submodules: allow parallel fetching, add tests and documentation

This enables the work of the previous patches.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

6 files changed, 40 insertions, 4 deletions

diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt
index 45583d8454..6b109f687a 100644
--- a/Documentation/fetch-options.txt
+++ b/Documentation/fetch-options.txt
@@ -100,6 +100,13 @@ ifndef::git-pull[]
 	reference to a commit that isn't already in the local submodule
 	clone.
 
+-j::
+--jobs=<n>::
+	Number of parallel children to be used for fetching submodules.
+	Each will fetch from different submodules, such that fetching many
+	submodules will be faster. By default submodules will be fetched
+	one at a time.
+
 --no-recurse-submodules::
 	Disable recursive fetching of submodules (this has the same effect as
 	using the '--recurse-submodules=no' option).
diff --git a/builtin/fetch.c b/builtin/fetch.c
index c85f3471d4..586840d761 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -37,6 +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 const char *depth;
 static const char *upload_pack;
 static struct strbuf default_rla = STRBUF_INIT;
@@ -99,6 +100,8 @@ static struct option builtin_fetch_options[] = {
 		    N_("fetch all tags and associated objects"), TAGS_SET),
 	OPT_SET_INT('n', NULL, &tags,
 		    N_("do not fetch all tags (--no-tags)"), TAGS_UNSET),
+	OPT_INTEGER('j', "jobs", &max_children,
+		    N_("number of submodules fetched in parallel")),
 	OPT_BOOL('p', "prune", &prune,
 		 N_("prune remote-tracking branches no longer on remote")),
 	{ OPTION_CALLBACK, 0, "recurse-submodules", NULL, N_("on-demand"),
@@ -1213,7 +1216,8 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		result = fetch_populated_submodules(&options,
 						    submodule_prefix,
 						    recurse_submodules,
-						    verbosity < 0);
+						    verbosity < 0,
+						    max_children);
 		argv_array_clear(&options);
 	}
 
diff --git a/builtin/pull.c b/builtin/pull.c
index 5145fc60a0..9e3c73809f 100644
--- a/builtin/pull.c
+++ b/builtin/pull.c
@@ -95,6 +95,7 @@ static int opt_force;
 static char *opt_tags;
 static char *opt_prune;
 static char *opt_recurse_submodules;
+static char *max_children;
 static int opt_dry_run;
 static char *opt_keep;
 static char *opt_depth;
@@ -178,6 +179,9 @@ static struct option pull_options[] = {
 		N_("on-demand"),
 		N_("control recursive fetching of submodules"),
 		PARSE_OPT_OPTARG),
+	OPT_PASSTHRU('j', "jobs", &max_children, N_("n"),
+		N_("number of submodules pulled in parallel"),
+		PARSE_OPT_OPTARG),
 	OPT_BOOL(0, "dry-run", &opt_dry_run,
 		N_("dry run")),
 	OPT_PASSTHRU('k', "keep", &opt_keep, NULL,
@@ -525,6 +529,8 @@ static int run_fetch(const char *repo, const char **refspecs)
 		argv_array_push(&args, opt_prune);
 	if (opt_recurse_submodules)
 		argv_array_push(&args, opt_recurse_submodules);
+	if (max_children)
+		argv_array_push(&args, max_children);
 	if (opt_dry_run)
 		argv_array_push(&args, "--dry-run");
 	if (opt_keep)
diff --git a/submodule.c b/submodule.c
index 4bc7a45393..b83939c294 100644
--- a/submodule.c
+++ b/submodule.c
@@ -729,10 +729,9 @@ static int fetch_finish(int retvalue, struct child_process *cp,
 
 int fetch_populated_submodules(const struct argv_array *options,
 			       const char *prefix, int command_line_option,
-			       int quiet)
+			       int quiet, int max_parallel_jobs)
 {
 	int i;
-	int max_parallel_jobs = 1;
 	struct submodule_parallel_fetch spf = SPF_INIT;
 
 	spf.work_tree = get_git_work_tree();
diff --git a/submodule.h b/submodule.h
index 5507c3d9a0..cbc000304e 100644
--- a/submodule.h
+++ b/submodule.h
@@ -31,7 +31,7 @@ void set_config_fetch_recurse_submodules(int value);
 void check_for_new_submodule_commits(unsigned char new_sha1[20]);
 int fetch_populated_submodules(const struct argv_array *options,
 			       const char *prefix, int command_line_option,
-			       int quiet);
+			       int quiet, int max_parallel_jobs);
 unsigned is_submodule_modified(const char *path, int ignore_untracked);
 int submodule_uses_gitfile(const char *path);
 int ok_to_remove_submodule(const char *path);
diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh
index 17759b145f..1241146227 100755
--- a/t/t5526-fetch-submodules.sh
+++ b/t/t5526-fetch-submodules.sh
@@ -71,6 +71,17 @@ test_expect_success "fetch --recurse-submodules recurses into submodules" '
 	test_i18ncmp expect.err actual.err
 '
 
+test_expect_success "fetch --recurse-submodules -j2 has the same output behaviour" '
+	add_upstream_commit &&
+	(
+		cd downstream &&
+		GIT_TRACE=$(pwd)/../trace.out git fetch --recurse-submodules -j2 2>../actual.err
+	) &&
+	test_must_be_empty actual.out &&
+	test_i18ncmp expect.err actual.err &&
+	grep "2 tasks" trace.out
+'
+
 test_expect_success "fetch alone only fetches superproject" '
 	add_upstream_commit &&
 	(
@@ -140,6 +151,15 @@ test_expect_success "--quiet propagates to submodules" '
 	! test -s actual.err
 '
 
+test_expect_success "--quiet propagates to parallel submodules" '
+	(
+		cd downstream &&
+		git fetch --recurse-submodules -j 2 --quiet  >../actual.out 2>../actual.err
+	) &&
+	! test -s actual.out &&
+	! test -s actual.err
+'
+
 test_expect_success "--dry-run propagates to submodules" '
 	add_upstream_commit &&
 	(