Robert Wojciechowski
a1faf7e916
* fix: isolate local worker databases and avoid port conflicts * fix: harden local worker startup preflight and database paths Handle auto-launch before the master binds, allow TIME_WAIT restarts without accepting active listeners, resolve relative paths in the worker cwd, and round-trip SQLite URLs through SQLAlchemy. Add regressions and remove the README additions.
98 lines
3.9 KiB
Python
98 lines
3.9 KiB
Python
"""Host-local worker port selection and launch preflight (no ComfyUI imports)."""
|
|
import errno
|
|
import os
|
|
import socket
|
|
from urllib.parse import urlsplit
|
|
|
|
|
|
def _port_number(value):
|
|
try:
|
|
port = int(value)
|
|
except (TypeError, ValueError):
|
|
raise ValueError("Worker port must be an integer between 1 and 65535") from None
|
|
if isinstance(value, (bool, float)) or not 1 <= port <= 65535:
|
|
raise ValueError("Worker port must be an integer between 1 and 65535")
|
|
return port
|
|
|
|
|
|
def _local_config(worker):
|
|
local_hosts = ("localhost", "127.0.0.1", "0.0.0.0", "::1", "::")
|
|
host = (worker.get("host") or "localhost").strip().lower()
|
|
if worker.get("type") == "local" or host in local_hosts:
|
|
return True
|
|
try:
|
|
host = urlsplit(host if "://" in host else "//" + host).hostname
|
|
except ValueError:
|
|
return False
|
|
return host in local_hosts
|
|
|
|
|
|
def _reserved_ports(workers, exclude_id=None):
|
|
reserved = {}
|
|
for worker in workers:
|
|
if exclude_id is not None and str(worker.get("id")) == str(exclude_id):
|
|
continue
|
|
if not _local_config(worker):
|
|
continue
|
|
try:
|
|
port = _port_number(worker.get("port"))
|
|
except ValueError:
|
|
continue
|
|
reserved[port] = worker.get("name") or worker.get("id") or "another local worker"
|
|
return reserved
|
|
|
|
|
|
def is_port_available(port):
|
|
"""Match asyncio's address reuse while rejecting active IPv4/IPv6 listeners."""
|
|
addresses = [(socket.AF_INET, "0.0.0.0")]
|
|
if socket.has_ipv6:
|
|
addresses.append((socket.AF_INET6, "::"))
|
|
for family, address in addresses:
|
|
try:
|
|
with socket.socket(family, socket.SOCK_STREAM) as probe:
|
|
if os.name != "nt":
|
|
# Like asyncio, allow a restart while old connections are
|
|
# in TIME_WAIT. Do not enable SO_REUSEPORT.
|
|
probe.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
|
|
elif hasattr(socket, "SO_EXCLUSIVEADDRUSE"):
|
|
# Windows SO_REUSEADDR can steal an active listener's port.
|
|
probe.setsockopt(socket.SOL_SOCKET, socket.SO_EXCLUSIVEADDRUSE, 1)
|
|
probe.bind((address, port))
|
|
probe.listen(1)
|
|
except OSError as exc:
|
|
if family == socket.AF_INET6 and exc.errno in (errno.EAFNOSUPPORT, errno.EADDRNOTAVAIL):
|
|
continue
|
|
return False
|
|
return True
|
|
|
|
|
|
def allocate_worker_ports(master_port, workers, count):
|
|
"""Select ports above the actual master, skipping reservations/listeners.
|
|
|
|
This is a snapshot, not a reservation. Launch must validate again because
|
|
another process can claim a suggested port before the user starts a worker.
|
|
"""
|
|
master_port = _port_number(master_port)
|
|
reserved = _reserved_ports(workers)
|
|
selected = []
|
|
if count == 0:
|
|
return selected
|
|
for port in range(master_port + 1, 65536):
|
|
if port not in reserved and is_port_available(port):
|
|
selected.append(port)
|
|
if len(selected) == count:
|
|
return selected
|
|
raise ValueError(f"Not enough available worker ports above master port {master_port}; need {count}")
|
|
|
|
|
|
def validate_worker_port(worker, master_port, workers):
|
|
"""Reject conflicts without silently changing a configured worker port."""
|
|
port = _port_number(worker.get("port"))
|
|
if port == _port_number(master_port):
|
|
raise ValueError(f"Worker port {port} conflicts with the master port {master_port}; choose another worker port")
|
|
reserved = _reserved_ports(workers, exclude_id=worker.get("id"))
|
|
if port in reserved:
|
|
raise ValueError(f"Worker port {port} is assigned to local worker {reserved[port]}; choose another worker port")
|
|
if not is_port_available(port):
|
|
raise ValueError(f"Worker port {port} is already in use on this host; choose another worker port")
|