From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
"Nicolas Pitre" <nico@fluxnic.net>,
"Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH] pack-objects: use streaming interface for reading large loose blobs
Date: Sat, 26 May 2012 17:28:01 +0700 [thread overview]
Message-ID: <1338028081-22638-1-git-send-email-pclouds@gmail.com> (raw)
git usually streams large blobs directly to packs. But there are cases
where git can create large loose blobs (unpack-objects or hash-object
over pipe). Or they can come from other git implementations.
core.bigfilethreshold can also be lowered down and introduce a new
wave of large loose blobs.
Use streaming interface to read/compress/write these blobs in one
go. Fall back to normal way if somehow streaming interface cannot be
used.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
On top of ng/pack-objects-cleanup. Changes since the last version is
we do not rely on close_istream(NULL); any more.
builtin/pack-objects.c | 73 +++++++++++++++++++++++++++++++++++++++++++++-----
t/t1050-large.sh | 12 +++++++++
2 files changed, 79 insertions(+), 6 deletions(-)
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index ccfcbad..f334820 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -16,6 +16,7 @@
#include "list-objects.h"
#include "progress.h"
#include "refs.h"
+#include "streaming.h"
#include "thread-utils.h"
static const char *pack_usage[] = {
@@ -150,6 +151,46 @@ static unsigned long do_compress(void **pptr, unsigned long size)
return stream.total_out;
}
+static unsigned long write_large_blob_data(struct git_istream *st, struct sha1file *f,
+ const unsigned char *sha1)
+{
+ git_zstream stream;
+ unsigned char ibuf[1024 * 16];
+ unsigned char obuf[1024 * 16];
+ unsigned long olen = 0;
+
+ memset(&stream, 0, sizeof(stream));
+ git_deflate_init(&stream, pack_compression_level);
+
+ for (;;) {
+ ssize_t readlen;
+ int zret = Z_OK;
+ readlen = read_istream(st, ibuf, sizeof(ibuf));
+ if (readlen == -1)
+ die(_("unable to read %s"), sha1_to_hex(sha1));
+
+ stream.next_in = ibuf;
+ stream.avail_in = readlen;
+ while ((stream.avail_in || readlen == 0) &&
+ (zret == Z_OK || zret == Z_BUF_ERROR)) {
+ stream.next_out = obuf;
+ stream.avail_out = sizeof(obuf);
+ zret = git_deflate(&stream, readlen ? 0 : Z_FINISH);
+ sha1write(f, obuf, stream.next_out - obuf);
+ olen += stream.next_out - obuf;
+ }
+ if (stream.avail_in)
+ die(_("deflate error (%d)"), zret);
+ if (readlen == 0) {
+ if (zret != Z_STREAM_END)
+ die(_("deflate error (%d)"), zret);
+ break;
+ }
+ }
+ git_deflate_end(&stream);
+ return olen;
+}
+
/*
* we are going to reuse the existing object data as is. make
* sure it is not corrupt.
@@ -208,11 +249,18 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent
unsigned hdrlen;
enum object_type type;
void *buf;
+ struct git_istream *st = NULL;
if (!usable_delta) {
- buf = read_sha1_file(entry->idx.sha1, &type, &size);
- if (!buf)
- die("unable to read %s", sha1_to_hex(entry->idx.sha1));
+ if (entry->type == OBJ_BLOB &&
+ entry->size > big_file_threshold &&
+ (st = open_istream(entry->idx.sha1, &type, &size, NULL)) != NULL)
+ buf = NULL;
+ else {
+ buf = read_sha1_file(entry->idx.sha1, &type, &size);
+ if (!buf)
+ die(_("unable to read %s"), sha1_to_hex(entry->idx.sha1));
+ }
/*
* make sure no cached delta data remains from a
* previous attempt before a pack split occurred.
@@ -233,7 +281,9 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent
OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
- if (entry->z_delta_size)
+ if (st) /* large blob case, just assume we don't compress well */
+ datalen = size;
+ else if (entry->z_delta_size)
datalen = entry->z_delta_size;
else
datalen = do_compress(&buf, size);
@@ -256,6 +306,8 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ if (st)
+ close_istream(st);
free(buf);
return 0;
}
@@ -268,6 +320,8 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent
* an additional 20 bytes for the base sha1.
*/
if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ if (st)
+ close_istream(st);
free(buf);
return 0;
}
@@ -276,13 +330,20 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent
hdrlen += 20;
} else {
if (limit && hdrlen + datalen + 20 >= limit) {
+ if (st)
+ close_istream(st);
free(buf);
return 0;
}
sha1write(f, header, hdrlen);
}
- sha1write(f, buf, datalen);
- free(buf);
+ if (st) {
+ datalen = write_large_blob_data(st, f, entry->idx.sha1);
+ close_istream(st);
+ } else {
+ sha1write(f, buf, datalen);
+ free(buf);
+ }
return hdrlen + datalen;
}
diff --git a/t/t1050-large.sh b/t/t1050-large.sh
index 55ed955..313889b 100755
--- a/t/t1050-large.sh
+++ b/t/t1050-large.sh
@@ -134,6 +134,18 @@ test_expect_success 'repack' '
git repack -ad
'
+test_expect_success 'pack-objects with large loose object' '
+ SHA1=`git hash-object huge` &&
+ test_create_repo loose &&
+ echo $SHA1 | git pack-objects --stdout |
+ GIT_ALLOC_LIMIT=0 GIT_DIR=loose/.git git unpack-objects &&
+ echo $SHA1 | GIT_DIR=loose/.git git pack-objects pack &&
+ test_create_repo packed &&
+ mv pack-* packed/.git/objects/pack &&
+ GIT_DIR=packed/.git git cat-file blob $SHA1 >actual &&
+ cmp huge actual
+'
+
test_expect_success 'tar achiving' '
git archive --format=tar HEAD >/dev/null
'
--
1.7.10.2.549.g9354186
next reply other threads:[~2012-05-26 10:32 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-26 10:28 Nguyễn Thái Ngọc Duy [this message]
2012-05-29 17:56 ` [PATCH] pack-objects: use streaming interface for reading large loose blobs Junio C Hamano
-- strict thread matches above, loose matches on Subject: below --
2012-05-12 10:26 Nguyễn Thái Ngọc Duy
2012-05-12 16:51 ` Nicolas Pitre
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=1338028081-22638-1-git-send-email-pclouds@gmail.com \
--to=pclouds@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=nico@fluxnic.net \
/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).