pack-objects: shrink delta_size field in struct object_entry

Allowing a delta size of 64 bits is crazy. Shrink this field down to
20 bits with one overflow bit.

If we find an existing delta larger than 1MB, we do not cache
delta_size at all and will get the value from oe_size(), potentially
from disk if it's larger than 4GB.

Note, since DELTA_SIZE() is used in try_delta() code, it must be
thread-safe. Luckily oe_size() does guarantee this so we it is
thread-safe.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 38 insertions, 11 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index cccd0f8040..88d2bb8153 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -34,10 +34,12 @@
 #define IN_PACK(obj) oe_in_pack(&to_pack, obj)
 #define SIZE(obj) oe_size(&to_pack, obj)
 #define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size)
+#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj)
 #define DELTA(obj) oe_delta(&to_pack, obj)
 #define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj)
 #define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj)
 #define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val)
+#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val)
 #define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val)
 #define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val)
 
@@ -144,7 +146,7 @@ static void *get_delta(struct object_entry *entry)
 		    oid_to_hex(&DELTA(entry)->idx.oid));
 	delta_buf = diff_delta(base_buf, base_size,
 			       buf, size, &delta_size, 0);
-	if (!delta_buf || delta_size != entry->delta_size)
+	if (!delta_buf || delta_size != DELTA_SIZE(entry))
 		die("delta size changed");
 	free(buf);
 	free(base_buf);
@@ -294,14 +296,14 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent
 		FREE_AND_NULL(entry->delta_data);
 		entry->z_delta_size = 0;
 	} else if (entry->delta_data) {
-		size = entry->delta_size;
+		size = DELTA_SIZE(entry);
 		buf = entry->delta_data;
 		entry->delta_data = NULL;
 		type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
 			OBJ_OFS_DELTA : OBJ_REF_DELTA;
 	} else {
 		buf = get_delta(entry);
-		size = entry->delta_size;
+		size = DELTA_SIZE(entry);
 		type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
 			OBJ_OFS_DELTA : OBJ_REF_DELTA;
 	}
@@ -1509,7 +1511,7 @@ static void check_object(struct object_entry *entry)
 			oe_set_type(entry, entry->in_pack_type);
 			SET_SIZE(entry, in_pack_size); /* delta size */
 			SET_DELTA(entry, base_entry);
-			entry->delta_size = in_pack_size;
+			SET_DELTA_SIZE(entry, in_pack_size);
 			entry->delta_sibling_idx = base_entry->delta_child_idx;
 			SET_DELTA_CHILD(base_entry, entry);
 			unuse_pack(&w_curs);
@@ -1937,7 +1939,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		max_size = trg_size/2 - 20;
 		ref_depth = 1;
 	} else {
-		max_size = trg_entry->delta_size;
+		max_size = DELTA_SIZE(trg_entry);
 		ref_depth = trg->depth;
 	}
 	max_size = (uint64_t)max_size * (max_depth - src->depth) /
@@ -2006,10 +2008,14 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
 	if (!delta_buf)
 		return 0;
+	if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
+		free(delta_buf);
+		return 0;
+	}
 
 	if (DELTA(trg_entry)) {
 		/* Prefer only shallower same-sized deltas. */
-		if (delta_size == trg_entry->delta_size &&
+		if (delta_size == DELTA_SIZE(trg_entry) &&
 		    src->depth + 1 >= trg->depth) {
 			free(delta_buf);
 			return 0;
@@ -2024,7 +2030,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	free(trg_entry->delta_data);
 	cache_lock();
 	if (trg_entry->delta_data) {
-		delta_cache_size -= trg_entry->delta_size;
+		delta_cache_size -= DELTA_SIZE(trg_entry);
 		trg_entry->delta_data = NULL;
 	}
 	if (delta_cacheable(src_size, trg_size, delta_size)) {
@@ -2037,7 +2043,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	}
 
 	SET_DELTA(trg_entry, src_entry);
-	trg_entry->delta_size = delta_size;
+	SET_DELTA_SIZE(trg_entry, delta_size);
 	trg->depth = src->depth + 1;
 
 	return 1;
@@ -2160,11 +2166,11 @@ static void find_deltas(struct object_entry **list, unsigned *list_size,
 		if (entry->delta_data && !pack_to_stdout) {
 			unsigned long size;
 
-			size = do_compress(&entry->delta_data, entry->delta_size);
+			size = do_compress(&entry->delta_data, DELTA_SIZE(entry));
 			if (size < (1U << OE_Z_DELTA_BITS)) {
 				entry->z_delta_size = size;
 				cache_lock();
-				delta_cache_size -= entry->delta_size;
+				delta_cache_size -= DELTA_SIZE(entry);
 				delta_cache_size += entry->z_delta_size;
 				cache_unlock();
 			} else {
diff --git a/pack-objects.h b/pack-objects.h
index ee2c7ab382..1c588184b2 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -12,6 +12,7 @@
  * above this limit. Don't lower it too much.
  */
 #define OE_SIZE_BITS		31
+#define OE_DELTA_SIZE_BITS	20
 
 /*
  * State flags for depth-first search used for analyzing delta cycles.
@@ -85,7 +86,8 @@ struct object_entry {
 				     * uses the same base as me
 				     */
 	void *delta_data;	/* cached delta (uncompressed) */
-	unsigned long delta_size;	/* delta data size (uncompressed) */
+	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
+	unsigned delta_size_valid:1;
 	unsigned z_delta_size:OE_Z_DELTA_BITS;
 	unsigned type_:TYPE_BITS;
 	unsigned in_pack_type:TYPE_BITS; /* could be delta */
@@ -309,4 +311,23 @@ static inline void oe_set_size(struct packing_data *pack,
 	}
 }
 
+static inline unsigned long oe_delta_size(struct packing_data *pack,
+					  const struct object_entry *e)
+{
+	if (e->delta_size_valid)
+		return e->delta_size_;
+	return oe_size(pack, e);
+}
+
+static inline void oe_set_delta_size(struct packing_data *pack,
+				     struct object_entry *e,
+				     unsigned long size)
+{
+	e->delta_size_ = size;
+	e->delta_size_valid = e->delta_size_ == size;
+	if (!e->delta_size_valid && size != oe_size(pack, e))
+		BUG("this can only happen in check_object() "
+		    "where delta size is the same as entry size");
+}
+
 #endif