Merge branch 'tb/pack-path-walk-bitmap-delta-islands' into seen

The pack-objects command now supports using reachability bitmaps and
delta-islands concurrently with the `--path-walk` option, allowing
faster packaging by falling back to path-walk when bitmaps cannot
fully satisfy the request.

* tb/pack-path-walk-bitmap-delta-islands:
  pack-objects: support `--delta-islands` with `--path-walk`
  pack-objects: extract `record_tree_depth()` helper
  pack-objects: support reachability bitmaps with `--path-walk`

Author: gitster

Documentation/git-pack-objects.adoc

@@ -402,11 +402,13 @@ will be automatically changed to version `1`.
 	of filenames that cause collisions in Git's default name-hash
 	algorithm.
 +
-Incompatible with `--delta-islands`. The `--use-bitmap-index` option is
-ignored in the presence of `--path-walk`. The `--path-walk` option
-supports the `--filter=<spec>` forms `blob:none`, `blob:limit=<n>`,
-`tree:0`, `object:type=<type>`, and `sparse:<oid>`. These supported filter
-types can be combined with the `combine:<spec>+<spec>` form.
+When `--use-bitmap-index` is specified with `--path-walk`, a successful
+bitmap traversal is used for object enumeration, with path-walk
+remaining as the fallback traversal when the bitmap cannot satisfy the
+request. The `--path-walk` option supports the `--filter=<spec>` forms
+`blob:none`, `blob:limit=<n>`, `tree:0`, `object:type=<type>`, and
+`sparse:<oid>`. These supported filter types can be combined with the
+`combine:<spec>+<spec>` form.
 
 
 DELTA ISLANDS

builtin/pack-objects.c

@@ -2734,6 +2734,22 @@ static inline void oe_set_tree_depth(struct packing_data *pack,
 	pack->tree_depth[e - pack->objects] = tree_depth;
 }
 
+static void record_tree_depth(const struct object_id *oid, const char *name)
+{
+	const char *p;
+	unsigned depth;
+	struct object_entry *ent;
+
+	/* the empty string is a root tree, which is depth 0 */
+	depth = *name ? 1 : 0;
+	for (p = strchr(name, '/'); p; p = strchr(p + 1, '/'))
+		depth++;
+
+	ent = packlist_find(&to_pack, oid);
+	if (ent && depth > oe_tree_depth(&to_pack, ent))
+		oe_set_tree_depth(&to_pack, ent, depth);
+}
+
 /*
  * Return the size of the object without doing any delta
  * reconstruction (so non-deltas are true object sizes, but deltas
@@ -4392,20 +4408,8 @@ static void show_object(struct object *obj, const char *name,
 	add_preferred_base_object(name);
 	add_object_entry(&obj->oid, obj->type, name, 0);
 
-	if (use_delta_islands) {
-		const char *p;
-		unsigned depth;
-		struct object_entry *ent;
-
-		/* the empty string is a root tree, which is depth 0 */
-		depth = *name ? 1 : 0;
-		for (p = strchr(name, '/'); p; p = strchr(p + 1, '/'))
-			depth++;
-
-		ent = packlist_find(&to_pack, &obj->oid);
-		if (ent && depth > oe_tree_depth(&to_pack, ent))
-			oe_set_tree_depth(&to_pack, ent, depth);
-	}
+	if (use_delta_islands)
+		record_tree_depth(&obj->oid, name);
 }
 
 static void show_object__ma_allow_any(struct object *obj, const char *name, void *data)
@@ -4749,6 +4753,31 @@ static int add_objects_by_path(const char *path,
 			continue;
 
 		add_object_entry(oid, type, path, exclude);
+
+		if (type == OBJ_COMMIT) {
+			struct commit *commit;
+
+			if (!write_bitmap_index && !use_delta_islands)
+				continue;
+
+			commit = lookup_commit(the_repository, oid);
+			if (!commit)
+				die(_("could not find commit %s"), oid_to_hex(oid));
+			if (write_bitmap_index)
+				index_commit_for_bitmap(commit);
+			/*
+			 * Skip island propagation for boundary commits.
+			 * The regular traversal's show_commit() is only
+			 * called for interesting commits; matching that
+			 * here keeps path-walk from doing extra work that
+			 * would only be a no-op anyway (boundary commits
+			 * are not in island_marks).
+			 */
+			if (use_delta_islands && !exclude)
+				propagate_island_marks(the_repository, commit);
+		} else if (type == OBJ_TREE && use_delta_islands) {
+			record_tree_depth(oid, path);
+		}
 	}
 
 	oe_end = to_pack.nr_objects;
@@ -4781,6 +4810,13 @@ static int get_object_list_path_walk(struct rev_info *revs)
 	info.path_fn = add_objects_by_path;
 	info.path_fn_data = &processed;
 
+	/*
+	 * Path-walk needs boundary commits to discover thin-pack bases, but
+	 * bitmap traversal does not understand the boundary state. Set it
+	 * here so any prior bitmap attempt sees the usual non-boundary walk.
+	 */
+	revs->boundary = 1;
+
 	/*
 	 * Allow the --[no-]sparse option to be interesting here, if only
 	 * for testing purposes. Paths with no interesting objects will not
@@ -5204,8 +5240,6 @@ int cmd_pack_objects(int argc,
 		const char *option = NULL;
 		if (!path_walk_filter_compatible(&filter_options))
 			option = "--filter";
-		else if (use_delta_islands)
-			option = "--delta-islands";
 
 		if (option) {
 			warning(_("cannot use %s with %s"),
@@ -5214,9 +5248,7 @@ int cmd_pack_objects(int argc,
 		}
 	}
 	if (path_walk) {
-		strvec_push(&rp, "--boundary");
 		strvec_push(&rp, "--objects");
-		use_bitmap_index = 0;
 	} else if (thin) {
 		use_internal_rev_list = 1;
 		strvec_push(&rp, shallow

t/t5310-pack-bitmaps.sh

@@ -577,6 +577,42 @@ test_bitmap_cases
 
 sane_unset GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL
 
+test_expect_success 'path-walk repack can write and use bitmap indexes' '
+	test_when_finished "rm -rf path-walk-bitmap" &&
+	git init path-walk-bitmap &&
+	(
+		cd path-walk-bitmap &&
+		test_commit first &&
+		test_commit second &&
+		test_commit third &&
+
+		git repack -a -d -b --path-walk &&
+		git rev-list --test-bitmap --use-bitmap-index HEAD &&
+
+		git rev-parse HEAD >in &&
+
+		git rev-list --objects --no-object-names HEAD >expect.raw &&
+		sort expect.raw >expect &&
+
+		for reuse in true false
+		do
+			: >trace.txt &&
+
+			GIT_TRACE2_EVENT="$(pwd)/trace.txt" \
+			git -c pack.allowPackReuse=$reuse pack-objects \
+				--stdout --revs --path-walk --use-bitmap-index \
+				<in >out.pack &&
+			grep "\"category\":\"bitmap\",\"key\":\"bitmap/hits\"" trace.txt &&
+
+			git index-pack out.pack &&
+
+			list_packed_objects out.idx >actual.raw &&
+			sort actual.raw >actual &&
+			test_cmp expect actual || return 1
+		done
+	)
+'
+
 test_expect_success 'incremental repack fails when bitmaps are requested' '
 	test_commit more-1 &&
 	test_must_fail git repack -d 2>err &&

t/t5320-delta-islands.sh

@@ -53,6 +53,35 @@ test_expect_success 'separate islands disallows delta' '
 	! is_delta_base $two $one
 '
 
+test_expect_success 'path-walk island repack respects islands' '
+	GIT_TRACE2_EVENT="$(pwd)/trace.path-walk-islands" \
+		git -c "pack.island=refs/heads/(.*)" repack -adfi \
+		--path-walk 2>err &&
+	test_region pack-objects path-walk trace.path-walk-islands &&
+	test_grep ! "cannot use --delta-islands with --path-walk" err &&
+	! is_delta_base $one $two &&
+	! is_delta_base $two $one
+'
+
+test_expect_success 'path-walk island bitmap repack respects islands' '
+	GIT_TRACE2_EVENT="$(pwd)/trace.path-walk-island-bitmap" \
+		git -c "pack.island=refs/heads/(.*)" repack -a -d -f -i -b \
+		--path-walk 2>err &&
+	test_region pack-objects path-walk trace.path-walk-island-bitmap &&
+	test_path_is_file .git/objects/pack/*.bitmap &&
+	git rev-list --test-bitmap --use-bitmap-index one &&
+	test_grep ! "cannot use --delta-islands with --path-walk" err &&
+	! is_delta_base $one $two &&
+	! is_delta_base $two $one
+'
+
+test_expect_success 'path-walk same island allows delta' '
+	GIT_TRACE2_EVENT="$(pwd)/trace.path-walk-same-island" \
+		git -c "pack.island=refs/heads" repack -adfi --path-walk &&
+	test_region pack-objects path-walk trace.path-walk-same-island &&
+	is_delta_base $one $two
+'
+
 test_expect_success 'same island allows delta' '
 	git -c "pack.island=refs/heads" repack -adfi &&
 	is_delta_base $one $two