Bigfile: teach "git add" to send a large file straight to a pack

When adding a new content to the repository, we have always slurped
the blob in its entirety in-core first, and computed the object name
and compressed it into a loose object file.  Handling large binary
files (e.g.  video and audio asset for games) has been problematic
because of this design.

At the middle level of "git add" callchain is an internal API
index_fd() that takes an open file descriptor to read from the
working tree file being added with its size. Teach it to call out to
fast-import when adding a large blob.

The write-out codepath in entry.c::write_entry() should be taught to
stream, instead of reading everything in core. This should not be so
hard to implement, especially if we limit ourselves only to loose
object files and non-delta representation in packfiles.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/sha1_file.c b/sha1_file.c
index 49416b02917ef600d927f8d9398c0a55a3eafc78..f0ca6a1749e2517bf3640f9d9f17e866c4eed47f 100644 (file)
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -11,6 +11,7 @@
 #include "pack.h"
 #include "blob.h"
 #include "commit.h"
+#include "run-command.h"
 #include "tag.h"
 #include "tree.h"
 #include "tree-walk.h"
@@ -2658,6 +2659,85 @@ static int index_core(unsigned char *sha1, int fd, size_t size,
        return ret;
 }
 
+/*
+ * This creates one packfile per large blob, because the caller
+ * immediately wants the result sha1, and fast-import can report the
+ * object name via marks mechanism only by closing the created
+ * packfile.
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above), but the primary
+ * motivation for trying to stream from the working tree file and to
+ * avoid mmaping it in core is to deal with large binary blobs, and
+ * by definition they do _not_ want to get any conversion.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+                       enum object_type type, const char *path,
+                       unsigned flags)
+{
+       struct child_process fast_import;
+       char export_marks[512];
+       const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
+       char tmpfile[512];
+       char fast_import_cmd[512];
+       char buf[512];
+       int len, tmpfd;
+
+       strcpy(tmpfile, git_path("hashstream_XXXXXX"));
+       tmpfd = git_mkstemp_mode(tmpfile, 0600);
+       if (tmpfd < 0)
+               die_errno("cannot create tempfile: %s", tmpfile);
+       if (close(tmpfd))
+               die_errno("cannot close tempfile: %s", tmpfile);
+       sprintf(export_marks, "--export-marks=%s", tmpfile);
+
+       memset(&fast_import, 0, sizeof(fast_import));
+       fast_import.in = -1;
+       fast_import.argv = argv;
+       fast_import.git_cmd = 1;
+       if (start_command(&fast_import))
+               die_errno("index-stream: git fast-import failed");
+
+       len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
+                     (unsigned long) size);
+       write_or_whine(fast_import.in, fast_import_cmd, len,
+                      "index-stream: feeding fast-import");
+       while (size) {
+               char buf[10240];
+               size_t sz = size < sizeof(buf) ? size : sizeof(buf);
+               size_t actual;
+
+               actual = read_in_full(fd, buf, sz);
+               if (actual < 0)
+                       die_errno("index-stream: reading input");
+               if (write_in_full(fast_import.in, buf, actual) != actual)
+                       die_errno("index-stream: feeding fast-import");
+               size -= actual;
+       }
+       if (close(fast_import.in))
+               die_errno("index-stream: closing fast-import");
+       if (finish_command(&fast_import))
+               die_errno("index-stream: finishing fast-import");
+
+       tmpfd = open(tmpfile, O_RDONLY);
+       if (tmpfd < 0)
+               die_errno("index-stream: cannot open fast-import mark");
+       len = read(tmpfd, buf, sizeof(buf));
+       if (len < 0)
+               die_errno("index-stream: reading fast-import mark");
+       if (close(tmpfd) < 0)
+               die_errno("index-stream: closing fast-import mark");
+       if (unlink(tmpfile))
+               die_errno("index-stream: unlinking fast-import mark");
+       if (len != 44 ||
+           memcmp(":1 ", buf, 3) ||
+           get_sha1_hex(buf + 3, sha1))
+               die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
+       return 0;
+}
+
 int index_fd(unsigned char *sha1, int fd, struct stat *st,
             enum object_type type, const char *path, unsigned flags)
 {
@@ -2666,8 +2746,10 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 
        if (!S_ISREG(st->st_mode))
                ret = index_pipe(sha1, fd, type, path, flags);
-       else
+       else if (size <= big_file_threshold || type != OBJ_BLOB)
                ret = index_core(sha1, fd, size, type, path, flags);
+       else
+               ret = index_stream(sha1, fd, size, type, path, flags);
        close(fd);
        return ret;
 }

diff --git a/t/t1050-large.sh b/t/t1050-large.sh
new file mode 100755 (executable)
index 0000000..deba111
--- /dev/null
+++ b/t/t1050-large.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+# Copyright (c) 2011, Google Inc.
+
+test_description='adding and checking out large blobs'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+       git config core.bigfilethreshold 200k &&
+       echo X | dd of=large bs=1k seek=2000
+'
+
+test_expect_success 'add a large file' '
+       git add large &&
+       # make sure we got a packfile and no loose objects
+       test -f .git/objects/pack/pack-*.pack &&
+       test ! -f .git/objects/??/??????????????????????????????????????
+'
+
+test_expect_success 'checkout a large file' '
+       large=$(git rev-parse :large) &&
+       git update-index --add --cacheinfo 100644 $large another &&
+       git checkout another &&
+       cmp large another ;# this must not be test_cmp
+'
+
+test_done