midx: write object id fanout chunk

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/technical/pack-format.txt

@@ -302,6 +302,11 @@ CHUNK DATA:
 	    name. This is the only chunk not guaranteed to be a multiple of four
 	    bytes in length, so should be the last chunk for alignment reasons.
 
+	OID Fanout (ID: {'O', 'I', 'D', 'F'})
+	    The ith entry, F[i], stores the number of OIDs with first
+	    byte at most i. Thus F[255] stores the total
+	    number of objects.
+
 	OID Lookup (ID: {'O', 'I', 'D', 'L'})
 	    The OIDs for all objects in the MIDX are stored in lexicographic
 	    order in this chunk.

midx.c

@@ -18,11 +18,13 @@
 #define MIDX_HASH_LEN 20
 #define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + MIDX_HASH_LEN)
 
-#define MIDX_MAX_CHUNKS 2
+#define MIDX_MAX_CHUNKS 3
 #define MIDX_CHUNK_ALIGNMENT 4
 #define MIDX_CHUNKID_PACKNAMES 0x504e414d /* "PNAM" */
+#define MIDX_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define MIDX_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define MIDX_CHUNKLOOKUP_WIDTH (sizeof(uint32_t) + sizeof(uint64_t))
+#define MIDX_CHUNK_FANOUT_SIZE (sizeof(uint32_t) * 256)
 
 static char *get_midx_filename(const char *object_dir)
 {
@@ -102,6 +104,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir)
 				m->chunk_pack_names = m->data + chunk_offset;
 				break;
 
+			case MIDX_CHUNKID_OIDFANOUT:
+				m->chunk_oid_fanout = (uint32_t *)(m->data + chunk_offset);
+				break;
+
 			case MIDX_CHUNKID_OIDLOOKUP:
 				m->chunk_oid_lookup = m->data + chunk_offset;
 				break;
@@ -121,9 +127,13 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir)
 
 	if (!m->chunk_pack_names)
 		die(_("multi-pack-index missing required pack-name chunk"));
+	if (!m->chunk_oid_fanout)
+		die(_("multi-pack-index missing required OID fanout chunk"));
 	if (!m->chunk_oid_lookup)
 		die(_("multi-pack-index missing required OID lookup chunk"));
 
+	m->num_objects = ntohl(m->chunk_oid_fanout[255]);
+
 	m->pack_names = xcalloc(m->num_packs, sizeof(*m->pack_names));
 
 	cur_pack_name = (const char *)m->chunk_pack_names;
@@ -389,6 +399,35 @@ static size_t write_midx_pack_names(struct hashfile *f,
 	return written;
 }
 
+static size_t write_midx_oid_fanout(struct hashfile *f,
+				    struct pack_midx_entry *objects,
+				    uint32_t nr_objects)
+{
+	struct pack_midx_entry *list = objects;
+	struct pack_midx_entry *last = objects + nr_objects;
+	uint32_t count = 0;
+	uint32_t i;
+
+	/*
+	* Write the first-level table (the list is sorted,
+	* but we use a 256-entry lookup to be able to avoid
+	* having to do eight extra binary search iterations).
+	*/
+	for (i = 0; i < 256; i++) {
+		struct pack_midx_entry *next = list;
+
+		while (next < last && next->oid.hash[0] == i) {
+			count++;
+			next++;
+		}
+
+		hashwrite_be32(f, count);
+		list = next;
+	}
+
+	return MIDX_CHUNK_FANOUT_SIZE;
+}
+
 static size_t write_midx_oid_lookup(struct hashfile *f, unsigned char hash_len,
 				    struct pack_midx_entry *objects,
 				    uint32_t nr_objects)
@@ -461,7 +500,7 @@ int write_midx_file(const char *object_dir)
 	FREE_AND_NULL(midx_name);
 
 	cur_chunk = 0;
-	num_chunks = 2;
+	num_chunks = 3;
 
 	written = write_midx_header(f, num_chunks, packs.nr);
 
@@ -469,9 +508,13 @@ int write_midx_file(const char *object_dir)
 	chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
 
 	cur_chunk++;
-	chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDLOOKUP;
+	chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDFANOUT;
 	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + packs.pack_name_concat_len;
 
+	cur_chunk++;
+	chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDLOOKUP;
+	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + MIDX_CHUNK_FANOUT_SIZE;
+
 	cur_chunk++;
 	chunk_ids[cur_chunk] = 0;
 	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_HASH_LEN;
@@ -505,6 +548,10 @@ int write_midx_file(const char *object_dir)
 				written += write_midx_pack_names(f, packs.names, packs.nr);
 				break;
 
+			case MIDX_CHUNKID_OIDFANOUT:
+				written += write_midx_oid_fanout(f, entries, nr_entries);
+				break;
+
 			case MIDX_CHUNKID_OIDLOOKUP:
 				written += write_midx_oid_lookup(f, MIDX_HASH_LEN, entries, nr_entries);
 				break;

midx.h

@@ -15,6 +15,7 @@ struct multi_pack_index {
 	uint32_t num_objects;
 
 	const unsigned char *chunk_pack_names;
+	const uint32_t *chunk_oid_fanout;
 	const unsigned char *chunk_oid_lookup;
 
 	const char **pack_names;

t/helper/test-read-midx.c

@@ -22,10 +22,12 @@ static int read_midx_file(const char *object_dir)
 
 	if (m->chunk_pack_names)
 		printf(" pack-names");
+	if (m->chunk_oid_fanout)
+		printf(" oid-fanout");
 	if (m->chunk_oid_lookup)
 		printf(" oid-lookup");
 
-	printf("\n");
+	printf("\nnum_objects: %d\n", m->num_objects);
 
 	printf("packs:\n");
 	for (i = 0; i < m->num_packs; i++)

t/t5319-multi-pack-index.sh

@@ -5,10 +5,12 @@ test_description='multi-pack-indexes'
 
 midx_read_expect () {
 	NUM_PACKS=$1
+	NUM_OBJECTS=$2
 	{
 		cat <<-EOF &&
-		header: 4d494458 1 2 $NUM_PACKS
-		chunks: pack-names oid-lookup
+		header: 4d494458 1 3 $NUM_PACKS
+		chunks: pack-names oid-fanout oid-lookup
+		num_objects: $NUM_OBJECTS
 		packs:
 		EOF
 		if test $NUM_PACKS -ge 1
@@ -24,7 +26,7 @@ midx_read_expect () {
 test_expect_success 'write midx with no packs' '
 	test_when_finished rm -f pack/multi-pack-index &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect 0
+	midx_read_expect 0 0
 '
 
 generate_objects () {
@@ -74,13 +76,13 @@ test_expect_success 'write midx with one v1 pack' '
 	pack=$(git pack-objects --index-version=1 pack/test <obj-list) &&
 	test_when_finished rm pack/test-$pack.pack pack/test-$pack.idx pack/multi-pack-index &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect 1
+	midx_read_expect 1 18
 '
 
 test_expect_success 'write midx with one v2 pack' '
 	git pack-objects --index-version=2,0x40 pack/test <obj-list &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect 1
+	midx_read_expect 1 18
 '
 
 test_expect_success 'add more objects' '
@@ -94,7 +96,7 @@ test_expect_success 'add more objects' '
 test_expect_success 'write midx with two packs' '
 	git pack-objects --index-version=1 pack/test-2 <obj-list &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect 2
+	midx_read_expect 2 34
 '
 
 test_expect_success 'add more packs' '
@@ -108,7 +110,7 @@ test_expect_success 'add more packs' '
 
 test_expect_success 'write midx with twelve packs' '
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect 12
+	midx_read_expect 12 74
 '
 
 test_done