#include "builtin.h"
#include "perf.h"
#include "util/util.h"
#include "util/evlist.h"
#include "util/cache.h"
#include "util/evsel.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
#include <sys/prctl.h>
#include <sys/resource.h>
#include <semaphore.h>
#include <pthread.h>
#include <math.h>
#define PR_SET_NAME 15 /* Set process name */
#define MAX_CPUS 4096
#define COMM_LEN 20
#define SYM_LEN 129
#define MAX_PID 65536
struct sched_atom;
struct task_desc {
unsigned long nr;
unsigned long pid;
char comm[COMM_LEN];
unsigned long nr_events;
unsigned long curr_event;
struct sched_atom **atoms;
pthread_t thread;
sem_t sleep_sem;
sem_t ready_for_work;
sem_t work_done_sem;
u64 cpu_usage;
};
enum sched_event_type {
SCHED_EVENT_RUN,
SCHED_EVENT_SLEEP,
SCHED_EVENT_WAKEUP,
SCHED_EVENT_MIGRATION,
};
struct sched_atom {
enum sched_event_type type;
int specific_wait;
u64 timestamp;
u64 duration;
unsigned long nr;
sem_t *wait_sem;
struct task_desc *wakee;
};
#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
THREAD_SCHED_IN,
THREAD_IGNORE
};
struct work_atom {
struct list_head list;
enum thread_state state;
u64 sched_out_time;
u64 wake_up_time;
u64 sched_in_time;
u64 runtime;
};
struct work_atoms {
struct list_head work_list;
struct thread *thread;
struct rb_node node;
u64 max_lat;
u64 max_lat_at;
u64 total_lat;
u64 nb_atoms;
u64 total_runtime;
};
typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
struct perf_sched;
struct trace_sched_handler {
int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
/* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
int (*fork_event)(struct perf_sched *sched, union perf_event *event,
struct machine *machine);
int (*migrate_task_event)(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine);
};
struct perf_sched {
struct perf_tool tool;
const char *sort_order;
unsigned long nr_tasks;
struct task_desc *pid_to_task[MAX_PID];
struct task_desc **tasks;
const struct trace_sched_handler *tp_handler;
pthread_mutex_t start_work_mutex;
pthread_mutex_t work_done_wait_mutex;
int profile_cpu;
/*
* Track the current task - that way we can know whether there's any
* weird events, such as a task being switched away that is not current.
*/
int max_cpu;
u32 curr_pid[MAX_CPUS];
struct thread *curr_thread[MAX_CPUS];
char next_shortname1;
char next_shortname2;
unsigned int replay_repeat;
unsigned long nr_run_events;
unsigned long nr_sleep_events;
unsigned long nr_wakeup_events;
unsigned long nr_sleep_corrections;
unsigned long nr_run_events_optimized;
unsigned long targetless_wakeups;
unsigned long multitarget_wakeups;
unsigned long nr_runs;
unsigned long nr_timestamps;
unsigned long nr_unordered_timestamps;
unsigned long nr_state_machine_bugs;
unsigned long nr_context_switch_bugs;
unsigned long nr_events;
unsigned long nr_lost_chunks;
unsigned long nr_lost_events;
u64 run_measurement_overhead;
u64 sleep_measurement_overhead;
u64 start_time;
u64 cpu_usage;
u64 runavg_cpu_usage;
u64 parent_cpu_usage;
u64 runavg_parent_cpu_usage;
u64 sum_runtime;
u64 sum_fluct;
u64 run_avg;
u64 all_runtime;
u64 all_count;
u64 cpu_last_switched[MAX_CPUS];
struct rb_root atom_root, sorted_atom_root;
struct list_head sort_list, cmp_pid;
};
static u64 get_nsecs(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
static void burn_nsecs(struct perf_sched *sched, u64 nsecs)
{
u64 T0 = get_nsecs(), T1;
do {
T1 = get_nsecs();
} while (T1 + sched->run_measurement_overhead < T0 + nsecs);
}
static void sleep_nsecs(u64 nsecs)
{
struct timespec ts;
ts.tv_nsec = nsecs % 999999999;
ts.tv_sec = nsecs / 999999999;
nanosleep(&ts, NULL);
}
static void calibrate_run_measurement_overhead(struct perf_sched *sched)
{
u64 T0, T1, delta, min_delta = 1000000000ULL;
int i;
for (i = 0; i < 10; i++) {
T0 = get_nsecs();
burn_nsecs(sched, 0);
T1 = get_nsecs();
delta = T1-T0;
min_delta = min(min_delta, delta);
}
sched->run_measurement_overhead = min_delta;
printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
}
static void calibrate_sleep_measurement_overhead(struct perf_sched *sched)
{
u64 T0, T1, delta, min_delta = 1000000000ULL;
int i;
for (i = 0; i < 10; i++) {
T0 = get_nsecs();
sleep_nsecs(10000);
T1 = get_nsecs();
delta = T1-T0;
min_delta = min(min_delta, delta);
}
min_delta -= 10000;
sched->sleep_measurement_overhead = min_delta;
printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
}
static struct sched_atom *
get_new_event(struct task_desc *task, u64 timestamp)
{
struct sched_atom *event = zalloc(sizeof(*event));
unsigned long idx = task->nr_events;
size_t size;
event->timestamp = timestamp;
event->nr = idx;
task->nr_events++;
size = sizeof(struct sched_atom *) * task->nr_events;
task->atoms = realloc(task->atoms, size);
BUG_ON(!task->atoms);
task->atoms[idx] = event;
return event;
}
static struct sched_atom *last_event(struct task_desc *task)
{
if (!task->nr_events)
return NULL;
return task->atoms[task->nr_events - 1];
}
static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, u64 duration)
{
struct sched_atom *event, *curr_event = last_event(task);
/*
* optimize an existing RUN event by merging this one
* to it:
*/
if (curr_event && curr_event->type == SCHED_EVENT_RUN) {
sched->nr_run_events_optimized++;
curr_event->duration += duration;
return;
}
event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_RUN;
event->duration = duration;
sched->nr_run_events++;
}
static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, struct task_desc *wakee)
{
struct sched_atom *event, *wakee_event;
event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_WAKEUP;
event->wakee = wakee;
wakee_event = last_event(wakee);
if (!wakee_event || wakee_event->type != SCHED_EVENT_SLEEP) {
sched->targetless_wakeups++;
return;
}
if (wakee_event->wait_sem) {
sched->multitarget_wakeups++;
return;
}
wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem));
sem_init(wakee_event->wait_sem, 0, 0);
wakee_event->specific_wait = 1;
event->wait_sem = wakee_event->wait_sem;
sched->nr_wakeup_events++;
}
static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, u64 task_state __maybe_unused)
{
struct sched_atom *event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_SLEEP;
sched->nr_sleep_events++;
}
static struct task_desc *register_pid(struct perf_sched *sched,
unsigned long pid, const char *comm)
{
struct task_desc *task;
BUG_ON(pid >= MAX_PID);
task = sched->pid_to_task[pid];
if (task)
return task;
task = zalloc(sizeof(*task));
task->pid = pid;
task->nr = sched->nr_tasks;
strcpy(task->comm, comm);
/*
* every task starts in sleeping state - this gets ignored
* if there's no wakeup pointing to this sleep state:
*/
add_sched_event_sleep(sched, task, 0, 0);
sched->pid_to_task[pid] = task;
sched->nr_tasks++;
sched->
builtin-sched.rar_Weird
版权申诉
31 浏览量
2022-09-21
19:04:12
上传
评论
收藏 10KB RAR 举报
刘良运
- 粉丝: 66
- 资源: 1万+
最新资源
- Docker容器配置进阶
- tensorflow-gpu-2.7.4-cp37-cp37m-manylinux2010-x86-64.whl
- 多段线、 圆、弧转多段线(仅我可见)
- tensorflow-2.7.2-cp38-cp38-manylinux2010-x86-64.whl
- yeyue-p8Yi4-ve4a83792.apk
- tensorflow-gpu-2.7.3-cp38-cp38-manylinux2010-x86-64.whl
- 五相感应电机矢量控制模型MATLAB
- RGLED (1) (1).circ
- IMG_20240427_215747.jpg
- python下前端WEB学习笔记
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈