git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jonathan Tan <jonathantanmy@google.com>
To: git@vger.kernel.org
Cc: Jonathan Tan <jonathantanmy@google.com>
Subject: [PATCH 4/4] promisor-remote: teach lazy-fetch in any repo
Date: Tue,  1 Jun 2021 14:34:19 -0700	[thread overview]
Message-ID: <b70a00b9b06e5142bb95891cfc2faa87d708ef0d.1622580781.git.jonathantanmy@google.com> (raw)
In-Reply-To: <cover.1622580781.git.jonathantanmy@google.com>

This is one step towards supporting partial clone submodules.

Even after this patch, we will still lack partial clone submodules
support, primarily because a lot of Git code that accesses submodule
objects does so by adding their object stores as alternates, meaning
that any lazy fetches that would occur in the submodule would be done
based on the config of the superproject, not of the submodule. This also
prevents testing of the functionality in this patch by user-facing
commands. So for now, test this mechanism using a test helper.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Makefile                      |  1 +
 object-file.c                 |  7 ++-----
 promisor-remote.c             | 14 +++++++++-----
 t/helper/test-partial-clone.c | 34 ++++++++++++++++++++++++++++++++++
 t/helper/test-tool.c          |  1 +
 t/helper/test-tool.h          |  1 +
 t/t0410-partial-clone.sh      | 24 ++++++++++++++++++++++++
 7 files changed, 72 insertions(+), 10 deletions(-)
 create mode 100644 t/helper/test-partial-clone.c

diff --git a/Makefile b/Makefile
index c3565fc0f8..f6653bcd5e 100644
--- a/Makefile
+++ b/Makefile
@@ -725,6 +725,7 @@ TEST_BUILTINS_OBJS += test-oidmap.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
+TEST_BUILTINS_OBJS += test-partial-clone.o
 TEST_BUILTINS_OBJS += test-path-utils.o
 TEST_BUILTINS_OBJS += test-pcre2-config.o
 TEST_BUILTINS_OBJS += test-pkt-line.o
diff --git a/object-file.c b/object-file.c
index f233b440b2..ebf273e9e7 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1570,15 +1570,12 @@ static int do_oid_object_info_extended(struct repository *r,
 		}
 
 		/* Check if it is a missing object */
-		if (fetch_if_missing && has_promisor_remote() &&
-		    !already_retried && r == the_repository &&
+		if (fetch_if_missing && repo_has_promisor_remote(r) &&
+		    !already_retried &&
 		    !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) {
 			/*
 			 * TODO Investigate checking promisor_remote_get_direct()
 			 * TODO return value and stopping on error here.
-			 * TODO Pass a repository struct through
-			 * promisor_remote_get_direct(), such that arbitrary
-			 * repositories work.
 			 */
 			promisor_remote_get_direct(r, real, 1);
 			already_retried = 1;
diff --git a/promisor-remote.c b/promisor-remote.c
index 5819d2cf28..1601f05d79 100644
--- a/promisor-remote.c
+++ b/promisor-remote.c
@@ -11,7 +11,8 @@ struct promisor_remote_config {
 	struct promisor_remote **promisors_tail;
 };
 
-static int fetch_objects(const char *remote_name,
+static int fetch_objects(struct repository *repo,
+			 const char *remote_name,
 			 const struct object_id *oids,
 			 int oid_nr)
 {
@@ -21,6 +22,11 @@ static int fetch_objects(const char *remote_name,
 
 	child.git_cmd = 1;
 	child.in = -1;
+	if (repo != the_repository) {
+		prepare_other_repo_env(&child.env_array);
+		strvec_pushf(&child.env_array, "%s=%s", GIT_DIR_ENVIRONMENT,
+			     repo->gitdir);
+	}
 	strvec_pushl(&child.args, "-c", "fetch.negotiationAlgorithm=noop",
 		     "fetch", remote_name, "--no-tags",
 		     "--no-write-fetch-head", "--recurse-submodules=no",
@@ -150,7 +156,7 @@ static void promisor_remote_init(struct repository *r)
 		xcalloc(sizeof(*r->promisor_remote_config), 1);
 	config->promisors_tail = &config->promisors;
 
-	git_config(promisor_remote_config, config);
+	repo_config(r, promisor_remote_config, config);
 
 	if (config->repository_format_partial_clone) {
 		struct promisor_remote *o, *previous;
@@ -246,10 +252,8 @@ int promisor_remote_get_direct(struct repository *repo,
 
 	promisor_remote_init(repo);
 
-	if (repo != the_repository)
-		BUG("only the_repository is supported for now");
 	for (r = repo->promisor_remote_config->promisors; r; r = r->next) {
-		if (fetch_objects(r->name, remaining_oids, remaining_nr) < 0) {
+		if (fetch_objects(repo, r->name, remaining_oids, remaining_nr) < 0) {
 			if (remaining_nr == 1)
 				continue;
 			remaining_nr = remove_fetched_oids(repo, &remaining_oids,
diff --git a/t/helper/test-partial-clone.c b/t/helper/test-partial-clone.c
new file mode 100644
index 0000000000..e7bc7eb21f
--- /dev/null
+++ b/t/helper/test-partial-clone.c
@@ -0,0 +1,34 @@
+#include "cache.h"
+#include "test-tool.h"
+#include "repository.h"
+#include "object-store.h"
+
+static void object_info(const char *gitdir, const char *oid_hex)
+{
+	struct repository r;
+	struct object_id oid;
+	unsigned long size;
+	struct object_info oi = {.sizep = &size};
+	const char *p;
+
+	if (repo_init(&r, gitdir, NULL))
+		die("could not init repo");
+	if (parse_oid_hex(oid_hex, &oid, &p))
+		die("could not parse oid");
+	if (oid_object_info_extended(&r, &oid, &oi, 0))
+		die("could not obtain object info");
+	printf("%d\n", (int) size);
+}
+
+int cmd__partial_clone(int argc, const char **argv)
+{
+	if (argc < 4)
+		die("too few arguments");
+
+	if (!strcmp(argv[1], "object-info"))
+		object_info(argv[2], argv[3]);
+	else
+		die("invalid argument '%s'", argv[1]);
+
+	return 0;
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index c5bd0c6d4c..b21e8f1519 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -46,6 +46,7 @@ static struct test_cmd cmds[] = {
 	{ "online-cpus", cmd__online_cpus },
 	{ "parse-options", cmd__parse_options },
 	{ "parse-pathspec-file", cmd__parse_pathspec_file },
+	{ "partial-clone", cmd__partial_clone },
 	{ "path-utils", cmd__path_utils },
 	{ "pcre2-config", cmd__pcre2_config },
 	{ "pkt-line", cmd__pkt_line },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index e8069a3b22..f845ced4b3 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -35,6 +35,7 @@ int cmd__oidmap(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);
 int cmd__parse_pathspec_file(int argc, const char** argv);
+int cmd__partial_clone(int argc, const char **argv);
 int cmd__path_utils(int argc, const char **argv);
 int cmd__pcre2_config(int argc, const char **argv);
 int cmd__pkt_line(int argc, const char **argv);
diff --git a/t/t0410-partial-clone.sh b/t/t0410-partial-clone.sh
index 584a039b85..e804d267e6 100755
--- a/t/t0410-partial-clone.sh
+++ b/t/t0410-partial-clone.sh
@@ -604,6 +604,30 @@ test_expect_success 'do not fetch when checking existence of tree we construct o
 	git -C repo cherry-pick side1
 '
 
+test_expect_success 'lazy-fetch when accessing object not in the_repository' '
+	rm -rf full partial.git &&
+	test_create_repo full &&
+	printf 12345 >full/file.txt &&
+	git -C full add file.txt &&
+	git -C full commit -m "first commit" &&
+
+	test_config -C full uploadpack.allowfilter 1 &&
+	test_config -C full uploadpack.allowanysha1inwant 1 &&
+	git clone --filter=blob:none --bare "file://$(pwd)/full" partial.git &&
+	FILE_HASH=$(git hash-object --stdin <full/file.txt) &&
+
+	# Sanity check that the file is missing
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	grep "[?]$FILE_HASH" out &&
+
+	OUT=$(test-tool partial-clone object-info partial.git "$FILE_HASH") &&
+	test "$OUT" -eq 5 &&
+
+	# Sanity check that the file is now present
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	! grep "[?]$FILE_HASH" out
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd
 
-- 
2.32.0.rc0.204.g9fa02ecfa5-goog


  parent reply	other threads:[~2021-06-01 21:34 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01 21:34 [PATCH 0/4] First steps towards partial clone submodules Jonathan Tan
2021-06-01 21:34 ` [PATCH 1/4] promisor-remote: read partialClone config here Jonathan Tan
2021-06-04 19:56   ` Taylor Blau
2021-06-05  1:38     ` Jonathan Tan
2021-06-07 22:41   ` Emily Shaffer
2021-06-01 21:34 ` [PATCH 2/4] promisor-remote: support per-repository config Jonathan Tan
2021-06-04 20:09   ` Taylor Blau
2021-06-05  1:43     ` Jonathan Tan
2021-06-04 21:21   ` Elijah Newren
2021-06-05  1:54     ` Jonathan Tan
2021-06-08  0:48   ` Emily Shaffer
2021-06-01 21:34 ` [PATCH 3/4] run-command: move envvar-resetting function Jonathan Tan
2021-06-04 20:19   ` Taylor Blau
2021-06-05  1:57     ` Jonathan Tan
2021-06-08  0:54   ` Emily Shaffer
2021-06-01 21:34 ` Jonathan Tan [this message]
2021-06-04 21:25   ` [PATCH 4/4] promisor-remote: teach lazy-fetch in any repo Taylor Blau
2021-06-05  2:11     ` Jonathan Tan
2021-06-04 21:35   ` Elijah Newren
2021-06-05  2:16     ` Jonathan Tan
2021-06-05  3:48     ` Elijah Newren
2021-06-05  0:22   ` Elijah Newren
2021-06-05  2:16     ` Jonathan Tan
2021-06-08  1:41   ` Emily Shaffer
2021-06-09  4:52     ` Jonathan Tan
2021-06-08  0:25 ` [PATCH v2 0/4] First steps towards partial clone submodules Jonathan Tan
2021-06-08  0:25   ` [PATCH v2 1/4] promisor-remote: read partialClone config here Jonathan Tan
2021-06-08  3:18     ` Junio C Hamano
2021-06-09  4:26       ` Jonathan Tan
2021-06-09  9:30         ` Junio C Hamano
2021-06-09 17:16           ` Jonathan Tan
2021-06-08 17:28     ` Elijah Newren
2021-06-09  4:44       ` Jonathan Tan
2021-06-09  5:34         ` Elijah Newren
2021-06-10 17:25           ` Jonathan Tan
2021-06-08  0:25   ` [PATCH v2 2/4] promisor-remote: support per-repository config Jonathan Tan
2021-06-08  3:30     ` Junio C Hamano
2021-06-09  4:29       ` Jonathan Tan
2021-06-08  0:25   ` [PATCH v2 3/4] run-command: move envvar-resetting function Jonathan Tan
2021-06-08  4:14     ` Junio C Hamano
2021-06-09  4:32       ` Jonathan Tan
2021-06-09  5:28         ` Junio C Hamano
2021-06-09 18:15           ` Jonathan Tan
2021-06-08  0:25   ` [PATCH v2 4/4] promisor-remote: teach lazy-fetch in any repo Jonathan Tan
2021-06-08  4:33     ` Junio C Hamano
2021-06-09  4:39       ` Jonathan Tan
2021-06-09  5:33         ` Junio C Hamano
2021-06-09 18:20           ` Jonathan Tan
2021-06-10  1:26             ` Junio C Hamano
2021-06-08 17:42     ` Elijah Newren
2021-06-09  4:46       ` Jonathan Tan
2021-06-08 17:50   ` [PATCH v2 0/4] First steps towards partial clone submodules Elijah Newren
2021-06-08 23:42     ` Junio C Hamano
2021-06-09  0:07       ` Elijah Newren
2021-06-09  0:18         ` Junio C Hamano
2021-06-09  4:58     ` Jonathan Tan
2021-06-08  1:44 ` [PATCH " Emily Shaffer
2021-06-10 17:35 ` [PATCH v3 0/5] " Jonathan Tan
2021-06-10 17:35   ` [PATCH v3 1/5] repository: move global r_f_p_c to repo struct Jonathan Tan
2021-06-10 20:47     ` Elijah Newren
2021-06-10 17:35   ` [PATCH v3 2/5] promisor-remote: support per-repository config Jonathan Tan
2021-06-10 17:35   ` [PATCH v3 3/5] submodule: refrain from filtering GIT_CONFIG_COUNT Jonathan Tan
2021-06-10 21:13     ` Elijah Newren
2021-06-10 21:51       ` Jeff King
2021-06-11 17:02         ` Jonathan Tan
2021-06-10 17:35   ` [PATCH v3 4/5] run-command: refactor subprocess env preparation Jonathan Tan
2021-06-10 21:21     ` Elijah Newren
2021-06-10 17:35   ` [PATCH v3 5/5] promisor-remote: teach lazy-fetch in any repo Jonathan Tan
2021-06-10 21:29   ` [PATCH v3 0/5] First steps towards partial clone submodules Elijah Newren
2021-06-15 21:22     ` Elijah Newren
2021-06-17 17:13 ` [PATCH v4 " Jonathan Tan
2021-06-17 17:13   ` [PATCH v4 1/5] repository: move global r_f_p_c to repo struct Jonathan Tan
2021-06-17 17:13   ` [PATCH v4 2/5] promisor-remote: support per-repository config Jonathan Tan
2021-06-17 17:13   ` [PATCH v4 3/5] submodule: refrain from filtering GIT_CONFIG_COUNT Jonathan Tan
2021-06-17 17:13   ` [PATCH v4 4/5] run-command: refactor subprocess env preparation Jonathan Tan
2021-06-17 17:13   ` [PATCH v4 5/5] promisor-remote: teach lazy-fetch in any repo Jonathan Tan
2021-06-19 20:01   ` [PATCH v4 0/5] First steps towards partial clone submodules Elijah Newren

Reply instructions:

You may reply publicly 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

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

  git send-email \
    --in-reply-to=b70a00b9b06e5142bb95891cfc2faa87d708ef0d.1622580781.git.jonathantanmy@google.com \
    --to=jonathantanmy@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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).