Files
neuron-tai/packages/gateway/meshnet_gateway/prefill_backpressure.py
2026-07-12 11:17:03 +03:00

131 lines
4.6 KiB
Python

"""Bounded, ordered prefill transfer primitives.
Prefill chunks mutate the downstream shard's session cache, so they must reach a
route in order. This deliberately uses a serial acknowledgement window: it is
the safe default for both current peers and old peers which do not advertise a
windowing capability. The configured in-flight limit is still explicit so a
future ordered transport can widen the window without changing callers.
"""
from __future__ import annotations
import os
from dataclasses import dataclass
from threading import Event
from typing import Callable, Iterable, TypeVar
DEFAULT_PREFILL_CHUNK_TOKENS = 128
DEFAULT_PREFILL_MAX_IN_FLIGHT = 1
DEFAULT_PREFILL_MAX_CHUNK_BYTES = 8 * 1024 * 1024
T = TypeVar("T")
R = TypeVar("R")
@dataclass(frozen=True)
class PrefillTransferLimits:
"""Configuration for one ordered prefill seam."""
chunk_tokens: int = DEFAULT_PREFILL_CHUNK_TOKENS
max_in_flight: int = DEFAULT_PREFILL_MAX_IN_FLIGHT
max_chunk_bytes: int = DEFAULT_PREFILL_MAX_CHUNK_BYTES
@property
def effective_in_flight(self) -> int:
"""Current peers require ordered session-cache mutation, hence one ack."""
return 1
@property
def max_buffered_bytes(self) -> int:
"""Hard accounting bound, including any future wider ack window."""
return self.max_chunk_bytes * self.max_in_flight
@classmethod
def from_env(cls) -> "PrefillTransferLimits":
# MESHNET_CHUNK_TOKENS was the pre-DIP-007 name. Keep it as a fallback
# so existing deployments retain their chunk shape while upgrading.
return cls(
chunk_tokens=_positive_env(
"MESHNET_PREFILL_CHUNK_TOKENS",
_positive_env("MESHNET_CHUNK_TOKENS", DEFAULT_PREFILL_CHUNK_TOKENS),
),
max_in_flight=_positive_env(
"MESHNET_PREFILL_MAX_IN_FLIGHT", DEFAULT_PREFILL_MAX_IN_FLIGHT,
),
max_chunk_bytes=_positive_env(
"MESHNET_PREFILL_MAX_CHUNK_BYTES", DEFAULT_PREFILL_MAX_CHUNK_BYTES,
),
)
class BoundedPrefillSender:
"""Send lazily-produced chunks with bounded ownership and ordered acks."""
def __init__(self, limits: PrefillTransferLimits) -> None:
self.limits = limits
self.buffered_bytes = 0
self.peak_buffered_bytes = 0
self.in_flight = 0
self.peak_in_flight = 0
self.closed = False
def send(
self,
chunks: Iterable[T],
*,
body_size: Callable[[T], int],
forward: Callable[[T], R],
cancelled: Event | None = None,
) -> list[R]:
"""Forward chunks in source order, releasing each body after its ack.
``forward`` is synchronous by design: a slow consumer therefore blocks
production of the next chunk instead of accumulating an unbounded queue.
Every retained body is dropped on cancellation or route failure.
"""
results: list[R] = []
try:
for chunk in chunks:
if self.closed or (cancelled is not None and cancelled.is_set()):
break
size = body_size(chunk)
if size < 0:
raise ValueError("prefill chunk size cannot be negative")
if size > self.limits.max_chunk_bytes:
raise ValueError(
f"prefill chunk exceeds {self.limits.max_chunk_bytes} byte limit"
)
self.buffered_bytes += size
self.in_flight += 1
self.peak_buffered_bytes = max(self.peak_buffered_bytes, self.buffered_bytes)
self.peak_in_flight = max(self.peak_in_flight, self.in_flight)
try:
results.append(forward(chunk))
finally:
# Do not retain a body while waiting for the next chunk.
self.buffered_bytes -= size
self.in_flight -= 1
except BaseException:
self.close()
raise
return results
def close(self) -> None:
"""Release accounting after cancellation or route failure.
The sender deliberately owns no queued chunk references; callers must
discard their iterator on close rather than trying to drain it.
"""
self.buffered_bytes = 0
self.in_flight = 0
self.closed = True
def _positive_env(name: str, default: int) -> int:
try:
value = int(os.environ.get(name, default))
except (TypeError, ValueError):
return default
return value if value > 0 else default