diff options
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node/transport/webrtc')
3 files changed, 143 insertions, 2 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/transport/webrtc/core.py b/packages/meshbay-node/src/meshbay_node/transport/webrtc/core.py index d197044..07820b2 100644 --- a/packages/meshbay-node/src/meshbay_node/transport/webrtc/core.py +++ b/packages/meshbay-node/src/meshbay_node/transport/webrtc/core.py @@ -15,6 +15,7 @@ from meshbay_common.protocol import MNP from meshbay_node import ops from meshbay_node import transfers as transfers_mod from meshbay_node.transport.webrtc import ( + proactor_udp, # noqa: F401 (patches asyncio's Windows loop on import) sctp_fix, # noqa: F401 (patches aiortc on import) sctp_stats, # noqa: F401 (patches aiortc on import) udp_buffer, # noqa: F401 (patches aioice on import) diff --git a/packages/meshbay-node/src/meshbay_node/transport/webrtc/proactor_udp.py b/packages/meshbay-node/src/meshbay_node/transport/webrtc/proactor_udp.py new file mode 100644 index 0000000..38cb97c --- /dev/null +++ b/packages/meshbay-node/src/meshbay_node/transport/webrtc/proactor_udp.py @@ -0,0 +1,139 @@ +"""Datagrams moved straight through the socket on Windows' event loop, applied +on import. + +The node runs on the ProactorEventLoop, the one that can start ffmpeg there +(`platform.configure_event_loop`), and so do its connection processes. Its +datagram transport keeps one overlapped operation in each direction and starts +the next only from the completion callback of the one before, which runs on a +later turn of the loop. So a socket sends **one datagram per turn of the loop, +and receives one**, however many are waiting, and a turn lasts as long as +everything else the loop has to do: the other connections, reading the file, +the hub. The busier the node, the slower every connection, with cores to spare. + +Measured on loopback, 1200-byte datagrams, with the loop otherwise busy 0.5 ms +a turn: 1,928 sent a second (2.3 MB/s), and 1,954 received, the kernel dropping +87 % of what arrived; straight through the socket, 88,000 sent, and every +datagram received at the 20,000 a second it was sent at. In the node holding the +connections itself, a browser's download over eight connections ran at 9.1 MB/s +with the node at 45 % of a core and an SCTP round trip of 745 ms on loopback: +that is the queue in front of each socket. In a connection process serving the +command-line client, 42 % of the time was `IocpProactor.sendto`. Linux never +paid for the sending half: the selector loop's transport tries the socket first +and queues only what it refuses. + +Sending: a datagram goes out with a non-blocking `sendto` when nothing is queued +and no overlapped send is pending, so order is kept; anything else, the socket +refusing included, goes through the proactor's own queue as before. + +Receiving: once an overlapped read completes, its datagram is delivered, then +whatever else the socket holds is read with non-blocking `recvfrom`, and only +then is the next overlapped read posted. Never while one is pending, which +could hand a later datagram to the completion port ahead of the ones read here. +The overlapped path turns the ICMP "port unreachable" a send to a silent +address brings back into an empty read; read directly it is a +ConnectionResetError, and it is skipped the same way. + +No effect off Windows, where the class is never used. +""" + +import sys +from asyncio import exceptions, proactor_events + +_Transport = proactor_events._ProactorDatagramTransport +_proactor_sendto = _Transport.sendto + +# Datagrams read straight from the socket after one completion, at most: a +# socket under a flood still lets the loop turn. +DRAIN_MAX = 256 + + +def sendto(self, data, addr=None) -> None: + if (self._write_fut is None and not self._buffer and not self._conn_lost + and isinstance(data, (bytes, bytearray, memoryview)) and data + and (self._address is None or addr in (None, self._address))): + try: + if self._address is not None: + self._sock.send(data) + else: + self._sock.sendto(data, addr) + return + except (BlockingIOError, InterruptedError): + pass + except OSError as exc: + # What the overlapped path does with a failed send. + self._protocol.error_received(exc) + return + _proactor_sendto(self, data, addr) + + +def _deliver(self, data, addr) -> None: + """To the protocol, and whatever it raises reported as a callback's would + be: in CPython's order the next read was posted first, and an exception + here must not end the reading either.""" + try: + self._protocol.datagram_received(data, addr) + except (SystemExit, KeyboardInterrupt): + raise + except BaseException as exc: + self._loop.call_exception_handler({ + "message": "Exception in datagram_received", "exception": exc, + "transport": self, "protocol": self._protocol}) + + +def _drain(self) -> None: + for _ in range(DRAIN_MAX): + if self._conn_lost or self._closing: + return + try: + if self._address is not None: + data, addr = self._sock.recv(self.max_size), self._address + else: + data, addr = self._sock.recvfrom(self.max_size) + except (BlockingIOError, InterruptedError): + return + except ConnectionResetError: + continue + except OSError as exc: + # The overlapped read posted next meets it again, and reports it + # the proactor's way. + self._protocol.error_received(exc) + return + if data: + _deliver(self, data, addr) + + +def _loop_reading(self, fut=None) -> None: + """CPython's own (3.12), but a completed read is delivered and the socket + drained before the next overlapped read is posted, not after.""" + try: + if self._conn_lost: + return + assert self._read_fut is fut or (self._read_fut is None and self._closing) + self._read_fut = None + if fut is not None: + res = fut.result() + if self._closing: + return + data, addr = (res, self._address) if self._address is not None else res + if data: + _deliver(self, data, addr) + _drain(self) + if self._conn_lost: + return + if self._address is not None: + self._read_fut = self._loop._proactor.recv(self._sock, self.max_size) + else: + self._read_fut = self._loop._proactor.recvfrom(self._sock, self.max_size) + except OSError as exc: + self._protocol.error_received(exc) + except exceptions.CancelledError: + if not self._closing: + raise + else: + if self._read_fut is not None: + self._read_fut.add_done_callback(self._loop_reading) + + +if sys.platform == "win32": + _Transport.sendto = sendto + _Transport._loop_reading = _loop_reading diff --git a/packages/meshbay-node/src/meshbay_node/transport/webrtc/worker.py b/packages/meshbay-node/src/meshbay_node/transport/webrtc/worker.py index 832428a..c933aba 100644 --- a/packages/meshbay-node/src/meshbay_node/transport/webrtc/worker.py +++ b/packages/meshbay-node/src/meshbay_node/transport/webrtc/worker.py @@ -224,9 +224,10 @@ async def _main() -> None: root.handlers[:] = [_Forward(writer.write)] root.setLevel(hello.get("level", logging.INFO)) - # Patches aiortc on import, as the node does for the connections it holds - # itself. + # Patches aiortc, and asyncio's Windows loop, on import, as the node does + # for the connections it holds itself. from meshbay_node.transport.webrtc import ( # noqa: F401 + proactor_udp, sctp_fix, sctp_stats, udp_buffer, |