introduce delta objects with offset to base

This adds a new object, namely OBJ_OFS_DELTA, renames OBJ_DELTA to
OBJ_REF_DELTA to better make the distinction between those two delta
objects, and adds support for the handling of those new delta objects
in sha1_file.c only.

The OBJ_OFS_DELTA contains a relative offset from the delta object's
position in a pack instead of the 20-byte SHA1 reference to identify
the base object.  Since the base is likely to be not so far away, the
relative offset is more likely to have a smaller encoding on average
than an absolute offset.  And for those delta objects the base must
always be stored first because there is no way to know the distance of
later objects when streaming a pack.  Hence this relative offset is
always meant to be negative.

The offset encoding is slightly denser than the one used for object
size -- credits to <linux@horizon.com> (whoever this is) for bringing
it to my attention.

This allows for pack size reduction between 3.2% (Linux-2.6) to over 5%
(linux-historic).  Runtime pack access should be faster too since delta
replay does skip a search in the pack index for each delta in a chain.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

1 files changed, 8 insertions, 8 deletions

diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 96c069a81d..c62734a2a6 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -232,7 +232,7 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha
 	int n = 1;
 	unsigned char c;
 
-	if (type < OBJ_COMMIT || type > OBJ_DELTA)
+	if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
 		die("bad type %d", type);
 
 	c = (type << 4) | (size & 15);
@@ -297,7 +297,7 @@ static int revalidate_pack_entry(struct object_entry *entry, unsigned char *data
 	used = unpack_object_header_gently(data, len, &type, &size);
 	if (!used)
 		return -1;
-	if (type == OBJ_DELTA)
+	if (type == OBJ_REF_DELTA)
 		used += 20; /* skip base object name */
 	data += used;
 	len -= used;
@@ -340,7 +340,7 @@ static unsigned long write_object(struct sha1file *f,
 	obj_type = entry->type;
 	if (! entry->in_pack)
 		to_reuse = 0;	/* can't reuse what we don't have */
-	else if (obj_type == OBJ_DELTA)
+	else if (obj_type == OBJ_REF_DELTA)
 		to_reuse = 1;	/* check_object() decided it for us */
 	else if (obj_type != entry->in_pack_type)
 		to_reuse = 0;	/* pack has delta which is unusable */
@@ -380,7 +380,7 @@ static unsigned long write_object(struct sha1file *f,
 		if (entry->delta) {
 			buf = delta_against(buf, size, entry);
 			size = entry->delta_size;
-			obj_type = OBJ_DELTA;
+			obj_type = OBJ_REF_DELTA;
 		}
 		/*
 		 * The object header is a byte of 'type' followed by zero or
@@ -409,11 +409,11 @@ static unsigned long write_object(struct sha1file *f,
 		sha1write(f, buf, datalen);
 		unuse_packed_git(p);
 		hdrlen = 0; /* not really */
-		if (obj_type == OBJ_DELTA)
+		if (obj_type == OBJ_REF_DELTA)
 			reused_delta++;
 		reused++;
 	}
-	if (obj_type == OBJ_DELTA)
+	if (obj_type == OBJ_REF_DELTA)
 		written_delta++;
 	written++;
 	return hdrlen + datalen;
@@ -916,7 +916,7 @@ static void check_object(struct object_entry *entry)
 		 * delta.
 		 */
 		if (!no_reuse_delta &&
-		    entry->in_pack_type == OBJ_DELTA &&
+		    entry->in_pack_type == OBJ_REF_DELTA &&
 		    (base_entry = locate_object_entry(base)) &&
 		    (!base_entry->preferred_base)) {
 
@@ -929,7 +929,7 @@ static void check_object(struct object_entry *entry)
 			/* uncompressed size of the delta data */
 			entry->size = entry->delta_size = size;
 			entry->delta = base_entry;
-			entry->type = OBJ_DELTA;
+			entry->type = OBJ_REF_DELTA;
 
 			entry->delta_sibling = base_entry->delta_child;
 			base_entry->delta_child = entry;