summaryrefslogtreecommitdiff
path: root/Lib/multiprocessing/pool.py
blob: a47cd0f58a05af04affbc7b37fe42337cd101d64 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
#
# Module providing the `Pool` class for managing a process pool
#
# multiprocessing/pool.py
#
# Copyright (c) 2006-2008, R Oudkerk
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
# 1. Redistributions of source code must retain the above copyright
#    notice, this list of conditions and the following disclaimer.
# 2. Redistributions in binary form must reproduce the above copyright
#    notice, this list of conditions and the following disclaimer in the
#    documentation and/or other materials provided with the distribution.
# 3. Neither the name of author nor the names of any contributors may be
#    used to endorse or promote products derived from this software
#    without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS "AS IS" AND
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#

__all__ = ['Pool']

#
# Imports
#

import threading
import Queue
import itertools
import collections
import time

from multiprocessing import Process, cpu_count, TimeoutError
from multiprocessing.util import Finalize, debug

#
# Constants representing the state of a pool
#

RUN = 0
CLOSE = 1
TERMINATE = 2

#
# Miscellaneous
#

job_counter = itertools.count()

def mapstar(args):
    return map(*args)

#
# Code run by worker processes
#

class MaybeEncodingError(Exception):
    """Wraps possible unpickleable errors, so they can be
    safely sent through the socket."""

    def __init__(self, exc, value):
        self.exc = repr(exc)
        self.value = repr(value)
        super(MaybeEncodingError, self).__init__(self.exc, self.value)

    def __str__(self):
        return "Error sending result: '%s'. Reason: '%s'" % (self.value,
                                                             self.exc)

    def __repr__(self):
        return "<MaybeEncodingError: %s>" % str(self)


def worker(inqueue, outqueue, initializer=None, initargs=(), maxtasks=None):
    assert maxtasks is None or (type(maxtasks) in (int, long) and maxtasks > 0)
    put = outqueue.put
    get = inqueue.get
    if hasattr(inqueue, '_writer'):
        inqueue._writer.close()
        outqueue._reader.close()

    if initializer is not None:
        initializer(*initargs)

    completed = 0
    while maxtasks is None or (maxtasks and completed < maxtasks):
        try:
            task = get()
        except (EOFError, IOError):
            debug('worker got EOFError or IOError -- exiting')
            break

        if task is None:
            debug('worker got sentinel -- exiting')
            break

        job, i, func, args, kwds = task
        try:
            result = (True, func(*args, **kwds))
        except Exception, e:
            result = (False, e)
        try:
            put((job, i, result))
        except Exception as e:
            wrapped = MaybeEncodingError(e, result[1])
            debug("Possible encoding error while sending result: %s" % (
                wrapped))
            put((job, i, (False, wrapped)))

        task = job = result = func = args = kwds = None
        completed += 1
    debug('worker exiting after %d tasks' % completed)

#
# Class representing a process pool
#

class Pool(object):
    '''
    Class which supports an async version of the `apply()` builtin
    '''
    Process = Process

    def __init__(self, processes=None, initializer=None, initargs=(),
                 maxtasksperchild=None):
        self._setup_queues()
        self._taskqueue = Queue.Queue()
        self._cache = {}
        self._state = RUN
        self._maxtasksperchild = maxtasksperchild
        self._initializer = initializer
        self._initargs = initargs

        if processes is None:
            try:
                processes = cpu_count()
            except NotImplementedError:
                processes = 1
        if processes < 1:
            raise ValueError("Number of processes must be at least 1")

        if initializer is not None and not hasattr(initializer, '__call__'):
            raise TypeError('initializer must be a callable')

        self._processes = processes
        self._pool = []
        self._repopulate_pool()

        self._worker_handler = threading.Thread(
            target=Pool._handle_workers,
            args=(self, )
            )
        self._worker_handler.daemon = True
        self._worker_handler._state = RUN
        self._worker_handler.start()


        self._task_handler = threading.Thread(
            target=Pool._handle_tasks,
            args=(self._taskqueue, self._quick_put, self._outqueue,
                  self._pool, self._cache)
            )
        self._task_handler.daemon = True
        self._task_handler._state = RUN
        self._task_handler.start()

        self._result_handler = threading.Thread(
            target=Pool._handle_results,
            args=(self._outqueue, self._quick_get, self._cache)
            )
        self._result_handler.daemon = True
        self._result_handler._state = RUN
        self._result_handler.start()

        self._terminate = Finalize(
            self, self._terminate_pool,
            args=(self._taskqueue, self._inqueue, self._outqueue, self._pool,
                  self._worker_handler, self._task_handler,
                  self._result_handler, self._cache),
            exitpriority=15
            )

    def _join_exited_workers(self):
        """Cleanup after any worker processes which have exited due to reaching
        their specified lifetime.  Returns True if any workers were cleaned up.
        """
        cleaned = False
        for i in reversed(range(len(self._pool))):
            worker = self._pool[i]
            if worker.exitcode is not None:
                # worker exited
                debug('cleaning up worker %d' % i)
                worker.join()
                cleaned = True
                del self._pool[i]
        return cleaned

    def _repopulate_pool(self):
        """Bring the number of pool processes up to the specified number,
        for use after reaping workers which have exited.
        """
        for i in range(self._processes - len(self._pool)):
            w = self.Process(target=worker,
                             args=(self._inqueue, self._outqueue,
                                   self._initializer,
                                   self._initargs, self._maxtasksperchild)
                            )
            self._pool.append(w)
            w.name = w.name.replace('Process', 'PoolWorker')
            w.daemon = True
            w.start()
            debug('added worker')

    def _maintain_pool(self):
        """Clean up any exited workers and start replacements for them.
        """
        if self._join_exited_workers():
            self._repopulate_pool()

    def _setup_queues(self):
        from .queues import SimpleQueue
        self._inqueue = SimpleQueue()
        self._outqueue = SimpleQueue()
        self._quick_put = self._inqueue._writer.send
        self._quick_get = self._outqueue._reader.recv

    def apply(self, func, args=(), kwds={}):
        '''
        Equivalent of `apply()` builtin
        '''
        assert self._state == RUN
        return self.apply_async(func, args, kwds).get()

    def map(self, func, iterable, chunksize=None):
        '''
        Equivalent of `map()` builtin
        '''
        assert self._state == RUN
        return self.map_async(func, iterable, chunksize).get()

    def imap(self, func, iterable, chunksize=1):
        '''
        Equivalent of `itertools.imap()` -- can be MUCH slower than `Pool.map()`
        '''
        assert self._state == RUN
        if chunksize == 1:
            result = IMapIterator(self._cache)
            self._taskqueue.put((((result._job, i, func, (x,), {})
                         for i, x in enumerate(iterable)), result._set_length))
            return result
        else:
            assert chunksize > 1
            task_batches = Pool._get_tasks(func, iterable, chunksize)
            result = IMapIterator(self._cache)
            self._taskqueue.put((((result._job, i, mapstar, (x,), {})
                     for i, x in enumerate(task_batches)), result._set_length))
            return (item for chunk in result for item in chunk)

    def imap_unordered(self, func, iterable, chunksize=1):
        '''
        Like `imap()` method but ordering of results is arbitrary
        '''
        assert self._state == RUN
        if chunksize == 1:
            result = IMapUnorderedIterator(self._cache)
            self._taskqueue.put((((result._job, i, func, (x,), {})
                         for i, x in enumerate(iterable)), result._set_length))
            return result
        else:
            assert chunksize > 1
            task_batches = Pool._get_tasks(func, iterable, chunksize)
            result = IMapUnorderedIterator(self._cache)
            self._taskqueue.put((((result._job, i, mapstar, (x,), {})
                     for i, x in enumerate(task_batches)), result._set_length))
            return (item for chunk in result for item in chunk)

    def apply_async(self, func, args=(), kwds={}, callback=None):
        '''
        Asynchronous equivalent of `apply()` builtin
        '''
        assert self._state == RUN
        result = ApplyResult(self._cache, callback)
        self._taskqueue.put(([(result._job, None, func, args, kwds)], None))
        return result

    def map_async(self, func, iterable, chunksize=None, callback=None):
        '''
        Asynchronous equivalent of `map()` builtin
        '''
        assert self._state == RUN
        if not hasattr(iterable, '__len__'):
            iterable = list(iterable)

        if chunksize is None:
            chunksize, extra = divmod(len(iterable), len(self._pool) * 4)
            if extra:
                chunksize += 1
        if len(iterable) == 0:
            chunksize = 0

        task_batches = Pool._get_tasks(func, iterable, chunksize)
        result = MapResult(self._cache, chunksize, len(iterable), callback)
        self._taskqueue.put((((result._job, i, mapstar, (x,), {})
                              for i, x in enumerate(task_batches)), None))
        return result

    @staticmethod
    def _handle_workers(pool):
        thread = threading.current_thread()

        # Keep maintaining workers until the cache gets drained, unless the pool
        # is terminated.
        while thread._state == RUN or (pool._cache and thread._state != TERMINATE):
            pool._maintain_pool()
            time.sleep(0.1)
        # send sentinel to stop workers
        pool._taskqueue.put(None)
        debug('worker handler exiting')

    @staticmethod
    def _handle_tasks(taskqueue, put, outqueue, pool, cache):
        thread = threading.current_thread()

        for taskseq, set_length in iter(taskqueue.get, None):
            task = None
            i = -1
            try:
                for i, task in enumerate(taskseq):
                    if thread._state:
                        debug('task handler found thread._state != RUN')
                        break
                    try:
                        put(task)
                    except Exception as e:
                        job, ind = task[:2]
                        try:
                            cache[job]._set(ind, (False, e))
                        except KeyError:
                            pass
                else:
                    if set_length:
                        debug('doing set_length()')
                        set_length(i+1)
                    continue
                break
            except Exception as ex:
                job, ind = task[:2] if task else (0, 0)
                if job in cache:
                    cache[job]._set(ind + 1, (False, ex))
                if set_length:
                    debug('doing set_length()')
                    set_length(i+1)
            finally:
                task = taskseq = job = None
        else:
            debug('task handler got sentinel')

        try:
            # tell result handler to finish when cache is empty
            debug('task handler sending sentinel to result handler')
            outqueue.put(None)

            # tell workers there is no more work
            debug('task handler sending sentinel to workers')
            for p in pool:
                put(None)
        except IOError:
            debug('task handler got IOError when sending sentinels')

        debug('task handler exiting')

    @staticmethod
    def _handle_results(outqueue, get, cache):
        thread = threading.current_thread()

        while 1:
            try:
                task = get()
            except (IOError, EOFError):
                debug('result handler got EOFError/IOError -- exiting')
                return

            if thread._state:
                assert thread._state == TERMINATE
                debug('result handler found thread._state=TERMINATE')
                break

            if task is None:
                debug('result handler got sentinel')
                break

            job, i, obj = task
            try:
                cache[job]._set(i, obj)
            except KeyError:
                pass
            task = job = obj = None

        while cache and thread._state != TERMINATE:
            try:
                task = get()
            except (IOError, EOFError):
                debug('result handler got EOFError/IOError -- exiting')
                return

            if task is None:
                debug('result handler ignoring extra sentinel')
                continue
            job, i, obj = task
            try:
                cache[job]._set(i, obj)
            except KeyError:
                pass
            task = job = obj = None

        if hasattr(outqueue, '_reader'):
            debug('ensuring that outqueue is not full')
            # If we don't make room available in outqueue then
            # attempts to add the sentinel (None) to outqueue may
            # block.  There is guaranteed to be no more than 2 sentinels.
            try:
                for i in range(10):
                    if not outqueue._reader.poll():
                        break
                    get()
            except (IOError, EOFError):
                pass

        debug('result handler exiting: len(cache)=%s, thread._state=%s',
              len(cache), thread._state)

    @staticmethod
    def _get_tasks(func, it, size):
        it = iter(it)
        while 1:
            x = tuple(itertools.islice(it, size))
            if not x:
                return
            yield (func, x)

    def __reduce__(self):
        raise NotImplementedError(
              'pool objects cannot be passed between processes or pickled'
              )

    def close(self):
        debug('closing pool')
        if self._state == RUN:
            self._state = CLOSE
            self._worker_handler._state = CLOSE

    def terminate(self):
        debug('terminating pool')
        self._state = TERMINATE
        self._worker_handler._state = TERMINATE
        self._terminate()

    def join(self):
        debug('joining pool')
        assert self._state in (CLOSE, TERMINATE)
        self._worker_handler.join()
        self._task_handler.join()
        self._result_handler.join()
        for p in self._pool:
            p.join()

    @staticmethod
    def _help_stuff_finish(inqueue, task_handler, size):
        # task_handler may be blocked trying to put items on inqueue
        debug('removing tasks from inqueue until task handler finished')
        inqueue._rlock.acquire()
        while task_handler.is_alive() and inqueue._reader.poll():
            inqueue._reader.recv()
            time.sleep(0)

    @classmethod
    def _terminate_pool(cls, taskqueue, inqueue, outqueue, pool,
                        worker_handler, task_handler, result_handler, cache):
        # this is guaranteed to only be called once
        debug('finalizing pool')

        worker_handler._state = TERMINATE
        task_handler._state = TERMINATE

        debug('helping task handler/workers to finish')
        cls._help_stuff_finish(inqueue, task_handler, len(pool))

        assert result_handler.is_alive() or len(cache) == 0

        result_handler._state = TERMINATE
        outqueue.put(None)                  # sentinel

        # We must wait for the worker handler to exit before terminating
        # workers because we don't want workers to be restarted behind our back.
        debug('joining worker handler')
        if threading.current_thread() is not worker_handler:
            worker_handler.join(1e100)

        # Terminate workers which haven't already finished.
        if pool and hasattr(pool[0], 'terminate'):
            debug('terminating workers')
            for p in pool:
                if p.exitcode is None:
                    p.terminate()

        debug('joining task handler')
        if threading.current_thread() is not task_handler:
            task_handler.join(1e100)

        debug('joining result handler')
        if threading.current_thread() is not result_handler:
            result_handler.join(1e100)

        if pool and hasattr(pool[0], 'terminate'):
            debug('joining pool workers')
            for p in pool:
                if p.is_alive():
                    # worker has not yet exited
                    debug('cleaning up worker %d' % p.pid)
                    p.join()

#
# Class whose instances are returned by `Pool.apply_async()`
#

class ApplyResult(object):

    def __init__(self, cache, callback):
        self._cond = threading.Condition(threading.Lock())
        self._job = job_counter.next()
        self._cache = cache
        self._ready = False
        self._callback = callback
        cache[self._job] = self

    def ready(self):
        return self._ready

    def successful(self):
        assert self._ready
        return self._success

    def wait(self, timeout=None):
        self._cond.acquire()
        try:
            if not self._ready:
                self._cond.wait(timeout)
        finally:
            self._cond.release()

    def get(self, timeout=None):
        self.wait(timeout)
        if not self._ready:
            raise TimeoutError
        if self._success:
            return self._value
        else:
            raise self._value

    def _set(self, i, obj):
        self._success, self._value = obj
        if self._callback and self._success:
            self._callback(self._value)
        self._cond.acquire()
        try:
            self._ready = True
            self._cond.notify()
        finally:
            self._cond.release()
        del self._cache[self._job]

AsyncResult = ApplyResult       # create alias -- see #17805

#
# Class whose instances are returned by `Pool.map_async()`
#

class MapResult(ApplyResult):

    def __init__(self, cache, chunksize, length, callback):
        ApplyResult.__init__(self, cache, callback)
        self._success = True
        self._value = [None] * length
        self._chunksize = chunksize
        if chunksize <= 0:
            self._number_left = 0
            self._ready = True
            del cache[self._job]
        else:
            self._number_left = length//chunksize + bool(length % chunksize)

    def _set(self, i, success_result):
        success, result = success_result
        if success:
            self._value[i*self._chunksize:(i+1)*self._chunksize] = result
            self._number_left -= 1
            if self._number_left == 0:
                if self._callback:
                    self._callback(self._value)
                del self._cache[self._job]
                self._cond.acquire()
                try:
                    self._ready = True
                    self._cond.notify()
                finally:
                    self._cond.release()

        else:
            self._success = False
            self._value = result
            del self._cache[self._job]
            self._cond.acquire()
            try:
                self._ready = True
                self._cond.notify()
            finally:
                self._cond.release()

#
# Class whose instances are returned by `Pool.imap()`
#

class IMapIterator(object):

    def __init__(self, cache):
        self._cond = threading.Condition(threading.Lock())
        self._job = job_counter.next()
        self._cache = cache
        self._items = collections.deque()
        self._index = 0
        self._length = None
        self._unsorted = {}
        cache[self._job] = self

    def __iter__(self):
        return self

    def next(self, timeout=None):
        self._cond.acquire()
        try:
            try:
                item = self._items.popleft()
            except IndexError:
                if self._index == self._length:
                    raise StopIteration
                self._cond.wait(timeout)
                try:
                    item = self._items.popleft()
                except IndexError:
                    if self._index == self._length:
                        raise StopIteration
                    raise TimeoutError
        finally:
            self._cond.release()

        success, value = item
        if success:
            return value
        raise value

    __next__ = next                    # XXX

    def _set(self, i, obj):
        self._cond.acquire()
        try:
            if self._index == i:
                self._items.append(obj)
                self._index += 1
                while self._index in self._unsorted:
                    obj = self._unsorted.pop(self._index)
                    self._items.append(obj)
                    self._index += 1
                self._cond.notify()
            else:
                self._unsorted[i] = obj

            if self._index == self._length:
                del self._cache[self._job]
        finally:
            self._cond.release()

    def _set_length(self, length):
        self._cond.acquire()
        try:
            self._length = length
            if self._index == self._length:
                self._cond.notify()
                del self._cache[self._job]
        finally:
            self._cond.release()

#
# Class whose instances are returned by `Pool.imap_unordered()`
#

class IMapUnorderedIterator(IMapIterator):

    def _set(self, i, obj):
        self._cond.acquire()
        try:
            self._items.append(obj)
            self._index += 1
            self._cond.notify()
            if self._index == self._length:
                del self._cache[self._job]
        finally:
            self._cond.release()

#
#
#

class ThreadPool(Pool):

    from .dummy import Process

    def __init__(self, processes=None, initializer=None, initargs=()):
        Pool.__init__(self, processes, initializer, initargs)

    def _setup_queues(self):
        self._inqueue = Queue.Queue()
        self._outqueue = Queue.Queue()
        self._quick_put = self._inqueue.put
        self._quick_get = self._outqueue.get

    @staticmethod
    def _help_stuff_finish(inqueue, task_handler, size):
        # put sentinels at head of inqueue to make workers finish
        inqueue.not_empty.acquire()
        try:
            inqueue.queue.clear()
            inqueue.queue.extend([None] * size)
            inqueue.not_empty.notify_all()
        finally:
            inqueue.not_empty.release()