[PATCH 37/38] perf session: Handle index files generally

[Namhyung Kim]

The current code assumes that the number of index item and cpu are
matched so it creates that number of threads.  But it's not the case
of non-system-wide session or data came from different machine.

Just creates threads at most number of online cpus and process data.

Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
 tools/perf/util/session.c | 76 +++++++++++++++++++++++++++++++++--------------
 tools/perf/util/tool.h    |  1 -
 2 files changed, 54 insertions(+), 23 deletions(-)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index a9e3dd309d4d..3c999bae8e52 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1501,26 +1501,51 @@ static struct ui_progress_ops mt_progress__ops = {
 	.update = mt_progress__update,
 };
 
+static int perf_session__get_index(struct perf_session *session)
+{
+	int ret;
+	static unsigned index = 1;
+	static pthread_mutex_t idx_lock = PTHREAD_MUTEX_INITIALIZER;
+
+	pthread_mutex_lock(&idx_lock);
+	if (index < session->header.nr_index)
+		ret = index++;
+	else
+		ret = -1;
+	pthread_mutex_unlock(&idx_lock);
+
+	return ret;
+}
+
 static void *processing_thread_idx(void *arg)
 {
 	struct perf_tool_mt *mt_tool = arg;
 	struct perf_session *session = mt_tool->session;
 	int fd = perf_data_file__fd(session->file);
-	u64 offset = session->header.index[mt_tool->idx].offset;
-	u64 size = session->header.index[mt_tool->idx].size;
 	u64 file_size = perf_data_file__size(session->file);
+	int idx;
 
-	ui_progress__init(&mt_tool->prog, size, "");
+	while ((idx = perf_session__get_index(session)) >= 0) {
+		u64 offset = session->header.index[idx].offset;
+		u64 size = session->header.index[idx].size;
+		struct perf_tool_mt *mtt = &mt_tool[idx];
 
-	pr_debug("processing samples using thread [%d]\n", mt_tool->idx);
-	if (__perf_session__process_events(session, &mt_tool->stats,
-					   fd, offset, size, file_size,
-					   &mt_tool->tool, &mt_tool->prog) < 0) {
-		pr_err("processing samples failed (thread [%d])\n", mt_tool->idx);
-		return NULL;
+		if (size == 0)
+			continue;
+
+		pr_debug("processing samples [index %d]\n", idx);
+
+		ui_progress__init(&mtt->prog, size, "");
+
+		if (__perf_session__process_events(session, &mtt->stats,
+						   fd, offset, size, file_size,
+						   &mtt->tool, &mtt->prog) < 0) {
+			pr_err("processing samples failed [index %d]\n", idx);
+			return NULL;
+		}
+		pr_debug("processing samples done [index %d]\n", idx);
 	}
 
-	pr_debug("processing samples done for thread [%d]\n", mt_tool->idx);
 	return arg;
 }
 
@@ -1538,6 +1563,7 @@ int perf_session__process_events_mt(struct perf_session *session,
 	int err, i, k;
 	int nr_index = session->header.nr_index;
 	u64 size = perf_data_file__size(file);
+	int nr_thread = sysconf(_SC_NPROCESSORS_ONLN);
 
 	if (perf_data_file__is_pipe(file) || !session->header.index) {
 		pr_err("data file doesn't contain the index table\n");
@@ -1561,15 +1587,11 @@ int perf_session__process_events_mt(struct perf_session *session,
 	ui_progress__ops = &mt_progress__ops;
 	ui_progress__ops->finish = orig_progress__ops->finish;
 
-	th_id = calloc(nr_index, sizeof(*th_id));
-	if (th_id == NULL)
-		goto out;
-
 	mt_tools = calloc(nr_index, sizeof(*mt_tools));
 	if (mt_tools == NULL)
 		goto out;
 
-	for (i = 1; i < nr_index; i++) {
+	for (i = 0; i < nr_index; i++) {
 		mt = &mt_tools[i];
 
 		memcpy(&mt->tool, tool, sizeof(*tool));
@@ -1583,20 +1605,30 @@ int perf_session__process_events_mt(struct perf_session *session,
 
 		mt->session = session;
 		mt->tool.ordered_events = false;
-		mt->idx = i;
 		mt->priv = arg;
 		mt->global_prog = &prog;
-
-		pthread_create(&th_id[i], NULL, processing_thread_idx, mt);
 	}
 
-	for (i = 1; i < nr_index; i++) {
+	if (nr_thread > nr_index - 1)
+		nr_thread = nr_index - 1;
+
+	th_id = calloc(nr_thread, sizeof(*th_id));
+	if (th_id == NULL)
+		goto out;
+
+	for (i = 0; i < nr_thread; i++)
+		pthread_create(&th_id[i], NULL, processing_thread_idx, mt_tools);
+
+	for (i = 0; i < nr_thread; i++) {
 		pthread_join(th_id[i], (void **)&mt);
 		if (mt == NULL) {
 			err = -EINVAL;
 			continue;
 		}
+	}
 
+	for (i = 0; i < nr_index; i++) {
+		mt = &mt_tools[i];
 		events_stats__add(&evlist->stats, &mt->stats);
 
 		evlist__for_each(evlist, evsel) {
@@ -1612,7 +1644,7 @@ int perf_session__process_events_mt(struct perf_session *session,
 	ui_progress__ops = orig_progress__ops;
 	ui_progress__init(&prog, nr_entries, "Merging related events...");
 
-	for (i = 1; i < nr_index; i++) {
+	for (i = 0; i < nr_index; i++) {
 		mt = &mt_tools[i];
 
 		evlist__for_each(evlist, evsel) {
@@ -1640,7 +1672,7 @@ int perf_session__process_events_mt(struct perf_session *session,
 	perf_tool__warn_about_errors(tool, &evlist->stats);
 
 	if (mt_tools) {
-		for (i = 1; i < nr_index; i++)
+		for (i = 0; i < nr_index; i++)
 			free(mt_tools[i].hists);
 		free(mt_tools);
 	}
@@ -1649,7 +1681,7 @@ int perf_session__process_events_mt(struct perf_session *session,
 	return err;
 
 err:
-	while (i-- > 1) {
+	while (i-- > 0) {
 		pthread_cancel(th_id[i]);
 		pthread_join(th_id[i], NULL);
 	}
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index aa7f110b9425..e52c936d1b9e 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -55,7 +55,6 @@ struct perf_tool_mt {
 	struct perf_session	*session;
 	struct ui_progress	prog;
 	struct ui_progress	*global_prog;
-	int			idx;
 
 	void			*priv;
 };
-- 
2.2.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/