[PATCH RESEND 1/2] perf stat: Fix event grouping on forked task

[PATCH RESEND 1/2] perf stat: Fix event grouping on forked task

[Namhyung Kim]

When event group is enabled for forked task (i.e. no target task was
specified) all events were disabled and marked ->enable_on_exec.
However they are not counted at all since only group leader will be
enabled on exec actually. So the result looked like below:

 $ ./perf stat --group -- sleep 1

 Performance counter stats for 'sleep 1':

          0.554926 task-clock                #    0.001 CPUs utilized
     <not counted> context-switches
     <not counted> CPU-migrations
     <not counted> page-faults
     <not counted> cycles
   <not supported> stalled-cycles-frontend
   <not supported> stalled-cycles-backend
     <not counted> instructions
     <not counted> branches
     <not counted> branch-misses

       1.001228093 seconds time elapsed

Fix it by disabling group leader only.

Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
---
 tools/perf/builtin-stat.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ea40e4e8b227..c941bb640f49 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (!target_pid && !target_tid) {
+	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
-- 
1.7.9

[PATCH RESEND 2/2] perf tools: Do not disable members of group event

[Namhyung Kim]

When event group is enabled for forked task (i.e. no target task/cpu
was specified) all events were disabled and marked ->enable_on_exec.
However they wouldn't be counted at all since only group leader will
be enabled on exec actually.

In contrast to perf stat, perf record doesn't have a real problem
as it enables all the event before proceeding. But it needs to be
fixed anyway IMHO.

Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
---
 tools/perf/util/evlist.c |    6 ++++--
 tools/perf/util/evsel.c  |    6 ++++--
 tools/perf/util/evsel.h  |    3 ++-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 159263d17c2d..1986d8051bd1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -51,13 +51,15 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, first);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f421f7cbc0d3..0221700075c5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -63,7 +63,8 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
+			struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
@@ -134,7 +135,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (!opts->target_pid && !opts->target_tid && !opts->system_wide) {
+	if (!opts->target_pid && !opts->target_tid && !opts->system_wide &&
+	    (!opts->group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 326b8e4d5035..3158ca3d69a1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -80,7 +80,8 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct perf_record_opts *opts,
+			struct perf_evsel *first);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-- 
1.7.9

[tip:perf/core] perf stat: Fix event grouping on forked task

[tip-bot for Namhyung Kim]

Commit-ID:  4c19ea453d81cf8bd9bd446e6b129998f79997e7
Gitweb:     http://git.kernel.org/tip/4c19ea453d81cf8bd9bd446e6b129998f79997e7
Author:     Namhyung Kim <namhyung.kim@lge.com>
AuthorDate: Fri, 16 Mar 2012 17:42:19 +0900
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 16 Mar 2012 16:13:45 -0300

perf stat: Fix event grouping on forked task

When event group is enabled for forked task (i.e. no target task was
specified) all events were disabled and marked ->enable_on_exec.
However they are not counted at all since only group leader will be
enabled on exec actually. So the result looked like below:

 $ ./perf stat --group -- sleep 1

 Performance counter stats for 'sleep 1':

          0.554926 task-clock                #    0.001 CPUs utilized
     <not counted> context-switches
     <not counted> CPU-migrations
     <not counted> page-faults
     <not counted> cycles
   <not supported> stalled-cycles-frontend
   <not supported> stalled-cycles-backend
     <not counted> instructions
     <not counted> branches
     <not counted> branch-misses

       1.001228093 seconds time elapsed

Fix it by disabling group leader only.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1331887340-32448-1-git-send-email-namhyung.kim@lge.com
Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ea40e4e..c941bb6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (!target_pid && !target_tid) {
+	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}

[tip:perf/core] perf tools: Do not disable members of group event

[tip-bot for Namhyung Kim]

Commit-ID:  5090c6aea84dcc474d0aabf9f66f1eab68a143eb
Gitweb:     http://git.kernel.org/tip/5090c6aea84dcc474d0aabf9f66f1eab68a143eb
Author:     Namhyung Kim <namhyung.kim@lge.com>
AuthorDate: Fri, 16 Mar 2012 17:42:20 +0900
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 16 Mar 2012 16:29:33 -0300

perf tools: Do not disable members of group event

When event group is enabled for forked task (i.e. no target task/cpu
was specified) all events were disabled and marked ->enable_on_exec.
However they wouldn't be counted at all since only group leader will
be enabled on exec actually.

In contrast to perf stat, perf record doesn't have a real problem
as it enables all the event before proceeding. But it needs to be
fixed anyway IMHO.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1331887340-32448-2-git-send-email-namhyung.kim@lge.com
Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c |    6 ++++--
 tools/perf/util/evsel.c  |    6 ++++--
 tools/perf/util/evsel.h  |    3 ++-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 159263d..1986d80 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -51,13 +51,15 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, first);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f421f7c..0221700 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -63,7 +63,8 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
+			struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
@@ -134,7 +135,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (!opts->target_pid && !opts->target_tid && !opts->system_wide) {
+	if (!opts->target_pid && !opts->target_tid && !opts->system_wide &&
+	    (!opts->group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 326b8e4..3158ca3 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -80,7 +80,8 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct perf_record_opts *opts,
+			struct perf_evsel *first);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);