fix: isolate local worker databases and avoid port conflicts (#93)

* 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.
This commit is contained in:
Robert Wojciechowski
2026-10-10 16:00:31 -07:00
committed by GitHub
parent 32ac027e0e
commit a1faf7e916
9 changed files with 614 additions and 4 deletions
+219 -1
View File
@@ -1,11 +1,16 @@
import importlib.util
import os
import sys
import tempfile
import types
import unittest
from argparse import Namespace
from pathlib import Path
from unittest.mock import patch
from sqlalchemy import create_engine
from sqlalchemy.engine import URL, make_url
def _load_process_module(module_filename: str):
module_path = Path(__file__).resolve().parents[1] / "workers" / "process" / module_filename
@@ -21,7 +26,7 @@ def _load_process_module(module_filename: str):
sys.modules[package_name] = root_pkg
workers_pkg = types.ModuleType(f"{package_name}.workers")
workers_pkg.__path__ = []
workers_pkg.__path__ = [str(module_path.parents[1])]
sys.modules[f"{package_name}.workers"] = workers_pkg
process_pkg = types.ModuleType(f"{package_name}.workers.process")
@@ -39,8 +44,23 @@ def _load_process_module(module_filename: str):
process_module = types.ModuleType(f"{package_name}.utils.process")
process_module.get_python_executable = lambda: "/usr/bin/test-python"
process_module.is_process_alive = lambda _pid: False
process_module.terminate_process = lambda *_args, **_kwargs: None
sys.modules[f"{package_name}.utils.process"] = process_module
config_module = types.ModuleType(f"{package_name}.utils.config")
config_module.load_config = lambda: {"workers": [], "settings": {"stop_workers_on_master_exit": False}}
config_module.save_config = lambda _config: None
sys.modules[f"{package_name}.utils.config"] = config_module
constants_module = types.ModuleType(f"{package_name}.utils.constants")
constants_module.PROCESS_TERMINATION_TIMEOUT = 1
constants_module.PROCESS_WAIT_TIMEOUT = 1
constants_module.WORKER_CHECK_INTERVAL = 0.01
sys.modules[f"{package_name}.utils.constants"] = constants_module
network_module = types.ModuleType(f"{package_name}.utils.network")
network_module.get_server_port = lambda: 8189
sys.modules[f"{package_name}.utils.network"] = network_module
spec = importlib.util.spec_from_file_location(
f"{package_name}.workers.process.{module_name}",
module_path,
@@ -70,6 +90,145 @@ class ComfyRootDiscoveryTests(unittest.TestCase):
class LaunchCommandBuilderTests(unittest.TestCase):
def build_command(self, root, worker=None, runtime=None):
builder = launch_builder_module.LaunchCommandBuilder()
worker = worker or {"id": "worker-a", "port": 8190}
runtime = runtime if runtime is not None else Namespace(database_url=None)
with patch.object(builder, "_get_runtime_args", return_value=runtime):
return builder.build_launch_command(worker, str(root))
def test_database_is_unique_and_stable_by_worker_id(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
first = self.build_command(root, {"id": "worker-a", "port": 8190})
renamed = self.build_command(root, {
"id": "worker-a", "port": 9001, "name": "Renamed", "cuda_device": 3,
})
second = self.build_command(root, {"id": "worker-b", "port": 8191})
database = first[first.index("--database-url") + 1]
self.assertEqual(database, renamed[renamed.index("--database-url") + 1])
self.assertNotEqual(database, second[second.index("--database-url") + 1])
self.assertTrue(database.startswith("sqlite:///" + root.as_posix() + "/"))
self.assertTrue(Path(database.removeprefix("sqlite:///")).parent.is_dir())
self.assertNotIn("--disable-assets", first)
def test_database_uses_effective_user_or_base_directory(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
for extra_args, expected in [
(f'--user-directory "{root / "custom user"}"', root / "custom user"),
(f'--base-directory "{root / "custom base"}"', root / "custom base" / "user"),
]:
with self.subTest(extra_args=extra_args):
cmd = self.build_command(root, {
"id": "worker-a", "port": 8190, "extra_args": extra_args,
})
database = cmd[cmd.index("--database-url") + 1]
self.assertTrue(database.startswith("sqlite:///" + expected.as_posix() + "/"))
cmd = self.build_command(root, runtime=Namespace(
database_url="sqlite:///master.db", user_directory=str(root / "runtime user"),
))
database = cmd[cmd.index("--database-url") + 1]
self.assertTrue(database.startswith("sqlite:///" + (root / "runtime user").as_posix() + "/"))
self.assertNotEqual(database, "sqlite:///master.db")
def test_relative_database_directories_use_worker_cwd(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory) / "ComfyUI"
root.mkdir()
(root / "main.py").touch()
launcher = Path(directory) / "launcher"
launcher.mkdir()
cases = [
(Namespace(database_url=None, user_directory="profiles"), "", root / "profiles"),
(Namespace(database_url=None, base_directory="data"), "", root / "data/user"),
(Namespace(database_url=None), "--user-directory=profiles", root / "profiles"),
(Namespace(database_url=None), "--base-directory data", root / "data/user"),
]
for runtime, extra, expected in cases:
with self.subTest(runtime=runtime, extra=extra), \
patch.object(os, "getcwd", return_value=str(launcher)):
cmd = self.build_command(root, {
"id": "worker-a", "port": 8190, "extra_args": extra,
}, runtime)
database = make_url(cmd[cmd.index("--database-url") + 1]).database
self.assertEqual(Path(database).parent, expected / "distributed/workers")
self.assertFalse((launcher / "profiles").exists())
self.assertFalse((launcher / "data").exists())
def test_database_url_round_trips_special_characters_without_collisions(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
for name in ["user?profile", "user%3Fprofile"]:
with self.subTest(name=name):
user = root / name
runtime = Namespace(database_url=None, user_directory=str(user))
# SQLAlchemy 2.0 cannot round-trip '?' in a filename. Fail
# clearly on those versions rather than silently sharing a DB.
sample = (user / "test.db").as_posix()
serialized = URL.create("sqlite", database=sample).render_as_string()
if make_url(serialized).database != sample:
with self.assertRaisesRegex(ValueError, "SQLAlchemy.*database path"):
self.build_command(root, runtime=runtime)
self.assertFalse(user.exists())
continue
databases = []
for worker_id in ["worker-a", "worker-b"]:
cmd = self.build_command(root, {"id": worker_id, "port": 8190}, runtime)
url = cmd[cmd.index("--database-url") + 1]
database = make_url(url).database
self.assertEqual(Path(database).parent, user / "distributed/workers")
engine = create_engine(url)
try:
with engine.connect() as connection:
actual = connection.exec_driver_sql("PRAGMA database_list").one()[2]
self.assertEqual(Path(actual), Path(database))
finally:
engine.dispose()
databases.append(database)
self.assertNotEqual(*databases)
def test_explicit_database_and_disabled_assets_are_preserved(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
for extra in ["--database-url sqlite:///explicit.db", "--database-url=sqlite:///explicit.db", "--disable-assets"]:
with self.subTest(extra=extra):
cmd = self.build_command(root, {"id": "worker-a", "port": 8190, "extra_args": extra})
self.assertEqual(sum(arg.split("=")[0] == "--database-url" for arg in cmd), 0 if extra == "--disable-assets" else 1)
self.assertFalse((root / "user").exists())
def test_older_comfyui_without_database_flag_keeps_existing_command(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
cmd = self.build_command(root, runtime=Namespace())
self.assertNotIn("--database-url", cmd)
self.assertFalse((root / "user").exists())
def test_worker_id_cannot_escape_database_directory(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
databases = []
for worker_id in ["../outside", "a/b", "a_b"]:
cmd = self.build_command(root, {"id": worker_id, "port": 8190})
path = Path(cmd[cmd.index("--database-url") + 1].removeprefix("sqlite:///"))
self.assertTrue(path.is_relative_to(root / "user"))
databases.append(path)
self.assertEqual(len(set(databases)), 3)
def test_extra_args_cannot_silently_override_the_configured_port(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
(root / "main.py").touch()
for extra in ["--port 8189", "--port=8189"]:
with self.subTest(extra=extra), self.assertRaisesRegex(ValueError, "configured worker port"):
self.build_command(root, {"id": "worker-a", "port": 8190, "extra_args": extra})
def test_inherits_runtime_layout_args_for_desktop(self):
builder = launch_builder_module.LaunchCommandBuilder()
runtime_args = Namespace(
@@ -130,5 +289,64 @@ class LaunchCommandBuilderTests(unittest.TestCase):
self.assertNotIn("--auto-launch", cmd)
class ProcessLaunchPortTests(unittest.TestCase):
def test_launch_before_master_listens_uses_configured_master_port(self):
lifecycle_module = _load_process_module("lifecycle.py")
cli_args = types.ModuleType("comfy.cli_args")
cli_args.args = Namespace(port=8189)
for missing in [AttributeError("PromptServer has no port"), None]:
with self.subTest(missing=missing), tempfile.TemporaryDirectory() as directory:
manager = types.SimpleNamespace(
find_comfy_root=lambda: directory,
build_launch_command=lambda _worker, _root: ["python", "main.py"],
processes={}, save_processes=lambda: None,
)
with patch.dict(sys.modules, {"comfy": types.ModuleType("comfy"), "comfy.cli_args": cli_args}), \
patch.object(lifecycle_module, "get_server_port", side_effect=missing if isinstance(missing, Exception) else None, return_value=None), \
patch.object(lifecycle_module, "validate_worker_port") as validate, \
patch.object(lifecycle_module.subprocess, "Popen", return_value=types.SimpleNamespace(pid=1234)) as spawn:
pid = lifecycle_module.ProcessLifecycle(manager).launch_worker({"id": "manual", "port": 8190})
validate.assert_called_once_with({"id": "manual", "port": 8190}, 8189, [])
spawn.assert_called_once()
self.assertEqual(pid, 1234)
def test_pre_listen_launch_still_rejects_the_configured_master_port(self):
lifecycle_module = _load_process_module("lifecycle.py")
cli_args = types.ModuleType("comfy.cli_args")
cli_args.args = Namespace(port=8189)
manager = types.SimpleNamespace(find_comfy_root=lambda: "/ComfyUI", processes={})
with patch.dict(sys.modules, {"comfy": types.ModuleType("comfy"), "comfy.cli_args": cli_args}), \
patch.object(lifecycle_module, "get_server_port", side_effect=AttributeError("port")), \
patch.object(lifecycle_module.subprocess, "Popen") as spawn:
with self.assertRaisesRegex(ValueError, "master port 8189"):
lifecycle_module.ProcessLifecycle(manager).launch_worker({"id": "manual", "port": 8189})
spawn.assert_not_called()
def test_conflict_is_rejected_before_building_or_spawning(self):
lifecycle_module = _load_process_module("lifecycle.py")
manager = types.SimpleNamespace(find_comfy_root=lambda: "/ComfyUI", processes={})
with patch.object(lifecycle_module.subprocess, "Popen") as spawn:
with self.assertRaisesRegex(ValueError, "master port 8189"):
lifecycle_module.ProcessLifecycle(manager).launch_worker({"id": "manual", "port": 8189})
spawn.assert_not_called()
self.assertEqual(manager.processes, {})
def test_available_port_reaches_existing_launch_path(self):
lifecycle_module = _load_process_module("lifecycle.py")
with tempfile.TemporaryDirectory() as directory:
manager = types.SimpleNamespace(
find_comfy_root=lambda: directory,
build_launch_command=lambda _worker, _root: ["python", "main.py", "--port", "8190"],
processes={}, save_processes=lambda: None,
)
with patch.object(lifecycle_module, "validate_worker_port") as validate, \
patch.object(lifecycle_module.subprocess, "Popen", return_value=types.SimpleNamespace(pid=1234)) as spawn:
pid = lifecycle_module.ProcessLifecycle(manager).launch_worker({"id": "manual", "port": 8190})
validate.assert_called_once_with({"id": "manual", "port": 8190}, 8189, [])
spawn.assert_called_once()
self.assertEqual(pid, 1234)
self.assertEqual(manager.processes["manual"]["pid"], 1234)
if __name__ == "__main__":
unittest.main()