git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCHv13 5/7] git submodule update: have a dedicated helper for cloning

From
Stefan Beller <sbeller@google.com>
Date
Feb 18, 2016, 23:33 UTC
Message-ID
<1455838398-12379-6-git-send-email-sbeller@google.com>
In-Reply-To
<1455838398-12379-1-git-send-email-sbeller@google.com>

This introduces a new helper function in git submodule--helper which takes care of cloning all submodules, which we want to parallelize eventually.

Some tests (such as empty URL, update_mode=none) are required in the helper to make the decision for cloning. These checks have been moved into the C function as well (no need to repeat them in the shell script).

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/submodule--helper.c | 231 ++++++++++++++++++++++++++++++++++++++++++++
 git-submodule.sh            |  45 +++------
 2 files changed, 242 insertions(+), 34 deletions(-)
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index f4c3eff..7629a41 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -255,6 +255,236 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 	return 0;
 }
 
+struct submodule_update_clone {
+	/* states */
+	int count;
+	int print_unmatched;
+	/* configuration */
+	int quiet;
+	const char *reference;
+	const char *depth;
+	const char *recursive_prefix;
+	const char *prefix;
+	struct module_list list;
+	struct string_list projectlines;
+	struct submodule_update_strategy update;
+	struct pathspec pathspec;
+};
+#define SUBMODULE_UPDATE_CLONE_INIT {0, 0, 0, NULL, NULL, NULL, NULL, MODULE_LIST_INIT, STRING_LIST_INIT_DUP, SUBMODULE_UPDATE_STRATEGY_INIT}
+
+static int update_clone_inspect_next_task(struct child_process *cp,
+					  struct strbuf *err,
+					  struct submodule_update_clone *pp,
+					  void **pp_task_cb,
+					  const struct cache_entry *ce)
+{
+	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 (pp->recursive_prefix)
+			strbuf_addf(err, "Skipping unmerged submodule %s/%s\n",
+				    pp->recursive_prefix, ce->name);
+		else
+			strbuf_addf(err, "Skipping unmerged submodule %s\n",
+				    ce->name);
+		goto cleanup;
+	}
+
+	sub = submodule_from_path(null_sha1, ce->name);
+
+	if (pp->recursive_prefix)
+		displaypath = relative_path(pp->recursive_prefix,
+					    ce->name, &displaypath_sb);
+	else
+		displaypath = ce->name;
+
+	if (pp->update.type == SM_UPDATE_NONE ||
+	    (pp->update.type == SM_UPDATE_UNSPECIFIED &&
+	     sub->update_strategy.type == SM_UPDATE_NONE)) {
+		strbuf_addf(err, "Skipping submodule '%s'\n",
+			    displaypath);
+		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 its
+		 * path have been specified
+		 */
+		if (pp->pathspec.nr)
+			strbuf_addf(err, _("Submodule path '%s' not initialized\n"
+				    "Maybe you want to use 'update --init'?"),
+				    displaypath);
+		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(&pp->projectlines, sb.buf);
+
+	if (needs_cloning) {
+		cp->git_cmd = 1;
+		cp->no_stdin = 1;
+		cp->stdout_to_stderr = 1;
+		cp->err = -1;
+		argv_array_push(&cp->args, "submodule--helper");
+		argv_array_push(&cp->args, "clone");
+		if (pp->quiet)
+			argv_array_push(&cp->args, "--quiet");
+
+		if (pp->prefix)
+			argv_array_pushl(&cp->args, "--prefix", pp->prefix, NULL);
+
+		argv_array_pushl(&cp->args, "--path", sub->path, NULL);
+		argv_array_pushl(&cp->args, "--name", sub->name, NULL);
+		argv_array_pushl(&cp->args, "--url", strdup(url), NULL);
+		if (pp->reference)
+			argv_array_push(&cp->args, pp->reference);
+		if (pp->depth)
+			argv_array_push(&cp->args, pp->depth);
+
+
+	}
+
+cleanup:
+	free(url);
+	strbuf_reset(&displaypath_sb);
+	strbuf_reset(&sb);
+
+	return needs_cloning;
+}
+
+static int update_clone_get_next_task(struct child_process *cp,
+				      struct strbuf *err,
+				      void *pp_cb,
+				      void **pp_task_cb)
+{
+	struct submodule_update_clone *pp = pp_cb;
+
+	for (; pp->count < pp->list.nr; pp->count++) {
+		const struct cache_entry *ce = pp->list.entries[pp->count];
+		if (update_clone_inspect_next_task(cp, err, pp,
+						   pp_task_cb, ce)) {
+			pp->count++;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int update_clone_start_failure(struct child_process *cp,
+				      struct strbuf *err,
+				      void *pp_cb,
+				      void *pp_task_cb)
+{
+	struct submodule_update_clone *pp = pp_cb;
+
+	strbuf_addf(err, "error when starting a child process");
+	pp->print_unmatched = 1;
+
+	return 1;
+}
+
+static int update_clone_task_finished(int result,
+				      struct child_process *cp,
+				      struct strbuf *err,
+				      void *pp_cb,
+				      void *pp_task_cb)
+{
+	struct submodule_update_clone *pp = pp_cb;
+
+	if (!result) {
+		return 0;
+	} else {
+		strbuf_addf(err, "error in one child process");
+		pp->print_unmatched = 1;
+		return 1;
+	}
+}
+
+static int update_clone(int argc, const char **argv, const char *prefix)
+{
+	const char *update = NULL;
+	struct string_list_item *item;
+	struct submodule_update_clone pp = SUBMODULE_UPDATE_CLONE_INIT;
+
+	struct option module_list_options[] = {
+		OPT_STRING(0, "prefix", &prefix,
+			   N_("path"),
+			   N_("path into the working tree")),
+		OPT_STRING(0, "recursive_prefix", &pp.recursive_prefix,
+			   N_("path"),
+			   N_("path into the working tree, across nested "
+			      "submodule boundaries")),
+		OPT_STRING(0, "update", &update,
+			   N_("string"),
+			   N_("update command for submodules")),
+		OPT_STRING(0, "reference", &pp.reference, "<repository>",
+			   N_("Use the local reference repository "
+			      "instead of a full clone")),
+		OPT_STRING(0, "depth", &pp.depth, "<depth>",
+			   N_("Create a shallow clone truncated to the "
+			      "specified number of revisions")),
+		OPT__QUIET(&pp.quiet, N_("do't print cloning progress")),
+		OPT_END()
+	};
+
+	const char *const git_submodule_helper_usage[] = {
+		N_("git submodule--helper list [--prefix=<path>] [<path>...]"),
+		NULL
+	};
+	pp.prefix = prefix;
+
+	argc = parse_options(argc, argv, prefix, module_list_options,
+			     git_submodule_helper_usage, 0);
+
+	if (update)
+		if (parse_submodule_update_strategy(update, &pp.update) < 0)
+			die(_("bad value for update parameter"));
+
+	if (module_list_compute(argc, argv, prefix, &pp.pathspec, &pp.list) < 0) {
+		printf("#unmatched\n");
+		return 1;
+	}
+
+	gitmodules_config();
+	/* Overlay the parsed .gitmodules file with .git/config */
+	git_config(submodule_config, NULL);
+	run_processes_parallel(1, update_clone_get_next_task,
+				  update_clone_start_failure,
+				  update_clone_task_finished,
+				  &pp);
+
+	if (pp.print_unmatched) {
+		printf("#unmatched\n");
+		return 1;
+	}
+
+	for_each_string_list_item(item, &pp.projectlines)
+		utf8_fprintf(stdout, "%s", item->string);
+
+	return 0;
+}
+
 struct cmd_struct {
 	const char *cmd;
 	int (*fn)(int, const char **, const char *);
@@ -264,6 +494,7 @@ 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)
diff --git a/git-submodule.sh b/git-submodule.sh
index 9ee86d4..9f554fb 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -664,17 +664,18 @@ 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"} \
+		"$@" | {
 	err=
-	while read mode sha1 stage sm_path
+	while read mode sha1 stage just_cloned sm_path
 	do
 		die_if_unmatched "$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)
@@ -691,27 +692,10 @@ cmd_update()
 
 		displaypath=$(relative_path "$prefix$sm_path")
 
-		if test "$update_module" = "none"
-		then
-			echo >&2 "Skipping submodule '$displaypath'"
-			continue
-		fi
-
-		if test -z "$url"
-		then
-			# Only mention uninitialized submodules when its
-			# path have been specified
-			test "$#" != "0" &&
-			say >&2 "$(eval_gettext "Submodule path '\$displaypath' not initialized
-Maybe you want to use 'update --init'?")"
-			continue
-		fi
-
-		if ! test -d "$sm_path"/.git && ! test -f "$sm_path"/.git
+		if test $just_cloned -eq 1
 		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 "$sm_path" &&
 				git rev-parse --verify HEAD) ||
@@ -751,13 +735,6 @@ Maybe you want to use 'update --init'?")"
 				die "$(eval_gettext "Unable to fetch in submodule path '\$displaypath'")"
 			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)
-- 
2.7.0.rc0.34.g65aed89
Previous: Stefan BellerNext: Jeff King
Message 6 of 13 in “[PATCHv13 0/7] Expose submodule parallelism to the user”
  1. Stefan BellerFeb 18, 2016
  2. 1/7 submodule-config: keep update strategy aroundStefan Beller, Feb 18, 2016
  3. 2/7 submodule-config: drop check against NULLStefan Beller, Feb 18, 2016
  4. 3/7 fetching submodules: respect `submodule.fetchJobs` config optionStefan Beller, Feb 18, 2016
  5. 4/7 submodule update: direct error message to stderrStefan Beller, Feb 18, 2016
  6. 5/7 git submodule update: have a dedicated helper for cloningStefan Beller, Feb 18, 2016
  7. Jeff KingFeb 19, 2016
  8. Stefan BellerFeb 19, 2016
  9. Eric SunshineFeb 19, 2016
  10. Jeff KingFeb 19, 2016
  11. Stefan BellerFeb 19, 2016
  12. 6/7 submodule update: expose parallelism to the userStefan Beller, Feb 18, 2016
  13. 7/7 clone: allow an explicit argument for parallel submodule clonesStefan Beller, Feb 18, 2016

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.