fix(exit): stop running jobs before Python joins the executor threads (#376)
ComfyUI returns from main.py after Ctrl+C without closing its event loop, and Python joins every executor thread before any atexit callback runs, so a scan batch, thumbnail batch or model download in flight kept ComfyUI alive until it ended (on Windows each ffmpeg up to its 30 s timeout). The package now registers a threading._register_atexit hook (after concurrent.futures', so it runs before that join) that sets an exit signal and kills the running encoder processes. Job.cancelled follows the signal, so every check a job already makes between files stops it at exit; map_parallel starts no further item, the scan walk stops between folders and a tagging model download stops before its next chunk. Without the internal hook exit behaves as before.
This commit is contained in:
@@ -0,0 +1,110 @@
|
||||
"""The process exit signal: running work stops at its next safe point (#376).
|
||||
|
||||
ComfyUI catches Ctrl+C in ``main.py`` and returns without closing its event
|
||||
loop. The interpreter then runs ``threading._shutdown``, which first calls the
|
||||
``threading._register_atexit`` callbacks, newest first. One of them,
|
||||
``concurrent.futures``'s ``_python_exit``, joins every executor thread, and
|
||||
only after that do the ``atexit`` callbacks run (the package teardown). A call
|
||||
still running on the default executor (a scan batch, a model download, a
|
||||
thumbnail batch) used to keep the process alive until it returned.
|
||||
|
||||
``install()`` registers a callback in that same list after ``concurrent.futures``
|
||||
did, so it runs before the join. It sets the signal that ``requested()`` reads
|
||||
(``Job.cancelled`` and ``map_parallel`` read it) and runs ``on_exit``.
|
||||
|
||||
``threading._register_atexit`` is CPython-internal. It has the same contract
|
||||
on 3.12, 3.13 and 3.14. Without it, or when it refuses the registration, exit
|
||||
behaves as before: the call in flight runs to its end.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import threading
|
||||
|
||||
logger = logging.getLogger("prompt_manager.exit")
|
||||
|
||||
_requested = threading.Event()
|
||||
_install_lock = threading.Lock()
|
||||
_installed = False
|
||||
_on_exit = []
|
||||
|
||||
|
||||
class ExitRequested(Exception):
|
||||
"""The interpreter is exiting: work not yet started is not started."""
|
||||
|
||||
|
||||
def requested():
|
||||
"""True once the interpreter has started exiting."""
|
||||
return _requested.is_set()
|
||||
|
||||
|
||||
def request():
|
||||
"""Set the signal (the exit hook; tests)."""
|
||||
_requested.set()
|
||||
|
||||
|
||||
def checkpoint():
|
||||
"""Raise ExitRequested once the interpreter is exiting."""
|
||||
if _requested.is_set():
|
||||
raise ExitRequested("ComfyUI is exiting")
|
||||
|
||||
|
||||
def checked(func):
|
||||
"""``func`` behind a checkpoint: a call that starts after the signal
|
||||
raises ExitRequested instead of running."""
|
||||
|
||||
def run(*args, **kwargs):
|
||||
checkpoint()
|
||||
return func(*args, **kwargs)
|
||||
|
||||
return run
|
||||
|
||||
|
||||
def _hook():
|
||||
"""The threading atexit callback. It never raises: an exception here
|
||||
would end ``threading._shutdown`` before it shuts the executors."""
|
||||
_requested.set()
|
||||
for action in tuple(_on_exit):
|
||||
try:
|
||||
action()
|
||||
except (Exception, KeyboardInterrupt):
|
||||
logger.error("Stopping work at exit failed", exc_info=True)
|
||||
|
||||
|
||||
def install(on_exit=None):
|
||||
"""Register the exit hook once per process; True when it is registered.
|
||||
|
||||
``on_exit`` (optional) runs inside the hook, after the signal is set.
|
||||
False (logged at DEBUG) when this Python has no ``_register_atexit`` or
|
||||
refuses it; exit then waits for running work as before.
|
||||
"""
|
||||
global _installed
|
||||
with _install_lock:
|
||||
if on_exit is not None and on_exit not in _on_exit:
|
||||
_on_exit.append(on_exit)
|
||||
if _installed:
|
||||
return True
|
||||
# Imported first so its pool join is registered before our hook:
|
||||
# the callbacks run newest first, so ours runs before that join.
|
||||
import concurrent.futures.thread # noqa: F401
|
||||
|
||||
register = getattr(threading, "_register_atexit", None)
|
||||
if not callable(register):
|
||||
logger.debug("threading._register_atexit is missing; exit waits for jobs")
|
||||
return False
|
||||
try:
|
||||
register(_hook)
|
||||
except RuntimeError as error: # already shutting down
|
||||
logger.debug(f"Exit hook not registered: {error}")
|
||||
return False
|
||||
_installed = True
|
||||
return True
|
||||
|
||||
|
||||
def reset():
|
||||
"""Clear the signal and forget the registration (tests only; a hook
|
||||
already registered stays in ``threading`` and sets the signal at exit)."""
|
||||
global _installed
|
||||
with _install_lock:
|
||||
_requested.clear()
|
||||
_installed = False
|
||||
_on_exit.clear()
|
||||
+5
-1
@@ -9,14 +9,18 @@ to linearly for both jobs.
|
||||
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
from .exit_signal import checked
|
||||
|
||||
|
||||
def map_parallel(func, items, workers):
|
||||
"""Apply ``func`` to every item on up to ``workers`` threads, keeping order.
|
||||
|
||||
``workers`` of 1 (or fewer) runs on the calling thread with no pool. An
|
||||
exception in ``func`` propagates to the caller, so callers that must
|
||||
survive bad input wrap ``func`` themselves.
|
||||
survive bad input wrap ``func`` themselves. An item that has not started
|
||||
when the interpreter starts exiting raises ExitRequested instead (#376).
|
||||
"""
|
||||
func = checked(func)
|
||||
items = list(items)
|
||||
workers = max(1, int(workers or 1))
|
||||
if workers == 1 or len(items) <= 1:
|
||||
|
||||
Reference in New Issue
Block a user