From: "ZheNing Hu via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
"Christian Couder" <christian.couder@gmail.com>,
"Hariom Verma" <hariom18599@gmail.com>,
"Bagas Sanjaya" <bagasdotme@gmail.com>,
"Jeff King" <peff@peff.net>,
"Ævar Arnfjörð Bjarmason" <avarab@gmail.com>,
"Eric Sunshine" <sunshine@sunshineco.com>,
"Philip Oakley" <philipoakley@iee.email>,
"ZheNing Hu" <adlternative@gmail.com>,
"ZheNing Hu" <adlternative@gmail.com>
Subject: [PATCH v2 17/17] [GSOC] cat-file: use fast path when using default_format
Date: Thu, 15 Jul 2021 15:40:25 +0000 [thread overview]
Message-ID: <5903d02324f3275b3aa442bb3ca2602564c543dc.1626363626.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.993.v2.git.1626363626.gitgitgadget@gmail.com>
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 --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;
--
gitgitgadget
prev parent reply other threads:[~2021-07-15 15:40 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-12 11:46 [PATCH 00/19] [GSOC] cat-file: reuse ref-filter logic ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 01/19] cat-file: handle trivial --batch format with --batch-all-objects ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 02/19] cat-file: merge two block into one ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 03/19] [GSOC] ref-filter: add obj-type check in grab contents ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 04/19] [GSOC] ref-filter: add %(raw) atom ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 05/19] [GSOC] ref-filter: --format=%(raw) re-support --perl ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 06/19] [GSOC] ref-filter: use non-const ref_format in *_atom_parser() ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 07/19] [GSOC] ref-filter: add %(rest) atom ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 08/19] [GSOC] ref-filter: pass get_object() return value to their callers ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 09/19] [GSOC] ref-filter: introduce free_ref_array_item_value() function ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 10/19] [GSOC] ref-filter: introduce reject_atom() ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 11/19] [GSOC] ref-filter: modify the error message and value in get_object ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 12/19] [GSOC] cat-file: add has_object_file() check ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 13/19] [GSOC] cat-file: change batch_objects parameter name ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 14/19] [GSOC] cat-file: reuse ref-filter logic ZheNing Hu via GitGitGadget
2021-07-12 13:17 ` Christian Couder
2021-07-12 13:26 ` Christian Couder
2021-07-12 13:51 ` ZheNing Hu
2021-07-12 13:49 ` ZheNing Hu
2021-07-12 20:38 ` Junio C Hamano
2021-07-14 16:24 ` ZheNing Hu
2021-07-15 1:53 ` ZheNing Hu
2021-07-15 9:45 ` Christian Couder
2021-07-15 13:53 ` ZheNing Hu
2021-07-15 14:55 ` ZheNing Hu
2021-07-12 11:46 ` [PATCH 15/19] [GSOC] cat-file: reuse err buf in batch_object_write() ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 16/19] [GSOC] cat-file: re-implement --textconv, --filters options ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 17/19] [GSOC] ref-filter: remove grab_oid() function ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 18/19] [GSOC] cat-file: create p1006-cat-file.sh ZheNing Hu via GitGitGadget
2021-07-12 11:46 ` [PATCH 19/19] [GSOC] cat-file: use fast path when using default_format ZheNing Hu via GitGitGadget
2021-07-12 12:36 ` [PATCH 00/19] [GSOC] cat-file: reuse ref-filter logic Christian Couder
2021-07-12 13:01 ` ZheNing Hu
2021-07-12 13:02 ` Philip Oakley
2021-07-12 13:27 ` ZheNing Hu
2021-07-15 15:40 ` [PATCH v2 00/17] " ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 01/17] [GSOC] ref-filter: add obj-type check in grab contents ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 02/17] [GSOC] ref-filter: add %(raw) atom ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 03/17] [GSOC] ref-filter: --format=%(raw) re-support --perl ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 04/17] [GSOC] ref-filter: use non-const ref_format in *_atom_parser() ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 05/17] [GSOC] ref-filter: add %(rest) atom ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 06/17] [GSOC] ref-filter: pass get_object() return value to their callers ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 07/17] [GSOC] ref-filter: introduce free_ref_array_item_value() function ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 08/17] [GSOC] ref-filter: add cat_file_mode to ref_format ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 09/17] [GSOC] ref-filter: modify the error message and value in get_object ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 10/17] [GSOC] cat-file: add has_object_file() check ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 11/17] [GSOC] cat-file: change batch_objects parameter name ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 12/17] [GSOC] cat-file: create p1006-cat-file.sh ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 13/17] [GSOC] cat-file: reuse ref-filter logic ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 14/17] [GSOC] cat-file: reuse err buf in batch_object_write() ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 15/17] [GSOC] cat-file: re-implement --textconv, --filters options ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` [PATCH v2 16/17] [GSOC] ref-filter: remove grab_oid() function ZheNing Hu via GitGitGadget
2021-07-15 15:40 ` ZheNing Hu via GitGitGadget [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5903d02324f3275b3aa442bb3ca2602564c543dc.1626363626.git.gitgitgadget@gmail.com \
--to=gitgitgadget@gmail.com \
--cc=adlternative@gmail.com \
--cc=avarab@gmail.com \
--cc=bagasdotme@gmail.com \
--cc=christian.couder@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=hariom18599@gmail.com \
--cc=peff@peff.net \
--cc=philipoakley@iee.email \
--cc=sunshine@sunshineco.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).