perf stat: Use group read for event groups

Make perf stat use  group read if there  are groups defined. The group
read will get the values for all member of groups within a single
syscall instead of calling read syscall for every event.

We can see considerable less amount of kernel cycles spent on single
group read, than reading each event separately, like for following perf
stat command:

  # perf stat -e {cycles,instructions} -I 10 -a sleep 1

Monitored with "perf stat -r 5 -e '{cycles:u,cycles:k}'"

Before:

        24,325,676      cycles:u
       297,040,775      cycles:k

       1.038554134 seconds time elapsed

After:
        25,034,418      cycles:u
       158,256,395      cycles:k

       1.036864497 seconds time elapsed

The perf_evsel__open fallback changes contributed by Andi Kleen.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20170726120206.9099-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 11 insertions, 0 deletions

diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 34d8baaf558a..cb45a6aecf9d 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -12,6 +12,7 @@ struct perf_counts_values {
 		};
 		u64 values[3];
 	};
+	bool	loaded;
 };
 
 struct perf_counts {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 89aecf3a35c7..3735c9e0080d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -49,6 +49,7 @@ static struct {
 	bool clockid_wrong;
 	bool lbr_flags;
 	bool write_backward;
+	bool group_read;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -1321,6 +1322,7 @@ perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread,
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
+	count->loaded = true;
 }
 
 static int
@@ -1677,6 +1679,8 @@ fallback_missing_features:
 	if (perf_missing_features.lbr_flags)
 		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
+	if (perf_missing_features.group_read && evsel->attr.inherit)
+		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1832,6 +1836,12 @@ try_fallback:
 		perf_missing_features.lbr_flags = true;
 		pr_debug2("switching off branch sample type no (cycles/flags)\n");
 		goto fallback_missing_features;
+	} else if (!perf_missing_features.group_read &&
+		    evsel->attr.inherit &&
+		   (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+		perf_missing_features.group_read = true;
+		pr_debug2("switching off group read\n");
+		goto fallback_missing_features;
 	}
 out_close:
 	do {