3.59%) Amean 4 0.1229 ( 0.00%) 0.1181 ( 3.84%) Amean 7 0.1921 ( 0.00%) 0.1911 ( 0.52%) Amean 12 0.3117 ( 0.00%) 0.2923 ( 6.23%) Amean 21 0.4050 ( 0.00%) 0.3899 ( 3.74%) Amean 30 0.4586 ( 0.00%) 0.4433 ( 3.33%) Amean 48 0.5910 ( 0.00%) 0.5694 ( 3.65%) Amean 79 0.8663 ( 0.00%) 0.8626 ( 0.43%) Amean 110 1.1543 ( 0.00%) 1.1517 ( 0.22%) Amean 141 1.4457 ( 0.00%) 1.4290 ( 1.16%) Amean 172 1.7090 ( 0.00%) 1.6924 ( 0.97%) Amean 192 1.9126 ( 0.00%) 1.9089 ( 0.19%) Some small gains and losses and while the variance data is not included, it's close to the noise. The UMA machine did not show anything particularly different pipetest 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v2r2 Min Time 4.13 ( 0.00%) 3.99 ( 3.39%) 1st-qrtle Time 4.38 ( 0.00%) 4.27 ( 2.51%) 2nd-qrtle Time 4.46 ( 0.00%) 4.39 ( 1.57%) 3rd-qrtle Time 4.56 ( 0.00%) 4.51 ( 1.10%) Max-90% Time 4.67 ( 0.00%) 4.60 ( 1.50%) Max-93% Time 4.71 ( 0.00%) 4.65 ( 1.27%) Max-95% Time 4.74 ( 0.00%) 4.71 ( 0.63%) Max-99% Time 4.88 ( 0.00%) 4.79 ( 1.84%) Max Time 4.93 ( 0.00%) 4.83 ( 2.03%) Mean Time 4.48 ( 0.00%) 4.39 ( 1.91%) Best99%Mean Time 4.47 ( 0.00%) 4.39 ( 1.91%) Best95%Mean Time 4.46 ( 0.00%) 4.38 ( 1.93%) Best90%Mean Time 4.45 ( 0.00%) 4.36 ( 1.98%) Best50%Mean Time 4.36 ( 0.00%) 4.25 ( 2.49%) Best10%Mean Time 4.23 ( 0.00%) 4.10 ( 3.13%) Best5%Mean Time 4.19 ( 0.00%) 4.06 ( 3.20%) Best1%Mean Time 4.13 ( 0.00%) 4.00 ( 3.39%) Small improvement and similar gains were seen on the UMA machine. The gain is small but it stands to reason that doing less work in the scheduler is a good thing. The downside is that the lack of schedstats and tracepoints may be surprising to experts doing performance analysis until they find the existence of the schedstats= parameter or schedstats sysctl. It will be automatically activated for latencytop and sleep profiling to alleviate the problem. For tracepoints, there is a simple warning as it's not safe to activate schedstats in the context when it's known the tracepoint may be wanted but is unavailable. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <mgalbraith@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1454663316-22048-1-git-send-email-mgorman@techsingularity.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
668 lines
15 KiB
C
668 lines
15 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 "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)
|
|
|
|
#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)
|
|
{
|
|
SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
|
|
SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
|
|
}
|
|
|
|
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
|
|
}
|