Replace experimental path walk feature with upstream version

Documentation/config/pack.adoc

@@ -156,12 +156,8 @@ pack.useSparse::
 	`true`.
 
 pack.usePathWalk::
-	When true, git will default to using the '--path-walk' option in
-	'git pack-objects' when the '--revs' option is present. This
-	algorithm groups objects by path to maximize the ability to
-	compute delta chains across historical versions of the same
-	object. This may disable other options, such as using bitmaps to
-	enumerate objects.
+	Enable the `--path-walk` option by default for `git pack-objects`
+	processes. See linkgit:git-pack-objects[1] for full details.
 
 pack.preferBitmapTips::
 	When selecting which commits will receive bitmaps, prefer a

Documentation/git-pack-objects.adoc

@@ -10,13 +10,13 @@ SYNOPSIS
 --------
 [verse]
 'git pack-objects' [-q | --progress | --all-progress] [--all-progress-implied]
-	[--no-reuse-delta] [--delta-base-offset] [--non-empty]
-	[--local] [--incremental] [--window=<n>] [--depth=<n>]
-	[--revs [--unpacked | --all]] [--keep-pack=<pack-name>]
-	[--cruft] [--cruft-expiration=<time>]
-	[--stdout [--filter=<filter-spec>] | <base-name>]
-	[--shallow] [--keep-true-parents] [--[no-]sparse]
-	[--name-hash-version=<n>] [--path-walk] < <object-list>
+		   [--no-reuse-delta] [--delta-base-offset] [--non-empty]
+		   [--local] [--incremental] [--window=<n>] [--depth=<n>]
+		   [--revs [--unpacked | --all]] [--keep-pack=<pack-name>]
+		   [--cruft] [--cruft-expiration=<time>]
+		   [--stdout [--filter=<filter-spec>] | <base-name>]
+		   [--shallow] [--keep-true-parents] [--[no-]sparse]
+		   [--name-hash-version=<n>] [--path-walk] < <object-list>
 
 
 DESCRIPTION
@@ -376,15 +376,16 @@ when writing reachability bitmap files with `--write-bitmap-index` and it
 will be automatically changed to version `1`.
 
 --path-walk::
-	By default, `git pack-objects` walks objects in an order that
-	presents trees and blobs in an order unrelated to the path they
-	appear relative to a commit's root tree. The `--path-walk` option
-	enables a different walking algorithm that organizes trees and
-	blobs by path. This has the potential to improve delta compression
-	especially in the presence of filenames that cause collisions in
-	Git's default name-hash algorithm. Due to changing how the objects
-	are walked, this option is not compatible with `--delta-islands`,
-	`--shallow`, or `--filter`.
+	Perform compression by first organizing objects by path, then a
+	second pass that compresses across paths as normal. This has the
+	potential to improve delta compression especially in the presence
+	of filenames that cause collisions in Git's default name-hash
+	algorithm.
++
+Incompatible with `--delta-islands`, `--shallow`, or `--filter`. The
+`--use-bitmap-index` option will be ignored in the presence of
+`--path-walk.`
+
 
 DELTA ISLANDS
 -------------

Documentation/git-repack.adoc

@@ -259,17 +259,8 @@ linkgit:git-multi-pack-index[1]).
 	See linkgit:git-pack-objects[1] for full details.
 
 --path-walk::
-	This option passes the `--path-walk` option to the underlying
-	`git pack-options` process (see linkgit:git-pack-objects[1]).
-	By default, `git pack-objects` walks objects in an order that
-	presents trees and blobs in an order unrelated to the path they
-	appear relative to a commit's root tree. The `--path-walk` option
-	enables a different walking algorithm that organizes trees and
-	blobs by path. This has the potential to improve delta compression
-	especially in the presence of filenames that cause collisions in
-	Git's default name-hash algorithm. Due to changing how the objects
-	are walked, this option is not compatible with `--delta-islands`
-	or `--filter`.
+	Pass the `--path-walk` option to the underlying `git pack-objects`
+	process. See linkgit:git-pack-objects[1] for full details.
 
 CONFIGURATION
 -------------

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
@@ -69,5 +77,5 @@ Examples
 
 See example usages in:
 	`t/helper/test-path-walk.c`,
+	`builtin/pack-objects.c`,
 	`builtin/backfill.c`
-	`builtin/pack-objects.c`

builtin/pack-objects.c

@@ -44,6 +44,7 @@
 #include "blob.h"
 #include "tree.h"
 #include "path-walk.h"
+#include "trace2.h"
 
 /*
  * Objects we are going to pack are collected in the `to_pack` structure.
@@ -187,8 +188,14 @@ static inline void oe_set_delta_size(struct packing_data *pack,
 #define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val)
 
 static const char *const pack_usage[] = {
-	N_("git pack-objects --stdout [<options>] [< <ref-list> | < <object-list>]"),
-	N_("git pack-objects [<options>] <base-name> [< <ref-list> | < <object-list>]"),
+	N_("git pack-objects [-q | --progress | --all-progress] [--all-progress-implied]\n"
+	   "                 [--no-reuse-delta] [--delta-base-offset] [--non-empty]\n"
+	   "                 [--local] [--incremental] [--window=<n>] [--depth=<n>]\n"
+	   "                 [--revs [--unpacked | --all]] [--keep-pack=<pack-name>]\n"
+	   "                 [--cruft] [--cruft-expiration=<time>]\n"
+	   "                 [--stdout [--filter=<filter-spec>] | <base-name>]\n"
+	   "                 [--shallow] [--keep-true-parents] [--[no-]sparse]\n"
+	   "                 [--name-hash-version=<n>] [--path-walk] < <object-list>"),
 	NULL
 };
 
@@ -203,6 +210,7 @@ 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;
@@ -3291,6 +3299,9 @@ static int add_ref_tag(const char *tag UNUSED, const char *referent UNUSED, cons
 static int should_attempt_deltas(struct object_entry *entry)
 {
 	if (DELTA(entry))
+		/* This happens if we decided to reuse existing
+		 * delta from a pack. "reuse_delta &&" is implied.
+		 */
 		return 0;
 
 	if (!entry->type_valid ||
@@ -3315,16 +3326,16 @@ static int should_attempt_deltas(struct object_entry *entry)
 	return 1;
 }
 
-static void find_deltas_for_region(struct object_entry *list UNUSED,
+static void find_deltas_for_region(struct object_entry *list,
 				   struct packing_region *region,
 				   unsigned int *processed)
 {
 	struct object_entry **delta_list;
-	uint32_t delta_list_nr = 0;
+	unsigned int delta_list_nr = 0;
 
 	ALLOC_ARRAY(delta_list, region->nr);
-	for (uint32_t i = 0; i < region->nr; i++) {
-		struct object_entry *entry = to_pack.objects + region->start + i;
+	for (size_t i = 0; i < region->nr; i++) {
+		struct object_entry *entry = list + region->start + i;
 		if (should_attempt_deltas(entry))
 			delta_list[delta_list_nr++] = entry;
 	}
@@ -3336,10 +3347,10 @@ static void find_deltas_for_region(struct object_entry *list UNUSED,
 
 static void find_deltas_by_region(struct object_entry *list,
 				  struct packing_region *regions,
-				  uint32_t start, uint32_t nr)
+				  size_t start, size_t nr)
 {
 	unsigned int processed = 0;
-	uint32_t progress_nr;
+	size_t progress_nr;
 
 	if (!nr)
 		return;
@@ -3422,7 +3433,10 @@ static void ll_find_deltas_by_region(struct object_entry *list,
 	}
 
 	if (progress > pack_to_stdout)
-		fprintf_ln(stderr, _("Path-based delta compression using up to %d threads"),
+		fprintf_ln(stderr,
+			   Q_("Path-based delta compression using up to %d thread",
+			      "Path-based delta compression using up to %d threads",
+			      delta_search_threads),
 			   delta_search_threads);
 	CALLOC_ARRAY(p, delta_search_threads);
 
@@ -4489,11 +4503,11 @@ static void mark_bitmap_preferred_tips(void)
 	}
 }
 
-static inline int is_oid_interesting(struct repository *repo,
-				     struct object_id *oid)
+static inline int is_oid_uninteresting(struct repository *repo,
+				       struct object_id *oid)
 {
 	struct object *o = lookup_object(repo, oid);
-	return o && !(o->flags & UNINTERESTING);
+	return !o || (o->flags & UNINTERESTING);
 }
 
 static int add_objects_by_path(const char *path,
@@ -4521,7 +4535,7 @@ static int add_objects_by_path(const char *path,
 					     OBJECT_INFO_FOR_PREFETCH) < 0)
 			continue;
 
-		exclude = !is_oid_interesting(the_repository, oid);
+		exclude = is_oid_uninteresting(the_repository, oid);
 
 		if (exclude && !thin)
 			continue;
@@ -4553,11 +4567,11 @@ static void get_object_list_path_walk(struct rev_info *revs)
 {
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	unsigned int processed = 0;
+	int result;
 
 	info.revs = revs;
 	info.path_fn = add_objects_by_path;
 	info.path_fn_data = &processed;
-	revs->tag_objects = 1;
 
 	/*
 	 * Allow the --[no-]sparse option to be interesting here, if only
@@ -4566,8 +4580,13 @@ 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);
+	trace2_region_leave("pack-objects", "path-walk", revs->repo);
 
-	if (walk_objects_by_path(&info))
+	if (result)
 		die(_("failed to pack objects via path-walk"));
 }
 
@@ -4617,7 +4636,7 @@ static void get_object_list(struct rev_info *revs, int ac, const char **av)
 
 	warn_on_object_refname_ambiguity = save_warning;
 
-	if (use_bitmap_index && !path_walk && !get_object_list_from_bitmap(revs))
+	if (use_bitmap_index && !get_object_list_from_bitmap(revs))
 		return;
 
 	if (use_delta_islands)
@@ -4767,7 +4786,6 @@ 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;
@@ -4947,17 +4965,18 @@ int cmd_pack_objects(int argc,
 
 	strvec_push(&rp, "pack-objects");
 
-	if (path_walk && filter_options.choice) {
-		warning(_("cannot use --filter with --path-walk"));
-		path_walk = 0;
-	}
-	if (path_walk && use_delta_islands) {
-		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) {
+		const char *option = NULL;
+		if (filter_options.choice)
+			option = "--filter";
+		else if (use_delta_islands)
+			option = "--delta-islands";
+
+		if (option) {
+			warning(_("cannot use %s with %s"),
+				option, "--path-walk");
+			path_walk = 0;
+		}
 	}
 	if (path_walk) {
 		strvec_push(&rp, "--boundary");

builtin/repack.c

@@ -1188,7 +1188,7 @@ int cmd_repack(int argc,
 		OPT_INTEGER(0, "name-hash-version", &po_args.name_hash_version,
 				N_("specify the name hash version to use for grouping similar objects by path")),
 		OPT_BOOL(0, "path-walk", &po_args.path_walk,
-				N_("(EXPERIMENTAL!) pass --path-walk to git-pack-objects")),
+				N_("pass --path-walk to git-pack-objects")),
 		OPT_NEGBIT('n', NULL, &run_update_server_info,
 				N_("do not run git-update-server-info"), 1),
 		OPT__QUIET(&po_args.quiet, N_("be quiet")),

ci/run-build-and-tests.sh

@@ -26,7 +26,6 @@ linux-TEST-vars)
 	export GIT_TEST_NO_WRITE_REV_INDEX=1
 	export GIT_TEST_CHECKOUT_WORKERS=2
 	export GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL=1
-	export GIT_TEST_PACK_PATH_WALK=1
 	;;
 linux-clang)
 	export GIT_TEST_DEFAULT_HASH=sha1

pack-objects.h

@@ -125,8 +125,8 @@ struct object_entry {
  * as given by a starting index and a number of elements.
  */
 struct packing_region {
-	uint32_t start;
-	uint32_t nr;
+	size_t start;
+	size_t nr;
 };
 
 struct packing_data {
@@ -135,7 +135,7 @@ struct packing_data {
 	uint32_t nr_objects, nr_alloc;
 
 	struct packing_region *regions;
-	uint32_t nr_regions, nr_regions_alloc;
+	size_t nr_regions, nr_regions_alloc;
 
 	int32_t *index;
 	uint32_t index_size;

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

revision.c

@@ -212,21 +212,6 @@ static void add_children_by_path(struct repository *r,
 	free_tree_buffer(tree);
 }
 
-void mark_trees_uninteresting_dense(struct repository *r,
-				    struct oidset *trees)
-{
-	struct object_id *oid;
-	struct oidset_iter iter;
-
-	oidset_iter_init(trees, &iter);
-	while ((oid = oidset_iter_next(&iter))) {
-		struct tree *tree = lookup_tree(r, oid);
-
-		if (tree->object.flags & UNINTERESTING)
-			mark_tree_contents_uninteresting(r, tree);
-	}
-}
-
 void mark_trees_uninteresting_sparse(struct repository *r,
 				     struct oidset *trees)
 {

revision.h

@@ -486,7 +486,6 @@ void put_revision_mark(const struct rev_info *revs,
 
 void mark_parents_uninteresting(struct rev_info *revs, struct commit *commit);
 void mark_tree_uninteresting(struct repository *r, struct tree *tree);
-void mark_trees_uninteresting_dense(struct repository *r, struct oidset *trees);
 void mark_trees_uninteresting_sparse(struct repository *r, struct oidset *trees);
 
 /**

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(),