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

[PATCH 8/8] submodules: allow parallel fetching, add tests and documentation

From
Stefan Beller <sbeller@google.com>
Date
Dec 14, 2015, 19:37 UTC
Message-ID
<1450121838-7069-9-git-send-email-sbeller@google.com>
In-Reply-To
<1450121838-7069-1-git-send-email-sbeller@google.com>
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>
---
 Documentation/fetch-options.txt |  7 +++++++
 builtin/fetch.c                 |  6 +++++-
 builtin/pull.c                  |  6 ++++++
 submodule.c                     |  3 +--
 submodule.h                     |  2 +-
 t/t5526-fetch-submodules.sh     | 20 ++++++++++++++++++++
 6 files changed, 40 insertions(+), 4 deletions(-)
diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt
index 45583d8..6b109f6 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 c85f347..586840d 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 5145fc6..9e3c738 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 6a2d786..0b48734 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 5507c3d..cbc0003 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 17759b14..1241146 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 &&
 	(
-- 
2.6.4.443.ge094245.dirty
Previous: Stefan BellerNext: Johannes Sixt
Message 28 of 30 in “Rerolling sb/submodule-parallel-fetch for the time after 2.7”
  1. 0/8 Rerolling sb/submodule-parallel-fetch for the time after 2.7Stefan Beller, Dec 14, 2015
  2. 1/8 submodule.c: write "Fetching submodule <foo>" to stderrStefan Beller, Dec 14, 2015
  3. 2/8 xread: poll on non blocking fdsStefan Beller, Dec 14, 2015
  4. Eric SunshineDec 14, 2015
  5. Stefan BellerDec 14, 2015
  6. Junio C HamanoDec 14, 2015
  7. Stefan BellerDec 14, 2015
  8. 3/8 xread_nonblock: add functionality to read from fds without blockingStefan Beller, Dec 14, 2015
  9. Junio C HamanoDec 14, 2015
  10. Eric SunshineDec 14, 2015
  11. Eric SunshineDec 14, 2015
  12. Junio C HamanoDec 14, 2015
  13. Jeff KingDec 14, 2015
  14. Stefan BellerDec 15, 2015
  15. Jeff KingDec 15, 2015
  16. Stefan BellerDec 15, 2015
  17. Jeff KingDec 15, 2015
  18. Johannes SixtDec 15, 2015
  19. Junio C HamanoDec 15, 2015
  20. 4/8 strbuf: add strbuf_read_once to read without blockingStefan Beller, Dec 14, 2015
  21. Eric SunshineDec 14, 2015
  22. Stefan BellerDec 14, 2015
  23. 5/8 sigchain: add command to pop all common signalsStefan Beller, Dec 14, 2015
  24. 6/8 run-command: add an asynchronous parallel child processorStefan Beller, Dec 14, 2015
  25. Johannes SixtDec 14, 2015
  26. Stefan BellerDec 14, 2015
  27. 7/8 fetch_populated_submodules: use new parallel job processingStefan Beller, Dec 14, 2015
  28. 8/8 submodules: allow parallel fetching, add tests and documentationStefan Beller, Dec 14, 2015
  29. Johannes SixtDec 14, 2015
  30. Junio C HamanoDec 14, 2015

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.