cpython/Lib/multiprocessing/popen_fork.py
Gregory P. Smith 3a7df632c9
gh-146313: Fix multiprocessing ResourceTracker deadlock after os.fork() (GH-146316)
`ResourceTracker.__del__` (added in gh-88887 circa Python 3.12) calls
os.waitpid(pid, 0) which blocks indefinitely if a process created via os.fork()
still holds the tracker pipe's write end. The tracker never sees EOF, never
exits, and the parent hangs at interpreter shutdown.

Fix with two layers:

- **At-fork handler.** An os.register_at_fork(after_in_child=...)
  handler closes the inherited pipe fd in the child unless a preserve
  flag is set. popen_fork.Popen._launch() sets the flag before its
  fork so mp.Process(fork) children keep the fd and reuse the parent's
  tracker (preserving gh-80849). Raw os.fork() children close the fd,
  letting the parent reap promptly.

- **Timeout safety-net.** _stop_locked() gains a wait_timeout
  parameter. When called from `__del__`, it polls with WNOHANG using
  exponential backoff for up to 1 second instead of blocking
  indefinitely. The at-fork handler makes this unreachable in
  well-behaved paths; it remains for abnormal shutdowns.

Co-authored-by: Itamar Oren <itamarost@gmail.com>
2026-04-11 23:06:19 -07:00

100 lines
3 KiB
Python

import atexit
import os
import signal
from . import util
__all__ = ['Popen']
#
# Start child process using fork
#
class Popen(object):
method = 'fork'
def __init__(self, process_obj):
util._flush_std_streams()
self.returncode = None
self.finalizer = None
self._launch(process_obj)
def duplicate_for_child(self, fd):
return fd
def poll(self, flag=os.WNOHANG):
if self.returncode is None:
try:
pid, sts = os.waitpid(self.pid, flag)
except OSError:
# Child process not yet created. See #1731717
# e.errno == errno.ECHILD == 10
return None
if pid == self.pid:
self.returncode = os.waitstatus_to_exitcode(sts)
return self.returncode
def wait(self, timeout=None):
if self.returncode is None:
if timeout is not None:
from multiprocessing.connection import wait
if not wait([self.sentinel], timeout):
return None
# This shouldn't block if wait() returned successfully.
return self.poll(os.WNOHANG if timeout == 0.0 else 0)
return self.returncode
def _send_signal(self, sig):
if self.returncode is None:
try:
os.kill(self.pid, sig)
except ProcessLookupError:
pass
except OSError:
if self.wait(timeout=0.1) is None:
raise
def interrupt(self):
self._send_signal(signal.SIGINT)
def terminate(self):
self._send_signal(signal.SIGTERM)
def kill(self):
self._send_signal(signal.SIGKILL)
def _launch(self, process_obj):
code = 1
parent_r, child_w = os.pipe()
child_r, parent_w = os.pipe()
# gh-146313: Tell the resource tracker's at-fork handler to keep
# the inherited pipe fd so this child reuses the parent's tracker
# (gh-80849) rather than closing it and launching its own.
from .resource_tracker import _fork_intent
_fork_intent.preserve_fd = True
try:
self.pid = os.fork()
finally:
# Reset in both parent and child so the flag does not leak
# into a subsequent raw os.fork() or nested Process launch.
_fork_intent.preserve_fd = False
if self.pid == 0:
try:
atexit._clear()
atexit.register(util._exit_function)
os.close(parent_r)
os.close(parent_w)
code = process_obj._bootstrap(parent_sentinel=child_r)
finally:
atexit._run_exitfuncs()
os._exit(code)
else:
os.close(child_w)
os.close(child_r)
self.finalizer = util.Finalize(self, util.close_fds,
(parent_r, parent_w,))
self.sentinel = parent_r
def close(self):
if self.finalizer is not None:
self.finalizer()