0
0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-15 15:04:27 +08:00
linux/tools/perf/util/spark.c
Jin Yao cebf7d51a6 perf diff: Report noisy for cycles diff
This patch prints the stddev and hist for the cycles diff of program
block. It can help us to understand if the cycles is noisy or not.

This patch is inspired by Andi Kleen's patch:

  https://lwn.net/Articles/600471/

We create new option '--cycles-hist'.

Example:

  perf record -b ./div
  perf record -b ./div
  perf diff -c cycles

  # Baseline                                [Program Block Range] Cycles Diff  Shared Object      Symbol
  # ........  .......................................................... ....  .................  ............................
  #
      46.72%                                      [div.c:40 -> div.c:40]    0  div                [.] main
      46.72%                                      [div.c:42 -> div.c:44]    0  div                [.] main
      46.72%                                      [div.c:42 -> div.c:39]    0  div                [.] main
      20.54%                          [random_r.c:357 -> random_r.c:394]    1  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:357 -> random_r.c:380]    0  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:388]    0  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:391]    0  libc-2.27.so       [.] __random_r
      17.04%                              [random.c:288 -> random.c:291]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:291 -> random.c:291]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:293 -> random.c:293]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:298 -> random.c:298]    0  libc-2.27.so       [.] __random
       8.40%                                      [div.c:22 -> div.c:25]    0  div                [.] compute_flag
       8.40%                                      [div.c:27 -> div.c:28]    0  div                [.] compute_flag
       5.14%                                    [rand.c:26 -> rand.c:27]    0  libc-2.27.so       [.] rand
       5.14%                                    [rand.c:28 -> rand.c:28]    0  libc-2.27.so       [.] rand
       2.15%                                  [rand@plt+0 -> rand@plt+0]    0  div                [.] rand@plt
       0.00%                                                                   [kernel.kallsyms]  [k] __x86_indirect_thunk_rax
       0.00%                                [do_mmap+714 -> do_mmap+732]  -10  [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+737 -> do_mmap+765]    1  [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+262 -> do_mmap+299]    0  [kernel.kallsyms]  [k] do_mmap
       0.00%  [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0]    7  [kernel.kallsyms]  [k] __x86_indirect_thunk_r15
       0.00%            [native_sched_clock+0 -> native_sched_clock+119]   -1  [kernel.kallsyms]  [k] native_sched_clock
       0.00%                 [native_write_msr+0 -> native_write_msr+16]  -13  [kernel.kallsyms]  [k] native_write_msr

When we enable the option '--cycles-hist', the output is

  perf diff -c cycles --cycles-hist

  # Baseline                                [Program Block Range] Cycles Diff        stddev/Hist  Shared Object      Symbol
  # ........  .......................................................... ....  .................  .................  ............................
  #
      46.72%                                      [div.c:40 -> div.c:40]    0  ± 37.8% ▁█▁▁██▁█   div                [.] main
      46.72%                                      [div.c:42 -> div.c:44]    0  ± 49.4% ▁▁▂█▂▂▂▂   div                [.] main
      46.72%                                      [div.c:42 -> div.c:39]    0  ± 24.1% ▃█▂▄▁▃▂▁   div                [.] main
      20.54%                          [random_r.c:357 -> random_r.c:394]    1  ± 33.5% ▅▂▁█▃▁▂▁   libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:357 -> random_r.c:380]    0  ± 39.4% ▁▁█▁██▅▁   libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:388]    0                     libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:391]    0  ± 41.2% ▁▃▁▂█▄▃▁   libc-2.27.so       [.] __random_r
      17.04%                              [random.c:288 -> random.c:291]    0  ± 48.8% ▁▁▁▁███▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:291 -> random.c:291]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:293 -> random.c:293]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0                     libc-2.27.so       [.] __random
      17.04%                              [random.c:298 -> random.c:298]    0  ± 75.6% ▃█▁▁▁▁▁▁   libc-2.27.so       [.] __random
       8.40%                                      [div.c:22 -> div.c:25]    0  ± 42.1% ▁▃▁▁███▁   div                [.] compute_flag
       8.40%                                      [div.c:27 -> div.c:28]    0  ± 41.8% ██▁▁▄▁▁▄   div                [.] compute_flag
       5.14%                                    [rand.c:26 -> rand.c:27]    0  ± 37.8% ▁▁▁████▁   libc-2.27.so       [.] rand
       5.14%                                    [rand.c:28 -> rand.c:28]    0                     libc-2.27.so       [.] rand
       2.15%                                  [rand@plt+0 -> rand@plt+0]    0                     div                [.] rand@plt
       0.00%                                                                                      [kernel.kallsyms]  [k] __x86_indirect_thunk_rax
       0.00%                                [do_mmap+714 -> do_mmap+732]  -10                     [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+737 -> do_mmap+765]    1                     [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+262 -> do_mmap+299]    0                     [kernel.kallsyms]  [k] do_mmap
       0.00%  [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0]    7                     [kernel.kallsyms]  [k] __x86_indirect_thunk_r15
       0.00%            [native_sched_clock+0 -> native_sched_clock+119]   -1  ± 38.5% ▄█▁        [kernel.kallsyms]  [k] native_sched_clock
       0.00%                 [native_write_msr+0 -> native_write_msr+16]  -13  ± 47.1% ▁█▇▃▁▁     [kernel.kallsyms]  [k] native_write_msr

 v8:
 ---
 Rebase to perf/core branch

 v7:
 ---
 1. v6 got Jiri's ACK.
 2. Rebase to latest perf/core branch.

 v6:
 ---
 1. Jiri provides better code for using data__hpp_register() in ui_init().
    Use this code in v6.

 v5:
 ---
 1. Refine the use of data__hpp_register() in ui_init() according to
    Jiri's suggestion.

 v4:
 ---
 1. Rename the new option from '--noisy' to '--cycles-hist'
 2. Remove the option '-n'.
 3. Only update the spark value and stats when '--cycles-hist' is enabled.
 4. Remove the code of printing '..'.

 v3:
 ---
 1. Move the histogram to a separate column
 2. Move the svals[] out of struct stats

 v2:
 ---
 Jiri got a compile error,

  CC       builtin-diff.o
  builtin-diff.c: In function ‘compute_cycles_diff’:
  builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
  712 |          labs(pair->block_info->cycles_spark[i] -
      |          ^~~~

 Because the result of u64 - u64 is still u64. Now we change the type of
 cycles_spark[] to s64.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-11 10:57:00 -03:00

35 lines
790 B
C

#include <stdio.h>
#include <limits.h>
#include <string.h>
#include <stdlib.h>
#include "spark.h"
#include "stat.h"
#define SPARK_SHIFT 8
/* Print spark lines on outf for numval values in val. */
int print_spark(char *bf, int size, unsigned long *val, int numval)
{
static const char *ticks[NUM_SPARKS] = {
"", "", "", "", "", "", "", ""
};
int i, printed = 0;
unsigned long min = ULONG_MAX, max = 0, f;
for (i = 0; i < numval; i++) {
if (val[i] < min)
min = val[i];
if (val[i] > max)
max = val[i];
}
f = ((max - min) << SPARK_SHIFT) / (NUM_SPARKS - 1);
if (f < 1)
f = 1;
for (i = 0; i < numval; i++) {
printed += scnprintf(bf + printed, size - printed, "%s",
ticks[((val[i] - min) << SPARK_SHIFT) / f]);
}
return printed;
}