From: Jin Yao <[email protected]>
For hybrid events, by default stat aggregates and reports the event counts
per pmu.
root@otcpl-adl-s-2:~# ./perf stat -e cycles -a -- sleep 1
Performance counter stats for 'system wide':
17,291,386 cycles [cpu_core]
1,556,803 cycles [cpu_atom]
1.002154118 seconds time elapsed
Sometime, it's also useful to aggregate event counts from all PMUs.
Create a new option '--hybrid-merge' to enable that behavior and report
the counts without PMUs.
root@otcpl-adl-s-2:~# ./perf stat -e cycles -a --hybrid-merge -- sleep 1
Performance counter stats for 'system wide':
19,041,587 cycles
1.002195329 seconds time elapsed
Reviewed-by: Andi Kleen <[email protected]>
Signed-off-by: Jin Yao <[email protected]>
---
tools/perf/Documentation/perf-stat.txt | 7 +++++++
tools/perf/builtin-stat.c | 3 ++-
tools/perf/util/stat-display.c | 3 ++-
tools/perf/util/stat.h | 1 +
4 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt
b/tools/perf/Documentation/perf-stat.txt
index b0e357d..3d083a3 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -418,6 +418,13 @@ Multiple events are created from a single event
specification when:
2. Aliases, which are listed immediately after the Kernel PMU events
by perf list, are used.
+--hybrid-merge::
+Merge the hybrid event counts from all PMUs.
+
+For hybrid events, by default stat aggregates and reports the event counts
+per pmu. But sometime, it's also useful to aggregate event counts from all
+PMUs. This option enables that behavior and reports the counts without PMUs.
+
--smi-cost::
Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bfe7305..d367cfe 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1184,6 +1184,7 @@ static struct option stat_options[] = {
OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
"disable CPU count aggregation", AGGR_NONE),
OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge
identical named events"),
+ OPT_BOOLEAN(0, "hybrid-merge", &stat_config.hybrid_merge, "Merge
identical named hybrid events"),
OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
"print counts with custom separator"),
OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
@@ -2379,7 +2380,7 @@ int cmd_stat(int argc, const char **argv)
evlist__check_cpu_maps(evsel_list);
- if (perf_pmu__hybrid_exist())
+ if (perf_pmu__hybrid_exist() && !stat_config.hybrid_merge)
stat_config.no_merge = true;
/*
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 961d5ac..21a3f80 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -568,6 +568,7 @@ static void collect_all_aliases(struct perf_stat_config
*config, struct evsel *c
!strcmp(alias->pmu_name, counter->pmu_name) ||
(evsel__is_hybrid_event(alias) &&
evsel__is_hybrid_event(counter) &&
+ !config->hybrid_merge &&
strcmp(alias->pmu_name, counter->pmu_name)))
break;
alias->merged_stat = true;
@@ -585,7 +586,7 @@ static bool collect_data(struct perf_stat_config *config,
struct evsel *counter,
cb(config, counter, data, true);
if (config->no_merge)
uniquify_event_name(counter);
- else if (counter->auto_merge_stats)
+ else if (counter->auto_merge_stats || config->hybrid_merge)
collect_all_aliases(config, counter, cb, data);
return true;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index d85c292..80f6715 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -123,6 +123,7 @@ struct perf_stat_config {
bool ru_display;
bool big_num;
bool no_merge;
+ bool hybrid_merge;
bool walltime_run_table;
bool all_kernel;
bool all_user;
--
2.7.4
