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

[PATCHv4 07/14] fetch_populated_submodules: use new parallel job processing

From
Stefan Beller <sbeller@google.com>
Date
Sep 23, 2015, 01:45 UTC
Message-ID
<1442972732-12118-8-git-send-email-sbeller@google.com>
In-Reply-To
<1442972732-12118-1-git-send-email-sbeller@google.com>

In a later patch we enable parallel processing of submodules, this only adds the possibility for it. So this change should not change any user facing behavior.

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 submodule.c | 119 +++++++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 85 insertions(+), 34 deletions(-)
diff --git a/submodule.c b/submodule.c
index 1d64e57..d7c7a6e 100644
--- a/submodule.c
+++ b/submodule.c
@@ -12,6 +12,7 @@
 #include "sha1-array.h"
 #include "argv-array.h"
 #include "blob.h"
+#include "thread-utils.h"
 
 static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
 static struct string_list changed_submodule_paths;
@@ -615,37 +616,82 @@ static void calculate_changed_submodule_paths(void)
 	initialized_fetch_ref_tips = 0;
 }
 
+struct submodule_parallel_fetch {
+	int count;
+	struct argv_array args;
+	const char *work_tree;
+	const char *prefix;
+	int command_line_option;
+	int quiet;
+	int result;
+};
+#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0}
+
+int get_next_submodule(void *data, struct child_process *cp,
+		       struct strbuf *err);
+
+void handle_submodule_fetch_start_err(void *data, struct child_process *cp, struct strbuf *err)
+{
+	struct submodule_parallel_fetch *spf = data;
+	spf->result = 1;
+}
+
+void handle_submodule_fetch_finish( void *data, struct child_process *cp, int retvalue)
+{
+	struct submodule_parallel_fetch *spf = data;
+
+	if (retvalue)
+		spf->result = 1;
+}
+
 int fetch_populated_submodules(const struct argv_array *options,
 			       const char *prefix, int command_line_option,
 			       int quiet)
 {
-	int i, result = 0;
-	struct child_process cp = CHILD_PROCESS_INIT;
-	struct argv_array argv = ARGV_ARRAY_INIT;
-	const char *work_tree = get_git_work_tree();
-	if (!work_tree)
+	int i;
+	int max_parallel_jobs = 1;
+	struct submodule_parallel_fetch spf = SPF_INIT;
+
+	spf.work_tree = get_git_work_tree();
+	spf.command_line_option = command_line_option;
+	spf.quiet = quiet;
+	spf.prefix = prefix;
+
+	if (!spf.work_tree)
 		goto out;
 
 	if (read_cache() < 0)
 		die("index file corrupt");
 
-	argv_array_push(&argv, "fetch");
+	argv_array_push(&spf.args, "fetch");
 	for (i = 0; i < options->argc; i++)
-		argv_array_push(&argv, options->argv[i]);
-	argv_array_push(&argv, "--recurse-submodules-default");
+		argv_array_push(&spf.args, options->argv[i]);
+	argv_array_push(&spf.args, "--recurse-submodules-default");
 	/* default value, "--submodule-prefix" and its value are added later */
 
-	cp.env = local_repo_env;
-	cp.git_cmd = 1;
-	cp.no_stdin = 1;
-
 	calculate_changed_submodule_paths();
+	run_processes_parallel(max_parallel_jobs, &spf,
+			       get_next_submodule,
+			       handle_submodule_fetch_start_err,
+			       handle_submodule_fetch_finish);
+
+	argv_array_clear(&spf.args);
+out:
+	string_list_clear(&changed_submodule_paths, 1);
+	return spf.result;
+}
+
+int get_next_submodule(void *data, struct child_process *cp,
+		       struct strbuf *err)
+{
+	int ret = 0;
+	struct submodule_parallel_fetch *spf = data;
 
-	for (i = 0; i < active_nr; i++) {
+	for ( ; spf->count < active_nr; spf->count++) {
 		struct strbuf submodule_path = STRBUF_INIT;
 		struct strbuf submodule_git_dir = STRBUF_INIT;
 		struct strbuf submodule_prefix = STRBUF_INIT;
-		const struct cache_entry *ce = active_cache[i];
+		const struct cache_entry *ce = active_cache[spf->count];
 		const char *git_dir, *default_argv;
 		const struct submodule *submodule;
 
@@ -657,7 +703,7 @@ int fetch_populated_submodules(const struct argv_array *options,
 			submodule = submodule_from_name(null_sha1, ce->name);
 
 		default_argv = "yes";
-		if (command_line_option == RECURSE_SUBMODULES_DEFAULT) {
+		if (spf->command_line_option == RECURSE_SUBMODULES_DEFAULT) {
 			if (submodule &&
 			    submodule->fetch_recurse !=
 						RECURSE_SUBMODULES_NONE) {
@@ -680,40 +726,45 @@ int fetch_populated_submodules(const struct argv_array *options,
 					default_argv = "on-demand";
 				}
 			}
-		} else if (command_line_option == RECURSE_SUBMODULES_ON_DEMAND) {
+		} else if (spf->command_line_option == RECURSE_SUBMODULES_ON_DEMAND) {
 			if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name))
 				continue;
 			default_argv = "on-demand";
 		}
 
-		strbuf_addf(&submodule_path, "%s/%s", work_tree, ce->name);
+		strbuf_addf(&submodule_path, "%s/%s", spf->work_tree, ce->name);
 		strbuf_addf(&submodule_git_dir, "%s/.git", submodule_path.buf);
-		strbuf_addf(&submodule_prefix, "%s%s/", prefix, ce->name);
+		strbuf_addf(&submodule_prefix, "%s%s/", spf->prefix, ce->name);
 		git_dir = read_gitfile(submodule_git_dir.buf);
 		if (!git_dir)
 			git_dir = submodule_git_dir.buf;
 		if (is_directory(git_dir)) {
-			if (!quiet)
-				fprintf(stderr, "Fetching submodule %s%s\n", prefix, ce->name);
-			cp.dir = submodule_path.buf;
-			argv_array_push(&argv, default_argv);
-			argv_array_push(&argv, "--submodule-prefix");
-			argv_array_push(&argv, submodule_prefix.buf);
-			cp.argv = argv.argv;
-			if (run_command(&cp))
-				result = 1;
-			argv_array_pop(&argv);
-			argv_array_pop(&argv);
-			argv_array_pop(&argv);
+			child_process_init(cp);
+			cp->dir = strbuf_detach(&submodule_path, NULL);
+			cp->env = local_repo_env;
+			cp->git_cmd = 1;
+			cp->no_stdin = 1;
+			cp->stdout_to_stderr = 1;
+			cp->err = -1;
+			if (!spf->quiet)
+				strbuf_addf(err, "Fetching submodule %s%s\n",
+					    spf->prefix, ce->name);
+			argv_array_init(&cp->args);
+			argv_array_pushv(&cp->args, spf->args.argv);
+			argv_array_push(&cp->args, default_argv);
+			argv_array_push(&cp->args, "--submodule-prefix");
+			argv_array_push(&cp->args, submodule_prefix.buf);
+			ret = 1;
 		}
 		strbuf_release(&submodule_path);
 		strbuf_release(&submodule_git_dir);
 		strbuf_release(&submodule_prefix);
+		if (ret) {
+			spf->count++;
+			return 1;
+		}
 	}
-	argv_array_clear(&argv);
-out:
-	string_list_clear(&changed_submodule_paths, 1);
-	return result;
+	return 0;
 }
 
 unsigned is_submodule_modified(const char *path, int ignore_untracked)

-- 
2.5.0.272.ga84127c.dirty
Previous: Junio C HamanoNext: Stefan Beller
Message 31 of 39 in “[PATCHv4 00/14] fetch submodules in parallel and a preview on parallel "submodule update"”
  1. Stefan BellerSep 23, 2015
  2. 01/14 submodule: Send "Fetching submodule <foo>" to standard errorStefan Beller, Sep 23, 2015
  3. 02/14 xread: poll on non blocking fdsStefan Beller, Sep 23, 2015
  4. 03/14 xread_nonblock: add functionality to read from fds without blockingStefan Beller, Sep 23, 2015
  5. 04/14 strbuf: add strbuf_read_once to read without blockingStefan Beller, Sep 23, 2015
  6. 05/14 run-command: factor out return value computationStefan Beller, Sep 23, 2015
  7. 06/14 run-command: add an asynchronous parallel child processorStefan Beller, Sep 23, 2015
  8. Junio C HamanoSep 23, 2015
  9. Stefan BellerSep 23, 2015
  10. Junio C HamanoSep 23, 2015
  11. Junio C HamanoSep 23, 2015
  12. Stefan BellerSep 23, 2015
  13. Junio C HamanoSep 23, 2015
  14. Junio C HamanoSep 23, 2015
  15. Junio C HamanoSep 23, 2015
  16. Junio C HamanoSep 23, 2015
  17. [PATCHv5] Another squash on run-command: add an asynchronous parallel child processorStefan Beller, Sep 23, 2015
  18. Junio C HamanoSep 24, 2015
  19. 0/2 Another squash on run-command: add an asynchronous parallel child processorStefan Beller, Sep 24, 2015
  20. 2/2 SQUASH for "fetch_populated_submodules: use new parallel job processing"Stefan Beller, Sep 24, 2015
  21. 1/2 SQUASH???Stefan Beller, Sep 24, 2015
  22. Junio C HamanoSep 25, 2015
  23. Junio C HamanoSep 25, 2015
  24. Stefan BellerSep 25, 2015
  25. Junio C HamanoSep 25, 2015
  26. Junio C HamanoSep 25, 2015
  27. Stefan BellerSep 25, 2015
  28. Junio C HamanoSep 25, 2015
  29. Stefan BellerSep 25, 2015
  30. Junio C HamanoSep 25, 2015
  31. 07/14 fetch_populated_submodules: use new parallel job processingStefan Beller, Sep 23, 2015
  32. 08/14 submodules: allow parallel fetching, add tests and documentationStefan Beller, Sep 23, 2015
  33. 09/14 submodule-config: Untangle logic in parse_configStefan Beller, Sep 23, 2015
  34. 10/14 submodule config: keep update strategy aroundStefan Beller, Sep 23, 2015
  35. 11/14 git submodule update: cmd_update_recursiveStefan Beller, Sep 23, 2015
  36. 12/14 git submodule update: cmd_update_cloneStefan Beller, Sep 23, 2015
  37. Junio C HamanoSep 23, 2015
  38. 13/14 git submodule update: cmd_update_fetchStefan Beller, Sep 23, 2015
  39. 14/14 Rewrite submodule update in CStefan Beller, Sep 23, 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.