git@vger.kernel.org mailing list mirror (one of many)
 help / Atom feed
From: Stefan Beller <sbeller@google.com>
To: sbeller@google.com
Cc: git@vger.kernel.org
Subject: [PATCH 8/9] fetch: retry fetching submodules if needed objects were not fetched
Date: Mon, 17 Sep 2018 14:35:58 -0700
Message-ID: <20180917213559.126404-9-sbeller@google.com> (raw)
In-Reply-To: <20180917213559.126404-1-sbeller@google.com>

Currently when git-fetch is asked to recurse into submodules, it dispatches
a plain "git-fetch -C <submodule-dir>" (with some submodule related options
such as prefix and recusing strategy, but) without any information of the
remote or the tip that should be fetched.

This works surprisingly well in some workflows (such as using submodules
as a third party library), while not so well in other scenarios, such
as in a Gerrit topic-based workflow, that can tie together changes
(potentially across repositories) on the server side. One of the parts
of such a Gerrit workflow is to download a change when wanting to examine
it, and you'd want to have its submodule changes that are in the same
topic downloaded as well. However these submodule changes reside in their
own repository in their own ref (refs/changes/<int>).

Retry fetching a submodule by object name if the object id that the
superproject points to, cannot be found.

This retrying does not happen when the "git fetch" done at the
superproject is not storing the fetched results in remote
tracking branches (i.e. instead just recording them to
FETCH_HEAD) in this step. A later patch will fix this.

builtin/fetch used to only inspect submodules when they were fetched
"on-demand", as in either on/off case it was clear whether the submodule
needs to be fetched. However to know whether we need to try fetching the
object ids, we need to identify the object names, which is done in this
function check_for_new_submodule_commits(), so we'll also run that code
in case the submodule recursion is set to "on".

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 builtin/fetch.c             |  9 ++--
 submodule.c                 | 87 ++++++++++++++++++++++++++++++++++++-
 t/t5526-fetch-submodules.sh | 16 +++++++
 3 files changed, 104 insertions(+), 8 deletions(-)

diff --git a/builtin/fetch.c b/builtin/fetch.c
index 61bec5d213d..95c44bf6ffa 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -700,8 +700,7 @@ static int update_local_ref(struct ref *ref,
 			what = _("[new ref]");
 		}
 
-		if ((recurse_submodules != RECURSE_SUBMODULES_OFF) &&
-		    (recurse_submodules != RECURSE_SUBMODULES_ON))
+		if (recurse_submodules != RECURSE_SUBMODULES_OFF)
 			check_for_new_submodule_commits(&ref->new_oid);
 		r = s_update_ref(msg, ref, 0);
 		format_display(display, r ? '!' : '*', what,
@@ -716,8 +715,7 @@ static int update_local_ref(struct ref *ref,
 		strbuf_add_unique_abbrev(&quickref, &current->object.oid, DEFAULT_ABBREV);
 		strbuf_addstr(&quickref, "..");
 		strbuf_add_unique_abbrev(&quickref, &ref->new_oid, DEFAULT_ABBREV);
-		if ((recurse_submodules != RECURSE_SUBMODULES_OFF) &&
-		    (recurse_submodules != RECURSE_SUBMODULES_ON))
+		if (recurse_submodules != RECURSE_SUBMODULES_OFF)
 			check_for_new_submodule_commits(&ref->new_oid);
 		r = s_update_ref("fast-forward", ref, 1);
 		format_display(display, r ? '!' : ' ', quickref.buf,
@@ -731,8 +729,7 @@ static int update_local_ref(struct ref *ref,
 		strbuf_add_unique_abbrev(&quickref, &current->object.oid, DEFAULT_ABBREV);
 		strbuf_addstr(&quickref, "...");
 		strbuf_add_unique_abbrev(&quickref, &ref->new_oid, DEFAULT_ABBREV);
-		if ((recurse_submodules != RECURSE_SUBMODULES_OFF) &&
-		    (recurse_submodules != RECURSE_SUBMODULES_ON))
+		if (recurse_submodules != RECURSE_SUBMODULES_OFF)
 			check_for_new_submodule_commits(&ref->new_oid);
 		r = s_update_ref("forced-update", ref, 1);
 		format_display(display, r ? '!' : '+', quickref.buf,
diff --git a/submodule.c b/submodule.c
index 88bce534268..7d59e56171f 100644
--- a/submodule.c
+++ b/submodule.c
@@ -1127,8 +1127,11 @@ struct submodule_parallel_fetch {
 	int result;
 
 	struct string_list changed_submodule_names;
+	struct string_list retry;
 };
-#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0, STRING_LIST_INIT_DUP }
+#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0, \
+		  STRING_LIST_INIT_DUP, \
+		  STRING_LIST_INIT_NODUP}
 
 static void calculate_changed_submodule_paths(
 	struct submodule_parallel_fetch *spf)
@@ -1259,8 +1262,10 @@ static int get_next_submodule(struct child_process *cp,
 {
 	int ret = 0;
 	struct submodule_parallel_fetch *spf = data;
+	struct string_list_item *it;
 
 	for (; spf->count < spf->r->index->cache_nr; spf->count++) {
+		int recurse_config;
 		struct strbuf submodule_prefix = STRBUF_INIT;
 		const struct cache_entry *ce = spf->r->index->cache[spf->count];
 		const char *git_dir, *default_argv;
@@ -1280,7 +1285,9 @@ static int get_next_submodule(struct child_process *cp,
 			}
 		}
 
-		switch (get_fetch_recurse_config(submodule, spf))
+		recurse_config = get_fetch_recurse_config(submodule, spf);
+
+		switch (recurse_config)
 		{
 		default:
 		case RECURSE_SUBMODULES_DEFAULT:
@@ -1321,9 +1328,50 @@ static int get_next_submodule(struct child_process *cp,
 		strbuf_release(&submodule_prefix);
 		if (ret) {
 			spf->count++;
+			if (submodule != &default_submodule)
+				/* discard const-ness: */
+				*task_cb = (void*)submodule;
 			return 1;
 		}
 	}
+
+retry_next:
+
+	if (spf->retry.nr) {
+		struct strbuf submodule_prefix = STRBUF_INIT;
+		const struct submodule *sub;
+
+		it = string_list_last(&spf->retry);
+		sub = submodule_from_name(spf->r, &null_oid,
+					  it->string);
+
+		child_process_init(cp);
+		cp->dir = get_submodule_git_dir(spf->r, sub->path);
+		if (!cp->dir) {
+			string_list_pop(&spf->retry, 0);
+			goto retry_next;
+		}
+		prepare_submodule_repo_env_in_gitdir(&cp->env_array);
+		cp->git_cmd = 1;
+
+		strbuf_addf(&submodule_prefix, "%s%s/", spf->prefix, sub->path);
+		argv_array_init(&cp->args);
+		argv_array_pushv(&cp->args, spf->args.argv);
+		argv_array_push(&cp->args, "on-demand");
+		argv_array_push(&cp->args, "--submodule-prefix");
+		argv_array_push(&cp->args, submodule_prefix.buf);
+
+		/* NEEDSWORK: have get_default_remote from s--h */
+		argv_array_push(&cp->args, "origin");
+		oid_array_for_each_unique(it->util,
+					  append_oid_to_argv, &cp->args);
+
+		*task_cb = NULL; /* make sure we do not recurse forever */
+		strbuf_release(&submodule_prefix);
+		string_list_pop(&spf->retry, 0);
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -1337,14 +1385,49 @@ static int fetch_start_failure(struct strbuf *err,
 	return 0;
 }
 
+static int commit_exists_in_sub(const struct object_id *oid, void *data)
+{
+	struct repository *subrepo = data;
+
+	enum object_type type = oid_object_info(subrepo, oid, NULL);
+
+	return type != OBJ_COMMIT;
+}
+
 static int fetch_finish(int retvalue, struct strbuf *err,
 			void *cb, void *task_cb)
 {
 	struct submodule_parallel_fetch *spf = cb;
+	struct submodule *sub = task_cb;
+	struct repository subrepo;
 
 	if (retvalue)
 		spf->result = 1;
 
+	if (!sub)
+		return 0;
+
+	if (repo_submodule_init(&subrepo, spf->r, sub->path) < 0)
+		warning(_("Could not get submodule repository for submodule '%s' in repository '%s'"),
+			  sub->path, spf->r->worktree);
+	else {
+		struct string_list_item *it;
+		struct oid_array *commits;
+
+		it = string_list_lookup(&spf->changed_submodule_names, sub->name);
+		if (!it)
+			return 0;
+
+		commits = it->util;
+		oid_array_filter(commits,
+				 commit_exists_in_sub,
+				 &subrepo);
+
+		if (commits->nr)
+			string_list_append(&spf->retry, sub->name)
+				->util = commits;
+	}
+
 	return 0;
 }
 
diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh
index 42692219a1a..af12c50e7dd 100755
--- a/t/t5526-fetch-submodules.sh
+++ b/t/t5526-fetch-submodules.sh
@@ -605,4 +605,20 @@ test_expect_success "fetch new commits when submodule got renamed" '
 	test_cmp expect actual
 '
 
+test_expect_success "fetch new commits on-demand when they are not reachable" '
+	git checkout --detach &&
+	C=$(git -C submodule commit-tree -m "new change outside refs/heads" HEAD^{tree}) &&
+	git -C submodule update-ref refs/changes/1 $C &&
+	git update-index --cacheinfo 160000 $C submodule &&
+	git commit -m "updated submodule outside of refs/heads" &&
+	D=$(git rev-parse HEAD) &&
+	git update-ref refs/changes/2 $D &&
+	(
+		cd downstream &&
+		git fetch --recurse-submodules --recurse-submodules-default on-demand origin refs/changes/2:refs/heads/my_branch &&
+		git -C submodule cat-file -t $C &&
+		git checkout --recurse-submodules FETCH_HEAD
+	)
+'
+
 test_done
-- 
2.19.0.397.gdd90340f6a-goog


  parent reply index

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-11 23:49 [PATCH 0/9] fetch: make sure submodule oids are fetched Stefan Beller
2018-09-11 23:49 ` [PATCH 1/9] string-list: add string_list_{pop, last} functions Stefan Beller
2018-09-12  2:24   ` Ramsay Jones
2018-09-12 17:52   ` Junio C Hamano
2018-09-11 23:49 ` [PATCH 2/9] sha1-array: provide oid_array_filter Stefan Beller
2018-09-12 18:02   ` Junio C Hamano
2018-09-11 23:49 ` [PATCH 3/9] submodule.c: fix indentation Stefan Beller
2018-09-12 18:02   ` Junio C Hamano
2018-09-11 23:49 ` [PATCH 4/9] submodule.c: sort changed_submodule_names before searching it Stefan Beller
2018-09-12 18:18   ` Junio C Hamano
2018-09-12 19:06     ` Stefan Beller
2018-09-11 23:49 ` [PATCH 5/9] submodule: move global changed_submodule_names into fetch submodule struct Stefan Beller
2018-09-11 23:49 ` [PATCH 6/9] submodule.c: do not copy around submodule list Stefan Beller
2018-09-12  2:25   ` Ramsay Jones
2018-09-11 23:49 ` [PATCH 7/9] submodule: fetch in submodules git directory instead of in worktree Stefan Beller
2018-09-12 18:36   ` Junio C Hamano
2018-09-13 19:29     ` Stefan Beller
2018-09-11 23:49 ` [PATCH 8/9] fetch: retry fetching submodules if sha1 were not fetched Stefan Beller
2018-09-12 19:03   ` Junio C Hamano
2018-09-11 23:49 ` [PATCH 9/9] builtin/fetch: check for submodule updates for non branch fetches Stefan Beller
2018-09-12 19:20   ` Junio C Hamano
2018-09-17 21:35 ` [PATCHv2 0/9] fetch: make sure submodule oids are fetched Stefan Beller
2018-09-17 21:35   ` [PATCH 1/9] string-list: add string_list_{pop, last} functions Stefan Beller
2018-09-21 22:08     ` [PATCH] " Stefan Beller
2018-09-17 21:35   ` [PATCH 2/9] sha1-array: provide oid_array_filter Stefan Beller
2018-09-17 21:42     ` Stefan Beller
2018-09-17 21:35   ` [PATCH 3/9] submodule.c: fix indentation Stefan Beller
2018-09-17 21:35   ` [PATCH 4/9] submodule.c: sort changed_submodule_names before searching it Stefan Beller
2018-09-17 21:35   ` [PATCH 5/9] submodule: move global changed_submodule_names into fetch submodule struct Stefan Beller
2018-09-17 21:35   ` [PATCH 6/9] submodule.c: do not copy around submodule list Stefan Beller
2018-09-17 21:35   ` [PATCH 7/9] submodule: fetch in submodules git directory instead of in worktree Stefan Beller
2018-09-17 21:35   ` Stefan Beller [this message]
2018-09-17 21:35   ` [PATCH 9/9] builtin/fetch: check for submodule updates for non branch fetches Stefan Beller
2018-10-16 18:13 [PATCH 0/9] Resending sb/submodule-recursive-fetch-gets-the-tip Stefan Beller
2018-10-16 18:13 ` [PATCH 8/9] fetch: retry fetching submodules if needed objects were not fetched Stefan Beller
2018-10-18  0:39   ` Jonathan Tan
2018-10-23 22:37     ` Stefan Beller
2018-10-23 23:37       ` Jonathan Tan
2018-10-25 21:42         ` Stefan Beller

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180917213559.126404-9-sbeller@google.com \
    --to=sbeller@google.com \
    --cc=git@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org mailing list mirror (one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox