[RFC 2/3] perf, tools: Display pmu name when printing unmerged events in stat
From: Agustin Vega-Frias
Date: Tue Feb 27 2018 - 17:35:50 EST
Starting on v4.12 event parsing code for dynamic pmu events supports
prefix-based matching of multiple pmus when creating dynamic events.
E.g., in a system with the following dynamic pmus:
l3cache_0_0
l3cache_0_1
l3cache_0_2
l3cache_0_3
passing l3cache/<config>/ as an event spec will result in the creation
of the event in all of the pmus. When this functionality is used in
stat the command will by default merge the event counts and display
a single value. E.g.:
./perf stat -a -e l3cache/read-miss/ ls > /dev/null
Performance counter stats for 'system wide':
328 l3cache/read-miss/
0.001661809 seconds time elapsed
JSON-based alias events behave in the same way:
$ ./perf stat -a -e l3cache_read_miss ls > /dev/null
Performance counter stats for 'system wide':
229 l3cache_read_miss
0.001656099 seconds time elapsed
This behavior can be disabled by the --no-merge option but the real
pmu name is lost and it's not possible to see which count corresponds
to which pmu:
$ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null
Performance counter stats for 'system wide':
67 l3cache/read-miss/
67 l3cache/read-miss/
63 l3cache/read-miss/
60 l3cache/read-miss/
0.001675706 seconds time elapsed
This is also the case for alias events, e.g.:
$ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null
Performance counter stats for 'system wide':
12 l3cache_read_miss
17 l3cache_read_miss
10 l3cache_read_miss
8 l3cache_read_miss
0.001661305 seconds time elapsed
This change adds the original pmu name to the event. For dynamic pmu
events the pmu name is restored in the event name:
$ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null
Performance counter stats for 'system wide':
63 l3cache_0_3/read-miss/
74 l3cache_0_1/read-miss/
64 l3cache_0_2/read-miss/
74 l3cache_0_0/read-miss/
0.001675706 seconds time elapsed
For alias events the name is added after the event name:
$ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null
Performance counter stats for 'system wide':
10 l3cache_read_miss [l3cache_0_3]
12 l3cache_read_miss [l3cache_0_1]
10 l3cache_read_miss [l3cache_0_2]
17 l3cache_read_miss [l3cache_0_0]
0.001661305 seconds time elapsed
Signed-off-by: Agustin Vega-Frias <agustinv@xxxxxxxxxxxxxx>
---
tools/perf/builtin-stat.c | 29 ++++++++++++++++++++++++++++-
tools/perf/util/evsel.c | 1 +
tools/perf/util/evsel.h | 1 +
tools/perf/util/parse-events.c | 8 +++++++-
4 files changed, 37 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d3..d196972 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1225,6 +1225,31 @@ static void aggr_update_shadow(void)
}
}
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+ char *new_name;
+ char *config;
+
+ if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+ strlen(counter->pmu_name)))
+ return;
+
+ config = strchr(counter->name, '/');
+ if (config) {
+ if (asprintf(&new_name,
+ "%s%s", counter->pmu_name, config) > 0) {
+ free(counter->name);
+ counter->name = new_name;
+ }
+ } else {
+ if (asprintf(&new_name,
+ "%s [%s]", counter->name, counter->pmu_name) > 0) {
+ free(counter->name);
+ counter->name = new_name;
+ }
+ }
+}
+
static void collect_all_aliases(struct perf_evsel *counter,
void (*cb)(struct perf_evsel *counter, void *data,
bool first),
@@ -1253,7 +1278,9 @@ static bool collect_data(struct perf_evsel *counter,
if (counter->merged_stat)
return false;
cb(counter, data, true);
- if (!no_merge && counter->auto_merge_stats)
+ if (no_merge)
+ uniquify_event_name(counter);
+ else if (counter->auto_merge_stats)
collect_all_aliases(counter, cb, data);
return true;
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef35168..4841000 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
evsel->metric_name = NULL;
evsel->metric_events = NULL;
evsel->collect_stat = false;
+ evsel->pmu_name = NULL;
}
struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a7487c6..c2ac16a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -142,6 +142,7 @@ struct perf_evsel {
struct perf_evsel **metric_events;
bool collect_stat;
bool weak_group;
+ const char *pmu_name;
};
union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 34589c4..bafc91e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
if (!head_config) {
attr.type = pmu->type;
evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
- return evsel ? 0 : -ENOMEM;
+ if (evsel) {
+ evsel->pmu_name = name;
+ return 0;
+ } else {
+ return -ENOMEM;
+ }
}
if (perf_pmu__check_alias(pmu, head_config, &info))
@@ -1276,6 +1281,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
evsel->snapshot = info.snapshot;
evsel->metric_expr = info.metric_expr;
evsel->metric_name = info.metric_name;
+ evsel->pmu_name = name;
}
return evsel ? 0 : -ENOMEM;
--
2.7.4