midx: implement writing incremental MIDX bitmaps

Now that the pack-bitmap machinery has learned how to read and interact
with an incremental MIDX bitmap, teach the pack-bitmap-write.c machinery
(and relevant callers from within the MIDX machinery) to write such
bitmaps.

The details for doing so are mostly straightforward. The main changes
are as follows:

  - find_object_pos() now makes use of an extra MIDX parameter which is
    used to locate the bit positions of objects which are from previous
    layers (and thus do not exist in the current layer's pack_order
    field).

    (Note also that the pack_order field is moved into struct
    write_midx_context to further simplify the callers for
    write_midx_bitmap()).

  - bitmap_writer_build_type_index() first determines how many objects
    precede the current bitmap layer and offsets the bits it sets in
    each respective type-level bitmap by that amount so they can be OR'd
    together.

Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

builtin/pack-objects.c

@@ -1342,7 +1342,8 @@ static void write_pack_file(void)
 
 			if (write_bitmap_index) {
 				bitmap_writer_init(&bitmap_writer,
-						   the_repository, &to_pack);
+						   the_repository, &to_pack,
+						   NULL);
 				bitmap_writer_set_checksum(&bitmap_writer, hash);
 				bitmap_writer_build_type_index(&bitmap_writer,
 							       written_list);

midx-write.c

@@ -645,15 +645,21 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx)
 	return pack_order;
 }
 
-static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash,
-				     struct write_midx_context *ctx)
+static void write_midx_reverse_index(struct write_midx_context *ctx,
+				     const char *object_dir,
+				     unsigned char *midx_hash)
 {
 	struct strbuf buf = STRBUF_INIT;
 	const char *tmp_file;
 
 	trace2_region_enter("midx", "write_midx_reverse_index", the_repository);
 
-	strbuf_addf(&buf, "%s-%s.rev", midx_name, hash_to_hex(midx_hash));
+	if (ctx->incremental)
+		get_split_midx_filename_ext(&buf, object_dir, midx_hash,
+					    MIDX_EXT_REV);
+	else
+		get_midx_filename_ext(&buf, object_dir, midx_hash,
+				      MIDX_EXT_REV);
 
 	tmp_file = write_rev_file_order(NULL, ctx->pack_order, ctx->entries_nr,
 					midx_hash, WRITE_REV);
@@ -826,20 +832,26 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr
 	return cb.commits;
 }
 
-static int write_midx_bitmap(const char *midx_name,
+static int write_midx_bitmap(struct write_midx_context *ctx,
+			     const char *object_dir,
 			     const unsigned char *midx_hash,
 			     struct packing_data *pdata,
 			     struct commit **commits,
 			     uint32_t commits_nr,
-			     uint32_t *pack_order,
 			     unsigned flags)
 {
 	int ret, i;
 	uint16_t options = 0;
 	struct bitmap_writer writer;
 	struct pack_idx_entry **index;
-	char *bitmap_name = xstrfmt("%s-%s.bitmap", midx_name,
-					hash_to_hex(midx_hash));
+	struct strbuf bitmap_name = STRBUF_INIT;
+
+	if (ctx->incremental)
+		get_split_midx_filename_ext(&bitmap_name, object_dir, midx_hash,
+					    MIDX_EXT_BITMAP);
+	else
+		get_midx_filename_ext(&bitmap_name, object_dir, midx_hash,
+				      MIDX_EXT_BITMAP);
 
 	trace2_region_enter("midx", "write_midx_bitmap", the_repository);
 
@@ -858,7 +870,8 @@ static int write_midx_bitmap(const char *midx_name,
 	for (i = 0; i < pdata->nr_objects; i++)
 		index[i] = &pdata->objects[i].idx;
 
-	bitmap_writer_init(&writer, the_repository, pdata);
+	bitmap_writer_init(&writer, the_repository, pdata,
+			   ctx->incremental ? ctx->base_midx : NULL);
 	bitmap_writer_show_progress(&writer, flags & MIDX_PROGRESS);
 	bitmap_writer_build_type_index(&writer, index);
 
@@ -876,19 +889,19 @@ static int write_midx_bitmap(const char *midx_name,
 	 * bitmap_writer_finish().
 	 */
 	for (i = 0; i < pdata->nr_objects; i++)
-		index[pack_order[i]] = &pdata->objects[i].idx;
+		index[ctx->pack_order[i]] = &pdata->objects[i].idx;
 
 	bitmap_writer_select_commits(&writer, commits, commits_nr);
 	ret = bitmap_writer_build(&writer);
 	if (ret < 0)
 		goto cleanup;
 
 	bitmap_writer_set_checksum(&writer, midx_hash);
-	bitmap_writer_finish(&writer, index, bitmap_name, options);
+	bitmap_writer_finish(&writer, index, bitmap_name.buf, options);
 
 cleanup:
 	free(index);
-	free(bitmap_name);
+	strbuf_release(&bitmap_name);
 	bitmap_writer_free(&writer);
 
 	trace2_region_leave("midx", "write_midx_bitmap", the_repository);
@@ -1072,8 +1085,6 @@ static int write_midx_internal(const char *object_dir,
 	trace2_region_enter("midx", "write_midx_internal", the_repository);
 
 	ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL);
-	if (ctx.incremental && (flags & MIDX_WRITE_BITMAP))
-		die(_("cannot write incremental MIDX with bitmap"));
 
 	if (ctx.incremental)
 		strbuf_addf(&midx_name,
@@ -1115,6 +1126,12 @@ static int write_midx_internal(const char *object_dir,
 	if (ctx.incremental) {
 		struct multi_pack_index *m = ctx.base_midx;
 		while (m) {
+			if (flags & MIDX_WRITE_BITMAP && load_midx_revindex(m)) {
+				error(_("could not load reverse index for MIDX %s"),
+				      hash_to_hex(get_midx_checksum(m)));
+				result = 1;
+				goto cleanup;
+			}
 			ctx.num_multi_pack_indexes_before++;
 			m = m->base_midx;
 		}
@@ -1381,7 +1398,7 @@ static int write_midx_internal(const char *object_dir,
 
 	if (flags & MIDX_WRITE_REV_INDEX &&
 	    git_env_bool("GIT_TEST_MIDX_WRITE_REV", 0))
-		write_midx_reverse_index(midx_name.buf, midx_hash, &ctx);
+		write_midx_reverse_index(&ctx, object_dir, midx_hash);
 
 	if (flags & MIDX_WRITE_BITMAP) {
 		struct packing_data pdata;
@@ -1404,8 +1421,8 @@ static int write_midx_internal(const char *object_dir,
 		FREE_AND_NULL(ctx.entries);
 		ctx.entries_nr = 0;
 
-		if (write_midx_bitmap(midx_name.buf, midx_hash, &pdata,
-				      commits, commits_nr, ctx.pack_order,
+		if (write_midx_bitmap(&ctx, object_dir,
+				      midx_hash, &pdata, commits, commits_nr,
 				      flags) < 0) {
 			error(_("could not write multi-pack bitmap"));
 			result = 1;

pack-bitmap-write.c

@@ -25,6 +25,8 @@
 #include "alloc.h"
 #include "refs.h"
 #include "strmap.h"
+#include "midx.h"
+#include "pack-revindex.h"
 
 struct bitmapped_commit {
 	struct commit *commit;
@@ -42,14 +44,16 @@ static inline int bitmap_writer_nr_selected_commits(struct bitmap_writer *writer
 }
 
 void bitmap_writer_init(struct bitmap_writer *writer, struct repository *r,
-			struct packing_data *pdata)
+			struct packing_data *pdata,
+			struct multi_pack_index *midx)
 {
 	memset(writer, 0, sizeof(struct bitmap_writer));
 	if (writer->bitmaps)
 		BUG("bitmap writer already initialized");
 	writer->bitmaps = kh_init_oid_map();
 	writer->pseudo_merge_commits = kh_init_oid_map();
 	writer->to_pack = pdata;
+	writer->midx = midx;
 
 	string_list_init_dup(&writer->pseudo_merge_groups);
 
@@ -104,6 +108,11 @@ void bitmap_writer_build_type_index(struct bitmap_writer *writer,
 				    struct pack_idx_entry **index)
 {
 	uint32_t i;
+	uint32_t base_objects = 0;
+
+	if (writer->midx)
+		base_objects = writer->midx->num_objects +
+			writer->midx->num_objects_in_base;
 
 	writer->commits = ewah_new();
 	writer->trees = ewah_new();
@@ -133,19 +142,19 @@ void bitmap_writer_build_type_index(struct bitmap_writer *writer,
 
 		switch (real_type) {
 		case OBJ_COMMIT:
-			ewah_set(writer->commits, i);
+			ewah_set(writer->commits, i + base_objects);
 			break;
 
 		case OBJ_TREE:
-			ewah_set(writer->trees, i);
+			ewah_set(writer->trees, i + base_objects);
 			break;
 
 		case OBJ_BLOB:
-			ewah_set(writer->blobs, i);
+			ewah_set(writer->blobs, i + base_objects);
 			break;
 
 		case OBJ_TAG:
-			ewah_set(writer->tags, i);
+			ewah_set(writer->tags, i + base_objects);
 			break;
 
 		default:
@@ -198,19 +207,37 @@ void bitmap_writer_push_commit(struct bitmap_writer *writer,
 static uint32_t find_object_pos(struct bitmap_writer *writer,
 				const struct object_id *oid, int *found)
 {
-	struct object_entry *entry = packlist_find(writer->to_pack, oid);
+	struct object_entry *entry;
+
+	entry = packlist_find(writer->to_pack, oid);
+	if (entry) {
+		uint32_t base_objects = 0;
+		if (writer->midx)
+			base_objects = writer->midx->num_objects +
+				writer->midx->num_objects_in_base;
 
-	if (!entry) {
 		if (found)
-			*found = 0;
-		warning("Failed to write bitmap index. Packfile doesn't have full closure "
-			"(object %s is missing)", oid_to_hex(oid));
-		return 0;
+			*found = 1;
+		return oe_in_pack_pos(writer->to_pack, entry) + base_objects;
+	} else if (writer->midx) {
+		uint32_t at, pos;
+
+		if (!bsearch_midx(oid, writer->midx, &at))
+			goto missing;
+		if (midx_to_pack_pos(writer->midx, at, &pos) < 0)
+			goto missing;
+
+		if (found)
+			*found = 1;
+		return pos;
 	}
 
+missing:
 	if (found)
-		*found = 1;
-	return oe_in_pack_pos(writer->to_pack, entry);
+		*found = 0;
+	warning("Failed to write bitmap index. Packfile doesn't have full closure "
+		"(object %s is missing)", oid_to_hex(oid));
+	return 0;
 }
 
 static void compute_xor_offsets(struct bitmap_writer *writer)
@@ -577,7 +604,7 @@ int bitmap_writer_build(struct bitmap_writer *writer)
 	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
 	struct prio_queue tree_queue = { NULL };
 	struct bitmap_index *old_bitmap;
-	uint32_t *mapping;
+	uint32_t *mapping = NULL;
 	int closed = 1; /* until proven otherwise */
 
 	if (writer->show_progress)
@@ -1010,7 +1037,7 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 	struct strbuf tmp_file = STRBUF_INIT;
 	struct hashfile *f;
 	off_t *offsets = NULL;
-	uint32_t i;
+	uint32_t i, base_objects;
 
 	struct bitmap_disk_header header;
 
@@ -1036,6 +1063,12 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 	if (options & BITMAP_OPT_LOOKUP_TABLE)
 		CALLOC_ARRAY(offsets, writer->to_pack->nr_objects);
 
+	if (writer->midx)
+		base_objects = writer->midx->num_objects +
+			writer->midx->num_objects_in_base;
+	else
+		base_objects = 0;
+
 	for (i = 0; i < bitmap_writer_nr_selected_commits(writer); i++) {
 		struct bitmapped_commit *stored = &writer->selected[i];
 		int commit_pos = oid_pos(&stored->commit->object.oid, index,
@@ -1044,7 +1077,7 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 
 		if (commit_pos < 0)
 			BUG(_("trying to write commit not in index"));
-		stored->commit_pos = commit_pos;
+		stored->commit_pos = commit_pos + base_objects;
 	}
 
 	write_selected_commits_v1(writer, f, offsets);

pack-bitmap.h

@@ -110,6 +110,7 @@ struct bitmap_writer {
 
 	kh_oid_map_t *bitmaps;
 	struct packing_data *to_pack;
+	struct multi_pack_index *midx; /* if appending to a MIDX chain */
 
 	struct bitmapped_commit *selected;
 	unsigned int selected_nr, selected_alloc;
@@ -124,7 +125,8 @@ struct bitmap_writer {
 };
 
 void bitmap_writer_init(struct bitmap_writer *writer, struct repository *r,
-			struct packing_data *pdata);
+			struct packing_data *pdata,
+			struct multi_pack_index *midx);
 void bitmap_writer_show_progress(struct bitmap_writer *writer, int show);
 void bitmap_writer_set_checksum(struct bitmap_writer *writer,
 				const unsigned char *sha1);

t/t5334-incremental-multi-pack-index.sh

@@ -43,4 +43,88 @@ test_expect_success 'convert incremental to non-incremental' '
 
 compare_results_with_midx 'non-incremental MIDX conversion'
 
+write_midx_layer () {
+	n=1
+	if test -f $midx_chain
+	then
+		n="$(($(wc -l <$midx_chain) + 1))"
+	fi
+
+	for i in 1 2
+	do
+		test_commit $n.$i &&
+		git repack -d || return 1
+	done &&
+	git multi-pack-index write --bitmap --incremental
+}
+
+test_expect_success 'write initial MIDX layer' '
+	git repack -ad &&
+	write_midx_layer
+'
+
+test_expect_success 'read bitmap from first MIDX layer' '
+	git rev-list --test-bitmap 1.2
+'
+
+test_expect_success 'write another MIDX layer' '
+	write_midx_layer
+'
+
+test_expect_success 'midx verify with multiple layers' '
+	git multi-pack-index verify
+'
+
+test_expect_success 'read bitmap from second MIDX layer' '
+	git rev-list --test-bitmap 2.2
+'
+
+test_expect_success 'read earlier bitmap from second MIDX layer' '
+	git rev-list --test-bitmap 1.2
+'
+
+test_expect_success 'show object from first pack' '
+	git cat-file -p 1.1
+'
+
+test_expect_success 'show object from second pack' '
+	git cat-file -p 2.2
+'
+
+for reuse in false single multi
+do
+	test_expect_success "full clone (pack.allowPackReuse=$reuse)" '
+		rm -fr clone.git &&
+
+		git config pack.allowPackReuse $reuse &&
+		git clone --no-local --bare . clone.git
+	'
+done
+
+test_expect_success 'relink existing MIDX layer' '
+	rm -fr "$midxdir" &&
+
+	GIT_TEST_MIDX_WRITE_REV=1 git multi-pack-index write --bitmap &&
+
+	midx_hash="$(test-tool read-midx --checksum $objdir)" &&
+
+	test_path_is_file "$packdir/multi-pack-index" &&
+	test_path_is_file "$packdir/multi-pack-index-$midx_hash.bitmap" &&
+	test_path_is_file "$packdir/multi-pack-index-$midx_hash.rev" &&
+
+	test_commit another &&
+	git repack -d &&
+	git multi-pack-index write --bitmap --incremental &&
+
+	test_path_is_missing "$packdir/multi-pack-index" &&
+	test_path_is_missing "$packdir/multi-pack-index-$midx_hash.bitmap" &&
+	test_path_is_missing "$packdir/multi-pack-index-$midx_hash.rev" &&
+
+	test_path_is_file "$midxdir/multi-pack-index-$midx_hash.midx" &&
+	test_path_is_file "$midxdir/multi-pack-index-$midx_hash.bitmap" &&
+	test_path_is_file "$midxdir/multi-pack-index-$midx_hash.rev" &&
+	test_line_count = 2 "$midx_chain"
+
+'
+
 test_done