Merge branch 'jk/prune-optim'

"git prune" has been taught to take advantage of reachability
bitmap when able.

* jk/prune-optim:
  t5304: rename "sha1" variables to "oid"
  prune: check SEEN flag for reachability
  prune: use bitmaps for reachability traversal
  prune: lazily perform reachability traversal

builtin/prune.c

@@ -31,16 +31,39 @@ static int prune_tmp_file(const char *fullpath)
 	return 0;
 }
 
+static void perform_reachability_traversal(struct rev_info *revs)
+{
+	static int initialized;
+	struct progress *progress = NULL;
+
+	if (initialized)
+		return;
+
+	if (show_progress)
+		progress = start_delayed_progress(_("Checking connectivity"), 0);
+	mark_reachable_objects(revs, 1, expire, progress);
+	stop_progress(&progress);
+	initialized = 1;
+}
+
+static int is_object_reachable(const struct object_id *oid,
+			       struct rev_info *revs)
+{
+	struct object *obj;
+
+	perform_reachability_traversal(revs);
+
+	obj = lookup_object(the_repository, oid->hash);
+	return obj && (obj->flags & SEEN);
+}
+
 static int prune_object(const struct object_id *oid, const char *fullpath,
 			void *data)
 {
+	struct rev_info *revs = data;
 	struct stat st;
 
-	/*
-	 * Do we know about this object?
-	 * It must have been reachable
-	 */
-	if (lookup_object(the_repository, oid->hash))
+	if (is_object_reachable(oid, revs))
 		return 0;
 
 	if (lstat(fullpath, &st)) {
@@ -102,7 +125,6 @@ static void remove_temporary_files(const char *path)
 int cmd_prune(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
-	struct progress *progress = NULL;
 	int exclude_promisor_objects = 0;
 	const struct option options[] = {
 		OPT__DRY_RUN(&show_only, N_("do not remove, show only")),
@@ -142,17 +164,13 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 
 	if (show_progress == -1)
 		show_progress = isatty(2);
-	if (show_progress)
-		progress = start_delayed_progress(_("Checking connectivity"), 0);
 	if (exclude_promisor_objects) {
 		fetch_if_missing = 0;
 		revs.exclude_promisor_objects = 1;
 	}
 
-	mark_reachable_objects(&revs, 1, expire, progress);
-	stop_progress(&progress);
 	for_each_loose_file_in_objdir(get_object_directory(), prune_object,
-				      prune_cruft, prune_subdir, NULL);
+				      prune_cruft, prune_subdir, &revs);
 
 	prune_packed_objects(show_only ? PRUNE_PACKED_DRY_RUN : 0);
 	remove_temporary_files(get_object_directory());
@@ -160,8 +178,10 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 	remove_temporary_files(s);
 	free(s);
 
-	if (is_repository_shallow(the_repository))
+	if (is_repository_shallow(the_repository)) {
+		perform_reachability_traversal(&revs);
 		prune_shallow(show_only ? PRUNE_SHOW_ONLY : 0);
+	}
 
 	return 0;
 }

reachable.c

@@ -12,6 +12,7 @@
 #include "packfile.h"
 #include "worktree.h"
 #include "object-store.h"
+#include "pack-bitmap.h"
 
 struct connectivity_progress {
 	struct progress *progress;
@@ -158,10 +159,44 @@ int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
 				      FOR_EACH_OBJECT_LOCAL_ONLY);
 }
 
+static void *lookup_object_by_type(struct repository *r,
+				   const struct object_id *oid,
+				   enum object_type type)
+{
+	switch (type) {
+	case OBJ_COMMIT:
+		return lookup_commit(r, oid);
+	case OBJ_TREE:
+		return lookup_tree(r, oid);
+	case OBJ_TAG:
+		return lookup_tag(r, oid);
+	case OBJ_BLOB:
+		return lookup_blob(r, oid);
+	default:
+		die("BUG: unknown object type %d", type);
+	}
+}
+
+static int mark_object_seen(const struct object_id *oid,
+			     enum object_type type,
+			     int exclude,
+			     uint32_t name_hash,
+			     struct packed_git *found_pack,
+			     off_t found_offset)
+{
+	struct object *obj = lookup_object_by_type(the_repository, oid, type);
+	if (!obj)
+		die("unable to create object '%s'", oid_to_hex(oid));
+
+	obj->flags |= SEEN;
+	return 0;
+}
+
 void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 			    timestamp_t mark_recent, struct progress *progress)
 {
 	struct connectivity_progress cp;
+	struct bitmap_index *bitmap_git;
 
 	/*
 	 * Set up revision parsing, and mark us as being interested
@@ -188,6 +223,13 @@ void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 	cp.progress = progress;
 	cp.count = 0;
 
+	bitmap_git = prepare_bitmap_walk(revs);
+	if (bitmap_git) {
+		traverse_bitmap_commit_list(bitmap_git, mark_object_seen);
+		free_bitmap_index(bitmap_git);
+		return;
+	}
+
 	/*
 	 * Set up the revision walk - this will move all commits
 	 * from the pending list to the commit walking list.

t/perf/p5304-prune.sh

@@ -0,0 +1,35 @@
+#!/bin/sh
+
+test_description='performance tests of prune'
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+test_expect_success 'remove reachable loose objects' '
+	git repack -ad
+'
+
+test_expect_success 'remove unreachable loose objects' '
+	git prune
+'
+
+test_expect_success 'confirm there are no loose objects' '
+	git count-objects | grep ^0
+'
+
+test_perf 'prune with no objects' '
+	git prune
+'
+
+test_expect_success 'repack with bitmaps' '
+	git repack -adb
+'
+
+# We have to create the object in each trial run, since otherwise
+# runs after the first see no object and just skip the traversal entirely!
+test_perf 'prune with bitmaps' '
+	echo "probably not present in repo" | git hash-object -w --stdin &&
+	git prune
+'
+
+test_done

t/t5304-prune.sh

@@ -118,10 +118,10 @@ test_expect_success 'prune: do not prune detached HEAD with no reflog' '
 
 test_expect_success 'prune: prune former HEAD after checking out branch' '
 
-	head_sha1=$(git rev-parse HEAD) &&
+	head_oid=$(git rev-parse HEAD) &&
 	git checkout --quiet master &&
 	git prune -v >prune_actual &&
-	grep "$head_sha1" prune_actual
+	grep "$head_oid" prune_actual
 
 '
 
@@ -265,15 +265,27 @@ EOF
 '
 
 test_expect_success 'prune .git/shallow' '
-	SHA1=$(echo hi|git commit-tree HEAD^{tree}) &&
-	echo $SHA1 >.git/shallow &&
+	oid=$(echo hi|git commit-tree HEAD^{tree}) &&
+	echo $oid >.git/shallow &&
 	git prune --dry-run >out &&
-	grep $SHA1 .git/shallow &&
-	grep $SHA1 out &&
+	grep $oid .git/shallow &&
+	grep $oid out &&
 	git prune &&
 	test_path_is_missing .git/shallow
 '
 
+test_expect_success 'prune .git/shallow when there are no loose objects' '
+	oid=$(echo hi|git commit-tree HEAD^{tree}) &&
+	echo $oid >.git/shallow &&
+	git update-ref refs/heads/shallow-tip $oid &&
+	git repack -ad &&
+	# verify assumption that all loose objects are gone
+	git count-objects | grep ^0 &&
+	git prune &&
+	echo $oid >expect &&
+	test_cmp expect .git/shallow
+'
+
 test_expect_success 'prune: handle alternate object database' '
 	test_create_repo A &&
 	git -C A commit --allow-empty -m "initial commit" &&
@@ -314,8 +326,8 @@ test_expect_success 'prune: handle HEAD reflog in multiple worktrees' '
 		git reset --hard HEAD^
 	) &&
 	git prune --expire=now &&
-	SHA1=`git hash-object expected` &&
-	git -C third-worktree show "$SHA1" >actual &&
+	oid=`git hash-object expected` &&
+	git -C third-worktree show "$oid" >actual &&
 	test_cmp expected actual
 '