Newer
Older
* builtin-stat.c
*
* Builtin stat command: Give a precise performance counters summary
* overview about any workload, CPU or specific PID.
*
* Sample output:
$ perf stat ./hackbench 10
Time: 0.118
Performance counter stats for './hackbench 10':
1708.761321 task-clock # 11.037 CPUs utilized
41,190 context-switches # 0.024 M/sec
6,735 CPU-migrations # 0.004 M/sec
17,318 page-faults # 0.010 M/sec
5,205,202,243 cycles # 3.046 GHz
3,856,436,920 stalled-cycles-frontend # 74.09% frontend cycles idle
1,600,790,871 stalled-cycles-backend # 30.75% backend cycles idle
2,603,501,247 instructions # 0.50 insns per cycle
# 1.48 stalled cycles per insn
484,357,498 branches # 283.455 M/sec
6,388,934 branch-misses # 1.32% of all branches
0.154822978 seconds time elapsed
* Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
*
* Improvements and fixes by:
*
* Arjan van de Ven <arjan@linux.intel.com>
* Yanmin Zhang <yanmin.zhang@intel.com>
* Wu Fengguang <fengguang.wu@intel.com>
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
* Jaswinder Singh Rajput <jaswinder@kernel.org>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include "builtin.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/stat.h"
#include "util/cpumap.h"

Zhang, Yanmin
committed
#include "util/thread.h"
#include "util/thread_map.h"
#include <sys/prctl.h>
#include <locale.h>

Peter Zijlstra
committed
#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 struct perf_evlist *evsel_list;
static struct perf_target target = {
.uid = UINT_MAX,
};
enum aggr_mode {
AGGR_NONE,
AGGR_GLOBAL,
AGGR_SOCKET,
static bool no_inherit = false;

Ian Munsie
committed
static bool scale = true;
static enum aggr_mode aggr_mode = AGGR_GLOBAL;
static volatile pid_t child_pid = -1;

Ian Munsie
committed
static bool null_run = false;
static int detailed_run = 0;
static bool big_num = true;
static int big_num_opt = -1;
static const char *csv_sep = NULL;
static bool csv_output = false;
static bool group = false;
static const char *pre_cmd = NULL;
static const char *post_cmd = NULL;
static bool sync_run = false;
static unsigned int initial_delay = 0;
static struct cpu_map *aggr_map;
static int (*aggr_get_id)(struct cpu_map *m, int cpu);
struct perf_stat {
struct stats res_stats[3];
};
static inline void diff_timespec(struct timespec *r, struct timespec *a,
struct timespec *b)
{
r->tv_sec = a->tv_sec - b->tv_sec;
if (a->tv_nsec < b->tv_nsec) {
r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
r->tv_sec--;
} else {
r->tv_nsec = a->tv_nsec - b->tv_nsec ;
}
}
static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
{
return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
}
static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
{
return perf_evsel__cpus(evsel)->nr;
}
static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
{
memset(evsel->priv, 0, sizeof(struct perf_stat));
}
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
evsel->priv = zalloc(sizeof(struct perf_stat));
return evsel->priv == NULL ? -ENOMEM : 0;
}
static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
{
free(evsel->priv);
evsel->priv = NULL;
}
static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
void *addr;
size_t sz;
sz = sizeof(*evsel->counts) +
(perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
addr = zalloc(sz);
if (!addr)
return -ENOMEM;
evsel->prev_raw_counts = addr;
return 0;
static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
free(evsel->prev_raw_counts);
evsel->prev_raw_counts = NULL;
static void perf_evlist__free_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
list_for_each_entry(evsel, &evlist->entries, node) {
perf_evsel__free_stat_priv(evsel);
perf_evsel__free_counts(evsel);
perf_evsel__free_prev_raw_counts(evsel);
}
}
static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
{
struct perf_evsel *evsel;
list_for_each_entry(evsel, &evlist->entries, node) {
if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
(alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
goto out_free;
}
return 0;
Loading
Loading full blame...