diff mbox series

[2/3] perf util: Use target->per_thread and target->system_wide flags

Message ID 1518467557-18505-3-git-send-email-mathieu.poirier@linaro.org
State New
Headers show
Series perf tools: Miscellaneous fix from the previous cycle | expand

Commit Message

Mathieu Poirier Feb. 12, 2018, 8:32 p.m. UTC 
From: Jin Yao <yao.jin@linux.intel.com>


Mathieu Poirier reports issue in commit ("73c0ca1eee3d perf thread_map:
Enumerate all threads from /proc") that it has negative impact on
'perf record --per-thread'. It has the effect of creating a kernel event
for each thread in the system for 'perf record --per-thread'.

Mathieu Poirier's patch ("perf util: Do not reuse target->per_thread flag")
can fix this issue by creating a new target->all_threads flag.

This patch is based on Mathieu Poirier's patch but it doesn't use a new
target->all_threads flag. This patch just uses 'target->per_thread &&
target->system_wide' as a condition to check for all threads case.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>

[Fixed checkpatch warning about line over 80 characters]
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>

---
 tools/perf/util/evlist.c     | 21 ++++++++++++++++++++-
 tools/perf/util/thread_map.c |  4 ++--
 tools/perf/util/thread_map.h |  2 +-
 3 files changed, 23 insertions(+), 4 deletions(-)

-- 
2.7.4
diff mbox series

Patch

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e5fc14e53c05..7b7d535396f7 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1086,11 +1086,30 @@  int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
+	bool all_threads = (target->per_thread && target->system_wide);
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 
+	/*
+	 * If specify '-a' and '--per-thread' to perf record, perf record
+	 * will override '--per-thread'. target->per_thread = false and
+	 * target->system_wide = true.
+	 *
+	 * If specify '--per-thread' only to perf record,
+	 * target->per_thread = true and target->system_wide = false.
+	 *
+	 * So target->per_thread && target->system_wide is false.
+	 * For perf record, thread_map__new_str doesn't call
+	 * thread_map__new_all_cpus. That will keep perf record's
+	 * current behavior.
+	 *
+	 * For perf stat, it allows the case that target->per_thread and
+	 * target->system_wide are all true. It means to collect system-wide
+	 * per-thread data. thread_map__new_str will call
+	 * thread_map__new_all_cpus to enumerate all threads.
+	 */
 	threads = thread_map__new_str(target->pid, target->tid, target->uid,
-				      target->per_thread);
+				      all_threads);
 
 	if (!threads)
 		return -1;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 3e1038f6491c..729dad8f412d 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -323,7 +323,7 @@  struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-				       uid_t uid, bool per_thread)
+				       uid_t uid, bool all_threads)
 {
 	if (pid)
 		return thread_map__new_by_pid_str(pid);
@@ -331,7 +331,7 @@  struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	if (!tid && uid != UINT_MAX)
 		return thread_map__new_by_uid(uid);
 
-	if (per_thread)
+	if (all_threads)
 		return thread_map__new_all_cpus();
 
 	return thread_map__new_by_tid_str(tid);
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0a806b99e73c..5ec91cfd1869 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -31,7 +31,7 @@  struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-		const char *tid, uid_t uid, bool per_thread);
+		const char *tid, uid_t uid, bool all_threads);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);