--- zzzz-none-000/linux-3.10.107/tools/perf/builtin-sched.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/tools/perf/builtin-sched.c 2021-02-04 17:41:59.000000000 +0000 @@ -10,6 +10,7 @@ #include "util/header.h" #include "util/session.h" #include "util/tool.h" +#include "util/cloexec.h" #include "util/parse-options.h" #include "util/trace-event.h" @@ -22,12 +23,13 @@ #include #include #include +#include #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 #define COMM_LEN 20 #define SYM_LEN 129 -#define MAX_PID 65536 +#define MAX_PID 1024000 struct sched_atom; @@ -66,7 +68,7 @@ struct task_desc *wakee; }; -#define TASK_STATE_TO_CHAR_STR "RSDTtZX" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" enum thread_state { THREAD_SLEEPING = 0, @@ -93,6 +95,7 @@ u64 total_lat; u64 nb_atoms; u64 total_runtime; + int num_merged; }; typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *); @@ -109,8 +112,9 @@ int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample); + /* 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, @@ -122,7 +126,7 @@ struct perf_tool tool; const char *sort_order; unsigned long nr_tasks; - struct task_desc *pid_to_task[MAX_PID]; + struct task_desc **pid_to_task; struct task_desc **tasks; const struct trace_sched_handler *tp_handler; pthread_mutex_t start_work_mutex; @@ -148,7 +152,6 @@ 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; @@ -166,8 +169,10 @@ u64 all_runtime; u64 all_count; u64 cpu_last_switched[MAX_CPUS]; - struct rb_root atom_root, sorted_atom_root; + struct rb_root atom_root, sorted_atom_root, merged_atom_root; struct list_head sort_list, cmp_pid; + bool force; + bool skip_merge; }; static u64 get_nsecs(void) @@ -325,8 +330,19 @@ unsigned long pid, const char *comm) { struct task_desc *task; + static int pid_max; - BUG_ON(pid >= MAX_PID); + if (sched->pid_to_task == NULL) { + if (sysctl__read_int("kernel/pid_max", &pid_max) < 0) + pid_max = MAX_PID; + BUG_ON((sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *))) == NULL); + } + if (pid >= (unsigned long)pid_max) { + BUG_ON((sched->pid_to_task = realloc(sched->pid_to_task, (pid + 1) * + sizeof(struct task_desc *))) == NULL); + while (pid >= (unsigned long)pid_max) + sched->pid_to_task[pid_max++] = NULL; + } task = sched->pid_to_task[pid]; @@ -345,7 +361,7 @@ sched->pid_to_task[pid] = task; sched->nr_tasks++; - sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *)); + sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_desc *)); BUG_ON(!sched->tasks); sched->tasks[task->nr] = task; @@ -424,21 +440,45 @@ return sum; } -static int self_open_counters(void) +static int self_open_counters(struct perf_sched *sched, unsigned long cur_task) { struct perf_event_attr attr; + char sbuf[STRERR_BUFSIZE], info[STRERR_BUFSIZE]; int fd; + struct rlimit limit; + bool need_privilege = false; memset(&attr, 0, sizeof(attr)); attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_TASK_CLOCK; - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - - if (fd < 0) +force_again: + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); + + if (fd < 0) { + if (errno == EMFILE) { + if (sched->force) { + BUG_ON(getrlimit(RLIMIT_NOFILE, &limit) == -1); + limit.rlim_cur += sched->nr_tasks - cur_task; + if (limit.rlim_cur > limit.rlim_max) { + limit.rlim_max = limit.rlim_cur; + need_privilege = true; + } + if (setrlimit(RLIMIT_NOFILE, &limit) == -1) { + if (need_privilege && errno == EPERM) + strcpy(info, "Need privilege\n"); + } else + goto force_again; + } else + strcpy(info, "Have a try with -f option\n"); + } pr_err("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); + "with %d (%s)\n%s", fd, + strerror_r(errno, sbuf, sizeof(sbuf)), info); + exit(EXIT_FAILURE); + } return fd; } @@ -456,6 +496,7 @@ struct sched_thread_parms { struct task_desc *task; struct perf_sched *sched; + int fd; }; static void *thread_func(void *ctx) @@ -466,13 +507,12 @@ u64 cpu_usage_0, cpu_usage_1; unsigned long i, ret; char comm2[22]; - int fd; + int fd = parms->fd; - free(parms); + zfree(&parms); sprintf(comm2, ":%s", this_task->comm); prctl(PR_SET_NAME, comm2); - fd = self_open_counters(); if (fd < 0) return NULL; again: @@ -524,6 +564,7 @@ BUG_ON(parms == NULL); parms->task = task = sched->tasks[i]; parms->sched = sched; + parms->fd = self_open_counters(sched, i); sem_init(&task->sleep_sem, 0, 0); sem_init(&task->ready_for_work, 0, 0); sem_init(&task->work_done_sem, 0, 0); @@ -568,13 +609,13 @@ cpu_usage_1 = get_cpu_usage_nsec_parent(); if (!sched->runavg_cpu_usage) sched->runavg_cpu_usage = sched->cpu_usage; - sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10; + sched->runavg_cpu_usage = (sched->runavg_cpu_usage * (sched->replay_repeat - 1) + sched->cpu_usage) / sched->replay_repeat; sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0; if (!sched->runavg_parent_cpu_usage) sched->runavg_parent_cpu_usage = sched->parent_cpu_usage; - sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 + - sched->parent_cpu_usage)/10; + sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * (sched->replay_repeat - 1) + + sched->parent_cpu_usage)/sched->replay_repeat; ret = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(ret); @@ -606,7 +647,7 @@ sched->sum_fluct += fluct; if (!sched->run_avg) sched->run_avg = delta; - sched->run_avg = (sched->run_avg * 9 + delta) / 10; + sched->run_avg = (sched->run_avg * (sched->replay_repeat - 1) + delta) / sched->replay_repeat; printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0); @@ -717,22 +758,34 @@ return 0; } -static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample) -{ - const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"), - *child_comm = perf_evsel__strval(evsel, sample, "child_comm"); - const u32 parent_pid = perf_evsel__intval(evsel, sample, "parent_pid"), - child_pid = perf_evsel__intval(evsel, sample, "child_pid"); +static int replay_fork_event(struct perf_sched *sched, + union perf_event *event, + struct machine *machine) +{ + struct thread *child, *parent; + + child = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ppid, + event->fork.ptid); + + if (child == NULL || parent == NULL) { + pr_debug("thread does not exist on fork event: child %p, parent %p\n", + child, parent); + goto out_put; + } if (verbose) { - printf("sched_fork event %p\n", evsel); - printf("... parent: %s/%d\n", parent_comm, parent_pid); - printf("... child: %s/%d\n", child_comm, child_pid); + printf("fork event\n"); + printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid); + printf("... child: %s/%d\n", thread__comm_str(child), child->tid); } - register_pid(sched, parent_pid, parent_comm); - register_pid(sched, child_pid, child_comm); + register_pid(sched, parent->tid, thread__comm_str(parent)); + register_pid(sched, child->tid, thread__comm_str(child)); +out_put: + thread__put(child); + thread__put(parent); return 0; } @@ -818,20 +871,12 @@ return -1; } - atoms->thread = thread; + atoms->thread = thread__get(thread); INIT_LIST_HEAD(&atoms->work_list); __thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid); return 0; } -static int latency_fork_event(struct perf_sched *sched __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ - /* should insert the newcomer */ - return 0; -} - static char sched_out_state(u64 prev_state) { const char *str = TASK_STATE_TO_CHAR_STR; @@ -917,7 +962,7 @@ struct work_atoms *out_events, *in_events; struct thread *sched_out, *sched_in; u64 timestamp0, timestamp = sample->time; - int cpu = sample->cpu; + int cpu = sample->cpu, err = -1; s64 delta; BUG_ON(cpu >= MAX_CPUS || cpu < 0); @@ -934,17 +979,19 @@ return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, -1, prev_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); + if (sched_out == NULL || sched_in == NULL) + goto out_put; out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { if (thread_atoms_insert(sched, sched_out)) - return -1; + goto out_put; out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { pr_err("out-event: Internal tree error"); - return -1; + goto out_put; } } if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp)) @@ -953,22 +1000,25 @@ in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); if (!in_events) { if (thread_atoms_insert(sched, sched_in)) - return -1; + goto out_put; in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); if (!in_events) { pr_err("in-event: Internal tree error"); - return -1; + goto out_put; } /* * Take came in we have not heard about yet, * add in an initial atom in runnable state: */ if (add_sched_out_event(in_events, 'R', timestamp)) - return -1; + goto out_put; } add_sched_in_event(in_events, timestamp); - - return 0; + err = 0; +out_put: + thread__put(sched_out); + thread__put(sched_in); + return err; } static int latency_runtime_event(struct perf_sched *sched, @@ -978,26 +1028,32 @@ { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, -1, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; - int cpu = sample->cpu; + int cpu = sample->cpu, err = -1; + + if (thread == NULL) + return -1; BUG_ON(cpu >= MAX_CPUS || cpu < 0); if (!atoms) { if (thread_atoms_insert(sched, thread)) - return -1; + goto out_put; atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); if (!atoms) { pr_err("in-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'R', timestamp)) - return -1; + goto out_put; } add_runtime_event(atoms, runtime, timestamp); - return 0; + err = 0; +out_put: + thread__put(thread); + return err; } static int latency_wakeup_event(struct perf_sched *sched, @@ -1005,29 +1061,27 @@ struct perf_sample *sample, struct machine *machine) { - const u32 pid = perf_evsel__intval(evsel, sample, "pid"), - success = perf_evsel__intval(evsel, sample, "success"); + const u32 pid = perf_evsel__intval(evsel, sample, "pid"); struct work_atoms *atoms; struct work_atom *atom; struct thread *wakee; u64 timestamp = sample->time; + int err = -1; - /* Note for later, it may be interesting to observe the failing cases */ - if (!success) - return 0; - - wakee = machine__findnew_thread(machine, pid); + wakee = machine__findnew_thread(machine, -1, pid); + if (wakee == NULL) + return -1; atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) - return -1; + goto out_put; atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { pr_err("wakeup-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'S', timestamp)) - return -1; + goto out_put; } BUG_ON(list_empty(&atoms->work_list)); @@ -1035,22 +1089,32 @@ atom = list_entry(atoms->work_list.prev, struct work_atom, list); /* + * As we do not guarantee the wakeup event happens when + * task is out of run queue, also may happen when task is + * on run queue and wakeup only change ->state to TASK_RUNNING, + * then we should not set the ->wake_up_time when wake up a + * task which is on run queue. + * * You WILL be missing events if you've recorded only * one CPU, or are only looking at only one, so don't - * make useless noise. + * skip in this case. */ if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING) - sched->nr_state_machine_bugs++; + goto out_ok; sched->nr_timestamps++; if (atom->sched_out_time > timestamp) { sched->nr_unordered_timestamps++; - return 0; + goto out_ok; } atom->state = THREAD_WAIT_CPU; atom->wake_up_time = timestamp; - return 0; +out_ok: + err = 0; +out_put: + thread__put(wakee); + return err; } static int latency_migrate_task_event(struct perf_sched *sched, @@ -1063,6 +1127,7 @@ struct work_atoms *atoms; struct work_atom *atom; struct thread *migrant; + int err = -1; /* * Only need to worry about migration when profiling one CPU. @@ -1070,19 +1135,21 @@ if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, pid); + migrant = machine__findnew_thread(machine, -1, pid); + if (migrant == NULL) + return -1; atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) - return -1; - register_pid(sched, migrant->pid, migrant->comm); + goto out_put; + register_pid(sched, migrant->tid, thread__comm_str(migrant)); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { pr_err("migration-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'R', timestamp)) - return -1; + goto out_put; } BUG_ON(list_empty(&atoms->work_list)); @@ -1094,8 +1161,10 @@ if (atom->sched_out_time > timestamp) sched->nr_unordered_timestamps++; - - return 0; + err = 0; +out_put: + thread__put(migrant); + return err; } static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list) @@ -1109,20 +1178,23 @@ /* * Ignore idle threads: */ - if (!strcmp(work_list->thread->comm, "swapper")) + if (!strcmp(thread__comm_str(work_list->thread), "swapper")) return; sched->all_runtime += work_list->total_runtime; sched->all_count += work_list->nb_atoms; - ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->pid); + if (work_list->num_merged > 1) + ret = printf(" %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged); + else + ret = printf(" %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid); for (i = 0; i < 24 - ret; i++) printf(" "); avg = work_list->total_lat / work_list->nb_atoms; - printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", + printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n", (double)work_list->total_runtime / 1e6, work_list->nb_atoms, (double)avg / 1e6, (double)work_list->max_lat / 1e6, @@ -1131,12 +1203,13 @@ static int pid_cmp(struct work_atoms *l, struct work_atoms *r) { - if (l->thread->pid < r->thread->pid) + if (l->thread == r->thread) + return 0; + if (l->thread->tid < r->thread->tid) return -1; - if (l->thread->pid > r->thread->pid) + if (l->thread->tid > r->thread->tid) return 1; - - return 0; + return (int)(l->thread - r->thread); } static int avg_cmp(struct work_atoms *l, struct work_atoms *r) @@ -1235,17 +1308,22 @@ static void perf_sched__sort_lat(struct perf_sched *sched) { struct rb_node *node; - + struct rb_root *root = &sched->atom_root; +again: for (;;) { struct work_atoms *data; - node = rb_first(&sched->atom_root); + node = rb_first(root); if (!node) break; - rb_erase(node, &sched->atom_root); + rb_erase(node, root); data = rb_entry(node, struct work_atoms, node); __thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list); } + if (root == &sched->atom_root) { + root = &sched->merged_atom_root; + goto again; + } } static int process_sched_wakeup_event(struct perf_tool *tool, @@ -1264,9 +1342,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - struct thread *sched_out __maybe_unused, *sched_in; + const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + struct thread *sched_in; int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; @@ -1289,26 +1366,35 @@ return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); + if (sched_in == NULL) + return -1; - sched->curr_thread[this_cpu] = sched_in; + sched->curr_thread[this_cpu] = thread__get(sched_in); printf(" "); new_shortname = 0; if (!sched_in->shortname[0]) { - sched_in->shortname[0] = sched->next_shortname1; - sched_in->shortname[1] = sched->next_shortname2; - - if (sched->next_shortname1 < 'Z') { - sched->next_shortname1++; + if (!strcmp(thread__comm_str(sched_in), "swapper")) { + /* + * Don't allocate a letter-number for swapper:0 + * as a shortname. Instead, we use '.' for it. + */ + sched_in->shortname[0] = '.'; + sched_in->shortname[1] = ' '; } else { - sched->next_shortname1='A'; - if (sched->next_shortname2 < '9') { - sched->next_shortname2++; + sched_in->shortname[0] = sched->next_shortname1; + sched_in->shortname[1] = sched->next_shortname2; + + if (sched->next_shortname1 < 'Z') { + sched->next_shortname1++; } else { - sched->next_shortname2='0'; + sched->next_shortname1 = 'A'; + if (sched->next_shortname2 < '9') + sched->next_shortname2++; + else + sched->next_shortname2 = '0'; } } new_shortname = 1; @@ -1320,23 +1406,22 @@ else printf("*"); - if (sched->curr_thread[cpu]) { - if (sched->curr_thread[cpu]->pid) - printf("%2s ", sched->curr_thread[cpu]->shortname); - else - printf(". "); - } else + if (sched->curr_thread[cpu]) + printf("%2s ", sched->curr_thread[cpu]->shortname); + else printf(" "); } printf(" %12.6f secs ", (double)timestamp/1e9); if (new_shortname) { printf("%s => %s:%d\n", - sched_in->shortname, sched_in->comm, sched_in->pid); + sched_in->shortname, thread__comm_str(sched_in), sched_in->tid); } else { printf("\n"); } + thread__put(sched_in); + return 0; } @@ -1379,25 +1464,20 @@ return 0; } -static int process_sched_fork_event(struct perf_tool *tool, - struct perf_evsel *evsel, - struct perf_sample *sample, - struct machine *machine __maybe_unused) +static int perf_sched__process_fork_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - if (sched->tp_handler->fork_event) - return sched->tp_handler->fork_event(sched, evsel, sample); + /* run the fork event through the perf machineruy */ + perf_event__process_fork(tool, event, sample, machine); - return 0; -} + /* and then run additional processing needed for this command */ + if (sched->tp_handler->fork_event) + return sched->tp_handler->fork_event(sched, event, machine); -static int process_sched_exit_event(struct perf_tool *tool __maybe_unused, - struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - pr_debug("sched_exit event %p\n", evsel); return 0; } @@ -1425,72 +1505,60 @@ struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); int err = 0; - if (thread == NULL) { - pr_debug("problem processing %s event, skipping it.\n", - perf_evsel__name(evsel)); - return -1; - } - - evsel->hists.stats.total_period += sample->period; - hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); - - if (evsel->handler.func != NULL) { - tracepoint_handler f = evsel->handler.func; + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; err = f(tool, evsel, sample, machine); } return err; } -static int perf_sched__read_events(struct perf_sched *sched, bool destroy, - struct perf_session **psession) +static int perf_sched__read_events(struct perf_sched *sched) { const struct perf_evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, - { "sched:sched_process_fork", process_sched_fork_event, }, - { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; struct perf_session *session; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + .force = sched->force, + }; + int rc = -1; - session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool); + session = perf_session__new(&file, false, &sched->tool); if (session == NULL) { pr_debug("No Memory for session\n"); return -1; } + symbol__init(&session->header.env); + if (perf_session__set_tracepoints_handlers(session, handlers)) goto out_delete; if (perf_session__has_traces(session, "record -R")) { - int err = perf_session__process_events(session, &sched->tool); + int err = perf_session__process_events(session); if (err) { pr_err("Failed to process events, error %d", err); goto out_delete; } - sched->nr_events = session->stats.nr_events[0]; - sched->nr_lost_events = session->stats.total_lost; - sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->evlist->stats.nr_events[0]; + sched->nr_lost_events = session->evlist->stats.total_lost; + sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST]; } - if (destroy) - perf_session__delete(session); - - if (psession) - *psession = session; - - return 0; - + rc = 0; out_delete: perf_session__delete(session); - return -1; + return rc; } static void print_bad_events(struct perf_sched *sched) @@ -1505,14 +1573,6 @@ (double)sched->nr_lost_events/(double)sched->nr_events * 100.0, sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks); } - if (sched->nr_state_machine_bugs && sched->nr_timestamps) { - printf(" INFO: %.3f%% state machine bugs (%ld out of %ld)", - (double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0, - sched->nr_state_machine_bugs, sched->nr_timestamps); - if (sched->nr_lost_events) - printf(" (due to lost events?)"); - printf("\n"); - } if (sched->nr_context_switch_bugs && sched->nr_timestamps) { printf(" INFO: %.3f%% context switch bugs (%ld out of %ld)", (double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0, @@ -1523,19 +1583,74 @@ } } +static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + struct work_atoms *this; + const char *comm = thread__comm_str(data->thread), *this_comm; + + while (*new) { + int cmp; + + this = container_of(*new, struct work_atoms, node); + parent = *new; + + this_comm = thread__comm_str(this->thread); + cmp = strcmp(comm, this_comm); + if (cmp > 0) { + new = &((*new)->rb_left); + } else if (cmp < 0) { + new = &((*new)->rb_right); + } else { + this->num_merged++; + this->total_runtime += data->total_runtime; + this->nb_atoms += data->nb_atoms; + this->total_lat += data->total_lat; + list_splice(&data->work_list, &this->work_list); + if (this->max_lat < data->max_lat) { + this->max_lat = data->max_lat; + this->max_lat_at = data->max_lat_at; + } + zfree(&data); + return; + } + } + + data->num_merged++; + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static void perf_sched__merge_lat(struct perf_sched *sched) +{ + struct work_atoms *data; + struct rb_node *node; + + if (sched->skip_merge) + return; + + while ((node = rb_first(&sched->atom_root))) { + rb_erase(node, &sched->atom_root); + data = rb_entry(node, struct work_atoms, node); + __merge_work_atoms(&sched->merged_atom_root, data); + } +} + static int perf_sched__lat(struct perf_sched *sched) { struct rb_node *next; - struct perf_session *session; setup_pager(); - if (perf_sched__read_events(sched, false, &session)) + + if (perf_sched__read_events(sched)) return -1; + + perf_sched__merge_lat(sched); perf_sched__sort_lat(sched); - printf("\n ---------------------------------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); - printf(" ---------------------------------------------------------------------------------------------------------------\n"); + printf("\n -----------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); next = rb_first(&sched->sorted_atom_root); @@ -1545,9 +1660,10 @@ work_list = rb_entry(next, struct work_atoms, node); output_lat_thread(sched, work_list); next = rb_next(next); + thread__zput(work_list->thread); } - printf(" -----------------------------------------------------------------------------------------\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", (double)sched->all_runtime / 1e6, sched->all_count); @@ -1556,7 +1672,6 @@ print_bad_events(sched); printf("\n"); - perf_session__delete(session); return 0; } @@ -1565,7 +1680,7 @@ sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); setup_pager(); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched)) return -1; print_bad_events(sched); return 0; @@ -1580,7 +1695,7 @@ test_calibrations(sched); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched)) return -1; printf("nr_run_events: %ld\n", sched->nr_run_events); @@ -1614,8 +1729,8 @@ for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { if (sort_dimension__add(tok, &sched->sort_list) < 0) { - error("Unknown --sort key: `%s'", tok); - usage_with_options(usage_msg, options); + usage_with_options_msg(usage_msg, options, + "Unknown --sort key: `%s'", tok); } } @@ -1632,7 +1747,6 @@ "record", "-a", "-R", - "-f", "-m", "1024", "-c", "1", "-e", "sched:sched_switch", @@ -1640,9 +1754,9 @@ "-e", "sched:sched_stat_sleep", "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", - "-e", "sched:sched_process_exit", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup", + "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; @@ -1671,19 +1785,19 @@ .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, .lost = perf_event__process_lost, - .fork = perf_event__process_fork, - .ordered_samples = true, + .fork = perf_sched__process_fork_event, + .ordered_events = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), .sort_list = LIST_HEAD_INIT(sched.sort_list), .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, - .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, .sort_order = default_sort_order, .replay_repeat = 10, .profile_cpu = -1, .next_shortname1 = 'A', .next_shortname2 = '0', + .skip_merge = 0, }; const struct option latency_options[] = { OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]", @@ -1694,6 +1808,8 @@ "CPU to profile on"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN('p', "pids", &sched.skip_merge, + "latency stats per pid instead of per comm"), OPT_END() }; const struct option replay_options[] = { @@ -1703,6 +1819,7 @@ "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN('f', "force", &sched.force, "don't complain, do it"), OPT_END() }; const struct option sched_options[] = { @@ -1722,15 +1839,16 @@ "perf sched replay []", NULL }; - const char * const sched_usage[] = { - "perf sched [] {record|latency|map|replay|script}", + const char *const sched_subcommands[] = { "record", "latency", "map", + "replay", "script", NULL }; + const char *sched_usage[] = { + NULL, NULL }; struct trace_sched_handler lat_ops = { .wakeup_event = latency_wakeup_event, .switch_event = latency_switch_event, .runtime_event = latency_runtime_event, - .fork_event = latency_fork_event, .migrate_task_event = latency_migrate_task_event, }; struct trace_sched_handler map_ops = { @@ -1741,9 +1859,13 @@ .switch_event = replay_switch_event, .fork_event = replay_fork_event, }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++) + sched.curr_pid[i] = -1; - argc = parse_options(argc, argv, sched_options, sched_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands, + sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(sched_usage, sched_options); @@ -1753,7 +1875,6 @@ if (!strcmp(argv[0], "script")) return cmd_script(argc, argv, prefix); - symbol__init(); if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strncmp(argv[0], "lat", 3)) {