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
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
|
// SPDX-License-Identifier: GPL-2.0
/*
* /proc/schedstat implementation
*/
#include "sched.h"
void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats)
{
u64 wait_start, prev_wait_start;
wait_start = rq_clock(rq);
prev_wait_start = schedstat_val(stats->wait_start);
if (p && likely(wait_start > prev_wait_start))
wait_start -= prev_wait_start;
__schedstat_set(stats->wait_start, wait_start);
}
void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats)
{
u64 delta = rq_clock(rq) - schedstat_val(stats->wait_start);
if (p) {
if (task_on_rq_migrating(p)) {
/*
* Preserve migrating task's wait time so wait_start
* time stamp can be adjusted to accumulate wait time
* prior to migration.
*/
__schedstat_set(stats->wait_start, delta);
return;
}
trace_sched_stat_wait(p, delta);
}
__schedstat_set(stats->wait_max,
max(schedstat_val(stats->wait_max), delta));
__schedstat_inc(stats->wait_count);
__schedstat_add(stats->wait_sum, delta);
__schedstat_set(stats->wait_start, 0);
}
void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats)
{
u64 sleep_start, block_start;
sleep_start = schedstat_val(stats->sleep_start);
block_start = schedstat_val(stats->block_start);
if (sleep_start) {
u64 delta = rq_clock(rq) - sleep_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > schedstat_val(stats->sleep_max)))
__schedstat_set(stats->sleep_max, delta);
__schedstat_set(stats->sleep_start, 0);
__schedstat_add(stats->sum_sleep_runtime, delta);
if (p) {
account_scheduler_latency(p, delta >> 10, 1);
trace_sched_stat_sleep(p, delta);
}
}
if (block_start) {
u64 delta = rq_clock(rq) - block_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > schedstat_val(stats->block_max)))
__schedstat_set(stats->block_max, delta);
__schedstat_set(stats->block_start, 0);
__schedstat_add(stats->sum_sleep_runtime, delta);
__schedstat_add(stats->sum_block_runtime, delta);
if (p) {
if (p->in_iowait) {
__schedstat_add(stats->iowait_sum, delta);
__schedstat_inc(stats->iowait_count);
trace_sched_stat_iowait(p, delta);
}
trace_sched_stat_blocked(p, delta);
/*
* Blocking time is in units of nanosecs, so shift by
* 20 to get a milliseconds-range estimation of the
* amount of time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING,
(void *)get_wchan(p),
delta >> 20);
}
account_scheduler_latency(p, delta >> 10, 0);
}
}
}
/*
* Current schedstat API version.
*
* 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;
if (v == (void *)1) {
seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
seq_printf(seq, "timestamp %lu\n", jiffies);
} else {
struct rq *rq;
#ifdef CONFIG_SMP
struct sched_domain *sd;
int dcount = 0;
#endif
cpu = (unsigned long)(v - 2);
rq = cpu_rq(cpu);
/* runqueue-specific stats */
seq_printf(seq,
"cpu%d %u 0 %u %u %u %u %llu %llu %lu",
cpu, rq->yld_count,
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;
seq_printf(seq, "domain%d %*pb", dcount++,
cpumask_pr_args(sched_domain_span(sd)));
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
}
return 0;
}
/*
* This iterator 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 *schedstat_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 *schedstat_next(struct seq_file *file, void *data, loff_t *offset)
{
(*offset)++;
return schedstat_start(file, offset);
}
static void schedstat_stop(struct seq_file *file, void *data)
{
}
static const struct seq_operations schedstat_sops = {
.start = schedstat_start,
.next = schedstat_next,
.stop = schedstat_stop,
.show = show_schedstat,
};
static int __init proc_schedstat_init(void)
{
proc_create_seq("schedstat", 0, NULL, &schedstat_sops);
return 0;
}
subsys_initcall(proc_schedstat_init);
|
