Source

python-clinic / Lib / concurrent / futures / process.py

  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
# Copyright 2009 Brian Quinlan. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.

"""Implements ProcessPoolExecutor.

The follow diagram and text describe the data-flow through the system:

|======================= In-process =====================|== Out-of-process ==|

+----------+     +----------+       +--------+     +-----------+    +---------+
|          |  => | Work Ids |    => |        |  => | Call Q    | => |         |
|          |     +----------+       |        |     +-----------+    |         |
|          |     | ...      |       |        |     | ...       |    |         |
|          |     | 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
import multiprocessing
from multiprocessing.queues import SimpleQueue, Full
from multiprocessing.connection import wait
import threading
import weakref

# 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 interpretor 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_queues = weakref.WeakKeyDictionary()
_shutdown = False

def _python_exit():
    global _shutdown
    _shutdown = True
    items = list(_threads_queues.items())
    for t, q in items:
        q.put(None)
    for t, q 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

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

def _process_worker(call_queue, result_queue):
    """Evaluates calls from call_queue and places the results in result_queue.

    This worker is run in a separate process.

    Args:
        call_queue: A multiprocessing.Queue of _CallItems that will be read and
            evaluated by the worker.
        result_queue: A multiprocessing.Queue of _ResultItems that will written
            to by the worker.
        shutdown: A multiprocessing.Event that will be set as a signal to the
            worker that it should exit when call_queue is empty.
    """
    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:
            result_queue.put(_ResultItem(call_item.work_id,
                                         exception=e))
        else:
            result_queue.put(_ResultItem(call_item.work_id,
                                         result=r))

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):
    """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 multiprocessing.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 multiprocessing.Queue that will be filled with _CallItems
            derived from _WorkItems for processing by the process workers.
        result_queue: A multiprocessing.Queue of _ResultItems generated by the
            process workers.
    """
    executor = None

    def shutting_down():
        return _shutdown or executor is None or executor._shutdown_thread

    def shutdown_worker():
        # This is an upper bound
        nb_children_alive = sum(p.is_alive() for p in processes.values())
        for i in range(0, nb_children_alive):
            call_queue.put_nowait(None)
        # Release the queue's resources as soon as possible.
        call_queue.close()
        # If .join() is not called on the created processes then
        # some multiprocessing.Queue methods may deadlock on Mac OS X.
        for p in processes.values():
            p.join()

    reader = result_queue._reader

    while True:
        _add_call_item_to_queue(pending_work_items,
                                work_ids_queue,
                                call_queue)

        sentinels = [p.sentinel for p in processes.values()]
        assert sentinels
        ready = wait([reader] + sentinels)
        if reader in ready:
            result_item = reader.recv()
        else:
            # Mark the process pool broken so that submits fail right now.
            executor = executor_reference()
            if executor is not None:
                executor._broken = True
                executor._shutdown_thread = True
                executor = None
            # All futures in flight must be marked failed
            for work_id, work_item in pending_work_items.items():
                work_item.future.set_exception(
                    BrokenProcessPool(
                        "A process in the process pool was "
                        "terminated abruptly while the future was "
                        "running or pending."
                    ))
                # 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
        # 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:
                # 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:
        # indetermine 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)


class BrokenProcessPool(RuntimeError):
    """
    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):
        """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.
        """
        _check_system_limits()

        if max_workers is None:
            self._max_workers = os.cpu_count() or 1
        else:
            self._max_workers = max_workers

        # 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.
        self._call_queue = multiprocessing.Queue(self._max_workers +
                                                 EXTRA_QUEUED_CALLS)
        # 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 = SimpleQueue()
        self._work_ids = queue.Queue()
        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 = {}

    def _start_queue_management_thread(self):
        # When the executor gets lost, the weakref callback will wake up
        # the queue management thread.
        def weakref_cb(_, q=self._result_queue):
            q.put(None)
        if self._queue_management_thread is None:
            # 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.daemon = True
            self._queue_management_thread.start()
            _threads_queues[self._queue_management_thread] = self._result_queue

    def _adjust_process_count(self):
        for _ in range(len(self._processes), self._max_workers):
            p = multiprocessing.Process(
                    target=_process_worker,
                    args=(self._call_queue,
                          self._result_queue))
            p.start()
            self._processes[p.pid] = p

    def submit(self, fn, *args, **kwargs):
        with self._shutdown_lock:
            if self._broken:
                raise BrokenProcessPool('A child process terminated '
                    'abruptly, the process pool is not usable anymore')
            if self._shutdown_thread:
                raise RuntimeError('cannot schedule new futures after 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._result_queue.put(None)

            self._start_queue_management_thread()
            return f
    submit.__doc__ = _base.Executor.submit.__doc__

    def shutdown(self, wait=True):
        with self._shutdown_lock:
            self._shutdown_thread = True
        if self._queue_management_thread:
            # Wake up queue management thread
            self._result_queue.put(None)
            if wait:
                self._queue_management_thread.join()
        # To reduce the risk of openning too many files, remove references to
        # objects that use file descriptors.
        self._queue_management_thread = None
        self._call_queue = None
        self._result_queue = None
        self._processes = None
    shutdown.__doc__ = _base.Executor.shutdown.__doc__

atexit.register(_python_exit)