#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
-static void print_stat(int argc, const char **argv);
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
-static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr(char *prefix);
+static void print_counters(struct timespec *ts, int argc, const char **argv);
/* Default events used for perf stat -T */
static const char *transaction_attrs = {
count = &zero;
switch (aggr_mode) {
+ case AGGR_THREAD:
case AGGR_CORE:
case AGGR_SOCKET:
case AGGR_NONE:
int i, ret;
aggr->val = aggr->ena = aggr->run = 0;
- memset(ps->res_stats, 0, sizeof(ps->res_stats));
+ init_stats(ps->res_stats);
if (counter->per_pkg)
zero_per_pkg(counter);
static void process_interval(void)
{
- static int num_print_interval;
- struct perf_evsel *counter;
struct timespec ts, rs;
- char prefix[64];
read_counters(false);
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
- sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
-
- if (num_print_interval == 0 && !csv_output) {
- switch (aggr_mode) {
- case AGGR_SOCKET:
- fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_CORE:
- fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_NONE:
- fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_GLOBAL:
- default:
- fprintf(output, "# time counts %*s events\n", unit_width, "unit");
- }
- }
-
- if (++num_print_interval == 25)
- num_print_interval = 0;
-
- switch (aggr_mode) {
- case AGGR_CORE:
- case AGGR_SOCKET:
- print_aggr(prefix);
- break;
- case AGGR_NONE:
- evlist__for_each(evsel_list, counter)
- print_counter(counter, prefix);
- break;
- case AGGR_GLOBAL:
- default:
- evlist__for_each(evsel_list, counter)
- print_counter_aggr(counter, prefix);
- }
- fflush(output);
+ print_counters(&rs, 0, NULL);
}
static void handle_initial_delay(void)
csv_output ? 0 : -4,
perf_evsel__cpus(evsel)->map[id], csv_sep);
break;
+ case AGGR_THREAD:
+ fprintf(output, "%*s-%*d%s",
+ csv_output ? 0 : 16,
+ thread_map__comm(evsel->threads, id),
+ csv_output ? 0 : -8,
+ thread_map__pid(evsel->threads, id),
+ csv_sep);
+ break;
case AGGR_GLOBAL:
default:
break;
}
}
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+ int nthreads = thread_map__nr(counter->threads);
+ int ncpus = cpu_map__nr(counter->cpus);
+ int cpu, thread;
+ double uval;
+
+ for (thread = 0; thread < nthreads; thread++) {
+ u64 ena = 0, run = 0, val = 0;
+
+ for (cpu = 0; cpu < ncpus; cpu++) {
+ val += perf_counts(counter->counts, cpu, thread)->val;
+ ena += perf_counts(counter->counts, cpu, thread)->ena;
+ run += perf_counts(counter->counts, cpu, thread)->run;
+ }
+
+ if (prefix)
+ fprintf(output, "%s", prefix);
+
+ uval = val * counter->scale;
+
+ if (nsec_counter(counter))
+ nsec_printout(thread, 0, counter, uval);
+ else
+ abs_printout(thread, 0, counter, uval);
+
+ if (!csv_output)
+ print_noise(counter, 1.0);
+
+ print_running(run, ena);
+ fputc('\n', output);
+ }
+}
+
/*
* Print out the results of a single counter:
* aggregated counts in system-wide mode
}
}
-static void print_stat(int argc, const char **argv)
+static void print_interval(char *prefix, struct timespec *ts)
+{
+ static int num_print_interval;
+
+ sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
+
+ if (num_print_interval == 0 && !csv_output) {
+ switch (aggr_mode) {
+ case AGGR_SOCKET:
+ fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit");
+ break;
+ case AGGR_CORE:
+ fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit");
+ break;
+ case AGGR_NONE:
+ fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit");
+ break;
+ case AGGR_THREAD:
+ fprintf(output, "# time comm-pid counts %*s events\n", unit_width, "unit");
+ break;
+ case AGGR_GLOBAL:
+ default:
+ fprintf(output, "# time counts %*s events\n", unit_width, "unit");
+ }
+ }
+
+ if (++num_print_interval == 25)
+ num_print_interval = 0;
+}
+
+static void print_header(int argc, const char **argv)
{
- struct perf_evsel *counter;
int i;
fflush(stdout);
fprintf(output, " (%d runs)", run_count);
fprintf(output, ":\n\n");
}
+}
+
+static void print_footer(void)
+{
+ if (!null_run)
+ fprintf(output, "\n");
+ fprintf(output, " %17.9f seconds time elapsed",
+ avg_stats(&walltime_nsecs_stats)/1e9);
+ if (run_count > 1) {
+ fprintf(output, " ");
+ print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+ avg_stats(&walltime_nsecs_stats));
+ }
+ fprintf(output, "\n\n");
+}
+
+static void print_counters(struct timespec *ts, int argc, const char **argv)
+{
+ struct perf_evsel *counter;
+ char buf[64], *prefix = NULL;
+
+ if (interval)
+ print_interval(prefix = buf, ts);
+ else
+ print_header(argc, argv);
switch (aggr_mode) {
case AGGR_CORE:
case AGGR_SOCKET:
- print_aggr(NULL);
+ print_aggr(prefix);
+ break;
+ case AGGR_THREAD:
+ evlist__for_each(evsel_list, counter)
+ print_aggr_thread(counter, prefix);
break;
case AGGR_GLOBAL:
evlist__for_each(evsel_list, counter)
- print_counter_aggr(counter, NULL);
+ print_counter_aggr(counter, prefix);
break;
case AGGR_NONE:
evlist__for_each(evsel_list, counter)
- print_counter(counter, NULL);
+ print_counter(counter, prefix);
break;
default:
break;
}
- if (!csv_output) {
- if (!null_run)
- fprintf(output, "\n");
- fprintf(output, " %17.9f seconds time elapsed",
- avg_stats(&walltime_nsecs_stats)/1e9);
- if (run_count > 1) {
- fprintf(output, " ");
- print_noise_pct(stddev_stats(&walltime_nsecs_stats),
- avg_stats(&walltime_nsecs_stats));
- }
- fprintf(output, "\n\n");
- }
+ if (!interval && !csv_output)
+ print_footer();
+
+ fflush(output);
}
static volatile int signr = -1;
break;
case AGGR_NONE:
case AGGR_GLOBAL:
+ case AGGR_THREAD:
default:
break;
}
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-core", &aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
+ OPT_SET_UINT(0, "per-thread", &aggr_mode,
+ "aggregate counts per thread", AGGR_THREAD),
OPT_UINTEGER('D', "delay", &initial_delay,
"ms to wait before starting measurement after program start"),
OPT_END()
run_count = 1;
}
- /* no_aggr, cgroup are for system-wide only */
- if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+ if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
+ fprintf(stderr, "The --per-thread option is only available "
+ "when monitoring via -p -t options.\n");
+ parse_options_usage(NULL, options, "p", 1);
+ parse_options_usage(NULL, options, "t", 1);
+ goto out;
+ }
+
+ /*
+ * no_aggr, cgroup are for system-wide only
+ * --per-thread is aggregated per thread, we dont mix it with cpu mode
+ */
+ if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
!target__has_cpu(&target)) {
fprintf(stderr, "both cgroup and no-aggregation "
"modes only available in system-wide mode\n");
}
goto out;
}
+
+ /*
+ * Initialize thread_map with comm names,
+ * so we could print it out on output.
+ */
+ if (aggr_mode == AGGR_THREAD)
+ thread_map__read_comms(evsel_list->threads);
+
if (interval && interval < 100) {
pr_err("print interval must be >= 100ms\n");
parse_options_usage(stat_usage, options, "I", 1);
status = run_perf_stat(argc, argv);
if (forever && status != -1) {
- print_stat(argc, argv);
+ print_counters(NULL, argc, argv);
perf_stat__reset_stats();
}
}
if (!forever && status != -1 && !interval)
- print_stat(argc, argv);
+ print_counters(NULL, argc, argv);
perf_evlist__free_stats(evsel_list);
out:
projects / karo-tx-linux.git / blobdiff