diff options
Diffstat (limited to 'Lib/concurrent')
| -rw-r--r-- | Lib/concurrent/__init__.py | 1 | ||||
| -rw-r--r-- | Lib/concurrent/futures/__init__.py | 53 | ||||
| -rw-r--r-- | Lib/concurrent/futures/_base.py | 629 | ||||
| -rw-r--r-- | Lib/concurrent/futures/process.py | 688 | ||||
| -rw-r--r-- | Lib/concurrent/futures/thread.py | 225 |
5 files changed, 0 insertions, 1596 deletions
diff --git a/Lib/concurrent/__init__.py b/Lib/concurrent/__init__.py deleted file mode 100644 index 196d378..0000000 --- a/Lib/concurrent/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# This directory is a Python package. diff --git a/Lib/concurrent/futures/__init__.py b/Lib/concurrent/futures/__init__.py deleted file mode 100644 index d746aea..0000000 --- a/Lib/concurrent/futures/__init__.py +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright 2009 Brian Quinlan. All Rights Reserved. -# Licensed to PSF under a Contributor Agreement. - -"""Execute computations asynchronously using threads or processes.""" - -__author__ = 'Brian Quinlan (brian@sweetapp.com)' - -from concurrent.futures._base import (FIRST_COMPLETED, - FIRST_EXCEPTION, - ALL_COMPLETED, - CancelledError, - TimeoutError, - InvalidStateError, - BrokenExecutor, - Future, - Executor, - wait, - as_completed) - -__all__ = ( - 'FIRST_COMPLETED', - 'FIRST_EXCEPTION', - 'ALL_COMPLETED', - 'CancelledError', - 'TimeoutError', - 'BrokenExecutor', - 'Future', - 'Executor', - 'wait', - 'as_completed', - 'ProcessPoolExecutor', - 'ThreadPoolExecutor', -) - - -def __dir__(): - return __all__ + ('__author__', '__doc__') - - -def __getattr__(name): - global ProcessPoolExecutor, ThreadPoolExecutor - - if name == 'ProcessPoolExecutor': - from .process import ProcessPoolExecutor as pe - ProcessPoolExecutor = pe - return pe - - if name == 'ThreadPoolExecutor': - from .thread import ThreadPoolExecutor as te - ThreadPoolExecutor = te - return te - - raise AttributeError(f"module {__name__} has no attribute {name}") diff --git a/Lib/concurrent/futures/_base.py b/Lib/concurrent/futures/_base.py deleted file mode 100644 index fd0acec..0000000 --- a/Lib/concurrent/futures/_base.py +++ /dev/null @@ -1,629 +0,0 @@ -# Copyright 2009 Brian Quinlan. All Rights Reserved. -# Licensed to PSF under a Contributor Agreement. - -__author__ = 'Brian Quinlan (brian@sweetapp.com)' - -import collections -import logging -import threading -import time - -FIRST_COMPLETED = 'FIRST_COMPLETED' -FIRST_EXCEPTION = 'FIRST_EXCEPTION' -ALL_COMPLETED = 'ALL_COMPLETED' -_AS_COMPLETED = '_AS_COMPLETED' - -# Possible future states (for internal use by the futures package). -PENDING = 'PENDING' -RUNNING = 'RUNNING' -# The future was cancelled by the user... -CANCELLED = 'CANCELLED' -# ...and _Waiter.add_cancelled() was called by a worker. -CANCELLED_AND_NOTIFIED = 'CANCELLED_AND_NOTIFIED' -FINISHED = 'FINISHED' - -_FUTURE_STATES = [ - PENDING, - RUNNING, - CANCELLED, - CANCELLED_AND_NOTIFIED, - FINISHED -] - -_STATE_TO_DESCRIPTION_MAP = { - PENDING: "pending", - RUNNING: "running", - CANCELLED: "cancelled", - CANCELLED_AND_NOTIFIED: "cancelled", - FINISHED: "finished" -} - -# Logger for internal use by the futures package. -LOGGER = logging.getLogger("concurrent.futures") - -class Error(Exception): - """Base class for all future-related exceptions.""" - pass - -class CancelledError(Error): - """The Future was cancelled.""" - pass - -class TimeoutError(Error): - """The operation exceeded the given deadline.""" - pass - -class InvalidStateError(Error): - """The operation is not allowed in this state.""" - pass - -class _Waiter(object): - """Provides the event that wait() and as_completed() block on.""" - def __init__(self): - self.event = threading.Event() - self.finished_futures = [] - - def add_result(self, future): - self.finished_futures.append(future) - - def add_exception(self, future): - self.finished_futures.append(future) - - def add_cancelled(self, future): - self.finished_futures.append(future) - -class _AsCompletedWaiter(_Waiter): - """Used by as_completed().""" - - def __init__(self): - super(_AsCompletedWaiter, self).__init__() - self.lock = threading.Lock() - - def add_result(self, future): - with self.lock: - super(_AsCompletedWaiter, self).add_result(future) - self.event.set() - - def add_exception(self, future): - with self.lock: - super(_AsCompletedWaiter, self).add_exception(future) - self.event.set() - - def add_cancelled(self, future): - with self.lock: - super(_AsCompletedWaiter, self).add_cancelled(future) - self.event.set() - -class _FirstCompletedWaiter(_Waiter): - """Used by wait(return_when=FIRST_COMPLETED).""" - - def add_result(self, future): - super().add_result(future) - self.event.set() - - def add_exception(self, future): - super().add_exception(future) - self.event.set() - - def add_cancelled(self, future): - super().add_cancelled(future) - self.event.set() - -class _AllCompletedWaiter(_Waiter): - """Used by wait(return_when=FIRST_EXCEPTION and ALL_COMPLETED).""" - - def __init__(self, num_pending_calls, stop_on_exception): - self.num_pending_calls = num_pending_calls - self.stop_on_exception = stop_on_exception - self.lock = threading.Lock() - super().__init__() - - def _decrement_pending_calls(self): - with self.lock: - self.num_pending_calls -= 1 - if not self.num_pending_calls: - self.event.set() - - def add_result(self, future): - super().add_result(future) - self._decrement_pending_calls() - - def add_exception(self, future): - super().add_exception(future) - if self.stop_on_exception: - self.event.set() - else: - self._decrement_pending_calls() - - def add_cancelled(self, future): - super().add_cancelled(future) - self._decrement_pending_calls() - -class _AcquireFutures(object): - """A context manager that does an ordered acquire of Future conditions.""" - - def __init__(self, futures): - self.futures = sorted(futures, key=id) - - def __enter__(self): - for future in self.futures: - future._condition.acquire() - - def __exit__(self, *args): - for future in self.futures: - future._condition.release() - -def _create_and_install_waiters(fs, return_when): - if return_when == _AS_COMPLETED: - waiter = _AsCompletedWaiter() - elif return_when == FIRST_COMPLETED: - waiter = _FirstCompletedWaiter() - else: - pending_count = sum( - f._state not in [CANCELLED_AND_NOTIFIED, FINISHED] for f in fs) - - if return_when == FIRST_EXCEPTION: - waiter = _AllCompletedWaiter(pending_count, stop_on_exception=True) - elif return_when == ALL_COMPLETED: - waiter = _AllCompletedWaiter(pending_count, stop_on_exception=False) - else: - raise ValueError("Invalid return condition: %r" % return_when) - - for f in fs: - f._waiters.append(waiter) - - return waiter - - -def _yield_finished_futures(fs, waiter, ref_collect): - """ - Iterate on the list *fs*, yielding finished futures one by one in - reverse order. - Before yielding a future, *waiter* is removed from its waiters - and the future is removed from each set in the collection of sets - *ref_collect*. - - The aim of this function is to avoid keeping stale references after - the future is yielded and before the iterator resumes. - """ - while fs: - f = fs[-1] - for futures_set in ref_collect: - futures_set.remove(f) - with f._condition: - f._waiters.remove(waiter) - del f - # Careful not to keep a reference to the popped value - yield fs.pop() - - -def as_completed(fs, timeout=None): - """An iterator over the given futures that yields each as it completes. - - Args: - fs: The sequence of Futures (possibly created by different Executors) to - iterate over. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - - Returns: - An iterator that yields the given Futures as they complete (finished or - cancelled). If any given Futures are duplicated, they will be returned - once. - - Raises: - TimeoutError: If the entire result iterator could not be generated - before the given timeout. - """ - if timeout is not None: - end_time = timeout + time.monotonic() - - fs = set(fs) - total_futures = len(fs) - with _AcquireFutures(fs): - finished = set( - f for f in fs - if f._state in [CANCELLED_AND_NOTIFIED, FINISHED]) - pending = fs - finished - waiter = _create_and_install_waiters(fs, _AS_COMPLETED) - finished = list(finished) - try: - yield from _yield_finished_futures(finished, waiter, - ref_collect=(fs,)) - - while pending: - if timeout is None: - wait_timeout = None - else: - wait_timeout = end_time - time.monotonic() - if wait_timeout < 0: - raise TimeoutError( - '%d (of %d) futures unfinished' % ( - len(pending), total_futures)) - - waiter.event.wait(wait_timeout) - - with waiter.lock: - finished = waiter.finished_futures - waiter.finished_futures = [] - waiter.event.clear() - - # reverse to keep finishing order - finished.reverse() - yield from _yield_finished_futures(finished, waiter, - ref_collect=(fs, pending)) - - finally: - # Remove waiter from unfinished futures - for f in fs: - with f._condition: - f._waiters.remove(waiter) - -DoneAndNotDoneFutures = collections.namedtuple( - 'DoneAndNotDoneFutures', 'done not_done') -def wait(fs, timeout=None, return_when=ALL_COMPLETED): - """Wait for the futures in the given sequence to complete. - - Args: - fs: The sequence of Futures (possibly created by different Executors) to - wait upon. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - return_when: Indicates when this function should return. The options - are: - - FIRST_COMPLETED - Return when any future finishes or is - cancelled. - FIRST_EXCEPTION - Return when any future finishes by raising an - exception. If no future raises an exception - then it is equivalent to ALL_COMPLETED. - ALL_COMPLETED - Return when all futures finish or are cancelled. - - Returns: - A named 2-tuple of sets. The first set, named 'done', contains the - futures that completed (is finished or cancelled) before the wait - completed. The second set, named 'not_done', contains uncompleted - futures. - """ - with _AcquireFutures(fs): - done = set(f for f in fs - if f._state in [CANCELLED_AND_NOTIFIED, FINISHED]) - not_done = set(fs) - done - - if (return_when == FIRST_COMPLETED) and done: - return DoneAndNotDoneFutures(done, not_done) - elif (return_when == FIRST_EXCEPTION) and done: - if any(f for f in done - if not f.cancelled() and f.exception() is not None): - return DoneAndNotDoneFutures(done, not_done) - - if len(done) == len(fs): - return DoneAndNotDoneFutures(done, not_done) - - waiter = _create_and_install_waiters(fs, return_when) - - waiter.event.wait(timeout) - for f in fs: - with f._condition: - f._waiters.remove(waiter) - - done.update(waiter.finished_futures) - return DoneAndNotDoneFutures(done, set(fs) - done) - -class Future(object): - """Represents the result of an asynchronous computation.""" - - def __init__(self): - """Initializes the future. Should not be called by clients.""" - self._condition = threading.Condition() - self._state = PENDING - self._result = None - self._exception = None - self._waiters = [] - self._done_callbacks = [] - - def _invoke_callbacks(self): - for callback in self._done_callbacks: - try: - callback(self) - except Exception: - LOGGER.exception('exception calling callback for %r', self) - - def __repr__(self): - with self._condition: - if self._state == FINISHED: - if self._exception: - return '<%s at %#x state=%s raised %s>' % ( - self.__class__.__name__, - id(self), - _STATE_TO_DESCRIPTION_MAP[self._state], - self._exception.__class__.__name__) - else: - return '<%s at %#x state=%s returned %s>' % ( - self.__class__.__name__, - id(self), - _STATE_TO_DESCRIPTION_MAP[self._state], - self._result.__class__.__name__) - return '<%s at %#x state=%s>' % ( - self.__class__.__name__, - id(self), - _STATE_TO_DESCRIPTION_MAP[self._state]) - - def cancel(self): - """Cancel the future if possible. - - Returns True if the future was cancelled, False otherwise. A future - cannot be cancelled if it is running or has already completed. - """ - with self._condition: - if self._state in [RUNNING, FINISHED]: - return False - - if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]: - return True - - self._state = CANCELLED - self._condition.notify_all() - - self._invoke_callbacks() - return True - - def cancelled(self): - """Return True if the future was cancelled.""" - with self._condition: - return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED] - - def running(self): - """Return True if the future is currently executing.""" - with self._condition: - return self._state == RUNNING - - def done(self): - """Return True of the future was cancelled or finished executing.""" - with self._condition: - return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED] - - def __get_result(self): - if self._exception: - raise self._exception - else: - return self._result - - def add_done_callback(self, fn): - """Attaches a callable that will be called when the future finishes. - - Args: - fn: A callable that will be called with this future as its only - argument when the future completes or is cancelled. The callable - will always be called by a thread in the same process in which - it was added. If the future has already completed or been - cancelled then the callable will be called immediately. These - callables are called in the order that they were added. - """ - with self._condition: - if self._state not in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]: - self._done_callbacks.append(fn) - return - try: - fn(self) - except Exception: - LOGGER.exception('exception calling callback for %r', self) - - def result(self, timeout=None): - """Return the result of the call that the future represents. - - Args: - timeout: The number of seconds to wait for the result if the future - isn't done. If None, then there is no limit on the wait time. - - Returns: - The result of the call that the future represents. - - Raises: - CancelledError: If the future was cancelled. - TimeoutError: If the future didn't finish executing before the given - timeout. - Exception: If the call raised then that exception will be raised. - """ - with self._condition: - if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]: - raise CancelledError() - elif self._state == FINISHED: - return self.__get_result() - - self._condition.wait(timeout) - - if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]: - raise CancelledError() - elif self._state == FINISHED: - return self.__get_result() - else: - raise TimeoutError() - - def exception(self, timeout=None): - """Return the exception raised by the call that the future represents. - - Args: - timeout: The number of seconds to wait for the exception if the - future isn't done. If None, then there is no limit on the wait - time. - - Returns: - The exception raised by the call that the future represents or None - if the call completed without raising. - - Raises: - CancelledError: If the future was cancelled. - TimeoutError: If the future didn't finish executing before the given - timeout. - """ - - with self._condition: - if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]: - raise CancelledError() - elif self._state == FINISHED: - return self._exception - - self._condition.wait(timeout) - - if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]: - raise CancelledError() - elif self._state == FINISHED: - return self._exception - else: - raise TimeoutError() - - # The following methods should only be used by Executors and in tests. - def set_running_or_notify_cancel(self): - """Mark the future as running or process any cancel notifications. - - Should only be used by Executor implementations and unit tests. - - If the future has been cancelled (cancel() was called and returned - True) then any threads waiting on the future completing (though calls - to as_completed() or wait()) are notified and False is returned. - - If the future was not cancelled then it is put in the running state - (future calls to running() will return True) and True is returned. - - This method should be called by Executor implementations before - executing the work associated with this future. If this method returns - False then the work should not be executed. - - Returns: - False if the Future was cancelled, True otherwise. - - Raises: - RuntimeError: if this method was already called or if set_result() - or set_exception() was called. - """ - with self._condition: - if self._state == CANCELLED: - self._state = CANCELLED_AND_NOTIFIED - for waiter in self._waiters: - waiter.add_cancelled(self) - # self._condition.notify_all() is not necessary because - # self.cancel() triggers a notification. - return False - elif self._state == PENDING: - self._state = RUNNING - return True - else: - LOGGER.critical('Future %s in unexpected state: %s', - id(self), - self._state) - raise RuntimeError('Future in unexpected state') - - def set_result(self, result): - """Sets the return value of work associated with the future. - - Should only be used by Executor implementations and unit tests. - """ - with self._condition: - if self._state in {CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED}: - raise InvalidStateError('{}: {!r}'.format(self._state, self)) - self._result = result - self._state = FINISHED - for waiter in self._waiters: - waiter.add_result(self) - self._condition.notify_all() - self._invoke_callbacks() - - def set_exception(self, exception): - """Sets the result of the future as being the given exception. - - Should only be used by Executor implementations and unit tests. - """ - with self._condition: - if self._state in {CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED}: - raise InvalidStateError('{}: {!r}'.format(self._state, self)) - self._exception = exception - self._state = FINISHED - for waiter in self._waiters: - waiter.add_exception(self) - self._condition.notify_all() - self._invoke_callbacks() - -class Executor(object): - """This is an abstract base class for concrete asynchronous executors.""" - - def submit(self, fn, /, *args, **kwargs): - """Submits a callable to be executed with the given arguments. - - Schedules the callable to be executed as fn(*args, **kwargs) and returns - a Future instance representing the execution of the callable. - - Returns: - A Future representing the given call. - """ - raise NotImplementedError() - - def map(self, fn, *iterables, timeout=None, chunksize=1): - """Returns an iterator equivalent to map(fn, iter). - - Args: - fn: A callable that will take as many arguments as there are - passed iterables. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - chunksize: The size of the chunks the iterable will be broken into - before being passed to a child process. This argument is only - used by ProcessPoolExecutor; it is ignored by - ThreadPoolExecutor. - - Returns: - An iterator equivalent to: map(func, *iterables) but the calls may - be evaluated out-of-order. - - Raises: - TimeoutError: If the entire result iterator could not be generated - before the given timeout. - Exception: If fn(*args) raises for any values. - """ - if timeout is not None: - end_time = timeout + time.monotonic() - - fs = [self.submit(fn, *args) for args in zip(*iterables)] - - # Yield must be hidden in closure so that the futures are submitted - # before the first iterator value is required. - def result_iterator(): - try: - # reverse to keep finishing order - fs.reverse() - while fs: - # Careful not to keep a reference to the popped future - if timeout is None: - yield fs.pop().result() - else: - yield fs.pop().result(end_time - time.monotonic()) - finally: - for future in fs: - future.cancel() - return result_iterator() - - def shutdown(self, wait=True): - """Clean-up the resources associated with the Executor. - - It is safe to call this method several times. Otherwise, no other - methods can be called after this one. - - Args: - wait: If True then shutdown will not return until all running - futures have finished executing and the resources used by the - executor have been reclaimed. - """ - pass - - def __enter__(self): - return self - - def __exit__(self, exc_type, exc_val, exc_tb): - self.shutdown(wait=True) - return False - - -class BrokenExecutor(RuntimeError): - """ - Raised when a executor has become non-functional after a severe failure. - """ diff --git a/Lib/concurrent/futures/process.py b/Lib/concurrent/futures/process.py deleted file mode 100644 index 9e2ab9d..0000000 --- a/Lib/concurrent/futures/process.py +++ /dev/null @@ -1,688 +0,0 @@ -# Copyright 2009 Brian Quinlan. All Rights Reserved. -# Licensed to PSF under a Contributor Agreement. - -"""Implements ProcessPoolExecutor. - -The following diagram and text describe the data-flow through the system: - -|======================= In-process =====================|== Out-of-process ==| - -+----------+ +----------+ +--------+ +-----------+ +---------+ -| | => | Work Ids | | | | Call Q | | Process | -| | +----------+ | | +-----------+ | Pool | -| | | ... | | | | ... | +---------+ -| | | 6 | => | | => | 5, call() | => | | -| | | 7 | | | | ... | | | -| Process | | ... | | Local | +-----------+ | Process | -| Pool | +----------+ | Worker | | #1..n | -| Executor | | Thread | | | -| | +----------- + | | +-----------+ | | -| | <=> | Work Items | <=> | | <= | Result Q | <= | | -| | +------------+ | | +-----------+ | | -| | | 6: call() | | | | ... | | | -| | | future | | | | 4, result | | | -| | | ... | | | | 3, except | | | -+----------+ +------------+ +--------+ +-----------+ +---------+ - -Executor.submit() called: -- creates a uniquely numbered _WorkItem and adds it to the "Work Items" dict -- adds the id of the _WorkItem to the "Work Ids" queue - -Local worker thread: -- reads work ids from the "Work Ids" queue and looks up the corresponding - WorkItem from the "Work Items" dict: if the work item has been cancelled then - it is simply removed from the dict, otherwise it is repackaged as a - _CallItem and put in the "Call Q". New _CallItems are put in the "Call Q" - until "Call Q" is full. NOTE: the size of the "Call Q" is kept small because - calls placed in the "Call Q" can no longer be cancelled with Future.cancel(). -- reads _ResultItems from "Result Q", updates the future stored in the - "Work Items" dict and deletes the dict entry - -Process #1..n: -- reads _CallItems from "Call Q", executes the calls, and puts the resulting - _ResultItems in "Result Q" -""" - -__author__ = 'Brian Quinlan (brian@sweetapp.com)' - -import atexit -import os -from concurrent.futures import _base -import queue -from queue import Full -import multiprocessing as mp -import multiprocessing.connection -from multiprocessing.queues import Queue -import threading -import weakref -from functools import partial -import itertools -import sys -import traceback - -# Workers are created as daemon threads and processes. This is done to allow the -# interpreter to exit when there are still idle processes in a -# ProcessPoolExecutor's process pool (i.e. shutdown() was not called). However, -# allowing workers to die with the interpreter has two undesirable properties: -# - The workers would still be running during interpreter shutdown, -# meaning that they would fail in unpredictable ways. -# - The workers could be killed while evaluating a work item, which could -# be bad if the callable being evaluated has external side-effects e.g. -# writing to a file. -# -# To work around this problem, an exit handler is installed which tells the -# workers to exit when their work queues are empty and then waits until the -# threads/processes finish. - -_threads_wakeups = weakref.WeakKeyDictionary() -_global_shutdown = False - - -class _ThreadWakeup: - def __init__(self): - self._reader, self._writer = mp.Pipe(duplex=False) - - def close(self): - self._writer.close() - self._reader.close() - - def wakeup(self): - self._writer.send_bytes(b"") - - def clear(self): - while self._reader.poll(): - self._reader.recv_bytes() - - -def _python_exit(): - global _global_shutdown - _global_shutdown = True - items = list(_threads_wakeups.items()) - for _, thread_wakeup in items: - thread_wakeup.wakeup() - for t, _ in items: - t.join() - -# Controls how many more calls than processes will be queued in the call queue. -# A smaller number will mean that processes spend more time idle waiting for -# work while a larger number will make Future.cancel() succeed less frequently -# (Futures in the call queue cannot be cancelled). -EXTRA_QUEUED_CALLS = 1 - - -# On Windows, WaitForMultipleObjects is used to wait for processes to finish. -# It can wait on, at most, 63 objects. There is an overhead of two objects: -# - the result queue reader -# - the thread wakeup reader -_MAX_WINDOWS_WORKERS = 63 - 2 - -# Hack to embed stringification of remote traceback in local traceback - -class _RemoteTraceback(Exception): - def __init__(self, tb): - self.tb = tb - def __str__(self): - return self.tb - -class _ExceptionWithTraceback: - def __init__(self, exc, tb): - tb = traceback.format_exception(type(exc), exc, tb) - tb = ''.join(tb) - self.exc = exc - self.tb = '\n"""\n%s"""' % tb - def __reduce__(self): - return _rebuild_exc, (self.exc, self.tb) - -def _rebuild_exc(exc, tb): - exc.__cause__ = _RemoteTraceback(tb) - return exc - -class _WorkItem(object): - def __init__(self, future, fn, args, kwargs): - self.future = future - self.fn = fn - self.args = args - self.kwargs = kwargs - -class _ResultItem(object): - def __init__(self, work_id, exception=None, result=None): - self.work_id = work_id - self.exception = exception - self.result = result - -class _CallItem(object): - def __init__(self, work_id, fn, args, kwargs): - self.work_id = work_id - self.fn = fn - self.args = args - self.kwargs = kwargs - - -class _SafeQueue(Queue): - """Safe Queue set exception to the future object linked to a job""" - def __init__(self, max_size=0, *, ctx, pending_work_items): - self.pending_work_items = pending_work_items - super().__init__(max_size, ctx=ctx) - - def _on_queue_feeder_error(self, e, obj): - if isinstance(obj, _CallItem): - tb = traceback.format_exception(type(e), e, e.__traceback__) - e.__cause__ = _RemoteTraceback('\n"""\n{}"""'.format(''.join(tb))) - work_item = self.pending_work_items.pop(obj.work_id, None) - # work_item can be None if another process terminated. In this case, - # the queue_manager_thread fails all work_items with BrokenProcessPool - if work_item is not None: - work_item.future.set_exception(e) - else: - super()._on_queue_feeder_error(e, obj) - - -def _get_chunks(*iterables, chunksize): - """ Iterates over zip()ed iterables in chunks. """ - it = zip(*iterables) - while True: - chunk = tuple(itertools.islice(it, chunksize)) - if not chunk: - return - yield chunk - -def _process_chunk(fn, chunk): - """ Processes a chunk of an iterable passed to map. - - Runs the function passed to map() on a chunk of the - iterable passed to map. - - This function is run in a separate process. - - """ - return [fn(*args) for args in chunk] - - -def _sendback_result(result_queue, work_id, result=None, exception=None): - """Safely send back the given result or exception""" - try: - result_queue.put(_ResultItem(work_id, result=result, - exception=exception)) - except BaseException as e: - exc = _ExceptionWithTraceback(e, e.__traceback__) - result_queue.put(_ResultItem(work_id, exception=exc)) - - -def _process_worker(call_queue, result_queue, initializer, initargs): - """Evaluates calls from call_queue and places the results in result_queue. - - This worker is run in a separate process. - - Args: - call_queue: A ctx.Queue of _CallItems that will be read and - evaluated by the worker. - result_queue: A ctx.Queue of _ResultItems that will written - to by the worker. - initializer: A callable initializer, or None - initargs: A tuple of args for the initializer - """ - if initializer is not None: - try: - initializer(*initargs) - except BaseException: - _base.LOGGER.critical('Exception in initializer:', exc_info=True) - # The parent will notice that the process stopped and - # mark the pool broken - return - while True: - call_item = call_queue.get(block=True) - if call_item is None: - # Wake up queue management thread - result_queue.put(os.getpid()) - return - try: - r = call_item.fn(*call_item.args, **call_item.kwargs) - except BaseException as e: - exc = _ExceptionWithTraceback(e, e.__traceback__) - _sendback_result(result_queue, call_item.work_id, exception=exc) - else: - _sendback_result(result_queue, call_item.work_id, result=r) - del r - - # Liberate the resource as soon as possible, to avoid holding onto - # open files or shared memory that is not needed anymore - del call_item - - -def _add_call_item_to_queue(pending_work_items, - work_ids, - call_queue): - """Fills call_queue with _WorkItems from pending_work_items. - - This function never blocks. - - Args: - pending_work_items: A dict mapping work ids to _WorkItems e.g. - {5: <_WorkItem...>, 6: <_WorkItem...>, ...} - work_ids: A queue.Queue of work ids e.g. Queue([5, 6, ...]). Work ids - are consumed and the corresponding _WorkItems from - pending_work_items are transformed into _CallItems and put in - call_queue. - call_queue: A multiprocessing.Queue that will be filled with _CallItems - derived from _WorkItems. - """ - while True: - if call_queue.full(): - return - try: - work_id = work_ids.get(block=False) - except queue.Empty: - return - else: - work_item = pending_work_items[work_id] - - if work_item.future.set_running_or_notify_cancel(): - call_queue.put(_CallItem(work_id, - work_item.fn, - work_item.args, - work_item.kwargs), - block=True) - else: - del pending_work_items[work_id] - continue - - -def _queue_management_worker(executor_reference, - processes, - pending_work_items, - work_ids_queue, - call_queue, - result_queue, - thread_wakeup): - """Manages the communication between this process and the worker processes. - - This function is run in a local thread. - - Args: - executor_reference: A weakref.ref to the ProcessPoolExecutor that owns - this thread. Used to determine if the ProcessPoolExecutor has been - garbage collected and that this function can exit. - process: A list of the ctx.Process instances used as - workers. - pending_work_items: A dict mapping work ids to _WorkItems e.g. - {5: <_WorkItem...>, 6: <_WorkItem...>, ...} - work_ids_queue: A queue.Queue of work ids e.g. Queue([5, 6, ...]). - call_queue: A ctx.Queue that will be filled with _CallItems - derived from _WorkItems for processing by the process workers. - result_queue: A ctx.SimpleQueue of _ResultItems generated by the - process workers. - thread_wakeup: A _ThreadWakeup to allow waking up the - queue_manager_thread from the main Thread and avoid deadlocks - caused by permanently locked queues. - """ - executor = None - - def shutting_down(): - return (_global_shutdown or executor is None - or executor._shutdown_thread) - - def shutdown_worker(): - # This is an upper bound on the number of children alive. - n_children_alive = sum(p.is_alive() for p in processes.values()) - n_children_to_stop = n_children_alive - n_sentinels_sent = 0 - # Send the right number of sentinels, to make sure all children are - # properly terminated. - while n_sentinels_sent < n_children_to_stop and n_children_alive > 0: - for i in range(n_children_to_stop - n_sentinels_sent): - try: - call_queue.put_nowait(None) - n_sentinels_sent += 1 - except Full: - break - n_children_alive = sum(p.is_alive() for p in processes.values()) - - # Release the queue's resources as soon as possible. - call_queue.close() - # If .join() is not called on the created processes then - # some ctx.Queue methods may deadlock on Mac OS X. - for p in processes.values(): - p.join() - - result_reader = result_queue._reader - wakeup_reader = thread_wakeup._reader - readers = [result_reader, wakeup_reader] - - while True: - _add_call_item_to_queue(pending_work_items, - work_ids_queue, - call_queue) - - # Wait for a result to be ready in the result_queue while checking - # that all worker processes are still running, or for a wake up - # signal send. The wake up signals come either from new tasks being - # submitted, from the executor being shutdown/gc-ed, or from the - # shutdown of the python interpreter. - worker_sentinels = [p.sentinel for p in processes.values()] - ready = mp.connection.wait(readers + worker_sentinels) - - cause = None - is_broken = True - if result_reader in ready: - try: - result_item = result_reader.recv() - is_broken = False - except BaseException as e: - cause = traceback.format_exception(type(e), e, e.__traceback__) - - elif wakeup_reader in ready: - is_broken = False - result_item = None - thread_wakeup.clear() - if is_broken: - # Mark the process pool broken so that submits fail right now. - executor = executor_reference() - if executor is not None: - executor._broken = ('A child process terminated ' - 'abruptly, the process pool is not ' - 'usable anymore') - executor._shutdown_thread = True - executor = None - bpe = BrokenProcessPool("A process in the process pool was " - "terminated abruptly while the future was " - "running or pending.") - if cause is not None: - bpe.__cause__ = _RemoteTraceback( - f"\n'''\n{''.join(cause)}'''") - # All futures in flight must be marked failed - for work_id, work_item in pending_work_items.items(): - work_item.future.set_exception(bpe) - # Delete references to object. See issue16284 - del work_item - pending_work_items.clear() - # Terminate remaining workers forcibly: the queues or their - # locks may be in a dirty state and block forever. - for p in processes.values(): - p.terminate() - shutdown_worker() - return - if isinstance(result_item, int): - # Clean shutdown of a worker using its PID - # (avoids marking the executor broken) - assert shutting_down() - p = processes.pop(result_item) - p.join() - if not processes: - shutdown_worker() - return - elif result_item is not None: - work_item = pending_work_items.pop(result_item.work_id, None) - # work_item can be None if another process terminated (see above) - if work_item is not None: - if result_item.exception: - work_item.future.set_exception(result_item.exception) - else: - work_item.future.set_result(result_item.result) - # Delete references to object. See issue16284 - del work_item - # Delete reference to result_item - del result_item - - # Check whether we should start shutting down. - executor = executor_reference() - # No more work items can be added if: - # - The interpreter is shutting down OR - # - The executor that owns this worker has been collected OR - # - The executor that owns this worker has been shutdown. - if shutting_down(): - try: - # Flag the executor as shutting down as early as possible if it - # is not gc-ed yet. - if executor is not None: - executor._shutdown_thread = True - # Since no new work items can be added, it is safe to shutdown - # this thread if there are no pending work items. - if not pending_work_items: - shutdown_worker() - return - except Full: - # This is not a problem: we will eventually be woken up (in - # result_queue.get()) and be able to send a sentinel again. - pass - executor = None - - -_system_limits_checked = False -_system_limited = None - - -def _check_system_limits(): - global _system_limits_checked, _system_limited - if _system_limits_checked: - if _system_limited: - raise NotImplementedError(_system_limited) - _system_limits_checked = True - try: - nsems_max = os.sysconf("SC_SEM_NSEMS_MAX") - except (AttributeError, ValueError): - # sysconf not available or setting not available - return - if nsems_max == -1: - # indetermined limit, assume that limit is determined - # by available memory only - return - if nsems_max >= 256: - # minimum number of semaphores available - # according to POSIX - return - _system_limited = ("system provides too few semaphores (%d" - " available, 256 necessary)" % nsems_max) - raise NotImplementedError(_system_limited) - - -def _chain_from_iterable_of_lists(iterable): - """ - Specialized implementation of itertools.chain.from_iterable. - Each item in *iterable* should be a list. This function is - careful not to keep references to yielded objects. - """ - for element in iterable: - element.reverse() - while element: - yield element.pop() - - -class BrokenProcessPool(_base.BrokenExecutor): - """ - Raised when a process in a ProcessPoolExecutor terminated abruptly - while a future was in the running state. - """ - - -class ProcessPoolExecutor(_base.Executor): - def __init__(self, max_workers=None, mp_context=None, - initializer=None, initargs=()): - """Initializes a new ProcessPoolExecutor instance. - - Args: - max_workers: The maximum number of processes that can be used to - execute the given calls. If None or not given then as many - worker processes will be created as the machine has processors. - mp_context: A multiprocessing context to launch the workers. This - object should provide SimpleQueue, Queue and Process. - initializer: A callable used to initialize worker processes. - initargs: A tuple of arguments to pass to the initializer. - """ - _check_system_limits() - - if max_workers is None: - self._max_workers = os.cpu_count() or 1 - if sys.platform == 'win32': - self._max_workers = min(_MAX_WINDOWS_WORKERS, - self._max_workers) - else: - if max_workers <= 0: - raise ValueError("max_workers must be greater than 0") - elif (sys.platform == 'win32' and - max_workers > _MAX_WINDOWS_WORKERS): - raise ValueError( - f"max_workers must be <= {_MAX_WINDOWS_WORKERS}") - - self._max_workers = max_workers - - if mp_context is None: - mp_context = mp.get_context() - self._mp_context = mp_context - - if initializer is not None and not callable(initializer): - raise TypeError("initializer must be a callable") - self._initializer = initializer - self._initargs = initargs - - # Management thread - self._queue_management_thread = None - - # Map of pids to processes - self._processes = {} - - # Shutdown is a two-step process. - self._shutdown_thread = False - self._shutdown_lock = threading.Lock() - self._broken = False - self._queue_count = 0 - self._pending_work_items = {} - - # Create communication channels for the executor - # Make the call queue slightly larger than the number of processes to - # prevent the worker processes from idling. But don't make it too big - # because futures in the call queue cannot be cancelled. - queue_size = self._max_workers + EXTRA_QUEUED_CALLS - self._call_queue = _SafeQueue( - max_size=queue_size, ctx=self._mp_context, - pending_work_items=self._pending_work_items) - # Killed worker processes can produce spurious "broken pipe" - # tracebacks in the queue's own worker thread. But we detect killed - # processes anyway, so silence the tracebacks. - self._call_queue._ignore_epipe = True - self._result_queue = mp_context.SimpleQueue() - self._work_ids = queue.Queue() - - # _ThreadWakeup is a communication channel used to interrupt the wait - # of the main loop of queue_manager_thread from another thread (e.g. - # when calling executor.submit or executor.shutdown). We do not use the - # _result_queue to send the wakeup signal to the queue_manager_thread - # as it could result in a deadlock if a worker process dies with the - # _result_queue write lock still acquired. - self._queue_management_thread_wakeup = _ThreadWakeup() - - def _start_queue_management_thread(self): - if self._queue_management_thread is None: - # When the executor gets garbarge collected, the weakref callback - # will wake up the queue management thread so that it can terminate - # if there is no pending work item. - def weakref_cb(_, - thread_wakeup=self._queue_management_thread_wakeup): - mp.util.debug('Executor collected: triggering callback for' - ' QueueManager wakeup') - thread_wakeup.wakeup() - # Start the processes so that their sentinels are known. - self._adjust_process_count() - self._queue_management_thread = threading.Thread( - target=_queue_management_worker, - args=(weakref.ref(self, weakref_cb), - self._processes, - self._pending_work_items, - self._work_ids, - self._call_queue, - self._result_queue, - self._queue_management_thread_wakeup), - name="QueueManagerThread") - self._queue_management_thread.daemon = True - self._queue_management_thread.start() - _threads_wakeups[self._queue_management_thread] = \ - self._queue_management_thread_wakeup - - def _adjust_process_count(self): - for _ in range(len(self._processes), self._max_workers): - p = self._mp_context.Process( - target=_process_worker, - args=(self._call_queue, - self._result_queue, - self._initializer, - self._initargs)) - p.start() - self._processes[p.pid] = p - - def submit(self, fn, /, *args, **kwargs): - with self._shutdown_lock: - if self._broken: - raise BrokenProcessPool(self._broken) - if self._shutdown_thread: - raise RuntimeError('cannot schedule new futures after shutdown') - if _global_shutdown: - raise RuntimeError('cannot schedule new futures after ' - 'interpreter shutdown') - - f = _base.Future() - w = _WorkItem(f, fn, args, kwargs) - - self._pending_work_items[self._queue_count] = w - self._work_ids.put(self._queue_count) - self._queue_count += 1 - # Wake up queue management thread - self._queue_management_thread_wakeup.wakeup() - - self._start_queue_management_thread() - return f - submit.__doc__ = _base.Executor.submit.__doc__ - - def map(self, fn, *iterables, timeout=None, chunksize=1): - """Returns an iterator equivalent to map(fn, iter). - - Args: - fn: A callable that will take as many arguments as there are - passed iterables. - timeout: The maximum number of seconds to wait. If None, then there - is no limit on the wait time. - chunksize: If greater than one, the iterables will be chopped into - chunks of size chunksize and submitted to the process pool. - If set to one, the items in the list will be sent one at a time. - - Returns: - An iterator equivalent to: map(func, *iterables) but the calls may - be evaluated out-of-order. - - Raises: - TimeoutError: If the entire result iterator could not be generated - before the given timeout. - Exception: If fn(*args) raises for any values. - """ - if chunksize < 1: - raise ValueError("chunksize must be >= 1.") - - results = super().map(partial(_process_chunk, fn), - _get_chunks(*iterables, chunksize=chunksize), - timeout=timeout) - return _chain_from_iterable_of_lists(results) - - def shutdown(self, wait=True): - with self._shutdown_lock: - self._shutdown_thread = True - if self._queue_management_thread: - # Wake up queue management thread - self._queue_management_thread_wakeup.wakeup() - if wait: - self._queue_management_thread.join() - # To reduce the risk of opening too many files, remove references to - # objects that use file descriptors. - self._queue_management_thread = None - if self._call_queue is not None: - self._call_queue.close() - if wait: - self._call_queue.join_thread() - self._call_queue = None - self._result_queue = None - self._processes = None - - if self._queue_management_thread_wakeup: - self._queue_management_thread_wakeup.close() - self._queue_management_thread_wakeup = None - - shutdown.__doc__ = _base.Executor.shutdown.__doc__ - -atexit.register(_python_exit) diff --git a/Lib/concurrent/futures/thread.py b/Lib/concurrent/futures/thread.py deleted file mode 100644 index b89f8f2..0000000 --- a/Lib/concurrent/futures/thread.py +++ /dev/null @@ -1,225 +0,0 @@ -# Copyright 2009 Brian Quinlan. All Rights Reserved. -# Licensed to PSF under a Contributor Agreement. - -"""Implements ThreadPoolExecutor.""" - -__author__ = 'Brian Quinlan (brian@sweetapp.com)' - -import atexit -from concurrent.futures import _base -import itertools -import queue -import threading -import weakref -import os - -# Workers are created as daemon threads. This is done to allow the interpreter -# to exit when there are still idle threads in a ThreadPoolExecutor's thread -# pool (i.e. shutdown() was not called). However, allowing workers to die with -# the interpreter has two undesirable properties: -# - The workers would still be running during interpreter shutdown, -# meaning that they would fail in unpredictable ways. -# - The workers could be killed while evaluating a work item, which could -# be bad if the callable being evaluated has external side-effects e.g. -# writing to a file. -# -# To work around this problem, an exit handler is installed which tells the -# workers to exit when their work queues are empty and then waits until the -# threads finish. - -_threads_queues = weakref.WeakKeyDictionary() -_shutdown = False -# Lock that ensures that new workers are not created while the interpreter is -# shutting down. Must be held while mutating _threads_queues and _shutdown. -_global_shutdown_lock = threading.Lock() - -def _python_exit(): - global _shutdown - with _global_shutdown_lock: - _shutdown = True - items = list(_threads_queues.items()) - for t, q in items: - q.put(None) - for t, q in items: - t.join() - -atexit.register(_python_exit) - - -class _WorkItem(object): - def __init__(self, future, fn, args, kwargs): - self.future = future - self.fn = fn - self.args = args - self.kwargs = kwargs - - def run(self): - if not self.future.set_running_or_notify_cancel(): - return - - try: - result = self.fn(*self.args, **self.kwargs) - except BaseException as exc: - self.future.set_exception(exc) - # Break a reference cycle with the exception 'exc' - self = None - else: - self.future.set_result(result) - - -def _worker(executor_reference, work_queue, initializer, initargs): - if initializer is not None: - try: - initializer(*initargs) - except BaseException: - _base.LOGGER.critical('Exception in initializer:', exc_info=True) - executor = executor_reference() - if executor is not None: - executor._initializer_failed() - return - try: - while True: - work_item = work_queue.get(block=True) - if work_item is not None: - work_item.run() - # Delete references to object. See issue16284 - del work_item - - # attempt to increment idle count - executor = executor_reference() - if executor is not None: - executor._idle_semaphore.release() - del executor - continue - - executor = executor_reference() - # Exit if: - # - The interpreter is shutting down OR - # - The executor that owns the worker has been collected OR - # - The executor that owns the worker has been shutdown. - if _shutdown or executor is None or executor._shutdown: - # Flag the executor as shutting down as early as possible if it - # is not gc-ed yet. - if executor is not None: - executor._shutdown = True - # Notice other workers - work_queue.put(None) - return - del executor - except BaseException: - _base.LOGGER.critical('Exception in worker', exc_info=True) - - -class BrokenThreadPool(_base.BrokenExecutor): - """ - Raised when a worker thread in a ThreadPoolExecutor failed initializing. - """ - - -class ThreadPoolExecutor(_base.Executor): - - # Used to assign unique thread names when thread_name_prefix is not supplied. - _counter = itertools.count().__next__ - - def __init__(self, max_workers=None, thread_name_prefix='', - initializer=None, initargs=()): - """Initializes a new ThreadPoolExecutor instance. - - Args: - max_workers: The maximum number of threads that can be used to - execute the given calls. - thread_name_prefix: An optional name prefix to give our threads. - initializer: A callable used to initialize worker threads. - initargs: A tuple of arguments to pass to the initializer. - """ - if max_workers is None: - # ThreadPoolExecutor is often used to: - # * CPU bound task which releases GIL - # * I/O bound task (which releases GIL, of course) - # - # We use cpu_count + 4 for both types of tasks. - # But we limit it to 32 to avoid consuming surprisingly large resource - # on many core machine. - max_workers = min(32, (os.cpu_count() or 1) + 4) - if max_workers <= 0: - raise ValueError("max_workers must be greater than 0") - - if initializer is not None and not callable(initializer): - raise TypeError("initializer must be a callable") - - self._max_workers = max_workers - self._work_queue = queue.SimpleQueue() - self._idle_semaphore = threading.Semaphore(0) - self._threads = set() - self._broken = False - self._shutdown = False - self._shutdown_lock = threading.Lock() - self._thread_name_prefix = (thread_name_prefix or - ("ThreadPoolExecutor-%d" % self._counter())) - self._initializer = initializer - self._initargs = initargs - - def submit(self, fn, /, *args, **kwargs): - with self._shutdown_lock, _global_shutdown_lock: - if self._broken: - raise BrokenThreadPool(self._broken) - - if self._shutdown: - raise RuntimeError('cannot schedule new futures after shutdown') - if _shutdown: - raise RuntimeError('cannot schedule new futures after ' - 'interpreter shutdown') - - f = _base.Future() - w = _WorkItem(f, fn, args, kwargs) - - self._work_queue.put(w) - self._adjust_thread_count() - return f - submit.__doc__ = _base.Executor.submit.__doc__ - - def _adjust_thread_count(self): - # if idle threads are available, don't spin new threads - if self._idle_semaphore.acquire(timeout=0): - return - - # When the executor gets lost, the weakref callback will wake up - # the worker threads. - def weakref_cb(_, q=self._work_queue): - q.put(None) - - num_threads = len(self._threads) - if num_threads < self._max_workers: - thread_name = '%s_%d' % (self._thread_name_prefix or self, - num_threads) - t = threading.Thread(name=thread_name, target=_worker, - args=(weakref.ref(self, weakref_cb), - self._work_queue, - self._initializer, - self._initargs)) - t.daemon = True - t.start() - self._threads.add(t) - _threads_queues[t] = self._work_queue - - def _initializer_failed(self): - with self._shutdown_lock: - self._broken = ('A thread initializer failed, the thread pool ' - 'is not usable anymore') - # Drain work queue and mark pending futures failed - while True: - try: - work_item = self._work_queue.get_nowait() - except queue.Empty: - break - if work_item is not None: - work_item.future.set_exception(BrokenThreadPool(self._broken)) - - def shutdown(self, wait=True): - with self._shutdown_lock: - self._shutdown = True - self._work_queue.put(None) - if wait: - for t in self._threads: - t.join() - shutdown.__doc__ = _base.Executor.shutdown.__doc__ |