It would be useful to support the overall statistics for perf-stat
interval mode. For example, report the summary at the end of
"perf-stat -I" output.
But since perf-stat can support many aggregation modes, such as
--per-thread, --per-socket, -M and etc, we need a solution which
doesn't bring much complexity.
The idea is to create new 'evsel->summary_counts' which sums up the
counts delta per interval. Before reporting the summary, we copy the
data from evsel->summary_counts to evsel->counts, and next we just
follow current code.
v2:
---
Rebase to perf/core branch
Signed-off-by: Jin Yao <yao....@linux.intel.com>
---
tools/perf/util/evsel.c | 10 ++++++++--
tools/perf/util/evsel.h | 1 +
tools/perf/util/stat.c | 20 ++++++++++++++++++++
3 files changed, 29 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a75bcb95bf23..abc503dd6eda 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1280,22 +1280,28 @@ void evsel__delete(struct evsel *evsel)
void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
struct perf_counts_values *count)
{
- struct perf_counts_values tmp;
+ struct perf_counts_values tmp, *summary;
- if (!evsel->prev_raw_counts)
+ if (!evsel->prev_raw_counts || !evsel->summary_counts)
return;
if (cpu == -1) {
tmp = evsel->prev_raw_counts->aggr;
evsel->prev_raw_counts->aggr = *count;
+ summary = &evsel->summary_counts->aggr;
} else {
tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
+ summary = perf_counts(evsel->summary_counts, cpu, thread);
}
count->val = count->val - tmp.val;
count->ena = count->ena - tmp.ena;
count->run = count->run - tmp.run;
+
+ summary->val += count->val;
+ summary->ena += count->ena;
+ summary->run += count->run;
}
void perf_counts_values__scale(struct perf_counts_values *count,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 783246bf8d0d..430639c99d04 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ struct evsel {
char *filter;
struct perf_counts *counts;
struct perf_counts *prev_raw_counts;
+ struct perf_counts *summary_counts;
int idx;
unsigned long max_events;
unsigned long nr_events_printed;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 774468341851..c3fd008b4e84 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -171,6 +171,24 @@ static void perf_evsel__reset_prev_raw_counts(struct evsel
*evsel)
}
}
+static int perf_evsel__alloc_summary_counts(struct evsel *evsel,
+ int ncpus, int nthreads)
+{
+ struct perf_counts *counts;
+
+ counts = perf_counts__new(ncpus, nthreads);
+ if (counts)
+ evsel->summary_counts = counts;
+
+ return counts ? 0 : -ENOMEM;
+}
+
+static void perf_evsel__free_summary_counts(struct evsel *evsel)
+{
+ perf_counts__delete(evsel->summary_counts);
+ evsel->summary_counts = NULL;
+}
+
static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
int ncpus = evsel__nr_cpus(evsel);
@@ -178,6 +196,7 @@ static int perf_evsel__alloc_stats(struct evsel *evsel,
bool alloc_raw)
if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+ perf_evsel__alloc_summary_counts(evsel, ncpus, nthreads) < 0 ||
(alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus,
nthreads) < 0))
return -ENOMEM;
@@ -208,6 +227,7 @@ void perf_evlist__free_stats(struct evlist *evlist)
perf_evsel__free_stat_priv(evsel);
perf_evsel__free_counts(evsel);
perf_evsel__free_prev_raw_counts(evsel);
+ perf_evsel__free_summary_counts(evsel);
}
}
--
2.17.1
