fetching submodules: respect submodule.fetchJobs config option

This allows to configure fetching and updating in parallel
without having the command line option.

This moved the responsibility to determine how many parallel processes
to start from builtin/fetch to submodule.c as we need a way to communicate
"The user did not specify the number of parallel processes in the command
line options" in the builtin fetch. The submodule code takes care of
the precedence (CLI > config > default).

Reviewed-by: Jonathan Nieder <[email protected]>
Signed-off-by: Stefan Beller <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: stefanbeller

Documentation/config.txt

@@ -2646,6 +2646,12 @@ 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

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 const char *depth;
 static const char *upload_pack;
 static struct strbuf default_rla = STRBUF_INIT;

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);
@@ -771,6 +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,
@@ -1117,3 +1126,8 @@ 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

@@ -26,6 +26,7 @@ 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);
@@ -57,5 +58,6 @@ 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