fetch: teach independent negotiation (no packfile)

Currently, the packfile negotiation step within a Git fetch cannot be
done independent of sending the packfile, even though there is at least
one application wherein this is useful. Therefore, make it possible for
this negotiation step to be done independently. A subsequent commit will
use this for one such application - push negotiation.

This feature is for protocol v2 only. (An implementation for protocol v0
would require a separate implementation in the fetch, transport, and
transport helper code.)

In the protocol, the main hindrance towards independent negotiation is
that the server can unilaterally decide to send the packfile. This is
solved by a "wait-for-done" argument: the server will then wait for the
client to say "done". In practice, the client will never say it; instead
it will cease requests once it is satisfied.

In the client, the main change lies in the transport and transport
helper code. fetch_refs_via_pack() performs everything needed - protocol
version and capability checks, and the negotiation itself.

There are 2 code paths that do not go through fetch_refs_via_pack() that
needed to be individually excluded: the bundle transport (excluded
through requiring smart_options, which the bundle transport doesn't
support) and transport helpers that do not support takeover. If or when
we support independent negotiation for protocol v0, we will need to
modify these 2 code paths to support it. But for now, report failure if
independent negotiation is requested in these cases.

Signed-off-by: Jonathan Tan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jonathantanmy

Documentation/technical/protocol-v2.txt

@@ -346,6 +346,14 @@ explained below.
 	client should download from all given URIs. Currently, the
 	protocols supported are "http" and "https".
 
+If the 'wait-for-done' feature is advertised, the following argument
+can be included in the client's request.
+
+    wait-for-done
+	Indicates to the server that it should never send "ready", but
+	should wait for the client to say "done" before sending the
+	packfile.
+
 The response of `fetch` is broken into a number of sections separated by
 delimiter packets (0001), with each section beginning with its section
 header. Most sections are sent only when the packfile is sent.

builtin/fetch.c

@@ -82,6 +82,7 @@ static struct string_list server_options = STRING_LIST_INIT_DUP;
 static struct string_list negotiation_tip = STRING_LIST_INIT_NODUP;
 static int fetch_write_commit_graph = -1;
 static int stdin_refspecs = 0;
+static int negotiate_only;
 
 static int git_fetch_config(const char *k, const char *v, void *cb)
 {
@@ -202,6 +203,8 @@ static struct option builtin_fetch_options[] = {
 			TRANSPORT_FAMILY_IPV6),
 	OPT_STRING_LIST(0, "negotiation-tip", &negotiation_tip, N_("revision"),
 			N_("report that we have only objects reachable from this object")),
+	OPT_BOOL(0, "negotiate-only", &negotiate_only,
+		 N_("do not fetch a packfile; instead, print ancestors of negotiation tips")),
 	OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 	OPT_BOOL(0, "auto-maintenance", &enable_auto_gc,
 		 N_("run 'maintenance --auto' after fetching")),
@@ -1986,7 +1989,29 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (remote) {
+	if (negotiate_only) {
+		struct oidset acked_commits = OIDSET_INIT;
+		struct oidset_iter iter;
+		const struct object_id *oid;
+
+		if (!remote)
+			die(_("must supply remote when using --negotiate-only"));
+		gtransport = prepare_transport(remote, 1);
+		if (gtransport->smart_options) {
+			gtransport->smart_options->acked_commits = &acked_commits;
+		} else {
+			warning(_("Protocol does not support --negotiate-only, exiting."));
+			return 1;
+		}
+		if (server_options.nr)
+			gtransport->server_options = &server_options;
+		result = transport_fetch_refs(gtransport, NULL);
+
+		oidset_iter_init(&acked_commits, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			printf("%s\n", oid_to_hex(oid));
+		oidset_clear(&acked_commits);
+	} else if (remote) {
 		if (filter_options.choice || has_promisor_remote())
 			fetch_one_setup_partial(remote);
 		result = fetch_one(remote, argc, argv, prune_tags_ok, stdin_refspecs);

fetch-pack.c

@@ -23,6 +23,8 @@
 #include "fetch-negotiator.h"
 #include "fsck.h"
 #include "shallow.h"
+#include "commit-reach.h"
+#include "commit-graph.h"
 
 static int transfer_unpack_limit = -1;
 static int fetch_unpack_limit = -1;
@@ -45,6 +47,8 @@ static struct string_list uri_protocols = STRING_LIST_INIT_DUP;
 /* Remember to update object flag allocation in object.h */
 #define COMPLETE	(1U << 0)
 #define ALTERNATE	(1U << 1)
+#define COMMON		(1U << 6)
+#define REACH_SCRATCH	(1U << 7)
 
 /*
  * After sending this many "have"s if we do not get any new ACK , we
@@ -1523,10 +1527,10 @@ enum fetch_state {
 	FETCH_DONE,
 };
 
-static void do_check_stateless_delimiter(const struct fetch_pack_args *args,
+static void do_check_stateless_delimiter(int stateless_rpc,
 					 struct packet_reader *reader)
 {
-	check_stateless_delimiter(args->stateless_rpc, reader,
+	check_stateless_delimiter(stateless_rpc, reader,
 				  _("git fetch-pack: expected response end packet"));
 }
 
@@ -1622,7 +1626,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 				 */
 				state = FETCH_GET_PACK;
 			} else {
-				do_check_stateless_delimiter(args, &reader);
+				do_check_stateless_delimiter(args->stateless_rpc, &reader);
 				state = FETCH_SEND_REQUEST;
 			}
 			break;
@@ -1645,7 +1649,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 				     packfile_uris.nr ? &index_pack_args : NULL,
 				     sought, nr_sought, &fsck_options.gitmodules_found))
 				die(_("git fetch-pack: fetch failed."));
-			do_check_stateless_delimiter(args, &reader);
+			do_check_stateless_delimiter(args->stateless_rpc, &reader);
 
 			state = FETCH_DONE;
 			break;
@@ -1962,6 +1966,105 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 	return ref_cpy;
 }
 
+static int add_to_object_array(const struct object_id *oid, void *data)
+{
+	struct object_array *a = data;
+
+	add_object_array(lookup_object(the_repository, oid), "", a);
+	return 0;
+}
+
+static void clear_common_flag(struct oidset *s)
+{
+	struct oidset_iter iter;
+	const struct object_id *oid;
+	oidset_iter_init(s, &iter);
+
+	while ((oid = oidset_iter_next(&iter))) {
+		struct object *obj = lookup_object(the_repository, oid);
+		obj->flags &= ~COMMON;
+	}
+}
+
+void negotiate_using_fetch(const struct oid_array *negotiation_tips,
+			   const struct string_list *server_options,
+			   int stateless_rpc,
+			   int fd[],
+			   struct oidset *acked_commits)
+{
+	struct fetch_negotiator negotiator;
+	struct packet_reader reader;
+	struct object_array nt_object_array = OBJECT_ARRAY_INIT;
+	struct strbuf req_buf = STRBUF_INIT;
+	int haves_to_send = INITIAL_FLUSH;
+	int in_vain = 0;
+	int seen_ack = 0;
+	int last_iteration = 0;
+	timestamp_t min_generation = GENERATION_NUMBER_INFINITY;
+
+	fetch_negotiator_init(the_repository, &negotiator);
+	mark_tips(&negotiator, negotiation_tips);
+
+	packet_reader_init(&reader, fd[0], NULL, 0,
+			   PACKET_READ_CHOMP_NEWLINE |
+			   PACKET_READ_DIE_ON_ERR_PACKET);
+
+	oid_array_for_each((struct oid_array *) negotiation_tips,
+			   add_to_object_array,
+			   &nt_object_array);
+
+	while (!last_iteration) {
+		int haves_added;
+		struct object_id common_oid;
+		int received_ready = 0;
+
+		strbuf_reset(&req_buf);
+		write_fetch_command_and_capabilities(&req_buf, server_options);
+
+		packet_buf_write(&req_buf, "wait-for-done");
+
+		haves_added = add_haves(&negotiator, &req_buf, &haves_to_send);
+		in_vain += haves_added;
+		if (!haves_added || (seen_ack && in_vain >= MAX_IN_VAIN))
+			last_iteration = 1;
+
+		/* Send request */
+		packet_buf_flush(&req_buf);
+		if (write_in_full(fd[1], req_buf.buf, req_buf.len) < 0)
+			die_errno(_("unable to write request to remote"));
+
+		/* Process ACKs/NAKs */
+		process_section_header(&reader, "acknowledgments", 0);
+		while (process_ack(&negotiator, &reader, &common_oid,
+				   &received_ready)) {
+			struct commit *commit = lookup_commit(the_repository,
+							      &common_oid);
+			if (commit) {
+				timestamp_t generation;
+
+				parse_commit_or_die(commit);
+				commit->object.flags |= COMMON;
+				generation = commit_graph_generation(commit);
+				if (generation < min_generation)
+					min_generation = generation;
+			}
+			in_vain = 0;
+			seen_ack = 1;
+			oidset_insert(acked_commits, &common_oid);
+		}
+		if (received_ready)
+			die(_("unexpected 'ready' from remote"));
+		else
+			do_check_stateless_delimiter(stateless_rpc, &reader);
+		if (can_all_from_reach_with_flag(&nt_object_array, COMMON,
+						 REACH_SCRATCH, 0,
+						 min_generation))
+			last_iteration = 1;
+	}
+	clear_common_flag(acked_commits);
+	strbuf_release(&req_buf);
+}
+
 int report_unmatched_refs(struct ref **sought, int nr_sought)
 {
 	int i, ret = 0;

fetch-pack.h

@@ -5,6 +5,7 @@
 #include "run-command.h"
 #include "protocol.h"
 #include "list-objects-filter-options.h"
+#include "oidset.h"
 
 struct oid_array;
 
@@ -81,6 +82,19 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       struct string_list *pack_lockfiles,
 		       enum protocol_version version);
 
+/*
+ * Execute the --negotiate-only mode of "git fetch", adding all known common
+ * commits to acked_commits.
+ *
+ * In the capability advertisement that has happened prior to invoking this
+ * function, the "wait-for-done" capability must be present.
+ */
+void negotiate_using_fetch(const struct oid_array *negotiation_tips,
+			   const struct string_list *server_options,
+			   int stateless_rpc,
+			   int fd[],
+			   struct oidset *acked_commits);
+
 /*
  * Print an appropriate error message for each sought ref that wasn't
  * matched.  Return 0 if all sought refs were matched, otherwise 1.

object.h

@@ -60,7 +60,7 @@ struct object_array {
 /*
  * object flag allocation:
  * revision.h:               0---------10         15             23------26
- * fetch-pack.c:             01
+ * fetch-pack.c:             01    67
  * negotiator/default.c:       2--5
  * walker.c:                 0-2
  * upload-pack.c:                4       11-----14  16-----19

t/t5701-git-serve.sh

@@ -16,7 +16,7 @@ test_expect_success 'test capability advertisement' '
 	version 2
 	agent=git/$(git version | cut -d" " -f3)
 	ls-refs=unborn
-	fetch=shallow
+	fetch=shallow wait-for-done
 	server-option
 	object-format=$(test_oid algo)
 	0000

t/t5702-protocol-v2.sh

@@ -585,6 +585,49 @@ test_expect_success 'deepen-relative' '
 	test_cmp expected actual
 '
 
+setup_negotiate_only () {
+	SERVER="$1"
+	URI="$2"
+
+	rm -rf "$SERVER" client
+
+	git init "$SERVER"
+	test_commit -C "$SERVER" one
+	test_commit -C "$SERVER" two
+
+	git clone "$URI" client
+	test_commit -C client three
+}
+
+test_expect_success 'file:// --negotiate-only' '
+	SERVER="server" &&
+	URI="file://$(pwd)/server" &&
+
+	setup_negotiate_only "$SERVER" "$URI" &&
+
+	git -c protocol.version=2 -C client fetch \
+		--no-tags \
+		--negotiate-only \
+		--negotiation-tip=$(git -C client rev-parse HEAD) \
+		origin >out &&
+	COMMON=$(git -C "$SERVER" rev-parse two) &&
+	grep "$COMMON" out
+'
+
+test_expect_success 'file:// --negotiate-only with protocol v0' '
+	SERVER="server" &&
+	URI="file://$(pwd)/server" &&
+
+	setup_negotiate_only "$SERVER" "$URI" &&
+
+	test_must_fail git -c protocol.version=0 -C client fetch \
+		--no-tags \
+		--negotiate-only \
+		--negotiation-tip=$(git -C client rev-parse HEAD) \
+		origin 2>err &&
+	test_i18ngrep "negotiate-only requires protocol v2" err
+'
+
 # Test protocol v2 with 'http://' transport
 #
 . "$TEST_DIRECTORY"/lib-httpd.sh
@@ -1035,6 +1078,52 @@ test_expect_success 'packfile-uri with transfer.fsckobjects fails when .gitmodul
 	test_i18ngrep "disallowed submodule name" err
 '
 
+test_expect_success 'http:// --negotiate-only' '
+	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
+	URI="$HTTPD_URL/smart/server" &&
+
+	setup_negotiate_only "$SERVER" "$URI" &&
+
+	git -c protocol.version=2 -C client fetch \
+		--no-tags \
+		--negotiate-only \
+		--negotiation-tip=$(git -C client rev-parse HEAD) \
+		origin >out &&
+	COMMON=$(git -C "$SERVER" rev-parse two) &&
+	grep "$COMMON" out
+'
+
+test_expect_success 'http:// --negotiate-only without wait-for-done support' '
+	SERVER="server" &&
+	URI="$HTTPD_URL/one_time_perl/server" &&
+
+	setup_negotiate_only "$SERVER" "$URI" &&
+
+	echo "s/ wait-for-done/ xxxx-xxx-xxxx/" \
+		>"$HTTPD_ROOT_PATH/one-time-perl" &&
+
+	test_must_fail git -c protocol.version=2 -C client fetch \
+		--no-tags \
+		--negotiate-only \
+		--negotiation-tip=$(git -C client rev-parse HEAD) \
+		origin 2>err &&
+	test_i18ngrep "server does not support wait-for-done" err
+'
+
+test_expect_success 'http:// --negotiate-only with protocol v0' '
+	SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
+	URI="$HTTPD_URL/smart/server" &&
+
+	setup_negotiate_only "$SERVER" "$URI" &&
+
+	test_must_fail git -c protocol.version=0 -C client fetch \
+		--no-tags \
+		--negotiate-only \
+		--negotiation-tip=$(git -C client rev-parse HEAD) \
+		origin 2>err &&
+	test_i18ngrep "negotiate-only requires protocol v2" err
+'
+
 # DO NOT add non-httpd-specific tests here, because the last part of this
 # test script is only executed when httpd is available and enabled.
 

transport-helper.c

@@ -684,6 +684,16 @@ static int fetch(struct transport *transport,
 		return transport->vtable->fetch(transport, nr_heads, to_fetch);
 	}
 
+	/*
+	 * If we reach here, then the server, the client, and/or the transport
+	 * helper does not support protocol v2. --negotiate-only requires
+	 * protocol v2.
+	 */
+	if (data->transport_options.acked_commits) {
+		warning(_("--negotiate-only requires protocol v2"));
+		return -1;
+	}
+
 	if (!data->get_refs_list_called)
 		get_refs_list_using_list(transport, 0);