Merge branch 'jt/cdn-offload'

The "fetch/clone" protocol has been updated to allow the server to
instruct the clients to grab pre-packaged packfile(s) in addition
to the packed object data coming over the wire.

* jt/cdn-offload:
  upload-pack: fix a sparse '0 as NULL pointer' warning
  upload-pack: send part of packfile response as uri
  fetch-pack: support more than one pack lockfile
  upload-pack: refactor reading of pack-objects out
  Documentation: add Packfile URIs design doc
  Documentation: order protocol v2 sections
  http-fetch: support fetching packfiles by URL
  http-fetch: refactor into function
  http: refactor finish_http_pack_request()
  http: use --stdin when indexing dumb HTTP pack

1 files changed, 117 insertions, 39 deletions

diff --git a/upload-pack.c b/upload-pack.c
index f899fdf..39d0cf0 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -84,6 +84,7 @@ struct upload_pack_data {
 	/* 0 for no sideband, otherwise DEFAULT_PACKET_MAX or LARGE_PACKET_MAX */
 	int use_sideband;
 
+	struct string_list uri_protocols;
 	enum allow_uor allow_uor;
 
 	struct list_objects_filter_options filter_options;
@@ -117,6 +118,7 @@ static void upload_pack_data_init(struct upload_pack_data *data)
 	struct oid_array haves = OID_ARRAY_INIT;
 	struct object_array shallows = OBJECT_ARRAY_INIT;
 	struct string_list deepen_not = STRING_LIST_INIT_DUP;
+	struct string_list uri_protocols = STRING_LIST_INIT_DUP;
 	struct object_array extra_edge_obj = OBJECT_ARRAY_INIT;
 
 	memset(data, 0, sizeof(*data));
@@ -127,6 +129,7 @@ static void upload_pack_data_init(struct upload_pack_data *data)
 	data->haves = haves;
 	data->shallows = shallows;
 	data->deepen_not = deepen_not;
+	data->uri_protocols = uri_protocols;
 	data->extra_edge_obj = extra_edge_obj;
 	packet_writer_init(&data->writer, 1);
 
@@ -179,13 +182,86 @@ static int write_one_shallow(const struct commit_graft *graft, void *cb_data)
 	return 0;
 }
 
-static void create_pack_file(struct upload_pack_data *pack_data)
+struct output_state {
+	char buffer[8193];
+	int used;
+	unsigned packfile_uris_started : 1;
+	unsigned packfile_started : 1;
+};
+
+static int relay_pack_data(int pack_objects_out, struct output_state *os,
+			   int use_sideband, int write_packfile_line)
+{
+	/*
+	 * We keep the last byte to ourselves
+	 * in case we detect broken rev-list, so that we
+	 * can leave the stream corrupted.  This is
+	 * unfortunate -- unpack-objects would happily
+	 * accept a valid packdata with trailing garbage,
+	 * so appending garbage after we pass all the
+	 * pack data is not good enough to signal
+	 * breakage to downstream.
+	 */
+	ssize_t readsz;
+
+	readsz = xread(pack_objects_out, os->buffer + os->used,
+		       sizeof(os->buffer) - os->used);
+	if (readsz < 0) {
+		return readsz;
+	}
+	os->used += readsz;
+
+	while (!os->packfile_started) {
+		char *p;
+		if (os->used >= 4 && !memcmp(os->buffer, "PACK", 4)) {
+			os->packfile_started = 1;
+			if (write_packfile_line) {
+				if (os->packfile_uris_started)
+					packet_delim(1);
+				packet_write_fmt(1, "\1packfile\n");
+			}
+			break;
+		}
+		if ((p = memchr(os->buffer, '\n', os->used))) {
+			if (!os->packfile_uris_started) {
+				os->packfile_uris_started = 1;
+				if (!write_packfile_line)
+					BUG("packfile_uris requires sideband-all");
+				packet_write_fmt(1, "\1packfile-uris\n");
+			}
+			*p = '\0';
+			packet_write_fmt(1, "\1%s\n", os->buffer);
+
+			os->used -= p - os->buffer + 1;
+			memmove(os->buffer, p + 1, os->used);
+		} else {
+			/*
+			 * Incomplete line.
+			 */
+			return readsz;
+		}
+	}
+
+	if (os->used > 1) {
+		send_client_data(1, os->buffer, os->used - 1, use_sideband);
+		os->buffer[0] = os->buffer[os->used - 1];
+		os->used = 1;
+	} else {
+		send_client_data(1, os->buffer, os->used, use_sideband);
+		os->used = 0;
+	}
+
+	return readsz;
+}
+
+static void create_pack_file(struct upload_pack_data *pack_data,
+			     const struct string_list *uri_protocols)
 {
 	struct child_process pack_objects = CHILD_PROCESS_INIT;
-	char data[8193], progress[128];
+	struct output_state output_state = { { 0 } };
+	char progress[128];
 	char abort_msg[] = "aborting due to possible repository "
 		"corruption on the remote side.";
-	int buffered = -1;
 	ssize_t sz;
 	int i;
 	FILE *pipe_fd;
@@ -229,6 +305,11 @@ static void create_pack_file(struct upload_pack_data *pack_data)
 					 spec);
 		}
 	}
+	if (uri_protocols) {
+		for (i = 0; i < uri_protocols->nr; i++)
+			argv_array_pushf(&pack_objects.args, "--uri-protocol=%s",
+					 uri_protocols->items[i].string);
+	}
 
 	pack_objects.in = -1;
 	pack_objects.out = -1;
@@ -318,40 +399,17 @@ static void create_pack_file(struct upload_pack_data *pack_data)
 			continue;
 		}
 		if (0 <= pu && (pfd[pu].revents & (POLLIN|POLLHUP))) {
-			/* Data ready; we keep the last byte to ourselves
-			 * in case we detect broken rev-list, so that we
-			 * can leave the stream corrupted.  This is
-			 * unfortunate -- unpack-objects would happily
-			 * accept a valid packdata with trailing garbage,
-			 * so appending garbage after we pass all the
-			 * pack data is not good enough to signal
-			 * breakage to downstream.
-			 */
-			char *cp = data;
-			ssize_t outsz = 0;
-			if (0 <= buffered) {
-				*cp++ = buffered;
-				outsz++;
-			}
-			sz = xread(pack_objects.out, cp,
-				  sizeof(data) - outsz);
-			if (0 < sz)
-				;
-			else if (sz == 0) {
+			int result = relay_pack_data(pack_objects.out,
+						     &output_state,
+						     pack_data->use_sideband,
+						     !!uri_protocols);
+
+			if (result == 0) {
 				close(pack_objects.out);
 				pack_objects.out = -1;
-			}
-			else
+			} else if (result < 0) {
 				goto fail;
-			sz += outsz;
-			if (1 < sz) {
-				buffered = data[sz-1] & 0xFF;
-				sz--;
 			}
-			else
-				buffered = -1;
-			send_client_data(1, data, sz,
-					 pack_data->use_sideband);
 		}
 
 		/*
@@ -376,9 +434,8 @@ static void create_pack_file(struct upload_pack_data *pack_data)
 	}
 
 	/* flush the data */
-	if (0 <= buffered) {
-		data[0] = buffered;
-		send_client_data(1, data, 1,
+	if (output_state.used > 0) {
+		send_client_data(1, output_state.buffer, output_state.used,
 				 pack_data->use_sideband);
 		fprintf(stderr, "flushed.\n");
 	}
@@ -1188,7 +1245,7 @@ void upload_pack(struct upload_pack_options *options)
 		receive_needs(&data, &reader);
 		if (data.want_obj.nr) {
 			get_common_commits(&data, &reader);
-			create_pack_file(&data);
+			create_pack_file(&data, NULL);
 		}
 	}
 
@@ -1341,10 +1398,18 @@ static void process_args(struct packet_reader *request,
 			continue;
 		}
 
+		if (skip_prefix(arg, "packfile-uris ", &p)) {
+			string_list_split(&data->uri_protocols, p, ',', -1);
+			continue;
+		}
+
 		/* ignore unknown lines maybe? */
 		die("unexpected line: '%s'", arg);
 	}
 
+	if (data->uri_protocols.nr && !data->writer.use_sideband)
+		string_list_clear(&data->uri_protocols, 0);
+
 	if (request->status != PACKET_READ_FLUSH)
 		die(_("expected flush after fetch arguments"));
 }
@@ -1502,8 +1567,12 @@ int upload_pack_v2(struct repository *r, struct argv_array *keys,
 			send_wanted_ref_info(&data);
 			send_shallow_info(&data);
 
-			packet_writer_write(&data.writer, "packfile\n");
-			create_pack_file(&data);
+			if (data.uri_protocols.nr) {
+				create_pack_file(&data, &data.uri_protocols);
+			} else {
+				packet_writer_write(&data.writer, "packfile\n");
+				create_pack_file(&data, NULL);
+			}
 			state = FETCH_DONE;
 			break;
 		case FETCH_DONE:
@@ -1522,6 +1591,7 @@ int upload_pack_advertise(struct repository *r,
 		int allow_filter_value;
 		int allow_ref_in_want;
 		int allow_sideband_all_value;
+		char *str = NULL;
 
 		strbuf_addstr(value, "shallow");
 
@@ -1543,6 +1613,14 @@ int upload_pack_advertise(struct repository *r,
 					   &allow_sideband_all_value) &&
 		     allow_sideband_all_value))
 			strbuf_addstr(value, " sideband-all");
+
+		if (!repo_config_get_string(the_repository,
+					    "uploadpack.blobpackfileuri",
+					    &str) &&
+		    str) {
+			strbuf_addstr(value, " packfile-uris");
+			free(str);
+		}
 	}
 
 	return 1;