submodule update: expose parallelism to the user

Expose possible parallelism either via the "--jobs" CLI parameter or
the "submodule.fetchJobs" setting.

By having the variable initialized to -1, we make sure 0 can be passed
into the parallel processing machine, which will then pick as many parallel
workers as there are CPUs.

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

Author: stefanbeller

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/submodule--helper.c

@@ -430,6 +430,7 @@ static int update_clone_task_finished(int result,
 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;
@@ -450,6 +451,8 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 		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()
 	};
@@ -477,7 +480,10 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 	gitmodules_config();
 	git_config(submodule_config, NULL);
 
-	run_processes_parallel(1,
+	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,

git-submodule.sh

@@ -645,6 +645,14 @@ cmd_update()
 		--depth=*)
 			depth=$1
 			;;
+		-j|--jobs)
+			case "$2" in '') usage ;; esac
+			jobs="--jobs=$2"
+			shift
+			;;
+		--jobs=*)
+			jobs=$1
+			;;
 		--)
 			shift
 			break
@@ -671,6 +679,7 @@ cmd_update()
 		${update:+--update "$update"} \
 		${reference:+--reference "$reference"} \
 		${depth:+--depth "$depth"} \
+		${jobs:+$jobs} \
 		"$@" || echo "#unmatched"
 	} | {
 	err=

t/t7406-submodule-update.sh

@@ -774,4 +774,16 @@ 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_done