Newer
Older
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
/*
* Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
*/
struct perf_event_attr very_detailed_attrs[] = {
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1I << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1I << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_DTLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_DTLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_ITLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_ITLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
/*
* Very, very detailed stats (-d -d -d), adding prefetch events:
*/
struct perf_event_attr very_very_detailed_attrs[] = {
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
/* Set attrs if no event is selected and !null_run: */
if (null_run)
return 0;
if (!evsel_list->nr_entries) {
if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
}
/* Detailed events get appended to the event list: */
if (detailed_run < 1)
return 0;
/* Append detailed run extra attributes: */
if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
int output_fd = 0;
const char *output_name = NULL;
const struct option options[] = {
OPT_CALLBACK('e', "event", &evsel_list, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK(0, "filter", &evsel_list, "filter",
"event filter", parse_filter),
OPT_BOOLEAN('i', "no-inherit", &no_inherit,
"child tasks do not inherit counters"),
OPT_STRING('p', "pid", &target.pid, "pid",
"stat events on existing process id"),
OPT_STRING('t', "tid", &target.tid, "tid",
"stat events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
OPT_BOOLEAN('c', "scale", &scale, "scale/normalize counters"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_INTEGER('r', "repeat", &run_count,
"repeat command and print average + stddev (max: 100)"),
OPT_BOOLEAN('n', "null", &null_run,
"null run - dont start any counters"),
OPT_INCR('d', "detailed", &detailed_run,
"detailed run - start a lot of events"),
OPT_BOOLEAN('S', "sync", &sync_run,
"call sync() before starting a run"),
OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
"print large numbers with thousands\' separators",
stat__set_big_num),
OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
"list of cpus to monitor in system-wide"),
OPT_BOOLEAN('A', "no-aggr", &no_aggr, "disable CPU count aggregation"),
OPT_STRING('x', "field-separator", &csv_sep, "separator",
"print counts with custom separator"),
OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
"monitor event in cgroup name only", parse_cgroups),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
OPT_INTEGER(0, "log-fd", &output_fd,
"log output to fd, instead of stderr"),
OPT_STRING(0, "pre", &pre_cmd, "command",
"command to run prior to the measured command"),
OPT_STRING(0, "post", &post_cmd, "command",
"command to run after to the measured command"),
OPT_END()
};
const char * const stat_usage[] = {
"perf stat [<options>] [<command>]",
NULL
};
struct perf_evsel *pos;
int status = -ENOMEM, run_idx;
setlocale(LC_ALL, "");
evsel_list = perf_evlist__new(NULL, NULL);
if (evsel_list == NULL)
return -ENOMEM;
argc = parse_options(argc, argv, options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
output = stderr;
if (output_name && strcmp(output_name, "-"))
output = NULL;
if (output_name && output_fd) {
fprintf(stderr, "cannot use both --output and --log-fd\n");
usage_with_options(stat_usage, options);
}
if (output_fd < 0) {
fprintf(stderr, "argument to --log-fd must be a > 0\n");
usage_with_options(stat_usage, options);
}
if (!output) {
struct timespec tm;
mode = append_file ? "a" : "w";
output = fopen(output_name, mode);
if (!output) {
perror("failed to create output file");
}
clock_gettime(CLOCK_REALTIME, &tm);
fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
mode = append_file ? "a" : "w";
output = fdopen(output_fd, mode);
if (!output) {
perror("Failed opening logfd");
return -errno;
}
if (!strcmp(csv_sep, "\\t"))
csv_sep = "\t";
} else
csv_sep = DEFAULT_SEPARATOR;
/*
* let the spreadsheet do the pretty-printing
*/
if (csv_output) {
if (big_num_opt == 1) {
fprintf(stderr, "-B option not supported with -x\n");
usage_with_options(stat_usage, options);
} else /* Nope, so disable big number formatting */
big_num = false;
} else if (big_num_opt == 0) /* User passed --no-big-num */
big_num = false;
if (!argc && !perf_target__has_task(&target))
usage_with_options(stat_usage, options);
usage_with_options(stat_usage, options);
/* no_aggr, cgroup are for system-wide only */
if ((no_aggr || nr_cgroups) && !perf_target__has_cpu(&target)) {
fprintf(stderr, "both cgroup and no-aggregation "
"modes only available in system-wide mode\n");
usage_with_options(stat_usage, options);
if (add_default_attributes())
goto out;
perf_target__validate(&target);
if (perf_evlist__create_maps(evsel_list, &target) < 0) {
if (perf_target__has_task(&target))
pr_err("Problems finding threads of monitor\n");
if (perf_target__has_cpu(&target))
perror("failed to parse CPUs map");
usage_with_options(stat_usage, options);
return -1;
}
list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_evsel__alloc_stat_priv(pos) < 0 ||
perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)

Zhang, Yanmin
committed
}
/*
* We dont want to block the signals - that would cause
* child tasks to inherit that and Ctrl-C would not work.
* What we want is for Ctrl-C to work in the exec()-ed
* task, but being ignored by perf stat itself:
*/
signal(SIGINT, skip_signal);
signal(SIGALRM, skip_signal);
signal(SIGABRT, skip_signal);
status = 0;
for (run_idx = 0; run_idx < run_count; run_idx++) {
if (run_count != 1 && verbose)
fprintf(output, "[ perf stat: executing run #%d ... ]\n",
run_idx + 1);
status = run_perf_stat(argc, argv);
}
if (status != -1)
print_stat(argc, argv);
list_for_each_entry(pos, &evsel_list->entries, node)
perf_evsel__free_stat_priv(pos);
perf_evlist__delete_maps(evsel_list);
out:
perf_evlist__delete(evsel_list);
return status;