maintenance: care about gvfs.sharedCache config

For Scalar and VFS for Git, we use an alternate as a shared object
cache. We need to enable the maintenance builtin to work on that
shared object cache, especially in the background.

'scalar run <task>' would set GIT_OBJECT_DIRECTORY to handle this.

We set GIT_OBJECT_DIRECTORY based on the gvfs.sharedCache config,
but we also need the checks in pack_loose() to look at that object
directory instead of the current ODB's.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>

Author: derrickstolee

builtin/gc.c

@@ -1338,21 +1338,37 @@ static int write_loose_object_to_stdin(const struct object_id *oid,
 	return ++(d->count) > d->batch_size;
 }
 
+static const char *shared_object_dir = NULL;
+
 static int pack_loose(struct maintenance_run_opts *opts)
 {
 	struct repository *r = the_repository;
 	int result = 0;
 	struct write_loose_object_data data;
 	struct child_process pack_proc = CHILD_PROCESS_INIT;
+	struct odb_source *prev_source = NULL;
+	const char *object_dir = r->objects->sources->path;
+
+	/* If set, use the shared object directory. */
+	if (shared_object_dir) {
+		prev_source =
+			odb_set_temporary_primary_source(r->objects,
+							 shared_object_dir, 0);
+		object_dir = shared_object_dir;
+	}
 
 	/*
 	 * Do not start pack-objects process
 	 * if there are no loose objects.
 	 */
 	if (!for_each_loose_file_in_source(r->objects->sources,
 					   bail_on_loose,
-					   NULL, NULL, NULL))
+					   NULL, NULL, NULL)) {
+		if (shared_object_dir)
+			odb_restore_primary_source(r->objects, prev_source,
+						   shared_object_dir);
 		return 0;
+	}
 
 	pack_proc.git_cmd = 1;
 
@@ -1361,7 +1377,7 @@ static int pack_loose(struct maintenance_run_opts *opts)
 		strvec_push(&pack_proc.args, "--quiet");
 	else
 		strvec_push(&pack_proc.args, "--no-quiet");
-	strvec_pushf(&pack_proc.args, "%s/pack/loose", r->objects->sources->path);
+	strvec_pushf(&pack_proc.args, "%s/pack/loose", object_dir);
 
 	pack_proc.in = -1;
 
@@ -1373,6 +1389,9 @@ static int pack_loose(struct maintenance_run_opts *opts)
 
 	if (start_command(&pack_proc)) {
 		error(_("failed to start 'git pack-objects' process"));
+		if (shared_object_dir)
+			odb_restore_primary_source(r->objects, prev_source,
+						   shared_object_dir);
 		return 1;
 	}
 
@@ -1400,6 +1419,10 @@ static int pack_loose(struct maintenance_run_opts *opts)
 		result = 1;
 	}
 
+	if (shared_object_dir)
+		odb_restore_primary_source(r->objects, prev_source,
+					   shared_object_dir);
+
 	return result;
 }
 
@@ -1832,11 +1855,12 @@ static int task_option_parse(const struct option *opt,
 }
 
 static int maintenance_run(int argc, const char **argv, const char *prefix,
-			   struct repository *repo UNUSED)
+			   struct repository *repo)
 {
 	struct maintenance_run_opts opts = MAINTENANCE_RUN_OPTS_INIT;
 	struct string_list selected_tasks = STRING_LIST_INIT_DUP;
 	struct gc_config cfg = GC_CONFIG_INIT;
+	const char *tmp_obj_dir = NULL;
 	struct option builtin_maintenance_run_options[] = {
 		OPT_BOOL(0, "auto", &opts.auto_flag,
 			 N_("run tasks based on the state of the repository")),
@@ -1873,6 +1897,17 @@ static int maintenance_run(int argc, const char **argv, const char *prefix,
 		usage_with_options(builtin_maintenance_run_usage,
 				   builtin_maintenance_run_options);
 
+	/*
+	 * To enable the VFS for Git/Scalar shared object cache, use
+	 * the gvfs.sharedcache config option to redirect the
+	 * maintenance to that location.
+	 */
+	if (!repo_config_get_value(repo, "gvfs.sharedcache", &tmp_obj_dir) &&
+	    tmp_obj_dir) {
+		shared_object_dir = xstrdup(tmp_obj_dir);
+		setenv(DB_ENVIRONMENT, shared_object_dir, 1);
+	}
+
 	ret = maintenance_run_tasks(&opts, &cfg);
 
 	string_list_clear(&selected_tasks, 0);

t/t7900-maintenance.sh

@@ -334,6 +334,37 @@ test_expect_success 'maintenance.loose-objects.batchSize' '
 	test_must_be_empty err
 '
 
+test_expect_success 'loose-objects and gvfs.sharedCache' '
+	git init gvfs-worktree &&
+	git init --bare gvfs-shared &&
+	git -C gvfs-worktree config gvfs.sharedCache "$PWD/gvfs-shared/objects" &&
+
+	# Hack to stop maintenance from running during "git commit"
+	echo in use >gvfs-worktree/.git/objects/maintenance.lock &&
+	git -C gvfs-worktree config maintenance.loose-objects.auto 1 &&
+	test_commit -C gvfs-worktree create-loose-object &&
+	rm gvfs-worktree/.git/objects/maintenance.lock &&
+	! ls -l gvfs-shared/objects/??/* &&
+	ls -l gvfs-worktree/.git/objects/??/* >loose-objects &&
+	test_file_not_empty loose-objects &&
+	! ls -l gvfs-shared/objects/pack/*.pack &&
+
+	# move the loose objects into the shared objects as if they had been
+	# fetched via the `gvfs-helper`
+	mv gvfs-worktree/.git/objects/?? gvfs-shared/objects/ &&
+
+	# Run `loose-objects` twice: The first run creates a pack-file
+	# but does not delete loose objects, the second run deletes
+	# loose objects but does not create a pack-file.
+	git -C gvfs-worktree maintenance run --task=loose-objects &&
+	git -C gvfs-worktree maintenance run --task=loose-objects &&
+
+	! ls -l gvfs-worktree/.git/objects/??/* &&
+	! ls -l gvfs-shared/.git/objects/??/* &&
+	ls -l gvfs-shared/objects/pack/*.pack >shared-packs &&
+	test_file_not_empty shared-packs
+'
+
 test_expect_success 'incremental-repack task' '
 	packDir=.git/objects/pack &&
 	for i in $(test_seq 1 5)