diff options
Diffstat (limited to 'packages/meshbay-cli/src/meshbay_cli/client')
3 files changed, 152 insertions, 0 deletions
diff --git a/packages/meshbay-cli/src/meshbay_cli/client/sctp_fix.py b/packages/meshbay-cli/src/meshbay_cli/client/sctp_fix.py new file mode 100644 index 0000000..62835d3 --- /dev/null +++ b/packages/meshbay-cli/src/meshbay_cli/client/sctp_fix.py @@ -0,0 +1,126 @@ +"""Fixes to aiortc's SCTP stack, applied on import (aiortc 1.15). + +The first two are the node's (`meshbay_node/transport/webrtc/sctp_fix.py`, where +why each is needed is written down); this is a copy because the client does not +depend on the node, and `meshbay-common` does not depend on aiortc (the hub uses +it without). `test_sctp_fix.py` in each package holds its copy to aiortc itself. + +In a download this side is the receiver of the node's 1 MiB `file_chunk` +messages, about 870 SCTP packets each, and two receiver costs set the ceiling. +Measured on loopback, 400 MB, one connection: + +- aiortc walked every fragment of the message in progress after each one + arrived, 153 million steps: two thirds of the client's CPU. Fixed by the + reassembly fix below — 20 MB/s became 28; +- it acknowledged every packet. RFC 4960 §6.2 asks for one SACK every second + packet (Chromium does that), and each SACK costs the node a DTLS decryption + and a parse on the one core that also sends: more of its time than sending + the data. One every second packet — 28 MB/s became 39, the node's own figure + for the transfer 49. + +A SACK still goes at once when something is out of order or duplicated (that is +the loss signal the sender is waiting for) or the packet carried anything other +than data; a lone packet is acknowledged within `SACK_DELAY_S`. +""" + +import asyncio +import contextlib + +from aiortc.rtcsctptransport import ( + SCTP_DATA_LAST_FRAG, + DataChunk, + InboundStream, + InitChunk, + RTCSctpTransport, + parse_packet, +) + +# RFC 4960 §6.2: at most 500 ms; 200 is what implementations use. +SACK_DELAY_S = 0.2 + + +def _flight_size_increase(self, chunk) -> None: + chunk._acked = False + self._flight_size += chunk._book_size + + +RTCSctpTransport._flight_size_increase = _flight_size_increase + + +_add_chunk = InboundStream.add_chunk +_pop_messages = InboundStream.pop_messages +_prune_chunks = InboundStream.prune_chunks + + +def add_chunk(self, chunk) -> None: + _add_chunk(self, chunk) + if chunk.flags & SCTP_DATA_LAST_FRAG: + self._last_frags = getattr(self, "_last_frags", 0) + 1 + + +def pop_messages(self): + # Only ever too high (a pruned last fragment), never too low: a message + # leaves the reassembly with exactly one last fragment, and only here. + if not getattr(self, "_last_frags", 0): + return + for message in _pop_messages(self): + self._last_frags -= 1 + yield message + + +def prune_chunks(self, tsn: int) -> int: + size = _prune_chunks(self, tsn) + self._last_frags = sum(1 for c in self.reassembly if c.flags & SCTP_DATA_LAST_FRAG) + return size + + +InboundStream.add_chunk = add_chunk +InboundStream.pop_messages = pop_messages +InboundStream.prune_chunks = prune_chunks + + +async def _handle_data(self, data: bytes) -> None: + """aiortc's own, down to the SACK at the end: that one may wait for a + second packet.""" + try: + _, _, verification_tag, chunks = parse_packet(data) + except ValueError: + return + if any(isinstance(x, InitChunk) for x in chunks): + assert len(chunks) == 1 + expected_tag = 0 + else: + expected_tag = self._local_verification_tag + if verification_tag != expected_tag: + return + for chunk in chunks: + await self._receive_chunk(chunk) + if not self._sack_needed: + return + self._sack_packets = getattr(self, "_sack_packets", 0) + 1 + if (self._sack_packets >= 2 or self._sack_misordered or self._sack_duplicates + or not all(isinstance(c, DataChunk) for c in chunks)): + await _sack_now(self) + elif getattr(self, "_sack_timer", None) is None: + self._sack_timer = self._loop.call_later(SACK_DELAY_S, _sack_later, self) + + +async def _sack_now(self) -> None: + timer = getattr(self, "_sack_timer", None) + if timer is not None: + timer.cancel() + self._sack_timer = None + self._sack_packets = 0 + if self._sack_needed and self._association_state != self.State.CLOSED: + # The DTLS transport may be gone under a timer that fired late. + with contextlib.suppress(ConnectionError): + await self._send_sack() + + +def _sack_later(self) -> None: + self._sack_timer = None + # Held: a task nobody references can be collected before it runs. + self._sack_task = asyncio.ensure_future(_sack_now(self)) + + +RTCSctpTransport._handle_data = _handle_data diff --git a/packages/meshbay-cli/src/meshbay_cli/client/session.py b/packages/meshbay-cli/src/meshbay_cli/client/session.py index d10acc8..b6fc9e2 100644 --- a/packages/meshbay-cli/src/meshbay_cli/client/session.py +++ b/packages/meshbay-cli/src/meshbay_cli/client/session.py @@ -63,6 +63,7 @@ from meshbay_common.handshake import ( from meshbay_common.join import join_transcript from ..errors import NODE, NODE_KEY, VERSION, CliError +from . import sctp_fix, udp_buffer # noqa: F401 (patch aiortc and aioice on import) from .account import Account from .keys import ( LEGACY_MAGIC, @@ -250,6 +251,13 @@ class GroupSession: raise CliError(NODE, "The group's index does not open under the group key; " "the session is ended.") from e + def open_delta(self, msg: dict) -> dict: + """A pushed `index_delta`, opened under the group key.""" + try: + return unseal(self.gek, PURPOSE_INDEX, "index_delta", self.group_id, msg) + except Exception as e: + raise CliError(NODE, "An index update does not open under the group key.") from e + async def close(self) -> None: with contextlib.suppress(Exception): await self.pc.close() diff --git a/packages/meshbay-cli/src/meshbay_cli/client/udp_buffer.py b/packages/meshbay-cli/src/meshbay_cli/client/udp_buffer.py new file mode 100644 index 0000000..c0045d8 --- /dev/null +++ b/packages/meshbay-cli/src/meshbay_cli/client/udp_buffer.py @@ -0,0 +1,18 @@ +"""A larger receive buffer on the client's ICE sockets, applied on import. + +In a download the client is the receiver, and it reads its socket from Python +— on the same event loop as the terminal interface — more slowly than a node +sends in bursts. aioice asks the kernel for 256 KB per socket; what does not fit +is dropped by this machine's kernel (`UdpRcvbufErrors`), the node's SCTP sender +takes each drop for congestion and halves its window. Measured on loopback, 400 +MB: 3245 drops and 19 MB/s with 256 KB. The node does the same for the same +reason in the other direction (`meshbay_node/transport/webrtc/udp_buffer.py`). + +Linux grants no more than `net.core.rmem_max`; Windows grants what is asked. +""" + +import aioice.turn + +WANTED = 4 * 1024 * 1024 + +aioice.turn.UDP_SOCKET_BUFFER_SIZE = WANTED |