linux/tools/perf/bench/bench.h
Ian Rogers 51876bd452 perf bench: Add kallsyms parsing
Add a benchmark for kallsyms parsing. Example output:

  Running 'internals/kallsyms-parse' benchmark:
  Average kallsyms__parse took: 103.971 ms (+- 0.121 ms)

Committer testing:

Test Machine: AMD Ryzen 5 3600X 6-Core Processor

  [root@five ~]# perf bench internals kallsyms-parse
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 79.692 ms (+- 0.101 ms)
  [root@five ~]# perf stat -r5 perf bench internals kallsyms-parse
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 80.563 ms (+- 0.079 ms)
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 81.046 ms (+- 0.155 ms)
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 80.874 ms (+- 0.104 ms)
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 81.173 ms (+- 0.133 ms)
  # Running 'internals/kallsyms-parse' benchmark:
    Average kallsyms__parse took: 81.169 ms (+- 0.074 ms)

   Performance counter stats for 'perf bench internals kallsyms-parse' (5 runs):

            8,093.54 msec task-clock                #    0.999 CPUs utilized            ( +-  0.14% )
               3,165      context-switches          #    0.391 K/sec                    ( +-  0.18% )
                  10      cpu-migrations            #    0.001 K/sec                    ( +- 23.13% )
                 744      page-faults               #    0.092 K/sec                    ( +-  0.21% )
      34,551,564,954      cycles                    #    4.269 GHz                      ( +-  0.05% )  (83.33%)
       1,160,584,308      stalled-cycles-frontend   #    3.36% frontend cycles idle     ( +-  1.60% )  (83.33%)
      14,974,323,985      stalled-cycles-backend    #   43.34% backend cycles idle      ( +-  0.24% )  (83.33%)
      58,712,905,705      instructions              #    1.70  insn per cycle
                                                    #    0.26  stalled cycles per insn  ( +-  0.01% )  (83.34%)
      14,136,433,778      branches                  # 1746.632 M/sec                    ( +-  0.01% )  (83.33%)
         141,943,217      branch-misses             #    1.00% of all branches          ( +-  0.04% )  (83.33%)

              8.1040 +- 0.0115 seconds time elapsed  ( +-  0.14% )

  [root@five ~]#

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lore.kernel.org/lkml/20200501221315.54715-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-05 16:35:32 -03:00

71 lines
2.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BENCH_H
#define BENCH_H
#include <sys/time.h>
extern struct timeval bench__start, bench__end, bench__runtime;
/*
* The madvise transparent hugepage constants were added in glibc
* 2.13. For compatibility with older versions of glibc, define these
* tokens if they are not already defined.
*
* PA-RISC uses different madvise values from other architectures and
* needs to be special-cased.
*/
#ifdef __hppa__
# ifndef MADV_HUGEPAGE
# define MADV_HUGEPAGE 67
# endif
# ifndef MADV_NOHUGEPAGE
# define MADV_NOHUGEPAGE 68
# endif
#else
# ifndef MADV_HUGEPAGE
# define MADV_HUGEPAGE 14
# endif
# ifndef MADV_NOHUGEPAGE
# define MADV_NOHUGEPAGE 15
# endif
#endif
int bench_numa(int argc, const char **argv);
int bench_sched_messaging(int argc, const char **argv);
int bench_sched_pipe(int argc, const char **argv);
int bench_mem_memcpy(int argc, const char **argv);
int bench_mem_memset(int argc, const char **argv);
int bench_futex_hash(int argc, const char **argv);
int bench_futex_wake(int argc, const char **argv);
int bench_futex_wake_parallel(int argc, const char **argv);
int bench_futex_requeue(int argc, const char **argv);
/* pi futexes */
int bench_futex_lock_pi(int argc, const char **argv);
int bench_epoll_wait(int argc, const char **argv);
int bench_epoll_ctl(int argc, const char **argv);
int bench_synthesize(int argc, const char **argv);
int bench_kallsyms_parse(int argc, const char **argv);
#define BENCH_FORMAT_DEFAULT_STR "default"
#define BENCH_FORMAT_DEFAULT 0
#define BENCH_FORMAT_SIMPLE_STR "simple"
#define BENCH_FORMAT_SIMPLE 1
#define BENCH_FORMAT_UNKNOWN -1
extern int bench_format;
extern unsigned int bench_repeat;
#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
#include <pthread.h>
#include <linux/compiler.h>
static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
size_t cpusetsize __maybe_unused,
cpu_set_t *cpuset __maybe_unused)
{
return 0;
}
#endif
#endif