perf stat: Micro-optimize the code: memcpy is only required if no event is selected and !null_run
Set attrs and nr_counters if no event is selected and !null_run.
Setting of attrs should depend on number of counters,
so we need to memcpy only for sizeof(default_attrs)
Also set nr_counters as ARRAY_SIZE(default_attrs) in place of
hardcoded value.
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1246126749.32198.16.camel@hpdv5.satnam>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3840a70..3e5ea4e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,7 +46,7 @@
#include <sys/prctl.h>
#include <math.h>
-static struct perf_counter_attr default_attrs[MAX_COUNTERS] = {
+static struct perf_counter_attr default_attrs[] = {
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES},
@@ -477,16 +477,17 @@
{
int status;
- memcpy(attrs, default_attrs, sizeof(attrs));
-
argc = parse_options(argc, argv, options, stat_usage, 0);
if (!argc)
usage_with_options(stat_usage, options);
if (run_count <= 0 || run_count > MAX_RUN)
usage_with_options(stat_usage, options);
- if (!null_run && !nr_counters)
- nr_counters = 8;
+ /* Set attrs and nr_counters if no event is selected and !null_run */
+ if (!null_run && !nr_counters) {
+ memcpy(attrs, default_attrs, sizeof(default_attrs));
+ nr_counters = ARRAY_SIZE(default_attrs);
+ }
nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
assert(nr_cpus <= MAX_NR_CPUS);