cat-file: skip expanding default format

When format is passed into --batch, --batch-check, --batch-command,
the format gets expanded. When nothing is passed in, the default format
is set and the expand_format() gets called.

We can save on these cycles by hardcoding how to print the
information when nothing is passed as the format, or when the default
format is passed. There is no need for the fully expanded format with
the default. Since batch_object_write() happens on every object provided
in batch mode, we get a nice performance improvement.

git rev-list --all > /tmp/all-obj.txt

git cat-file --batch-check </tmp/all-obj.txt

with HEAD^:

Time (mean ± σ): 57.6 ms ± 1.7 ms [User: 51.5 ms, System: 6.2 ms]
Range (min … max): 54.6 ms … 64.7 ms 50 runs

with HEAD:

Time (mean ± σ): 49.8 ms ± 1.7 ms [User: 42.6 ms, System: 7.3 ms]
Range (min … max): 46.9 ms … 55.9 ms 56 runs

If nothing is provided as a format argument, or if the default format is
passed, skip expanding of the format and print the object info with a
default format.

See https://lore.kernel.org/git/[email protected]/

Signed-off-by: Ævar Arnfjörð Bjarmason <[email protected]>
Signed-off-by: John Cai <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: john-cai

builtin/cat-file.c

@@ -351,6 +351,13 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 	}
 }
 
+static void print_default_format(struct strbuf *scratch, struct expand_data *data)
+{
+	strbuf_addf(scratch, "%s %s %"PRIuMAX"\n", oid_to_hex(&data->oid),
+		    type_name(data->type),
+		    (uintmax_t)data->size);
+}
+
 /*
  * If "pack" is non-NULL, then "offset" is the byte offset within the pack from
  * which the object may be accessed (though note that we may also rely on
@@ -382,8 +389,14 @@ static void batch_object_write(const char *obj_name,
 	}
 
 	strbuf_reset(scratch);
-	strbuf_expand(scratch, opt->format, expand_format, data);
-	strbuf_addch(scratch, '\n');
+
+	if (!opt->format) {
+		print_default_format(scratch, data);
+	} else {
+		strbuf_expand(scratch, opt->format, expand_format, data);
+		strbuf_addch(scratch, '\n');
+	}
+
 	batch_write(opt, scratch->buf, scratch->len);
 
 	if (opt->print_contents) {
@@ -508,6 +521,8 @@ static int batch_unordered_packed(const struct object_id *oid,
 				      data);
 }
 
+#define DEFAULT_FORMAT "%(objectname) %(objecttype) %(objectsize)"
+
 static int batch_objects(struct batch_options *opt)
 {
 	struct strbuf input = STRBUF_INIT;
@@ -516,22 +531,24 @@ static int batch_objects(struct batch_options *opt)
 	int save_warning;
 	int retval = 0;
 
-	if (!opt->format)
-		opt->format = "%(objectname) %(objecttype) %(objectsize)";
-
 	/*
 	 * Expand once with our special mark_query flag, which will prime the
 	 * object_info to be handed to oid_object_info_extended for each
 	 * object.
 	 */
 	memset(&data, 0, sizeof(data));
 	data.mark_query = 1;
-	strbuf_expand(&output, opt->format, expand_format, &data);
+	strbuf_expand(&output,
+		      opt->format ? opt->format : DEFAULT_FORMAT,
+		      expand_format,
+		      &data);
 	data.mark_query = 0;
 	strbuf_release(&output);
 	if (opt->cmdmode)
 		data.split_on_whitespace = 1;
 
+	if (opt->format && !strcmp(opt->format, DEFAULT_FORMAT))
+		opt->format = NULL;
 	/*
 	 * If we are printing out the object, then always fill in the type,
 	 * since we will want to decide whether or not to stream.

t/perf/p1006-cat-file.sh

@@ -0,0 +1,12 @@
+#!/bin/sh
+
+test_description='Tests listing object info performance'
+. ./perf-lib.sh
+
+test_perf_large_repo
+
+test_perf 'cat-file --batch-check' '
+	git cat-file --batch-all-objects --batch-check
+'
+
+test_done