path: root/tools/perf/builtin-stat.c

/*
 * 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: 0.104

    Performance counter stats for '/home/mingo/hackbench':

       1255.538611  task clock ticks     #      10.143 CPU utilization factor
             54011  context switches     #       0.043 M/sec
               385  CPU migrations       #       0.000 M/sec
             17755  pagefaults           #       0.014 M/sec
        3808323185  CPU cycles           #    3033.219 M/sec
        1575111190  instructions         #    1254.530 M/sec
          17367895  cache references     #      13.833 M/sec
           7674421  cache misses         #       6.112 M/sec

    Wall-clock time elapsed:   123.786620 msecs

 *
 * Copyright (C) 2008, 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 "perf.h"
#include "builtin.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/color.h"
#include "util/header.h"
#include "util/cpumap.h"
#include "util/thread.h"
#include "util/thread_map.h"

#include <sys/prctl.h>
#include <math.h>
#include <locale.h>

#define DEFAULT_SEPARATOR	" "

static struct perf_event_attr default_attrs[] = {

  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},

  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},

};

/*
 * Detailed stats:
 */
static struct perf_event_attr detailed_attrs[] = {

  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},

  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},

  { .type = PERF_TYPE_HW_CACHE,
    .config =
	 PERF_COUNT_HW_CACHE_L1D		<<  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_L1D		<<  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_LL			<<  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_LL			<<  0  |
	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
};

struct perf_evlist		*evsel_list;

static bool			system_wide			=  false;
static int			run_idx				=  0;

static int			run_count			=  1;
static bool			no_inherit			= false;
static bool			scale				=  true;
static bool			no_aggr				= false;
static pid_t			target_pid			= -1;
static pid_t			target_tid			= -1;
static pid_t			child_pid			= -1;
static bool			null_run			=  false;
static bool			detailed_run			=  false;
static bool			sync_run			=  false;
static bool			big_num				=  true;
static int			big_num_opt			=  -1;
static const char		*cpu_list;
static const char		*csv_sep			= NULL;
static bool			csv_output			= false;

static volatile int done = 0;

struct stats
{
	double n, mean, M2;
};

struct perf_stat {
	struct