[PATCH] cat-file: skip expanding default format

From

John Cai via GitGitGadget <gitgitgadget@gmail.com>

Date

Mar 4, 2022, 21:37 UTC

Message-ID

<pull.1221.git.git.1646429845306.gitgitgadget@gmail.com>

From: John Cai <johncai86@gmail.com>

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

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

with HEAD^:

with HEAD:

Based-on-patch-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: John Cai <johncai86@gmail.com>

See https://lore.kernel.org/git/87eecf8ork.fsf@evledraar.gmail.com/
---
    optimize cat file batch info writing
    
    When cat-file --batch or --batch-check is used, we can skip having to
    expand the format if no format is specified or if the default format is
    specified. In this case we know exactly how to print the objects without
    the full expanded format.
    
    This was first discussed in [1].
    
    We get a little performance boost from this optimization because this
    happens for each objects provided to --batch, --batch-check, or
    --batch-command. Because batch_object_write() is called on every oid
    provided in batch mode, this optimization adds up when a large number of
    oid info is printed.
    
    git rev-list --all >/tmp/all-objs.txt
    
    git cat-file --batch-check </tmp/all-obj.txt (with hyperfine)
    
    run on origin/master:
    
    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
    
    run on jc/optimize-cat-file-batch-default-format:
    
    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
    
     1. https://lore.kernel.org/git/87eecf8ork.fsf@evledraar.gmail.com/

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-1221%2Fjohn-cai%2Fjc%2Foptimize-cat-file-batch-default-format-v1
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-1221/john-cai/jc/optimize-cat-file-batch-default-format-v1
Pull-Request: https://github.com/git/git/pull/1221

 builtin/cat-file.c       | 39 +++++++++++++++++++++++++++++++++------
 t/perf/p1006-cat-file.sh | 16 ++++++++++++++++
 2 files changed, 49 insertions(+), 6 deletions(-)
 create mode 100755 t/perf/p1006-cat-file.sh

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 7b3f42950ec..6a337941638 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -17,6 +17,7 @@
 #include "object-store.h"
 #include "promisor-remote.h"
 
+static const char *default_format = "%(objectname) %(objecttype) %(objectsize)";
 struct batch_options {
 	int enabled;
 	int follow_symlinks;
@@ -351,6 +352,14 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 	}
 }
 
+static void print_default_format(char *buf, int len, struct expand_data *data)
+{
+	snprintf(buf, len, "%s %s %"PRIuMAX"\n", oid_to_hex(&data->oid),
+		 data->info.type_name->buf,
+		 (uintmax_t)*data->info.sizep);
+
+}
+
 /*
  * 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
@@ -363,6 +372,12 @@ static void batch_object_write(const char *obj_name,
 			       struct packed_git *pack,
 			       off_t offset)
 {
+	const char *fmt;
+
+	struct strbuf type_name = STRBUF_INIT;
+	if (!opt->format)
+		data->info.type_name = &type_name;
+
 	if (!data->skip_object_info) {
 		int ret;
 
@@ -377,12 +392,21 @@ static void batch_object_write(const char *obj_name,
 			printf("%s missing\n",
 			       obj_name ? obj_name : oid_to_hex(&data->oid));
 			fflush(stdout);
-			return;
+			goto cleanup;
 		}
 	}
 
+	if (!opt->format && !opt->print_contents) {
+		char buf[1024];
+
+		print_default_format(buf, 1024, data);
+		batch_write(opt, buf, strlen(buf));
+		goto cleanup;
+	}
+
+	fmt = opt->format ? opt->format : default_format;
 	strbuf_reset(scratch);
-	strbuf_expand(scratch, opt->format, expand_format, data);
+	strbuf_expand(scratch, fmt, expand_format, data);
 	strbuf_addch(scratch, '\n');
 	batch_write(opt, scratch->buf, scratch->len);
 
@@ -390,8 +414,12 @@ static void batch_object_write(const char *obj_name,
 		print_object_or_die(opt, data);
 		batch_write(opt, "\n", 1);
 	}
+
+cleanup:
+	strbuf_release(&type_name);
 }
 
+
 static void batch_one_object(const char *obj_name,
 			     struct strbuf *scratch,
 			     struct batch_options *opt,
@@ -515,9 +543,7 @@ static int batch_objects(struct batch_options *opt)
 	struct expand_data data;
 	int save_warning;
 	int retval = 0;
-
-	if (!opt->format)
-		opt->format = "%(objectname) %(objecttype) %(objectsize)";
+	const char *fmt;
 
 	/*
 	 * Expand once with our special mark_query flag, which will prime the
@@ -526,7 +552,8 @@ static int batch_objects(struct batch_options *opt)
 	 */
 	memset(&data, 0, sizeof(data));
 	data.mark_query = 1;
-	strbuf_expand(&output, opt->format, expand_format, &data);
+	fmt = opt->format ? opt->format : default_format;
+	strbuf_expand(&output, fmt, expand_format, &data);
 	data.mark_query = 0;
 	strbuf_release(&output);
 	if (opt->cmdmode)
diff --git a/t/perf/p1006-cat-file.sh b/t/perf/p1006-cat-file.sh
new file mode 100755
index 00000000000..e463623f5a3
--- /dev/null
+++ b/t/perf/p1006-cat-file.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+
+test_description='Basic sort performance tests'
+. ./perf-lib.sh
+
+test_perf_large_repo
+
+test_expect_success 'setup' '
+	git rev-list --all >rla
+'
+
+test_perf 'cat-file --batch-check' '
+	git cat-file --batch-check <rla
+'
+
+test_done

base-commit: 715d08a9e51251ad8290b181b6ac3b9e1f9719d7

-- 
gitgitgadget