Create object subdirectories on demand

This makes it possible to have a "sparse" git object subdirectory
structure, something that has become much more attractive now that people
use pack-files all the time.

As a result of pack-files, a git object directory doesn't necessarily have
any individual objects lying around, and in that case it's just wasting
space to keep the empty first-level object directories around: on many
filesystems the 256 empty directories will be aboue 1MB of diskspace.

Even more importantly, after you re-pack a project that _used_ to be
unpacked, you could be left with huge directories that no longer contain
anything, but that waste space and take time to look through.

With this change, "git prune-packed" can just do an rmdir() on the
directories, and they'll get removed if empty, and re-created on demand.

This patch also tries to fix up "write_sha1_from_fd()" to use the new
common infrastructure for creating the object files, closing a hole where
we might otherwise leave half-written objects in the object database.

[jc: I unoptimized the part that really removes the fan-out directories
 to ease transition.  init-db still wastes 1MB of diskspace to hold 256
 empty fan-outs, and prune-packed rmdir()'s the grown but empty directories,
 but runs mkdir() immediately after that -- reducing the saving from 150KB
 to 146KB.  These parts will be re-introduced when everybody has the
 on-demand capability.]

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

daemon.c

@@ -142,7 +142,7 @@ static int upload(char *dir, int dirlen)
 	 * is ok with us doing this.
 	 */
 	if ((!export_all_trees && access("git-daemon-export-ok", F_OK)) ||
-	    access("objects/00", X_OK) ||
+	    access("objects/", X_OK) ||
 	    access("HEAD", R_OK)) {
 		logerror("Not a valid git-daemon-enabled repository: '%s'", dir);
 		return -1;

fsck-objects.c

@@ -329,9 +329,8 @@ static int fsck_dir(int i, char *path)
 	DIR *dir = opendir(path);
 	struct dirent *de;
 
-	if (!dir) {
-		return error("missing sha1 directory '%s'", path);
-	}
+	if (!dir)
+		return 0;
 
 	while ((de = readdir(dir)) != NULL) {
 		char name[100];

git-rename.perl

@@ -15,7 +15,7 @@
 my $GIT_DIR = $ENV{'GIT_DIR'} || ".git";
 
 unless ( -d $GIT_DIR && -d $GIT_DIR . "/objects" && 
-	-d $GIT_DIR . "/objects/00" && -d $GIT_DIR . "/refs") {
+	-d $GIT_DIR . "/objects/" && -d $GIT_DIR . "/refs") {
 	usage("Git repository not found.");
 }
 

git-sh-setup.sh

@@ -22,4 +22,4 @@ refs/*)	: ;;
 *)	false ;;
 esac &&
 [ -d "$GIT_DIR/refs" ] &&
-[ -d "$GIT_OBJECT_DIRECTORY/00" ]
+[ -d "$GIT_OBJECT_DIRECTORY/" ]

prune-packed.c

@@ -26,6 +26,9 @@ static void prune_dir(int i, DIR *dir, char *pathname, int len)
 		else if (unlink(pathname) < 0)
 			error("unable to unlink %s", pathname);
 	}
+	pathname[len] = 0;
+	if (rmdir(pathname))
+		mkdir(pathname, 0777);
 }
 
 static void prune_packed_objects(void)
@@ -46,7 +49,7 @@ static void prune_packed_objects(void)
 		sprintf(pathname + len, "%02x/", i);
 		d = opendir(pathname);
 		if (!d)
-			die("unable to open %s", pathname);
+			continue;
 		prune_dir(i, d, pathname, len + 3);
 		closedir(d);
 	}

sha1_file.c

@@ -1248,6 +1248,73 @@ char *write_sha1_file_prepare(void *buf,
 	return sha1_file_name(sha1);
 }
 
+/*
+ * Link the tempfile to the final place, possibly creating the
+ * last directory level as you do so.
+ *
+ * Returns the errno on failure, 0 on success.
+ */
+static int link_temp_to_file(const char *tmpfile, char *filename)
+{
+	int ret;
+
+	if (!link(tmpfile, filename))
+		return 0;
+
+	/*
+	 * Try to mkdir the last path component if that failed
+	 * with an ENOENT.
+	 *
+	 * Re-try the "link()" regardless of whether the mkdir
+	 * succeeds, since a race might mean that somebody
+	 * else succeeded.
+	 */
+	ret = errno;
+	if (ret == ENOENT) {
+		char *dir = strrchr(filename, '/');
+		if (dir) {
+			*dir = 0;
+			mkdir(filename, 0777);
+			*dir = '/';
+			if (!link(tmpfile, filename))
+				return 0;
+			ret = errno;
+		}
+	}
+	return ret;
+}
+
+/*
+ * Move the just written object into its final resting place
+ */
+static int move_temp_to_file(const char *tmpfile, char *filename)
+{
+	int ret = link_temp_to_file(tmpfile, filename);
+	if (ret) {
+		/*
+		 * Coda hack - coda doesn't like cross-directory links,
+		 * so we fall back to a rename, which will mean that it
+		 * won't be able to check collisions, but that's not a
+		 * big deal.
+		 *
+		 * When this succeeds, we just return 0. We have nothing
+		 * left to unlink.
+		 */
+		if (ret == EXDEV && !rename(tmpfile, filename))
+			return 0;
+	}
+	unlink(tmpfile);
+	if (ret) {
+		if (ret != EEXIST) {
+			fprintf(stderr, "unable to write sha1 filename %s: %s", filename, strerror(ret));
+			return -1;
+		}
+		/* FIXME!!! Collision check here ? */
+	}
+
+	return 0;
+}
+
 int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
 {
 	int size;
@@ -1257,7 +1324,7 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	char *filename;
 	static char tmpfile[PATH_MAX];
 	unsigned char hdr[50];
-	int fd, hdrlen, ret;
+	int fd, hdrlen;
 
 	/* Normally if we have it in the pack then we do not bother writing
 	 * it out into .git/objects/??/?{38} file.
@@ -1320,32 +1387,7 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	close(fd);
 	free(compressed);
 
-	ret = link(tmpfile, filename);
-	if (ret < 0) {
-		ret = errno;
-
-		/*
-		 * Coda hack - coda doesn't like cross-directory links,
-		 * so we fall back to a rename, which will mean that it
-		 * won't be able to check collisions, but that's not a
-		 * big deal.
-		 *
-		 * When this succeeds, we just return 0. We have nothing
-		 * left to unlink.
-		 */
-		if (ret == EXDEV && !rename(tmpfile, filename))
-			return 0;
-	}
-	unlink(tmpfile);
-	if (ret) {
-		if (ret != EEXIST) {
-			fprintf(stderr, "unable to write sha1 filename %s: %s", filename, strerror(ret));
-			return -1;
-		}
-		/* FIXME!!! Collision check here ? */
-	}
-
-	return 0;
+	return move_temp_to_file(tmpfile, filename);
 }
 
 int write_sha1_to_fd(int fd, const unsigned char *sha1)
@@ -1420,8 +1462,7 @@ int write_sha1_to_fd(int fd, const unsigned char *sha1)
 int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 		       size_t bufsize, size_t *bufposn)
 {
-	char *filename = sha1_file_name(sha1);
-
+	char tmpfile[PATH_MAX];
 	int local;
 	z_stream stream;
 	unsigned char real_sha1[20];
@@ -1429,10 +1470,11 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 	int ret;
 	SHA_CTX c;
 
-	local = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0666);
+	snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory());
 
+	local = mkstemp(tmpfile);
 	if (local < 0)
-		return error("Couldn't open %s\n", filename);
+		return error("Couldn't open %s for %s\n", tmpfile, sha1_to_hex(sha1));
 
 	memset(&stream, 0, sizeof(stream));
 
@@ -1462,7 +1504,7 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 		size = read(fd, buffer + *bufposn, bufsize - *bufposn);
 		if (size <= 0) {
 			close(local);
-			unlink(filename);
+			unlink(tmpfile);
 			if (!size)
 				return error("Connection closed?");
 			perror("Reading from connection");
@@ -1475,15 +1517,15 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 	close(local);
 	SHA1_Final(real_sha1, &c);
 	if (ret != Z_STREAM_END) {
-		unlink(filename);
+		unlink(tmpfile);
 		return error("File %s corrupted", sha1_to_hex(sha1));
 	}
 	if (memcmp(sha1, real_sha1, 20)) {
-		unlink(filename);
+		unlink(tmpfile);
 		return error("File %s has bad hash\n", sha1_to_hex(sha1));
 	}
-	
-	return 0;
+
+	return move_temp_to_file(tmpfile, sha1_file_name(sha1));
 }
 
 int has_pack_index(const unsigned char *sha1)

t/t0000-basic.sh

@@ -28,7 +28,7 @@ test_expect_success \
     '.git/objects should be empty after git-init-db in an empty repo.' \
     'cmp -s /dev/null should-be-empty' 
 
-# also it should have 258 subdirectories; 256 fan-out, pack, and info.
+# also it should have 258 subdirectories; 256 fan-out anymore, pack, and info.
 # 259 is counting "objects" itself
 find .git/objects -type d -print >full-of-directories
 test_expect_success \