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: 0.118

  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 "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	" "
#define CNTR_NOT_SUPPORTED	"<not supported>"
#define CNTR_NOT_COUNTED	"<not counted>"

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_FRONTEND	},
  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
  { .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 (-d), covering the L1 and last level data caches:
 */
static struct perf_event_attr detailed_attrs[] = {

  { .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_COU