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

[PATCH v2 1/3] serialize collection of changed submodules

From
Heiko Voigt <hvoigt@hvoigt.net>
Date
Oct 7, 2016, 15:06 UTC
Message-ID
<10cd5be93601bc52388100e80b6c6735a7cacfb4.1475851621.git.hvoigt@hvoigt.net>
In-Reply-To
<cover.1475851621.git.hvoigt@hvoigt.net>

To check whether a submodule needs to be pushed we need to collect all changed submodules. Lets collect them first and then execute the possibly expensive test whether certain revisions are already pushed only once per submodule.

There is further potential for optimization since we can assemble one command and only issued that instead of one call for each remote ref in the submodule.

Signed-off-by: Heiko Voigt <hvoigt@hvoigt.net>
---
 submodule.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 58 insertions(+), 5 deletions(-)
diff --git a/submodule.c b/submodule.c
index 2de06a3351..59c9d15905 100644
--- a/submodule.c
+++ b/submodule.c
@@ -554,19 +554,34 @@ static int submodule_needs_pushing(const char *path, const unsigned char sha1[20
 	return 0;
 }
 
+static struct sha1_array *get_sha1s_from_list(struct string_list *submodules,
+		const char *path)
+{
+	struct string_list_item *item;
+
+	item = string_list_insert(submodules, path);
+	if (item->util)
+		return (struct sha1_array *) item->util;
+
+	/* NEEDSWORK: should we have sha1_array_init()? */
+	item->util = xcalloc(1, sizeof(struct sha1_array));
+	return (struct sha1_array *) item->util;
+}
+
 static void collect_submodules_from_diff(struct diff_queue_struct *q,
 					 struct diff_options *options,
 					 void *data)
 {
 	int i;
-	struct string_list *needs_pushing = data;
+	struct string_list *submodules = data;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
+		struct sha1_array *hashes;
 		if (!S_ISGITLINK(p->two->mode))
 			continue;
-		if (submodule_needs_pushing(p->two->path, p->two->oid.hash))
-			string_list_insert(needs_pushing, p->two->path);
+		hashes = get_sha1s_from_list(submodules, p->two->path);
+		sha1_array_append(hashes, p->two->oid.hash);
 	}
 }
 
@@ -582,14 +597,41 @@ static void find_unpushed_submodule_commits(struct commit *commit,
 	diff_tree_combined_merge(commit, 1, &rev);
 }
 
+struct collect_submodule_from_sha1s_data {
+	char *submodule_path;
+	struct string_list *needs_pushing;
+};
+
+static void collect_submodules_from_sha1s(const unsigned char sha1[20],
+		void *data)
+{
+	struct collect_submodule_from_sha1s_data *me =
+		(struct collect_submodule_from_sha1s_data *) data;
+
+	if (submodule_needs_pushing(me->submodule_path, sha1))
+		string_list_insert(me->needs_pushing, me->submodule_path);
+}
+
+static void free_submodules_sha1s(struct string_list *submodules)
+{
+	int i;
+	for (i = 0; i < submodules->nr; i++) {
+		struct string_list_item *item = &submodules->items[i];
+		struct sha1_array *hashes = (struct sha1_array *) item->util;
+		sha1_array_clear(hashes);
+	}
+	string_list_clear(submodules, 1);
+}
+
 int find_unpushed_submodules(unsigned char new_sha1[20],
 		const char *remotes_name, struct string_list *needs_pushing)
 {
 	struct rev_info rev;
 	struct commit *commit;
 	const char *argv[] = {NULL, NULL, "--not", "NULL", NULL};
-	int argc = ARRAY_SIZE(argv) - 1;
+	int argc = ARRAY_SIZE(argv) - 1, i;
 	char *sha1_copy;
+	struct string_list submodules = STRING_LIST_INIT_DUP;
 
 	struct strbuf remotes_arg = STRBUF_INIT;
 
@@ -603,12 +645,23 @@ int find_unpushed_submodules(unsigned char new_sha1[20],
 		die("revision walk setup failed");
 
 	while ((commit = get_revision(&rev)) != NULL)
-		find_unpushed_submodule_commits(commit, needs_pushing);
+		find_unpushed_submodule_commits(commit, &submodules);
 
 	reset_revision_walk();
 	free(sha1_copy);
 	strbuf_release(&remotes_arg);
 
+	for (i = 0; i < submodules.nr; i++) {
+		struct string_list_item *item = &submodules.items[i];
+		struct collect_submodule_from_sha1s_data data;
+		data.submodule_path = item->string;
+		data.needs_pushing = needs_pushing;
+		sha1_array_for_each_unique((struct sha1_array *) item->util,
+				collect_submodules_from_sha1s,
+				&data);
+	}
+	free_submodules_sha1s(&submodules);
+
 	return needs_pushing->nr;
 }
 
-- 
2.10.1.637.g09b28c5
Previous: Heiko VoigtNext: Stefan Beller
Message 2 of 19 in “Speedup finding of unpushed submodules”
  1. 0/3 Speedup finding of unpushed submodulesHeiko Voigt, Oct 7, 2016
  2. 1/3 serialize collection of changed submodulesHeiko Voigt, Oct 7, 2016
  3. Stefan BellerOct 7, 2016
  4. Junio C HamanoOct 10, 2016
  5. Heiko VoigtOct 12, 2016
  6. Junio C HamanoOct 12, 2016
  7. Heiko VoigtOct 13, 2016
  8. Heiko VoigtOct 12, 2016
  9. 2/3 serialize collection of refs that contain submodule changesHeiko Voigt, Oct 7, 2016
  10. Stefan BellerOct 7, 2016
  11. Heiko VoigtOct 12, 2016
  12. Stefan BellerOct 20, 2016
  13. Junio C HamanoOct 10, 2016
  14. 3/3 batch check whether submodule needs pushing into one callHeiko Voigt, Oct 7, 2016
  15. Stefan BellerOct 7, 2016
  16. Junio C HamanoOct 10, 2016
  17. Heiko VoigtOct 12, 2016
  18. Junio C HamanoOct 12, 2016
  19. Heiko VoigtOct 13, 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.