Lazily open pack index files on demand

In some repository configurations the user may have many packfiles,
but all of the recent commits/trees/tags/blobs are likely to
be in the most recent packfile (the one with the newest mtime).
It is therefore common to be able to complete an entire operation
by accessing only one packfile, even if there are 25 packfiles
available to the repository.

Rather than opening and mmaping the corresponding .idx file for
every pack found, we now only open and map the .idx when we suspect
there might be an object of interest in there.

Of course we cannot known in advance which packfile contains an
object, so we still need to scan the entire packed_git list to
locate anything.  But odds are users want to access objects in the
most recently created packfiles first, and that may be all they
ever need for the current operation.

Junio observed in b867092f that placing recent packfiles before
older ones can slightly improve access times for recent objects,
without degrading it for historical object access.

This change improves upon Junio's observations by trying even harder
to avoid the .idx files that we won't need.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

1 files changed, 35 insertions, 3 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 12d2ef2011..6a5ba63500 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -530,6 +530,21 @@ static int check_packed_git_idx(const char *path,  struct packed_git *p)
 	return 0;
 }
 
+int open_pack_index (struct packed_git *p)
+{
+	char *idx_name;
+	int ret;
+
+	if (p->index_data)
+		return 0;
+
+	idx_name = xstrdup(p->pack_name);
+	strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx");
+	ret = check_packed_git_idx(idx_name, p);
+	free(idx_name);
+	return ret;
+}
+
 static void scan_windows(struct packed_git *p,
 	struct packed_git **lru_p,
 	struct pack_window **lru_w,
@@ -605,6 +620,9 @@ static int open_packed_git_1(struct packed_git *p)
 	unsigned char *idx_sha1;
 	long fd_flag;
 
+	if (!p->index_data && open_pack_index(p))
+		return error("packfile %s index unavailable", p->pack_name);
+
 	p->pack_fd = open(p->pack_name, O_RDONLY);
 	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
 		return -1;
@@ -757,8 +775,7 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 		return NULL;
 	memcpy(p->pack_name, path, path_len);
 	strcpy(p->pack_name + path_len, ".pack");
-	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode) ||
-	    check_packed_git_idx(path, p)) {
+	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
 		free(p);
 		return NULL;
 	}
@@ -766,6 +783,10 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 	/* ok, it looks sane as far as we can check without
 	 * actually mapping the pack file.
 	 */
+	p->index_version = 0;
+	p->index_data = NULL;
+	p->index_size = 0;
+	p->num_objects = 0;
 	p->pack_size = st.st_size;
 	p->next = NULL;
 	p->windows = NULL;
@@ -1572,10 +1593,15 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
 	return data;
 }
 
-const unsigned char *nth_packed_object_sha1(const struct packed_git *p,
+const unsigned char *nth_packed_object_sha1(struct packed_git *p,
 					    uint32_t n)
 {
 	const unsigned char *index = p->index_data;
+	if (!index) {
+		if (open_pack_index(p))
+			return NULL;
+		index = p->index_data;
+	}
 	if (n >= p->num_objects)
 		return NULL;
 	index += 4 * 256;
@@ -1612,6 +1638,12 @@ off_t find_pack_entry_one(const unsigned char *sha1,
 	const unsigned char *index = p->index_data;
 	unsigned hi, lo;
 
+	if (!index) {
+		if (open_pack_index(p))
+			return 0;
+		level1_ofs = p->index_data;
+		index = p->index_data;
+	}
 	if (p->index_version > 1) {
 		level1_ofs += 2;
 		index += 8;