pack-objects: Allow use of pre-generated pack.

git-pack-objects can reuse pack files stored in $GIT_DIR/pack-cache
directory, when a necessary pack is found.  This is hopefully useful
when upload-pack (called from git-daemon) is expected to receive
requests for the same set of objects many times (e.g full cloning
request of any project, or updates from the set of heads previous day
to the latest for a slow moving project).

Currently git-pack-objects does *not* keep pack files it creates for
reusing.  It might be useful to add --update-cache option to it,
which would allow it store pack files it created in the pack-cache
directory, and prune rarely used ones from it.

Signed-off-by: Junio C Hamano <junkio@cox.net>

4 files changed, 112 insertions, 12 deletions

diff --git a/Makefile b/Makefile
index 5b0306d39..701067d43 100644
--- a/Makefile
+++ b/Makefile
@@ -159,7 +159,7 @@ LIB_OBJS = \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
 	quote.o read-cache.o refs.o run-command.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
-	tag.o tree.o usage.o config.o environment.o ctype.o \
+	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	$(DIFF_OBJS)
 
 LIBS = $(LIB_FILE)
diff --git a/cache.h b/cache.h
index d77601682..2e36cc5b8 100644
--- a/cache.h
+++ b/cache.h
@@ -413,4 +413,5 @@ static inline int sane_case(int x, int high)
 	return x;
 }
 
+extern int copy_fd(int ifd, int ofd);
 #endif /* CACHE_H */
diff --git a/copy.c b/copy.c
new file mode 100644
index 000000000..20092757d
--- /dev/null
+++ b/copy.c
@@ -0,0 +1,37 @@
+#include "cache.h"
+
+int copy_fd(int ifd, int ofd)
+{
+	while (1) {
+		int len;
+		char buffer[8192];
+		char *buf = buffer;
+		len = read(ifd, buffer, sizeof(buffer));
+		if (!len)
+			break;
+		if (len < 0) {
+			if (errno == EAGAIN)
+				continue;
+			return error("copy-fd: read returned %s",
+				     strerror(errno));
+		}
+		while (1) {
+			int written = write(ofd, buf, len);
+			if (written > 0) {
+				buf += written;
+				len -= written;
+				if (!len)
+					break;
+			}
+			if (!written)
+				return error("copy-fd: write returned 0");
+			if (errno == EAGAIN || errno == EINTR)
+				continue;
+			return error("copy-fd: write returned %s",
+				     strerror(errno));
+		}
+	}
+	close(ifd);
+	return 0;
+}
+
diff --git a/pack-objects.c b/pack-objects.c
index b3e615203..4e941e739 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -400,6 +400,71 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 	free(array);
 }
 
+static void prepare_pack(int window, int depth)
+{
+	get_object_details();
+
+	fprintf(stderr, "Packing %d objects\n", nr_objects);
+
+	sorted_by_type = create_sorted_list(type_size_sort);
+	if (window && depth)
+		find_deltas(sorted_by_type, window+1, depth);
+	write_pack_file();
+}
+
+static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
+{
+	static const char cache[] = "pack-cache/pack-%s.%s";
+	char *cached_pack, *cached_idx;
+	int ifd, ofd, ifd_ix = -1;
+
+	cached_pack = git_path(cache, sha1_to_hex(sha1), "pack");
+	ifd = open(cached_pack, O_RDONLY);
+	if (ifd < 0)
+		return 0;
+
+	if (!pack_to_stdout) {
+		cached_idx = git_path(cache, sha1_to_hex(sha1), "idx");
+		ifd_ix = open(cached_idx, O_RDONLY);
+		if (ifd_ix < 0) {
+			close(ifd);
+			return 0;
+		}
+	}
+
+	fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+		sha1_to_hex(sha1));
+
+	if (pack_to_stdout) {
+		if (copy_fd(ifd, 1))
+			exit(1);
+		close(ifd);
+	}
+	else {
+		char name[PATH_MAX];
+		snprintf(name, sizeof(name),
+			 "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack");
+		ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
+		if (ofd < 0)
+			die("unable to open %s (%s)", name, strerror(errno));
+		if (copy_fd(ifd, ofd))
+			exit(1);
+		close(ifd);
+
+		snprintf(name, sizeof(name),
+			 "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx");
+		ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
+		if (ofd < 0)
+			die("unable to open %s (%s)", name, strerror(errno));
+		if (copy_fd(ifd_ix, ofd))
+			exit(1);
+		close(ifd_ix);
+		puts(sha1_to_hex(sha1));
+	}
+
+	return 1;
+}
+
 int main(int argc, char **argv)
 {
 	SHA_CTX ctx;
@@ -472,9 +537,6 @@ int main(int argc, char **argv)
 	}
 	if (non_empty && !nr_objects)
 		return 0;
-	get_object_details();
-
-	fprintf(stderr, "Packing %d objects\n", nr_objects);
 
 	sorted_by_sha = create_sorted_list(sha1_sort);
 	SHA1_Init(&ctx);
@@ -485,14 +547,14 @@ int main(int argc, char **argv)
 	}
 	SHA1_Final(object_list_sha1, &ctx);
 
-	sorted_by_type = create_sorted_list(type_size_sort);
-	if (window && depth)
-		find_deltas(sorted_by_type, window+1, depth);
-
-	write_pack_file();
-	if (!pack_to_stdout) {
-		write_index_file();
-		puts(sha1_to_hex(object_list_sha1));
+	if (reuse_cached_pack(object_list_sha1, pack_to_stdout))
+		;
+	else {
+		prepare_pack(window, depth);
+		if (!pack_to_stdout) {
+			write_index_file();
+			puts(sha1_to_hex(object_list_sha1));
+		}
 	}
 	return 0;
 }