midx: write object offsets

The final pair of chunks for the multi-pack-index file stores the object
offsets. We default to using 32-bit offsets as in the pack-index version
1 format, but if there exists an offset larger than 32-bits, we use a
trick similar to the pack-index version 2 format by storing all offsets
at least 2^31 in a 64-bit table; we use the 32-bit table to point into
that 64-bit table as necessary.

We only store these 64-bit offsets if necessary, so create a test that
manipulates a version 2 pack-index to fake a large offset. This allows
us to test that the large offset table is created, but the data does not
match the actual packfile offsets. The multi-pack-index offset does match
the (corrupted) pack-index offset, so a future feature will compare these
offsets during a 'verify' step.

Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: derrickstolee

Documentation/technical/pack-format.txt

@@ -311,7 +311,20 @@ CHUNK DATA:
 	    The OIDs for all objects in the MIDX are stored in lexicographic
 	    order in this chunk.
 
-	(This section intentionally left incomplete.)
+	Object Offsets (ID: {'O', 'O', 'F', 'F'})
+	    Stores two 4-byte values for every object.
+	    1: The pack-int-id for the pack storing this object.
+	    2: The offset within the pack.
+		If all offsets are less than 2^31, then the large offset chunk
+		will not exist and offsets are stored as in IDX v1.
+		If there is at least one offset value larger than 2^32-1, then
+		the large offset chunk must exist. If the large offset chunk
+		exists and the 31st bit is on, then removing that bit reveals
+		the row in the large offsets containing the 8-byte offset of
+		this object.
+
+	[Optional] Object Large Offsets (ID: {'L', 'O', 'F', 'F'})
+	    8-byte offsets into large packfiles.
 
 TRAILER:
 

midx.c

@@ -18,13 +18,18 @@
 #define MIDX_HASH_LEN 20
 #define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + MIDX_HASH_LEN)
 
-#define MIDX_MAX_CHUNKS 3
+#define MIDX_MAX_CHUNKS 5
 #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_CHUNKID_OBJECTOFFSETS 0x4f4f4646 /* "OOFF" */
+#define MIDX_CHUNKID_LARGEOFFSETS 0x4c4f4646 /* "LOFF" */
 #define MIDX_CHUNKLOOKUP_WIDTH (sizeof(uint32_t) + sizeof(uint64_t))
 #define MIDX_CHUNK_FANOUT_SIZE (sizeof(uint32_t) * 256)
+#define MIDX_CHUNK_OFFSET_WIDTH (2 * sizeof(uint32_t))
+#define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
+#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
 
 static char *get_midx_filename(const char *object_dir)
 {
@@ -112,6 +117,14 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir)
 				m->chunk_oid_lookup = m->data + chunk_offset;
 				break;
 
+			case MIDX_CHUNKID_OBJECTOFFSETS:
+				m->chunk_object_offsets = m->data + chunk_offset;
+				break;
+
+			case MIDX_CHUNKID_LARGEOFFSETS:
+				m->chunk_large_offsets = m->data + chunk_offset;
+				break;
+
 			case 0:
 				die(_("terminating multi-pack-index chunk id appears earlier than expected"));
 				break;
@@ -131,6 +144,8 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir)
 		die(_("multi-pack-index missing required OID fanout chunk"));
 	if (!m->chunk_oid_lookup)
 		die(_("multi-pack-index missing required OID lookup chunk"));
+	if (!m->chunk_object_offsets)
+		die(_("multi-pack-index missing required object offsets chunk"));
 
 	m->num_objects = ntohl(m->chunk_oid_fanout[255]);
 
@@ -454,6 +469,56 @@ static size_t write_midx_oid_lookup(struct hashfile *f, unsigned char hash_len,
 	return written;
 }
 
+static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_needed,
+					struct pack_midx_entry *objects, uint32_t nr_objects)
+{
+	struct pack_midx_entry *list = objects;
+	uint32_t i, nr_large_offset = 0;
+	size_t written = 0;
+
+	for (i = 0; i < nr_objects; i++) {
+		struct pack_midx_entry *obj = list++;
+
+		hashwrite_be32(f, obj->pack_int_id);
+
+		if (large_offset_needed && obj->offset >> 31)
+			hashwrite_be32(f, MIDX_LARGE_OFFSET_NEEDED | nr_large_offset++);
+		else if (!large_offset_needed && obj->offset >> 32)
+			BUG("object %s requires a large offset (%"PRIx64") but the MIDX is not writing large offsets!",
+			    oid_to_hex(&obj->oid),
+			    obj->offset);
+		else
+			hashwrite_be32(f, (uint32_t)obj->offset);
+
+		written += MIDX_CHUNK_OFFSET_WIDTH;
+	}
+
+	return written;
+}
+
+static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_offset,
+				       struct pack_midx_entry *objects, uint32_t nr_objects)
+{
+	struct pack_midx_entry *list = objects;
+	size_t written = 0;
+
+	while (nr_large_offset) {
+		struct pack_midx_entry *obj = list++;
+		uint64_t offset = obj->offset;
+
+		if (!(offset >> 31))
+			continue;
+
+		hashwrite_be32(f, offset >> 32);
+		hashwrite_be32(f, offset & 0xffffffffUL);
+		written += 2 * sizeof(uint32_t);
+
+		nr_large_offset--;
+	}
+
+	return written;
+}
+
 int write_midx_file(const char *object_dir)
 {
 	unsigned char cur_chunk, num_chunks = 0;
@@ -466,8 +531,9 @@ int write_midx_file(const char *object_dir)
 	uint64_t written = 0;
 	uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
 	uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
-	uint32_t nr_entries;
+	uint32_t nr_entries, num_large_offsets = 0;
 	struct pack_midx_entry *entries = NULL;
+	int large_offsets_needed = 0;
 
 	midx_name = get_midx_filename(object_dir);
 	if (safe_create_leading_directories(midx_name)) {
@@ -494,13 +560,19 @@ int write_midx_file(const char *object_dir)
 	sort_packs_by_name(packs.names, packs.nr, pack_perm);
 
 	entries = get_sorted_entries(packs.list, pack_perm, packs.nr, &nr_entries);
+	for (i = 0; i < nr_entries; i++) {
+		if (entries[i].offset > 0x7fffffff)
+			num_large_offsets++;
+		if (entries[i].offset > 0xffffffff)
+			large_offsets_needed = 1;
+	}
 
 	hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR);
 	f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
 	FREE_AND_NULL(midx_name);
 
 	cur_chunk = 0;
-	num_chunks = 3;
+	num_chunks = large_offsets_needed ? 5 : 4;
 
 	written = write_midx_header(f, num_chunks, packs.nr);
 
@@ -516,9 +588,21 @@ int write_midx_file(const char *object_dir)
 	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + MIDX_CHUNK_FANOUT_SIZE;
 
 	cur_chunk++;
-	chunk_ids[cur_chunk] = 0;
+	chunk_ids[cur_chunk] = MIDX_CHUNKID_OBJECTOFFSETS;
 	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_HASH_LEN;
 
+	cur_chunk++;
+	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_CHUNK_OFFSET_WIDTH;
+	if (large_offsets_needed) {
+		chunk_ids[cur_chunk] = MIDX_CHUNKID_LARGEOFFSETS;
+
+		cur_chunk++;
+		chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] +
+					   num_large_offsets * MIDX_CHUNK_LARGE_OFFSET_WIDTH;
+	}
+
+	chunk_ids[cur_chunk] = 0;
+
 	for (i = 0; i <= num_chunks; i++) {
 		if (i && chunk_offsets[i] < chunk_offsets[i - 1])
 			BUG("incorrect chunk offsets: %"PRIu64" before %"PRIu64,
@@ -556,6 +640,14 @@ int write_midx_file(const char *object_dir)
 				written += write_midx_oid_lookup(f, MIDX_HASH_LEN, entries, nr_entries);
 				break;
 
+			case MIDX_CHUNKID_OBJECTOFFSETS:
+				written += write_midx_object_offsets(f, large_offsets_needed, entries, nr_entries);
+				break;
+
+			case MIDX_CHUNKID_LARGEOFFSETS:
+				written += write_midx_large_offsets(f, num_large_offsets, entries, nr_entries);
+				break;
+
 			default:
 				BUG("trying to write unknown chunk id %"PRIx32,
 				    chunk_ids[i]);

midx.h

@@ -17,6 +17,8 @@ struct multi_pack_index {
 	const unsigned char *chunk_pack_names;
 	const uint32_t *chunk_oid_fanout;
 	const unsigned char *chunk_oid_lookup;
+	const unsigned char *chunk_object_offsets;
+	const unsigned char *chunk_large_offsets;
 
 	const char **pack_names;
 	char object_dir[FLEX_ARRAY];

t/helper/test-read-midx.c

@@ -26,6 +26,10 @@ static int read_midx_file(const char *object_dir)
 		printf(" oid-fanout");
 	if (m->chunk_oid_lookup)
 		printf(" oid-lookup");
+	if (m->chunk_object_offsets)
+		printf(" object-offsets");
+	if (m->chunk_large_offsets)
+		printf(" large-offsets");
 
 	printf("\nnum_objects: %d\n", m->num_objects);
 

t/t5319-multi-pack-index.sh

@@ -6,27 +6,30 @@ test_description='multi-pack-indexes'
 midx_read_expect () {
 	NUM_PACKS=$1
 	NUM_OBJECTS=$2
+	NUM_CHUNKS=$3
+	OBJECT_DIR=$4
+	EXTRA_CHUNKS="$5"
 	{
 		cat <<-EOF &&
-		header: 4d494458 1 3 $NUM_PACKS
-		chunks: pack-names oid-fanout oid-lookup
+		header: 4d494458 1 $NUM_CHUNKS $NUM_PACKS
+		chunks: pack-names oid-fanout oid-lookup object-offsets$EXTRA_CHUNKS
 		num_objects: $NUM_OBJECTS
 		packs:
 		EOF
 		if test $NUM_PACKS -ge 1
 		then
-			ls pack/ | grep idx | sort
+			ls $OBJECT_DIR/pack/ | grep idx | sort
 		fi &&
-		printf "object-dir: .\n"
+		printf "object-dir: $OBJECT_DIR\n"
 	} >expect &&
-	test-tool read-midx . >actual &&
+	test-tool read-midx $OBJECT_DIR >actual &&
 	test_cmp expect actual
 }
 
 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 0
+	midx_read_expect 0 0 4 .
 '
 
 generate_objects () {
@@ -76,13 +79,13 @@ 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 18
+	midx_read_expect 1 18 4 .
 '
 
 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 18
+	midx_read_expect 1 18 4 .
 '
 
 test_expect_success 'add more objects' '
@@ -96,7 +99,7 @@ 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 34
+	midx_read_expect 2 34 4 .
 '
 
 test_expect_success 'add more packs' '
@@ -110,7 +113,33 @@ 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 74
+	midx_read_expect 12 74 4 .
+'
+
+# usage: corrupt_data <file> <pos> [<data>]
+corrupt_data () {
+	file=$1
+	pos=$2
+	data="${3:-\0}"
+	printf "$data" | dd of="$file" bs=1 seek="$pos" conv=notrunc
+}
+
+# Force 64-bit offsets by manipulating the idx file.
+# This makes the IDX file _incorrect_ so be careful to clean up after!
+test_expect_success 'force some 64-bit offsets with pack-objects' '
+	mkdir objects64 &&
+	mkdir objects64/pack &&
+	for i in $(test_seq 1 11)
+	do
+		generate_objects 11
+	done &&
+	commit_and_list_objects &&
+	pack64=$(git pack-objects --index-version=2,0x40 objects64/pack/test-64 <obj-list) &&
+	idx64=objects64/pack/test-64-$pack64.idx &&
+	chmod u+w $idx64 &&
+	corrupt_data $idx64 2999 "\02" &&
+	midx64=$(git multi-pack-index --object-dir=objects64 write) &&
+	midx_read_expect 1 63 5 objects64 " large-offsets"
 '
 
 test_done