Replace path walk feature with upstream version

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

Author: derrickstolee

Documentation/technical/api-path-walk.adoc

@@ -56,6 +56,14 @@ better off using the revision walk API instead.
 	the revision walk so that the walk emits commits marked with the
 	`UNINTERESTING` flag.
 
+`edge_aggressive`::
+	For performance reasons, usually only the boundary commits are
+	explored to find UNINTERESTING objects. However, in the case of
+	shallow clones it can be helpful to mark all trees and blobs
+	reachable from UNINTERESTING tip commits as UNINTERESTING. This
+	matches the behavior of `--objects-edge-aggressive` in the
+	revision API.
+
 `pl`::
 	This pattern list pointer allows focusing the path-walk search to
 	a set of patterns, only emitting paths that match the given

builtin/pack-objects.c

@@ -204,6 +204,7 @@ static int keep_unreachable, unpack_unreachable, include_tag;
 static timestamp_t unpack_unreachable_expiration;
 static int pack_loose_unreachable;
 static int cruft;
+static int shallow = 0;
 static timestamp_t cruft_expiration;
 static int local;
 static int have_non_local_packs;
@@ -4568,6 +4569,7 @@ static void get_object_list_path_walk(struct rev_info *revs)
 	 * base objects.
 	 */
 	info.prune_all_uninteresting = sparse;
+	info.edge_aggressive = shallow;
 
 	trace2_region_enter("pack-objects", "path-walk", revs->repo);
 	result = walk_objects_by_path(&info);
@@ -4773,7 +4775,6 @@ int cmd_pack_objects(int argc,
 		     struct repository *repo UNUSED)
 {
 	int use_internal_rev_list = 0;
-	int shallow = 0;
 	int all_progress_implied = 0;
 	struct strvec rp = STRVEC_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
@@ -4961,10 +4962,6 @@ int cmd_pack_objects(int argc,
 		warning(_("cannot use delta islands with --path-walk"));
 		path_walk = 0;
 	}
-	if (path_walk && shallow) {
-		warning(_("cannot use --shallow with --path-walk"));
-		path_walk = 0;
-	}
 	if (path_walk) {
 		strvec_push(&rp, "--boundary");
 		 /*

path-walk.c

@@ -503,7 +503,11 @@ int walk_objects_by_path(struct path_walk_info *info)
 	if (prepare_revision_walk(info->revs))
 		die(_("failed to setup revision walk"));
 
-	/* Walk trees to mark them as UNINTERESTING. */
+	/*
+	 * Walk trees to mark them as UNINTERESTING.
+	 * This is particularly important when 'edge_aggressive' is set.
+	 */
+	info->revs->edge_hint_aggressive = info->edge_aggressive;
 	edge_repo = info->revs->repo;
 	edge_tree_list = root_tree_list;
 	mark_edges_uninteresting(info->revs, show_edge,

path-walk.h

@@ -50,6 +50,13 @@ struct path_walk_info {
 	 */
 	int prune_all_uninteresting;
 
+	/**
+	 * When 'edge_aggressive' is set, then the revision walk will use
+	 * the '--object-edge-aggressive' option to mark even more objects
+	 * as uninteresting.
+	 */
+	int edge_aggressive;
+
 	/**
 	 * Specify a sparse-checkout definition to match our paths to. Do not
 	 * walk outside of this sparse definition. If the patterns are in

t/helper/test-path-walk.c

@@ -82,6 +82,8 @@ int cmd__path_walk(int argc, const char **argv)
 			 N_("toggle inclusion of tree objects")),
 		OPT_BOOL(0, "prune", &info.prune_all_uninteresting,
 			 N_("toggle pruning of uninteresting paths")),
+		OPT_BOOL(0, "edge-aggressive", &info.edge_aggressive,
+			 N_("toggle aggressive edge walk")),
 		OPT_BOOL(0, "stdin-pl", &stdin_pl,
 			 N_("read a pattern list over stdin")),
 		OPT_END(),

t/perf/p5313-pack-objects.sh

@@ -22,71 +22,55 @@ test_expect_success 'create rev input' '
 	EOF
 '
 
-for version in 1 2
-do
-	export version
+test_all_with_args () {
+	parameter=$1
+	export parameter
 
-	test_perf "thin pack with version $version" '
+	test_perf "thin pack with $parameter" '
 		git pack-objects --thin --stdout --revs --sparse \
-			--name-hash-version=$version <in-thin >out
+			$parameter <in-thin >out
 	'
 
-	test_size "thin pack size with version $version" '
+	test_size "thin pack size with $parameter" '
 		test_file_size out
 	'
 
-	test_perf "big pack with version $version" '
+	test_perf "big pack with $parameter" '
 		git pack-objects --stdout --revs --sparse \
-			--name-hash-version=$version <in-big >out
+			$parameter <in-big >out
 	'
 
-	test_size "big pack size with version $version" '
+	test_size "big pack size with $parameter" '
 		test_file_size out
 	'
 
-	test_perf "shallow fetch pack with version $version" '
+	test_perf "shallow fetch pack with $parameter" '
 		git pack-objects --stdout --revs --sparse --shallow \
-			--name-hash-version=$version <in-shallow >out
+			$parameter <in-shallow >out
 	'
 
-	test_size "shallow pack size with version $version" '
+	test_size "shallow pack size with $parameter" '
 		test_file_size out
 	'
+}
+
+for version in 1 2
+do
+	export version
+
+	test_all_with_args --name-hash-version=$version
 
-	test_perf "repack with version $version" '
+	test_perf "repack with --name-hash-version=$version" '
 		git repack -adf --name-hash-version=$version
 	'
 
-	test_size "repack size with version $version" '
+	test_size "repack size with --name-hash-version=$version" '
 		gitdir=$(git rev-parse --git-dir) &&
 		pack=$(ls $gitdir/objects/pack/pack-*.pack) &&
 		test_file_size "$pack"
 	'
 done
 
-test_perf 'thin pack with --path-walk' '
-	git pack-objects --thin --stdout --revs --sparse --path-walk <in-thin >out
-'
-
-test_size 'thin pack size with --path-walk' '
-	test_file_size out
-'
-
-test_perf 'big pack with --path-walk' '
-	git pack-objects --stdout --revs --sparse --path-walk <in-big >out
-'
-
-test_size 'big pack size with --path-walk' '
-	test_file_size out
-'
-
-test_perf 'repack with --path-walk' '
-	git repack -adf --path-walk
-'
-
-test_size 'repack size with --path-walk' '
-	pack=$(ls .git/objects/pack/pack-*.pack) &&
-	test_file_size "$pack"
-'
+test_all_with_args --path-walk
 
 test_done

t/t5538-push-shallow.sh

@@ -123,4 +123,45 @@ EOF
 	git cat-file blob $(echo 1|git hash-object --stdin) >/dev/null
 	)
 '
+
+test_expect_success 'push new commit from shallow clone has correct object count' '
+	git init origin &&
+	test_commit -C origin a &&
+	test_commit -C origin b &&
+
+	git clone --depth=1 "file://$(pwd)/origin" client &&
+	git -C client checkout -b topic &&
+	git -C client commit --allow-empty -m "empty" &&
+	GIT_PROGRESS_DELAY=0 git -C client push --progress origin topic 2>err &&
+	test_grep "Enumerating objects: 1, done." err
+'
+
+test_expect_success 'push new commit from shallow clone has good deltas' '
+	git init base &&
+	test_seq 1 999 >base/a &&
+	test_commit -C base initial &&
+	git -C base add a &&
+	git -C base commit -m "big a" &&
+
+	git clone --depth=1 "file://$(pwd)/base" deltas &&
+	git -C deltas checkout -b deltas &&
+	test_seq 1 1000 >deltas/a &&
+	git -C deltas commit -a -m "bigger a" &&
+	GIT_PROGRESS_DELAY=0 git -C deltas push --progress origin deltas 2>err &&
+
+	test_grep "Enumerating objects: 5, done" err &&
+
+	# If the delta base is found, then this message uses "bytes".
+	# If the delta base is not found, then this message uses "KiB".
+	test_grep "Writing objects: .* bytes" err &&
+
+	git -C deltas commit --amend -m "changed message" &&
+	GIT_TRACE2_EVENT="$(pwd)/config-push.txt" \
+	GIT_PROGRESS_DELAY=0 git -C deltas -c pack.usePathWalk=true \
+		push --progress -f origin deltas 2>err &&
+
+	test_grep "Enumerating objects: 1, done" err &&
+	test_region pack-objects path-walk config-push.txt
+'
+
 test_done

t/t6601-path-walk.sh

@@ -376,6 +376,26 @@ test_expect_success 'topic, not base, boundary with pruning' '
 	test_cmp_sorted expect out
 '
 
+test_expect_success 'topic, not base, --edge-aggressive with pruning' '
+	test-tool path-walk --prune --edge-aggressive -- topic --not base >out &&
+
+	cat >expect <<-EOF &&
+	0:commit::$(git rev-parse topic)
+	1:tree::$(git rev-parse topic^{tree})
+	1:tree::$(git rev-parse base^{tree}):UNINTERESTING
+	2:tree:right/:$(git rev-parse topic:right)
+	2:tree:right/:$(git rev-parse base:right):UNINTERESTING
+	3:blob:right/c:$(git rev-parse base:right/c):UNINTERESTING
+	3:blob:right/c:$(git rev-parse topic:right/c)
+	blobs:2
+	commits:1
+	tags:0
+	trees:4
+	EOF
+
+	test_cmp_sorted expect out
+'
+
 test_expect_success 'trees are reported exactly once' '
 	test_when_finished "rm -rf unique-trees" &&
 	test_create_repo unique-trees &&