Merge branch 'sb/submodule-parallel-update'

A major part of "git submodule update" has been ported to C to take
advantage of the recently added framework to run download tasks in
parallel.

* sb/submodule-parallel-update:
  clone: allow an explicit argument for parallel submodule clones
  submodule update: expose parallelism to the user
  submodule helper: remove double 'fatal: ' prefix
  git submodule update: have a dedicated helper for cloning
  run_processes_parallel: rename parameters for the callbacks
  run_processes_parallel: treat output of children as byte array
  submodule update: direct error message to stderr
  fetching submodules: respect `submodule.fetchJobs` config option
  submodule-config: drop check against NULL
  submodule-config: keep update strategy around

Documentation/config.txt

@@ -2738,6 +2738,12 @@ submodule.<name>.ignore::
 	"--ignore-submodules" option. The 'git submodule' commands are not
 	affected by this setting.
 
+submodule.fetchJobs::
+	Specifies how many submodules are fetched/cloned at the same time.
+	A positive integer allows up to that number of submodules fetched
+	in parallel. A value of 0 will give some reasonable default.
+	If unset, it defaults to 1.
+
 tag.sort::
 	This variable controls the sort ordering of tags when displayed by
 	linkgit:git-tag[1]. Without the "--sort=<value>" option provided, the

Documentation/git-clone.txt

@@ -14,7 +14,7 @@ SYNOPSIS
 	  [-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
 	  [--dissociate] [--separate-git-dir <git dir>]
 	  [--depth <depth>] [--[no-]single-branch]
-	  [--recursive | --recurse-submodules] [--] <repository>
+	  [--recursive | --recurse-submodules] [--jobs <n>] [--] <repository>
 	  [<directory>]
 
 DESCRIPTION
@@ -219,6 +219,10 @@ objects from the source repository into a pack in the cloned repository.
 	The result is Git repository can be separated from working
 	tree.
 
+-j <n>::
+--jobs <n>::
+	The number of submodules fetched at the same time.
+	Defaults to the `submodule.fetchJobs` option.
 
 <repository>::
 	The (possibly remote) repository to clone from.  See the

Documentation/git-submodule.txt

@@ -16,7 +16,7 @@ SYNOPSIS
 'git submodule' [--quiet] deinit [-f|--force] [--] <path>...
 'git submodule' [--quiet] update [--init] [--remote] [-N|--no-fetch]
 	      [-f|--force] [--rebase|--merge] [--reference <repository>]
-	      [--depth <depth>] [--recursive] [--] [<path>...]
+	      [--depth <depth>] [--recursive] [--jobs <n>] [--] [<path>...]
 'git submodule' [--quiet] summary [--cached|--files] [(-n|--summary-limit) <n>]
 	      [commit] [--] [<path>...]
 'git submodule' [--quiet] foreach [--recursive] <command>
@@ -377,6 +377,11 @@ for linkgit:git-clone[1]'s `--reference` and `--shared` options carefully.
 	clone with a history truncated to the specified number of revisions.
 	See linkgit:git-clone[1]
 
+-j <n>::
+--jobs <n>::
+	This option is only valid for the update command.
+	Clone new submodules in parallel with as many jobs.
+	Defaults to the `submodule.fetchJobs` option.
 
 <path>...::
 	Paths to submodule(s). When specified this will restrict the command

builtin/clone.c

@@ -51,6 +51,7 @@ static enum transport_family family;
 static struct string_list option_config;
 static struct string_list option_reference;
 static int option_dissociate;
+static int max_jobs = -1;
 
 static struct option builtin_clone_options[] = {
 	OPT__VERBOSITY(&option_verbosity),
@@ -73,6 +74,8 @@ static struct option builtin_clone_options[] = {
 		    N_("initialize submodules in the clone")),
 	OPT_BOOL(0, "recurse-submodules", &option_recursive,
 		    N_("initialize submodules in the clone")),
+	OPT_INTEGER('j', "jobs", &max_jobs,
+		    N_("number of submodules cloned in parallel")),
 	OPT_STRING(0, "template", &option_template, N_("template-directory"),
 		   N_("directory from which templates will be used")),
 	OPT_STRING_LIST(0, "reference", &option_reference, N_("repo"),
@@ -100,10 +103,6 @@ static struct option builtin_clone_options[] = {
 	OPT_END()
 };
 
-static const char *argv_submodule[] = {
-	"submodule", "update", "--init", "--recursive", NULL
-};
-
 static const char *get_repo_path_1(struct strbuf *path, int *is_bundle)
 {
 	static char *suffix[] = { "/.git", "", ".git/.git", ".git" };
@@ -732,8 +731,16 @@ static int checkout(void)
 	err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),
 			   sha1_to_hex(sha1), "1", NULL);
 
-	if (!err && option_recursive)
-		err = run_command_v_opt(argv_submodule, RUN_GIT_CMD);
+	if (!err && option_recursive) {
+		struct argv_array args = ARGV_ARRAY_INIT;
+		argv_array_pushl(&args, "submodule", "update", "--init", "--recursive", NULL);
+
+		if (max_jobs != -1)
+			argv_array_pushf(&args, "--jobs=%d", max_jobs);
+
+		err = run_command_v_opt(args.argv, RUN_GIT_CMD);
+		argv_array_clear(&args);
+	}
 
 	return err;
 }

builtin/fetch.c

@@ -37,7 +37,7 @@ static int prune = -1; /* unspecified */
 static int all, append, dry_run, force, keep, multiple, update_head_ok, verbosity;
 static int progress = -1, recurse_submodules = RECURSE_SUBMODULES_DEFAULT;
 static int tags = TAGS_DEFAULT, unshallow, update_shallow;
-static int max_children = 1;
+static int max_children = -1;
 static enum transport_family family;
 static const char *depth;
 static const char *upload_pack;

builtin/submodule--helper.c

@@ -249,6 +249,257 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 	return 0;
 }
 
+struct submodule_update_clone {
+	/* index into 'list', the list of submodules to look into for cloning */
+	int current;
+	struct module_list list;
+	unsigned warn_if_uninitialized : 1;
+
+	/* update parameter passed via commandline */
+	struct submodule_update_strategy update;
+
+	/* configuration parameters which are passed on to the children */
+	int quiet;
+	const char *reference;
+	const char *depth;
+	const char *recursive_prefix;
+	const char *prefix;
+
+	/* Machine-readable status lines to be consumed by git-submodule.sh */
+	struct string_list projectlines;
+
+	/* If we want to stop as fast as possible and return an error */
+	unsigned quickstop : 1;
+};
+#define SUBMODULE_UPDATE_CLONE_INIT {0, MODULE_LIST_INIT, 0, \
+	SUBMODULE_UPDATE_STRATEGY_INIT, 0, NULL, NULL, NULL, NULL, \
+	STRING_LIST_INIT_DUP, 0}
+
+/**
+ * Determine whether 'ce' needs to be cloned. If so, prepare the 'child' to
+ * run the clone. Returns 1 if 'ce' needs to be cloned, 0 otherwise.
+ */
+static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
+					   struct child_process *child,
+					   struct submodule_update_clone *suc,
+					   struct strbuf *out)
+{
+	const struct submodule *sub = NULL;
+	struct strbuf displaypath_sb = STRBUF_INIT;
+	struct strbuf sb = STRBUF_INIT;
+	const char *displaypath = NULL;
+	char *url = NULL;
+	int needs_cloning = 0;
+
+	if (ce_stage(ce)) {
+		if (suc->recursive_prefix)
+			strbuf_addf(&sb, "%s/%s", suc->recursive_prefix, ce->name);
+		else
+			strbuf_addf(&sb, "%s", ce->name);
+		strbuf_addf(out, _("Skipping unmerged submodule %s"), sb.buf);
+		strbuf_addch(out, '\n');
+		goto cleanup;
+	}
+
+	sub = submodule_from_path(null_sha1, ce->name);
+
+	if (suc->recursive_prefix)
+		displaypath = relative_path(suc->recursive_prefix,
+					    ce->name, &displaypath_sb);
+	else
+		displaypath = ce->name;
+
+	if (suc->update.type == SM_UPDATE_NONE
+	    || (suc->update.type == SM_UPDATE_UNSPECIFIED
+		&& sub->update_strategy.type == SM_UPDATE_NONE)) {
+		strbuf_addf(out, _("Skipping submodule '%s'"), displaypath);
+		strbuf_addch(out, '\n');
+		goto cleanup;
+	}
+
+	/*
+	 * Looking up the url in .git/config.
+	 * We must not fall back to .gitmodules as we only want
+	 * to process configured submodules.
+	 */
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "submodule.%s.url", sub->name);
+	git_config_get_string(sb.buf, &url);
+	if (!url) {
+		/*
+		 * Only mention uninitialized submodules when their
+		 * path have been specified
+		 */
+		if (suc->warn_if_uninitialized) {
+			strbuf_addf(out,
+				_("Submodule path '%s' not initialized"),
+				displaypath);
+			strbuf_addch(out, '\n');
+			strbuf_addstr(out,
+				_("Maybe you want to use 'update --init'?"));
+			strbuf_addch(out, '\n');
+		}
+		goto cleanup;
+	}
+
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s/.git", ce->name);
+	needs_cloning = !file_exists(sb.buf);
+
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%06o %s %d %d\t%s\n", ce->ce_mode,
+			sha1_to_hex(ce->sha1), ce_stage(ce),
+			needs_cloning, ce->name);
+	string_list_append(&suc->projectlines, sb.buf);
+
+	if (!needs_cloning)
+		goto cleanup;
+
+	child->git_cmd = 1;
+	child->no_stdin = 1;
+	child->stdout_to_stderr = 1;
+	child->err = -1;
+	argv_array_push(&child->args, "submodule--helper");
+	argv_array_push(&child->args, "clone");
+	if (suc->quiet)
+		argv_array_push(&child->args, "--quiet");
+	if (suc->prefix)
+		argv_array_pushl(&child->args, "--prefix", suc->prefix, NULL);
+	argv_array_pushl(&child->args, "--path", sub->path, NULL);
+	argv_array_pushl(&child->args, "--name", sub->name, NULL);
+	argv_array_pushl(&child->args, "--url", url, NULL);
+	if (suc->reference)
+		argv_array_push(&child->args, suc->reference);
+	if (suc->depth)
+		argv_array_push(&child->args, suc->depth);
+
+cleanup:
+	free(url);
+	strbuf_reset(&displaypath_sb);
+	strbuf_reset(&sb);
+
+	return needs_cloning;
+}
+
+static int update_clone_get_next_task(struct child_process *child,
+				      struct strbuf *err,
+				      void *suc_cb,
+				      void **void_task_cb)
+{
+	struct submodule_update_clone *suc = suc_cb;
+
+	for (; suc->current < suc->list.nr; suc->current++) {
+		const struct cache_entry *ce = suc->list.entries[suc->current];
+		if (prepare_to_clone_next_submodule(ce, child, suc, err)) {
+			suc->current++;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int update_clone_start_failure(struct strbuf *err,
+				      void *suc_cb,
+				      void *void_task_cb)
+{
+	struct submodule_update_clone *suc = suc_cb;
+	suc->quickstop = 1;
+	return 1;
+}
+
+static int update_clone_task_finished(int result,
+				      struct strbuf *err,
+				      void *suc_cb,
+				      void *void_task_cb)
+{
+	struct submodule_update_clone *suc = suc_cb;
+
+	if (!result)
+		return 0;
+
+	suc->quickstop = 1;
+	return 1;
+}
+
+static int update_clone(int argc, const char **argv, const char *prefix)
+{
+	const char *update = NULL;
+	int max_jobs = -1;
+	struct string_list_item *item;
+	struct pathspec pathspec;
+	struct submodule_update_clone suc = SUBMODULE_UPDATE_CLONE_INIT;
+
+	struct option module_update_clone_options[] = {
+		OPT_STRING(0, "prefix", &prefix,
+			   N_("path"),
+			   N_("path into the working tree")),
+		OPT_STRING(0, "recursive-prefix", &suc.recursive_prefix,
+			   N_("path"),
+			   N_("path into the working tree, across nested "
+			      "submodule boundaries")),
+		OPT_STRING(0, "update", &update,
+			   N_("string"),
+			   N_("rebase, merge, checkout or none")),
+		OPT_STRING(0, "reference", &suc.reference, N_("repo"),
+			   N_("reference repository")),
+		OPT_STRING(0, "depth", &suc.depth, "<depth>",
+			   N_("Create a shallow clone truncated to the "
+			      "specified number of revisions")),
+		OPT_INTEGER('j', "jobs", &max_jobs,
+			    N_("parallel jobs")),
+		OPT__QUIET(&suc.quiet, N_("don't print cloning progress")),
+		OPT_END()
+	};
+
+	const char *const git_submodule_helper_usage[] = {
+		N_("git submodule--helper update_clone [--prefix=<path>] [<path>...]"),
+		NULL
+	};
+	suc.prefix = prefix;
+
+	argc = parse_options(argc, argv, prefix, module_update_clone_options,
+			     git_submodule_helper_usage, 0);
+
+	if (update)
+		if (parse_submodule_update_strategy(update, &suc.update) < 0)
+			die(_("bad value for update parameter"));
+
+	if (module_list_compute(argc, argv, prefix, &pathspec, &suc.list) < 0)
+		return 1;
+
+	if (pathspec.nr)
+		suc.warn_if_uninitialized = 1;
+
+	/* Overlay the parsed .gitmodules file with .git/config */
+	gitmodules_config();
+	git_config(submodule_config, NULL);
+
+	if (max_jobs < 0)
+		max_jobs = parallel_submodules();
+
+	run_processes_parallel(max_jobs,
+			       update_clone_get_next_task,
+			       update_clone_start_failure,
+			       update_clone_task_finished,
+			       &suc);
+
+	/*
+	 * We saved the output and put it out all at once now.
+	 * That means:
+	 * - the listener does not have to interleave their (checkout)
+	 *   work with our fetching.  The writes involved in a
+	 *   checkout involve more straightforward sequential I/O.
+	 * - the listener can avoid doing any work if fetching failed.
+	 */
+	if (suc.quickstop)
+		return 1;
+
+	for_each_string_list_item(item, &suc.projectlines)
+		utf8_fprintf(stdout, "%s", item->string);
+
+	return 0;
+}
+
 struct cmd_struct {
 	const char *cmd;
 	int (*fn)(int, const char **, const char *);
@@ -258,19 +509,20 @@ static struct cmd_struct commands[] = {
 	{"list", module_list},
 	{"name", module_name},
 	{"clone", module_clone},
+	{"update-clone", update_clone}
 };
 
 int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
 {
 	int i;
 	if (argc < 2)
-		die(_("fatal: submodule--helper subcommand must be "
+		die(_("submodule--helper subcommand must be "
 		      "called with a subcommand"));
 
 	for (i = 0; i < ARRAY_SIZE(commands); i++)
 		if (!strcmp(argv[1], commands[i].cmd))
 			return commands[i].fn(argc - 1, argv + 1, prefix);
 
-	die(_("fatal: '%s' is not a valid submodule--helper "
+	die(_("'%s' is not a valid submodule--helper "
 	      "subcommand"), argv[1]);
 }

git-submodule.sh

@@ -663,6 +663,14 @@ cmd_update()
 		--depth=*)
 			depth=$1
 			;;
+		-j|--jobs)
+			case "$2" in '') usage ;; esac
+			jobs="--jobs=$2"
+			shift
+			;;
+		--jobs=*)
+			jobs=$1
+			;;
 		--)
 			shift
 			break
@@ -682,17 +690,21 @@ cmd_update()
 		cmd_init "--" "$@" || return
 	fi
 
-	cloned_modules=
-	git submodule--helper list --prefix "$wt_prefix" "$@" | {
+	{
+	git submodule--helper update-clone ${GIT_QUIET:+--quiet} \
+		${wt_prefix:+--prefix "$wt_prefix"} \
+		${prefix:+--recursive-prefix "$prefix"} \
+		${update:+--update "$update"} \
+		${reference:+--reference "$reference"} \
+		${depth:+--depth "$depth"} \
+		${jobs:+$jobs} \
+		"$@" || echo "#unmatched"
+	} | {
 	err=
-	while read mode sha1 stage sm_path
+	while read mode sha1 stage just_cloned sm_path
 	do
 		die_if_unmatched "$mode"
-		if test "$stage" = U
-		then
-			echo >&2 "Skipping unmerged submodule $prefix$sm_path"
-			continue
-		fi
+
 		name=$(git submodule--helper name "$sm_path") || exit
 		url=$(git config submodule."$name".url)
 		branch=$(get_submodule_config "$name" branch master)
@@ -709,27 +721,10 @@ cmd_update()
 
 		displaypath=$(relative_path "$prefix$sm_path")
 
-		if test "$update_module" = "none"
+		if test $just_cloned -eq 1
 		then
-			echo "Skipping submodule '$displaypath'"
-			continue
-		fi
-
-		if test -z "$url"
-		then
-			# Only mention uninitialized submodules when its
-			# path have been specified
-			test "$#" != "0" &&
-			say "$(eval_gettext "Submodule path '\$displaypath' not initialized
-Maybe you want to use 'update --init'?")"
-			continue
-		fi
-
-		if ! test -d "$sm_path"/.git && ! test -f "$sm_path"/.git
-		then
-			git submodule--helper clone ${GIT_QUIET:+--quiet} --prefix "$prefix" --path "$sm_path" --name "$name" --url "$url" "$reference" "$depth" || exit
-			cloned_modules="$cloned_modules;$name"
 			subsha1=
+			update_module=checkout
 		else
 			subsha1=$(clear_local_git_env; cd "$sm_path" &&
 				git rev-parse --verify HEAD) ||
@@ -774,13 +769,6 @@ Maybe you want to use 'update --init'?")"
 				die "$(eval_gettext "Fetched in submodule path '\$displaypath', but it did not contain $sha1. Direct fetching of that commit failed.")"
 			fi
 
-			# Is this something we just cloned?
-			case ";$cloned_modules;" in
-			*";$name;"*)
-				# then there is no local change to integrate
-				update_module=checkout ;;
-			esac
-
 			must_die_on_failure=
 			case "$update_module" in
 			checkout)

run-command.c

@@ -902,7 +902,7 @@ struct parallel_processes {
 	struct strbuf buffered_output; /* of finished children */
 };
 
-static int default_start_failure(struct strbuf *err,
+static int default_start_failure(struct strbuf *out,
 				 void *pp_cb,
 				 void *pp_task_cb)
 {
@@ -910,7 +910,7 @@ static int default_start_failure(struct strbuf *err,
 }
 
 static int default_task_finished(int result,
-				 struct strbuf *err,
+				 struct strbuf *out,
 				 void *pp_cb,
 				 void *pp_task_cb)
 {
@@ -994,7 +994,7 @@ static void pp_cleanup(struct parallel_processes *pp)
 	 * When get_next_task added messages to the buffer in its last
 	 * iteration, the buffered output is non empty.
 	 */
-	fputs(pp->buffered_output.buf, stderr);
+	strbuf_write(&pp->buffered_output, stderr);
 	strbuf_release(&pp->buffered_output);
 
 	sigchain_pop_common();
@@ -1079,7 +1079,7 @@ static void pp_output(struct parallel_processes *pp)
 	int i = pp->output_owner;
 	if (pp->children[i].state == GIT_CP_WORKING &&
 	    pp->children[i].err.len) {
-		fputs(pp->children[i].err.buf, stderr);
+		strbuf_write(&pp->children[i].err, stderr);
 		strbuf_reset(&pp->children[i].err);
 	}
 }
@@ -1117,11 +1117,11 @@ static int pp_collect_finished(struct parallel_processes *pp)
 			strbuf_addbuf(&pp->buffered_output, &pp->children[i].err);
 			strbuf_reset(&pp->children[i].err);
 		} else {
-			fputs(pp->children[i].err.buf, stderr);
+			strbuf_write(&pp->children[i].err, stderr);
 			strbuf_reset(&pp->children[i].err);
 
 			/* Output all other finished child processes */
-			fputs(pp->buffered_output.buf, stderr);
+			strbuf_write(&pp->buffered_output, stderr);
 			strbuf_reset(&pp->buffered_output);
 
 			/*

run-command.h

@@ -140,7 +140,7 @@ void NORETURN async_exit(int code);
  * return the negative signal number.
  */
 typedef int (*get_next_task_fn)(struct child_process *cp,
-				struct strbuf *err,
+				struct strbuf *out,
 				void *pp_cb,
 				void **pp_task_cb);
 
@@ -149,7 +149,7 @@ typedef int (*get_next_task_fn)(struct child_process *cp,
  * a new process.
  *
  * You must not write to stdout or stderr in this function. Add your
- * message to the strbuf err instead, which will be printed without
+ * message to the strbuf out instead, which will be printed without
  * messing up the output of the other parallel processes.
  *
  * pp_cb is the callback cookie as passed into run_processes_parallel,
@@ -159,7 +159,7 @@ typedef int (*get_next_task_fn)(struct child_process *cp,
  * To send a signal to other child processes for abortion, return
  * the negative signal number.
  */
-typedef int (*start_failure_fn)(struct strbuf *err,
+typedef int (*start_failure_fn)(struct strbuf *out,
 				void *pp_cb,
 				void *pp_task_cb);
 
@@ -167,7 +167,7 @@ typedef int (*start_failure_fn)(struct strbuf *err,
  * This callback is called on every child process that finished processing.
  *
  * You must not write to stdout or stderr in this function. Add your
- * message to the strbuf err instead, which will be printed without
+ * message to the strbuf out instead, which will be printed without
  * messing up the output of the other parallel processes.
  *
  * pp_cb is the callback cookie as passed into run_processes_parallel,
@@ -178,7 +178,7 @@ typedef int (*start_failure_fn)(struct strbuf *err,
  * the negative signal number.
  */
 typedef int (*task_finished_fn)(int result,
-				struct strbuf *err,
+				struct strbuf *out,
 				void *pp_cb,
 				void *pp_task_cb);
 

strbuf.c

@@ -395,6 +395,12 @@ ssize_t strbuf_read_once(struct strbuf *sb, int fd, size_t hint)
 	return cnt;
 }
 
+ssize_t strbuf_write(struct strbuf *sb, FILE *f)
+{
+	return sb->len ? fwrite(sb->buf, 1, sb->len, f) : 0;
+}
+
+
 #define STRBUF_MAXLINK (2*PATH_MAX)
 
 int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint)

strbuf.h

@@ -386,6 +386,12 @@ extern ssize_t strbuf_read_file(struct strbuf *sb, const char *path, size_t hint
  */
 extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint);
 
+/**
+ * Write the whole content of the strbuf to the stream not stopping at
+ * NUL bytes.
+ */
+extern ssize_t strbuf_write(struct strbuf *sb, FILE *stream);
+
 /**
  * Read a line from a FILE *, overwriting the existing contents of
  * the strbuf.  The strbuf_getline*() family of functions share

submodule-config.c

@@ -59,6 +59,7 @@ static void free_one_config(struct submodule_entry *entry)
 {
 	free((void *) entry->config->path);
 	free((void *) entry->config->name);
+	free((void *) entry->config->update_strategy.command);
 	free(entry->config);
 }
 
@@ -194,6 +195,8 @@ static struct submodule *lookup_or_create_by_name(struct submodule_cache *cache,
 
 	submodule->path = NULL;
 	submodule->url = NULL;
+	submodule->update_strategy.type = SM_UPDATE_UNSPECIFIED;
+	submodule->update_strategy.command = NULL;
 	submodule->fetch_recurse = RECURSE_SUBMODULES_NONE;
 	submodule->ignore = NULL;
 
@@ -293,7 +296,7 @@ static int parse_config(const char *var, const char *value, void *data)
 	if (!strcmp(item.buf, "path")) {
 		if (!value)
 			ret = config_error_nonbool(var);
-		else if (!me->overwrite && submodule->path != NULL)
+		else if (!me->overwrite && submodule->path)
 			warn_multiple_config(me->commit_sha1, submodule->name,
 					"path");
 		else {
@@ -317,7 +320,7 @@ static int parse_config(const char *var, const char *value, void *data)
 	} else if (!strcmp(item.buf, "ignore")) {
 		if (!value)
 			ret = config_error_nonbool(var);
-		else if (!me->overwrite && submodule->ignore != NULL)
+		else if (!me->overwrite && submodule->ignore)
 			warn_multiple_config(me->commit_sha1, submodule->name,
 					"ignore");
 		else if (strcmp(value, "untracked") &&
@@ -333,13 +336,23 @@ static int parse_config(const char *var, const char *value, void *data)
 	} else if (!strcmp(item.buf, "url")) {
 		if (!value) {
 			ret = config_error_nonbool(var);
-		} else if (!me->overwrite && submodule->url != NULL) {
+		} else if (!me->overwrite && submodule->url) {
 			warn_multiple_config(me->commit_sha1, submodule->name,
 					"url");
 		} else {
 			free((void *) submodule->url);
 			submodule->url = xstrdup(value);
 		}
+	} else if (!strcmp(item.buf, "update")) {
+		if (!value)
+			ret = config_error_nonbool(var);
+		else if (!me->overwrite &&
+			 submodule->update_strategy.type != SM_UPDATE_UNSPECIFIED)
+			warn_multiple_config(me->commit_sha1, submodule->name,
+					     "update");
+		else if (parse_submodule_update_strategy(value,
+			 &submodule->update_strategy) < 0)
+				die(_("invalid value for %s"), var);
 	}
 
 	strbuf_release(&name);

submodule-config.h

@@ -2,6 +2,7 @@
 #define SUBMODULE_CONFIG_CACHE_H
 
 #include "hashmap.h"
+#include "submodule.h"
 #include "strbuf.h"
 
 /*
@@ -14,6 +15,7 @@ struct submodule {
 	const char *url;
 	int fetch_recurse;
 	const char *ignore;
+	struct submodule_update_strategy update_strategy;
 	/* the sha1 blob id of the responsible .gitmodules file */
 	unsigned char gitmodules_sha1[20];
 };

submodule.c

@@ -15,6 +15,7 @@
 #include "thread-utils.h"
 
 static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
+static int parallel_jobs = 1;
 static struct string_list changed_submodule_paths;
 static int initialized_fetch_ref_tips;
 static struct sha1_array ref_tips_before_fetch;
@@ -169,7 +170,12 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt,
 
 int submodule_config(const char *var, const char *value, void *cb)
 {
-	if (starts_with(var, "submodule."))
+	if (!strcmp(var, "submodule.fetchjobs")) {
+		parallel_jobs = git_config_int(var, value);
+		if (parallel_jobs < 0)
+			die(_("negative values not allowed for submodule.fetchJobs"));
+		return 0;
+	} else if (starts_with(var, "submodule."))
 		return parse_submodule_config_option(var, value);
 	else if (!strcmp(var, "fetch.recursesubmodules")) {
 		config_fetch_recurse_submodules = parse_fetch_recurse_submodules_arg(var, value);
@@ -210,6 +216,27 @@ void gitmodules_config(void)
 	}
 }
 
+int parse_submodule_update_strategy(const char *value,
+		struct submodule_update_strategy *dst)
+{
+	free((void*)dst->command);
+	dst->command = NULL;
+	if (!strcmp(value, "none"))
+		dst->type = SM_UPDATE_NONE;
+	else if (!strcmp(value, "checkout"))
+		dst->type = SM_UPDATE_CHECKOUT;
+	else if (!strcmp(value, "rebase"))
+		dst->type = SM_UPDATE_REBASE;
+	else if (!strcmp(value, "merge"))
+		dst->type = SM_UPDATE_MERGE;
+	else if (skip_prefix(value, "!", &value)) {
+		dst->type = SM_UPDATE_COMMAND;
+		dst->command = xstrdup(value);
+	} else
+		return -1;
+	return 0;
+}
+
 void handle_ignore_submodules_arg(struct diff_options *diffopt,
 				  const char *arg)
 {
@@ -750,6 +777,9 @@ int fetch_populated_submodules(const struct argv_array *options,
 	argv_array_push(&spf.args, "--recurse-submodules-default");
 	/* default value, "--submodule-prefix" and its value are added later */
 
+	if (max_parallel_jobs < 0)
+		max_parallel_jobs = parallel_jobs;
+
 	calculate_changed_submodule_paths();
 	run_processes_parallel(max_parallel_jobs,
 			       get_next_submodule,
@@ -1094,3 +1124,8 @@ void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir)
 	strbuf_release(&rel_path);
 	free((void *)real_work_tree);
 }
+
+int parallel_submodules(void)
+{
+	return parallel_jobs;
+}

submodule.h

@@ -14,6 +14,21 @@ enum {
 	RECURSE_SUBMODULES_ON = 2
 };
 
+enum submodule_update_type {
+	SM_UPDATE_UNSPECIFIED = 0,
+	SM_UPDATE_CHECKOUT,
+	SM_UPDATE_REBASE,
+	SM_UPDATE_MERGE,
+	SM_UPDATE_NONE,
+	SM_UPDATE_COMMAND
+};
+
+struct submodule_update_strategy {
+	enum submodule_update_type type;
+	const char *command;
+};
+#define SUBMODULE_UPDATE_STRATEGY_INIT {SM_UPDATE_UNSPECIFIED, NULL}
+
 int is_staging_gitmodules_ok(void);
 int update_path_in_gitmodules(const char *oldpath, const char *newpath);
 int remove_path_from_gitmodules(const char *path);
@@ -22,6 +37,8 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt,
 		const char *path);
 int submodule_config(const char *var, const char *value, void *cb);
 void gitmodules_config(void);
+int parse_submodule_update_strategy(const char *value,
+		struct submodule_update_strategy *dst);
 void handle_ignore_submodules_arg(struct diff_options *diffopt, const char *);
 void show_submodule_summary(FILE *f, const char *path,
 		const char *line_prefix,
@@ -42,5 +59,6 @@ int find_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_nam
 		struct string_list *needs_pushing);
 int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_name);
 void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir);
+int parallel_submodules(void);
 
 #endif

t/t5526-fetch-submodules.sh

@@ -471,4 +471,18 @@ test_expect_success "don't fetch submodule when newly recorded commits are alrea
 	test_i18ncmp expect.err actual.err
 '
 
+test_expect_success 'fetching submodules respects parallel settings' '
+	git config fetch.recurseSubmodules true &&
+	(
+		cd downstream &&
+		GIT_TRACE=$(pwd)/trace.out git fetch --jobs 7 &&
+		grep "7 tasks" trace.out &&
+		git config submodule.fetchJobs 8 &&
+		GIT_TRACE=$(pwd)/trace.out git fetch &&
+		grep "8 tasks" trace.out &&
+		GIT_TRACE=$(pwd)/trace.out git fetch --jobs 9 &&
+		grep "9 tasks" trace.out
+	)
+'
+
 test_done

t/t7400-submodule-basic.sh

@@ -462,7 +462,7 @@ test_expect_success 'update --init' '
 	git config --remove-section submodule.example &&
 	test_must_fail git config submodule.example.url &&
 
-	git submodule update init > update.out &&
+	git submodule update init 2> update.out &&
 	cat update.out &&
 	test_i18ngrep "not initialized" update.out &&
 	test_must_fail git rev-parse --resolve-git-dir init/.git &&
@@ -480,7 +480,7 @@ test_expect_success 'update --init from subdirectory' '
 	mkdir -p sub &&
 	(
 		cd sub &&
-		git submodule update ../init >update.out &&
+		git submodule update ../init 2>update.out &&
 		cat update.out &&
 		test_i18ngrep "not initialized" update.out &&
 		test_must_fail git rev-parse --resolve-git-dir ../init/.git &&

t/t7406-submodule-update.sh

@@ -774,4 +774,31 @@ test_expect_success 'submodule update --recursive drops module name before recur
 	 test_i18ngrep "Submodule path .deeper/submodule/subsubmodule.: checked out" actual
 	)
 '
+
+test_expect_success 'submodule update can be run in parallel' '
+	(cd super2 &&
+	 GIT_TRACE=$(pwd)/trace.out git submodule update --jobs 7 &&
+	 grep "7 tasks" trace.out &&
+	 git config submodule.fetchJobs 8 &&
+	 GIT_TRACE=$(pwd)/trace.out git submodule update &&
+	 grep "8 tasks" trace.out &&
+	 GIT_TRACE=$(pwd)/trace.out git submodule update --jobs 9 &&
+	 grep "9 tasks" trace.out
+	)
+'
+
+test_expect_success 'git clone passes the parallel jobs config on to submodules' '
+	test_when_finished "rm -rf super4" &&
+	GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules --jobs 7 . super4 &&
+	grep "7 tasks" trace.out &&
+	rm -rf super4 &&
+	git config --global submodule.fetchJobs 8 &&
+	GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules . super4 &&
+	grep "8 tasks" trace.out &&
+	rm -rf super4 &&
+	GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules --jobs 9 . super4 &&
+	grep "9 tasks" trace.out &&
+	rm -rf super4
+'
+
 test_done