[PATCH 38/38] perf data: Implement 'index' subcommand

[Namhyung Kim <namhyung@kernel.org>]

The index command first splits a given data file into intermediate
data files and merges them into a final data file with an index table
so that it can processed using multi threads.  The HEADER_DATA_INDEX
feature bit is added to distinguish data file that has an index table.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-data.txt |  25 ++-
 tools/perf/builtin-data.c              | 349 ++++++++++++++++++++++++++++++++-
 2 files changed, 370 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index be8fa1a0a97e..fdac46ea6732 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -22,6 +22,11 @@ COMMANDS
 	like:
 	  perf --debug data-convert data convert ...
 
+index::
+	Build an index table for data file so that it can be processed
+	with multiple threads concurrently.
+
+
 OPTIONS for 'convert'
 ---------------------
 --to-ctf::
@@ -34,7 +39,25 @@ OPTIONS for 'convert'
 --verbose::
         Be more verbose (show counter open errors, etc).
 
+OPTIONS for 'index'
+-------------------
+-i::
+--input::
+	Specify input perf data file path.
+
+-o::
+--output::
+	Specify output perf data directory path.
+
+-v::
+--verbose::
+        Be more verbose (show counter open errors, etc).
+
+-f::
+--force::
+        Don't complain, do it.
+
 SEE ALSO
 --------
-linkperf:perf[1]
+linkperf:perf[1], linkperf:perf-report[1]
 [1] Common Trace Format - http://www.efficios.com/ctf
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 155cf75b8199..8df7321434c0 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -2,11 +2,16 @@
 #include "builtin.h"
 #include "perf.h"
 #include "debug.h"
+#include "session.h"
+#include "evlist.h"
 #include "parse-options.h"
 #include "data-convert-bt.h"
+#include <sys/mman.h>
 
 typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
 
+static const char *output_name;
+
 struct data_cmd {
 	const char	*name;
 	const char	*summary;
@@ -42,6 +47,15 @@ static void print_usage(void)
 	printf("\n");
 }
 
+static int cmd_data_convert(int argc, const char **argv, const char *prefix);
+static int data_cmd_index(int argc, const char **argv, const char *prefix);
+
+static struct data_cmd data_cmds[] = {
+	{ "convert", "converts data file between formats", cmd_data_convert },
+	{ "index", "merge data file and add index", data_cmd_index },
+	{ .name = NULL, },
+};
+
 static const char * const data_convert_usage[] = {
 	"perf data convert [<options>]",
 	NULL
@@ -84,11 +98,340 @@ static int cmd_data_convert(int argc, const char **argv,
 	return 0;
 }
 
-static struct data_cmd data_cmds[] = {
-	{ "convert", "converts data file between formats", cmd_data_convert },
-	{ .name = NULL, },
+#define FD_HASH_BITS  7
+#define FD_HASH_SIZE  (1 << FD_HASH_BITS)
+#define FD_HASH_MASK  (FD_HASH_SIZE - 1)
+
+struct data_index {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	enum {
+		PER_CPU,
+		PER_THREAD,
+	} split_mode;
+	char			*tmpdir;
+	int 			header_fd;
+	u64			header_written;
+	struct hlist_head	fd_hash[FD_HASH_SIZE];
+	int			fd_hash_nr;
+	int			output_fd;
 };
 
+struct fdhash_node {
+	int			id;
+	int			fd;
+	struct hlist_node	list;
+};
+
+static struct hlist_head *get_hash(struct data_index *index, int id)
+{
+	return &index->fd_hash[id % FD_HASH_MASK];
+}
+
+static int perf_event__rewrite_header(struct perf_tool *tool,
+				      union perf_event *event)
+{
+	struct data_index *index = container_of(tool, struct data_index, tool);
+	ssize_t size;
+
+	size = writen(index->header_fd, event, event->header.size);
+	if (size < 0)
+		return -errno;
+
+	index->header_written += size;
+	return 0;
+}
+
+static int split_other_events(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine __maybe_unused)
+{
+	return perf_event__rewrite_header(tool, event);
+}
+
+static int split_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel __maybe_unused,
+				struct machine *machine __maybe_unused)
+{
+	struct data_index *index = container_of(tool, struct data_index, tool);
+	int id = index->split_mode == PER_CPU ? sample->cpu : sample->tid;
+	int fd = -1;
+	char buf[PATH_MAX];
+	struct hlist_head *head;
+	struct fdhash_node *node;
+
+	head = get_hash(index, id);
+	hlist_for_each_entry(node, head, list) {
+		if (node->id == id) {
+			fd = node->fd;
+			break;
+		}
+	}
+
+	if (fd == -1) {
+		scnprintf(buf, sizeof(buf), "%s/perf.data.%d",
+			  index->tmpdir, index->fd_hash_nr++);
+
+		fd = open(buf, O_RDWR|O_CREAT|O_TRUNC, 0600);
+		if (fd < 0) {
+			pr_err("cannot open data file: %s: %m\n", buf);
+			return -1;
+		}
+
+		node = malloc(sizeof(*node));
+		if (node == NULL) {
+			pr_err("memory allocation failed\n");
+			return -1;
+		}
+
+		node->id = id;
+		node->fd = fd;
+
+		hlist_add_head(&node->list, head);
+	}
+
+	return writen(fd, event, event->header.size) > 0 ? 0 : -errno;
+}
+
+static int split_data_file(struct data_index *index)
+{
+	struct perf_session *session = index->session;
+	char buf[PATH_MAX];
+	u64 sample_type;
+	int header_fd;
+
+	if (asprintf(&index->tmpdir, "%s.dir", output_name) < 0) {
+		pr_err("memory allocation failed\n");
+		return -1;
+	}
+
+	if (mkdir(index->tmpdir, 0700) < 0) {
+		pr_err("cannot create intermediate directory\n");
+		return -1;
+	}
+
+	/*
+	 * This is necessary to write (copy) build-id table.  After
+	 * processing header, dsos list will only contain dso which
+	 * was on the original build-id table.
+	 */
+	dsos__hit_all(session);
+
+	scnprintf(buf, sizeof(buf), "%s/perf.header", index->tmpdir);
+	header_fd = open(buf, O_RDWR|O_CREAT|O_TRUNC, 0600);
+	if (header_fd < 0) {
+		pr_err("cannot open header file: %s: %m\n", buf);
+		return -1;
+	}
+
+	lseek(header_fd, session->header.data_offset, SEEK_SET);
+
+	sample_type = perf_evlist__combined_sample_type(session->evlist);
+	if (sample_type & PERF_SAMPLE_CPU)
+		index->split_mode = PER_CPU;
+	else
+		index->split_mode = PER_THREAD;
+
+	pr_debug("splitting data file for %s\n",
+		 index->split_mode == PER_CPU ? "CPUs" : "threads");
+
+	index->header_fd = header_fd;
+	if (perf_session__process_events(session, &index->tool) < 0) {
+		pr_err("failed to process events\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int build_index_table(struct data_index *index)
+{
+	int i, n;
+	u64 offset;
+	u64 nr_index = index->fd_hash_nr + 1;
+	struct perf_file_section *idx;
+	struct perf_session *session = index->session;
+
+	idx = calloc(nr_index, sizeof(*idx));
+	if (idx == NULL)
+		return -1;
+
+	idx[0].offset = session->header.data_offset;
+	idx[0].size   = index->header_written;
+
+	offset = idx[0].offset + idx[0].size;
+
+	for (i = 0, n = 1; i < FD_HASH_SIZE; i++) {
+		struct fdhash_node *node;
+
+		hlist_for_each_entry(node, &index->fd_hash[i], list) {
+			struct stat stbuf;
+
+			if (fstat(node->fd, &stbuf) < 0)
+				goto out;
+
+			idx[n].offset = offset;
+			idx[n].size   = stbuf.st_size;
+			n++;
+
+			offset += stbuf.st_size;
+		}
+	}
+
+	BUG_ON(n != (int)nr_index);
+
+	session->header.index = idx;
+	session->header.nr_index = nr_index;
+	perf_header__set_feat(&session->header, HEADER_DATA_INDEX);
+
+	perf_session__write_header(session, session->evlist,
+				   index->output_fd, true);
+	return 0;
+
+out:
+	free(idx);
+	return -1;
+}
+
+static int cleanup_temp_files(struct data_index *index)
+{
+	int i;
+
+	for (i = 0; i < FD_HASH_SIZE; i++) {
+		struct fdhash_node *pos;
+		struct hlist_node *tmp;
+
+		hlist_for_each_entry_safe(pos, tmp, &index->fd_hash[i], list) {
+			hlist_del(&pos->list);
+			close(pos->fd);
+			free(pos);
+		}
+	}
+	close(index->header_fd);
+
+	rm_rf(index->tmpdir);
+	zfree(&index->tmpdir);
+	return 0;
+}
+
+static int __data_cmd_index(struct data_index *index)
+{
+	struct perf_session *session = index->session;
+	char *output = NULL;
+	int ret = -1;
+	int i, n;
+
+	if (!output_name) {
+		if (asprintf(&output, "%s.out", session->file->path) < 0) {
+			pr_err("memory allocation failed\n");
+			return -1;
+		}
+
+		output_name = output;
+	}
+
+	index->output_fd = open(output_name, O_RDWR|O_CREAT|O_TRUNC, 0600);
+	if (index->output_fd < 0) {
+		pr_err("cannot create output file: %s\n", output_name);
+		goto out;
+	}
+
+	/*
+	 * This is necessary to write (copy) build-id table.  After
+	 * processing header, dsos list will contain dso which was on
+	 * the original build-id table.
+	 */
+	dsos__hit_all(session);
+
+	if (split_data_file(index) < 0)
+		goto out_clean;
+
+	if (build_index_table(index) < 0)
+		goto out_clean;
+
+	/* copy meta-events */
+	if (copyfile_offset(index->header_fd, session->header.data_offset,
+			   index->output_fd, session->header.data_offset,
+			   index->header_written) < 0)
+		goto out_clean;
+
+	/* copy sample events */
+	for (i = 0, n = 1; i < FD_HASH_SIZE; i++) {
+		struct fdhash_node *node;
+
+		hlist_for_each_entry(node, &index->fd_hash[i], list) {
+			if (copyfile_offset(node->fd, 0, index->output_fd,
+					    session->header.index[n].offset,
+					    session->header.index[n].size) < 0)
+				goto out_clean;
+			n++;
+		}
+	}
+	ret = 0;
+
+out_clean:
+	cleanup_temp_files(index);
+	close(index->output_fd);
+out:
+	free(output);
+	return ret;
+}
+
+int data_cmd_index(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	bool force = false;
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.mode  = PERF_DATA_MODE_READ,
+	};
+	struct data_index index = {
+		.tool = {
+			.sample		= split_sample_event,
+			.fork		= split_other_events,
+			.comm		= split_other_events,
+			.exit		= split_other_events,
+			.mmap		= split_other_events,
+			.mmap2		= split_other_events,
+			.lost		= split_other_events,
+			.throttle	= split_other_events,
+			.unthrottle	= split_other_events,
+			.ordered_events = false,
+		},
+	};
+	const char * const index_usage[] = {
+		"perf data index [<options>]",
+		NULL
+	};
+	const struct option index_options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_STRING('o', "output", &output_name, "file", "output directory name"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, index_options, index_usage, 0);
+	if (argc)
+		usage_with_options(index_usage, index_options);
+
+	file.path = input_name;
+	file.force = force;
+	session = perf_session__new(&file, false, &index.tool);
+	if (session == NULL)
+		return -1;
+
+	index.session = session;
+	symbol__init(&session->header.env);
+
+	__data_cmd_index(&index);
+
+	perf_session__delete(session);
+	return 0;
+}
+
 int cmd_data(int argc, const char **argv, const char *prefix)
 {
 	struct data_cmd *cmd;
-- 
2.2.2