diff options
Diffstat (limited to 'Lib/concurrent')
-rw-r--r-- | Lib/concurrent/futures/_base.py | 21 | ||||
-rw-r--r-- | Lib/concurrent/futures/process.py | 54 | ||||
-rw-r--r-- | Lib/concurrent/futures/thread.py | 10 |
3 files changed, 77 insertions, 8 deletions
diff --git a/Lib/concurrent/futures/_base.py b/Lib/concurrent/futures/_base.py index acd05d0b2aa..9e447137adc 100644 --- a/Lib/concurrent/futures/_base.py +++ b/Lib/concurrent/futures/_base.py @@ -302,17 +302,20 @@ class Future(object): with self._condition: if self._state == FINISHED: if self._exception: - return '<Future at %s state=%s raised %s>' % ( - hex(id(self)), + 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 '<Future at %s state=%s returned %s>' % ( - hex(id(self)), + return '<%s at %#x state=%s returned %s>' % ( + self.__class__.__name__, + id(self), _STATE_TO_DESCRIPTION_MAP[self._state], self._result.__class__.__name__) - return '<Future at %s state=%s>' % ( - hex(id(self)), + return '<%s at %#x state=%s>' % ( + self.__class__.__name__, + id(self), _STATE_TO_DESCRIPTION_MAP[self._state]) def cancel(self): @@ -517,7 +520,7 @@ class Executor(object): """ raise NotImplementedError() - def map(self, fn, *iterables, timeout=None): + def map(self, fn, *iterables, timeout=None, chunksize=1): """Returns a iterator equivalent to map(fn, iter). Args: @@ -525,6 +528,10 @@ class Executor(object): 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 diff --git a/Lib/concurrent/futures/process.py b/Lib/concurrent/futures/process.py index 07b5225d1da..fc64dbe84bf 100644 --- a/Lib/concurrent/futures/process.py +++ b/Lib/concurrent/futures/process.py @@ -55,6 +55,8 @@ from multiprocessing import SimpleQueue from multiprocessing.connection import wait import threading import weakref +from functools import partial +import itertools # 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 @@ -108,6 +110,26 @@ class _CallItem(object): self.args = args self.kwargs = kwargs +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 _process_worker(call_queue, result_queue): """Evaluates calls from call_queue and places the results in result_queue. @@ -334,6 +356,9 @@ class ProcessPoolExecutor(_base.Executor): if max_workers is None: self._max_workers = os.cpu_count() or 1 else: + if max_workers <= 0: + raise ValueError("max_workers must be greater than 0") + self._max_workers = max_workers # Make the call queue slightly larger than the number of processes to @@ -408,6 +433,35 @@ class ProcessPoolExecutor(_base.Executor): return f submit.__doc__ = _base.Executor.submit.__doc__ + def map(self, fn, *iterables, timeout=None, chunksize=1): + """Returns a 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 itertools.chain.from_iterable(results) + def shutdown(self, wait=True): with self._shutdown_lock: self._shutdown_thread = True diff --git a/Lib/concurrent/futures/thread.py b/Lib/concurrent/futures/thread.py index f9beb0f7f7e..3ae442d9870 100644 --- a/Lib/concurrent/futures/thread.py +++ b/Lib/concurrent/futures/thread.py @@ -10,6 +10,7 @@ from concurrent.futures import _base 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 @@ -80,13 +81,20 @@ def _worker(executor_reference, work_queue): _base.LOGGER.critical('Exception in worker', exc_info=True) class ThreadPoolExecutor(_base.Executor): - def __init__(self, max_workers): + def __init__(self, max_workers=None): """Initializes a new ThreadPoolExecutor instance. Args: max_workers: The maximum number of threads that can be used to execute the given calls. """ + if max_workers is None: + # Use this number because ThreadPoolExecutor is often + # used to overlap I/O instead of CPU work. + max_workers = (os.cpu_count() or 1) * 5 + if max_workers <= 0: + raise ValueError("max_workers must be greater than 0") + self._max_workers = max_workers self._work_queue = queue.Queue() self._threads = set() |