diff mbox series

[v2,17/17,GSOC] cat-file: use fast path when using default_format

Message ID 5903d02324f3275b3aa442bb3ca2602564c543dc.1626363626.git.gitgitgadget@gmail.com (mailing list archive)
State Superseded
Headers show
Series cat-file: reuse ref-filter logic | expand

Commit Message

ZheNing Hu July 15, 2021, 3:40 p.m. UTC 
From: ZheNing Hu <adlternative@gmail.com>

Add the member `default_format` to struct `batch_options`,
when we are using the default format on `git cat-file --batch`,
or `git cat-file --batch-check`, `default_format` will be set,
if we don't use `--textconv` or `--filter`, then we will not call
verify_ref_format(), has_object_file() and format_ref_array_item().
Instead, we get the object data directly through
oid_object_info_extended() and then output the data directly.

By using this fast path, we can reduce some of the extra overhead
when `cat-file --batch` using ref-filter. The running time of
`git cat-file --batch-check` will be similar to before, and the
running time of `git cat-file --batch` will be 9.1% less than before.

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Mentored-by: Christian Couder <christian.couder@gmail.com>
Mentored-by: Hariom Verma <hariom18599@gmail.com>
Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 builtin/cat-file.c | 79 +++++++++++++++++++++++++++++++++-------------
 1 file changed, 57 insertions(+), 22 deletions(-)
diff mbox series

Patch

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 3a6153e778f..8edc19f2d5a 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -26,6 +26,7 @@  struct batch_options {
 	int all_objects;
 	int unordered;
 	int cmdmode; /* may be 'w' or 'c' for --filters or --textconv */
+	int default_format;
 	struct ref_format format;
 };
 
@@ -196,6 +197,7 @@  static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 
 struct expand_data {
 	struct object_id oid;
+	struct object_info info;
 	const char *rest;
 	int split_on_whitespace;
 };
@@ -216,27 +218,58 @@  static void batch_object_write(const char *obj_name,
 			       struct batch_options *opt,
 			       struct expand_data *data)
 {
-	int ret;
-	struct ref_array_item item = { data->oid, data->rest, opt->cmdmode };
-
-	strbuf_reset(scratch);
-	strbuf_reset(err);
-
-	ret = format_ref_array_item(&item, &opt->format, scratch, err);
-	if (ret < 0)
-		die("%s\n", err->buf);
-	if (ret) {
-		/* ret > 0 means when the object corresponding to oid
-		 * cannot be found in format_ref_array_item(), we only print
-		 * the error message.
-		 */
-		printf("%s\n", err->buf);
+	if (opt->default_format && !opt->cmdmode) {
+		struct strbuf type_name = STRBUF_INIT;
+		unsigned long size;
+		void *content;
+
+		if (opt->print_contents)
+			data->info.contentp = &content;
+
+		data->info.type_name = &type_name;
+		data->info.sizep = &size;
+
+		if (oid_object_info_extended(the_repository, &data->oid, &data->info,
+					     OBJECT_INFO_LOOKUP_REPLACE) < 0) {
+			printf("%s missing\n",
+			       obj_name ? obj_name : oid_to_hex(&data->oid));
+			fflush(stdout);
+			return;
+		}
+
+		fprintf(stdout, "%s %s %"PRIuMAX"\n", oid_to_hex(&data->oid),
+			data->info.type_name->buf,
+			(uintmax_t)*data->info.sizep);
 		fflush(stdout);
+		strbuf_release(&type_name);
+		if (opt->print_contents) {
+			batch_write(opt, content, *data->info.sizep);
+			batch_write(opt, "\n", 1);
+			free(content);
+		}
 	} else {
-		strbuf_addch(scratch, '\n');
-		batch_write(opt, scratch->buf, scratch->len);
+		int ret;
+		struct ref_array_item item = { data->oid, data->rest, opt->cmdmode };
+
+		strbuf_reset(scratch);
+		strbuf_reset(err);
+
+		ret = format_ref_array_item(&item, &opt->format, scratch, err);
+		if (ret < 0)
+			die("%s\n", err->buf);
+		if (ret) {
+			/* ret > 0 means when the object corresponding to oid
+			 * cannot be found in format_ref_array_item(), we only print
+			 * the error message.
+			 */
+			printf("%s\n", err->buf);
+			fflush(stdout);
+		} else {
+			strbuf_addch(scratch, '\n');
+			batch_write(opt, scratch->buf, scratch->len);
+		}
+		free_ref_array_item_value(&item);
 	}
-	free_ref_array_item_value(&item);
 }
 
 static void batch_one_object(const char *obj_name,
@@ -288,7 +321,7 @@  static void batch_one_object(const char *obj_name,
 		return;
 	}
 
-	if (!has_object_file(&data->oid)) {
+	if ((!opt->default_format || opt->cmdmode) && !has_object_file(&data->oid)) {
 		printf("%s missing\n",
 		       obj_name ? obj_name : oid_to_hex(&data->oid));
 		fflush(stdout);
@@ -380,7 +413,7 @@  static int batch_objects(struct batch_options *batch, const struct option *optio
 	if (batch->print_contents)
 		strbuf_addstr(&format, "\n%(raw)");
 	batch->format.format = format.buf;
-	if (verify_ref_format(&batch->format))
+	if ((!batch->default_format || batch->cmdmode) && verify_ref_format(&batch->format))
 		usage_with_options(cat_file_usage, options);
 
 	if (batch->cmdmode || batch->format.use_rest)
@@ -483,7 +516,8 @@  static int batch_option_callback(const struct option *opt,
 	bo->enabled = 1;
 	bo->print_contents = !strcmp(opt->long_name, "batch");
 	bo->format.format = arg;
-
+	if (arg)
+		bo->default_format = 0;
 	return 0;
 }
 
@@ -492,7 +526,8 @@  int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	int opt = 0;
 	const char *exp_type = NULL, *obj_name = NULL;
 	struct batch_options batch = {
-		.format = REF_FORMAT_INIT
+		.format = REF_FORMAT_INIT,
+		.default_format = 1
 	};
 	int unknown_type = 0;