Inheritance in iterable implementation of python's multiprocessing.Queue - python-3.x

Question

I found the default implementation of python's multiprocessing.Queue lacking, in that it's not iterable like any other collection. So I went about the effort of creating a 'subclass' of it, adding the feature in. As you can see from the code below, it's not a proper subclass, as multiprocess.Queue isn't a direct class itself, but a factory function, and the real underlying class is multiprocess.queues.Queue. I don't have the understanding nor effort to expend necessary to go about mimicking the factory function just so I can inherit from the class properly, so I simply had the new class create it's own instance from the factory and treat it as the superclass. Here is the code;
from multiprocessing import Queue, Value, Lock
import queue
class QueueClosed(Exception):
pass
class IterableQueue:
def __init__(self, maxsize=0):
self.closed = Value('b', False)
self.close_lock = Lock()
self.queue = Queue(maxsize)
def close(self):
with self.close_lock:
self.closed.value = True
self.queue.close()
def put(self, elem, block=True, timeout=None):
with self.close_lock:
if self.closed.value:
raise QueueClosed()
else:
self.queue.put(elem, block, timeout)
def put_nowait(self, elem):
self.put(elem, False)
def get(self, block=True):
if not block:
return self.queue.get_nowait()
elif self.closed.value:
try:
return self.queue.get_nowait()
except queue.Empty:
return None
else:
val = None
while not self.closed.value:
try:
val = self.queue.get_nowait()
break
except queue.Empty:
pass
return val
def get_nowait(self):
return self.queue.get_nowait()
def join_thread(self):
return self.queue.join_thread()
def __iter__(self):
return self
def __next__(self):
val = self.get()
if val == None:
raise StopIteration()
else:
return val
def __enter__(self):
return self
def __exit__(self, *args):
self.close()
This allows me to instantiate an IterableQueue object just like a normal multiprocessing.Queue, put elements into it like normal, and then inside child consumers, simply loop over it like so;
from iterable_queue import IterableQueue
from multiprocessing import Process, cpu_count
import os
def fib(n):
if n < 2:
return n
return fib(n-1) + fib(n-2)
def consumer(queue):
print(f"[{os.getpid()}] Consuming")
for i in queue:
print(f"[{os.getpid()}] < {i}")
n = fib(i)
print(f"[{os.getpid()}] {i} > {n}")
print(f"[{os.getpid()}] Closing")
def producer():
print("Enqueueing")
with IterableQueue() as queue:
procs = [Process(target=consumer, args=(queue,)) for _ in range(cpu_count())]
[p.start() for p in procs]
[queue.put(i) for i in range(36)]
print("Finished")
if __name__ == "__main__":
producer()
and it works almost seamlessly; the consumers exit the loop once the queue has been closed, but only after exhausting all remaining elements. However, I was unsatisfied with the lack of inherited methods. In an attempt to mimic actual inheritance behavior, I tried adding the following meta function call to the class;
def __getattr__(self, name):
if name in self.__dict__:
return self.__dict__[name]
else:
return self.queue.__getattr__[name]
However, this fails when instances of the IterableQueue class are manipulated inside child multiprocessing.Process threads, as the class's __dict__ property is not preserved within them. I attempted to remedy this in a hacky manner by replacing the class's default __dict__ with a multiprocessing.Manager().dict(), like so;
def __init__(self, maxsize=0):
self.closed = Value('b', False)
self.close_lock = Lock()
self.queue = Queue(maxsize)
self.__dict__ = Manager().dict(self.__dict__)
However on doing so, I received an error stating RuntimeError: Synchronized objects should only be shared between processes through inheritance. So my question is, how should I go about inheriting from the Queue class properly such that the subclass has inherited access to all of it's properties? In addition, while the queue is empty but not closed, the consumers all sit in a busy loop instead of a true IO block, taking up valuable cpu resources. If you have any suggestions on concurrency and race condition issues I might run into with this code, or how I might solve the busy loop issue, I'd be willing to take suggestions therein as well.
Based on code provided by MisterMiyagi, I created this general purpose IterableQueue class which can accept arbitrary input, blocks properly, and does not hang on queue close;
from multiprocessing.queues import Queue
from multiprocessing import get_context
class QueueClosed(Exception):
pass
class IterableQueue(Queue):
def __init__(self, maxsize=0, *, ctx=None):
super().__init__(
maxsize=maxsize,
ctx=ctx if ctx is not None else get_context()
)
def close(self):
super().put((None, False))
super().close()
def __iter__(self):
return self
def __next__(self):
try:
return self.get()
except QueueClosed:
raise StopIteration
def get(self, *args, **kwargs):
result, is_open = super().get(*args, **kwargs)
if not is_open:
super().put((None, False))
raise QueueClosed
return result
def put(self, val, *args, **kwargs):
super().put((val, True), *args, **kwargs)
def __enter__(self):
return self
def __exit__(self, *args):
self.close()

Answer 1

The multiprocess.Queue wrapper only serves to use the default context.
def Queue(self, maxsize=0):
'''Returns a queue object'''
from .queues import Queue
return Queue(maxsize, ctx=self.get_context())
When inheriting, you can replicate this in the __init__ method. This allows you to inherit the entire Queue behaviour. You only need to add the iterator methods:
from multiprocessing.queues import Queue
from multiprocessing import get_context
class IterableQueue(Queue):
"""
``multiprocessing.Queue`` that can be iterated to ``get`` values
:param sentinel: signal that no more items will be received
"""
def __init__(self, maxsize=0, *, ctx=None, sentinel=None):
self.sentinel = sentinel
super().__init__(
maxsize=maxsize,
ctx=ctx if ctx is not None else get_context()
)
def close(self):
self.put(self.sentinel)
# wait until buffer is flushed...
while self._buffer:
time.sleep(0.01)
# before shutting down the sender
super().close()
def __iter__(self):
return self
def __next__(self):
result = self.get()
if result == self.sentinel:
# re-queue sentinel for other listeners
self.put(result)
raise StopIteration
return result
Note that the sentinel to indicate end-of-queue is compared by equality, because identity is not preserved across processes. The often-used queue.Queue sentinel object() does not work properly with this.