diff options
| author | Andi Kleen <ak@linux.intel.com> | 2016-02-26 16:27:56 -0800 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2016-03-03 11:06:43 -0300 |
| commit | 9dec4473abe7967c204fe700baf5344ade34e9c8 (patch) | |
| tree | aaa71efdd6e2aaec1e6ceebe4d2bd92c64e81381 /tools/perf/builtin-stat.c | |
| parent | f9a5978ac4ede901fa73d7c28ae1c5d89bc2a46a (diff) | |
| download | op-kernel-dev-9dec4473abe7967c204fe700baf5344ade34e9c8.zip op-kernel-dev-9dec4473abe7967c204fe700baf5344ade34e9c8.tar.gz | |
perf stat: Check existence of frontend/backed stalled cycles
Only put the frontend/backend stalled cycles into the default perf stat
events when the CPU actually supports them.
This avoids empty columns with --metric-only on newer Intel CPUs.
Committer note:
Before:
$ perf stat ls
Performance counter stats for 'ls':
1.080893 task-clock (msec) # 0.619 CPUs utilized
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/sec
97 page-faults # 0.090 M/sec
3,327,741 cycles # 3.079 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,609,544 instructions # 0.48 insn per cycle
319,117 branches # 295.235 M/sec
12,246 branch-misses # 3.84% of all branches
0.001746508 seconds time elapsed
$
After:
$ perf stat ls
Performance counter stats for 'ls':
0.693948 task-clock (msec) # 0.662 CPUs utilized
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/sec
95 page-faults # 0.137 M/sec
1,792,509 cycles # 2.583 GHz
1,599,047 instructions # 0.89 insn per cycle
316,328 branches # 455.838 M/sec
12,453 branch-misses # 3.94% of all branches
0.001048987 seconds time elapsed
$
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1456532881-26621-2-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/builtin-stat.c')
| -rw-r--r-- | tools/perf/builtin-stat.c | 22 |
1 files changed, 20 insertions, 2 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 8c0bc0f..24f222d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1441,7 +1441,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) */ static int add_default_attributes(void) { - struct perf_event_attr default_attrs[] = { + struct perf_event_attr default_attrs0[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, @@ -1449,8 +1449,14 @@ static int add_default_attributes(void) { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, +}; + struct perf_event_attr frontend_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, +}; + struct perf_event_attr backend_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + struct perf_event_attr default_attrs1[] = { { .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 }, @@ -1567,7 +1573,19 @@ static int add_default_attributes(void) } if (!evsel_list->nr_entries) { - if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0) + if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0) + return -1; + if (pmu_have_event("cpu", "stalled-cycles-frontend")) { + if (perf_evlist__add_default_attrs(evsel_list, + frontend_attrs) < 0) + return -1; + } + if (pmu_have_event("cpu", "stalled-cycles-backend")) { + if (perf_evlist__add_default_attrs(evsel_list, + backend_attrs) < 0) + return -1; + } + if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; } |
