fetch-pack: in protocol v2, in_vain only after ACK

When fetching, Git stops negotiation when it has sent at least
MAX_IN_VAIN (which is 256) "have" lines without having any of them
ACK-ed. But this is supposed to trigger only after the first ACK, as
pack-protocol.txt says:

  However, the 256 limit *only* turns on in the canonical client
  implementation if we have received at least one "ACK %s continue"
  during a prior round.  This helps to ensure that at least one common
  ancestor is found before we give up entirely.

The code path for protocol v0 observes this, but not protocol v2,
resulting in shorter negotiation rounds but significantly larger
packfiles. Teach the code path for protocol v2 to check this criterion
only after at least one ACK was received.

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

Author: jonathantanmy

fetch-pack.c

@@ -1143,6 +1143,7 @@ static void add_common(struct strbuf *req_buf, struct oidset *common)
 }
 
 static int add_haves(struct fetch_negotiator *negotiator,
+		     int seen_ack,
 		     struct strbuf *req_buf,
 		     int *haves_to_send, int *in_vain)
 {
@@ -1157,7 +1158,7 @@ static int add_haves(struct fetch_negotiator *negotiator,
 	}
 
 	*in_vain += haves_added;
-	if (!haves_added || *in_vain >= MAX_IN_VAIN) {
+	if (!haves_added || (seen_ack && *in_vain >= MAX_IN_VAIN)) {
 		/* Send Done */
 		packet_buf_write(req_buf, "done\n");
 		ret = 1;
@@ -1173,7 +1174,7 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
 			      struct fetch_pack_args *args,
 			      const struct ref *wants, struct oidset *common,
 			      int *haves_to_send, int *in_vain,
-			      int sideband_all)
+			      int sideband_all, int seen_ack)
 {
 	int ret = 0;
 	struct strbuf req_buf = STRBUF_INIT;
@@ -1230,7 +1231,8 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
 		add_common(&req_buf, common);
 
 		/* Add initial haves */
-		ret = add_haves(negotiator, &req_buf, haves_to_send, in_vain);
+		ret = add_haves(negotiator, seen_ack, &req_buf,
+				haves_to_send, in_vain);
 	}
 
 	/* Send request */
@@ -1464,6 +1466,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 	int haves_to_send = INITIAL_FLUSH;
 	struct fetch_negotiator negotiator_alloc;
 	struct fetch_negotiator *negotiator;
+	int seen_ack = 0;
 
 	if (args->no_dependents) {
 		negotiator = NULL;
@@ -1520,7 +1523,8 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 			if (send_fetch_request(negotiator, fd[1], args, ref,
 					       &common,
 					       &haves_to_send, &in_vain,
-					       reader.use_sideband))
+					       reader.use_sideband,
+					       seen_ack))
 				state = FETCH_GET_PACK;
 			else
 				state = FETCH_PROCESS_ACKS;
@@ -1533,6 +1537,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 				break;
 			case COMMON_FOUND:
 				in_vain = 0;
+				seen_ack = 1;
 				/* fallthrough */
 			case NO_COMMON_FOUND:
 				state = FETCH_SEND_REQUEST;

t/t5500-fetch-pack.sh

@@ -385,6 +385,24 @@ test_expect_success 'clone shallow with packed refs' '
 	test_cmp count8.expected count8.actual
 '
 
+test_expect_success 'in_vain not triggered before first ACK' '
+	rm -rf myserver myclient trace &&
+	git init myserver &&
+	test_commit -C myserver foo &&
+	git clone "file://$(pwd)/myserver" myclient &&
+
+	# MAX_IN_VAIN is 256. Because of batching, the client will send 496
+	# (16+32+64+128+256) commits, not 256, before giving up. So create 496
+	# irrelevant commits.
+	test_commit_bulk -C myclient 496 &&
+
+	# The new commit that the client wants to fetch.
+	test_commit -C myserver bar &&
+
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C myclient fetch --progress origin &&
+	test_i18ngrep "Total 3 " trace
+'
+
 test_expect_success 'fetch in shallow repo unreachable shallow objects' '
 	(
 		git clone --bare --branch B --single-branch "file://$(pwd)/." no-reflog &&