Iterable multiprocessing Queue not exiting - python

import multiprocessing.queues as queues
import multiprocessing
class I(queues.Queue):
def __init__(self, maxsize=0):
super(I, self).__init__(maxsize)
self.length = 0
def __iter__(self):
return self
def put(self, obj, block=True, timeout=None):
super(I, self).put(obj,block,timeout)
self.length += 1
def get(self, block = True, timeout = None):
self.length -= 1
return super(I, self).get(block, timeout)
def __len__(self):
return self.length
def next(self):
item = self.get()
if item == 'Done':
raise StopIteration
return item
def thisworker(item):
print 'got this item: %s' % item
return item
q=I()
q.put(1)
q.put('Done')
the_pool = multiprocessing.Pool(1)
print the_pool.map(thisworker, q)
I'm trying to create an iterable queue to use with multiprocessing pool map.
The idea is that the function thisworker would append some items to the queue until a condition is met and then exit after putting 'Done' in the queue (I've not done it here in this code yet)
But, this code never completes, it always hangs up.
I'm not able to debug the real cause.
Request your help
PS: I've used self.length because the map_async method called from under the_pool.map requires to use the length of the iterable to form a variable: chunksize, which will be used to get tasks from the pool.

The problem is that you're treating 'Done' as a special-case item in the Queue, which indicates that the iteration should stop. So, if you iterate over the Queue using a for loop with your example, all that will be returned is 1. However, you're claiming that the length of the Queue is 2. This is screwing up the map code, which is relying on that length to accurately represent the number of items in the iterable in order to know when all the results have returned from the workers:
class MapResult(ApplyResult):
def __init__(self, cache, chunksize, length, callback):
ApplyResult.__init__(self, cache, callback)
...
# _number_left is used to know when the MapResult is done
self._number_left = length//chunksize + bool(length % chunksize)
So, you need to make the length actually be accurate. You can do that a few ways, but I would recommend not requiring a sentinel to be loaded into the Queue at all, and use get_nowait instead:
import multiprocessing.queues as queues
import multiprocessing
from Queue import Empty
class I(queues.Queue):
def __init__(self, maxsize=0):
super(I, self).__init__(maxsize)
self.length = 0
... <snip>
def next(self):
try:
item = self.get_nowait()
except Empty:
raise StopIteration
return item
def thisworker(item):
print 'got this item: %s' % item
return item
q=I()
q.put(1)
the_pool = multiprocessing.Pool(1)
print the_pool.map(thisworker, q)
Also, note that this approach isn't process safe. The length attribute will only be correct if you only put into the Queue from a single process, and then never put again after sending the Queue to a worker process. It also won't work in Python 3 without adjusting the imports and implementation, because the constructor for multiprocessing.queues.Queue has changed.
Instead of subclassing multiprocessing.queues.Queue, I would recommend using the iter built-in to iterate over the Queue:
q = multiprocessing.Queue()
q.put(1)
q.put(2)
q.put(None) # None is our sentinel, you could use 'Done', if you wanted
the_pool.map(thisworker, iter(q.get, None)) # This will call q.get() until None is returned
This will work on all versions of Python, is much less code, and is process-safe.
Edit:
Based on the requirements you mentioned in the comment to my answer, I think you're better off using imap instead of map, so that you don't need to know the length of the Queue at all. The reality is, you can't accurately determine that, and in fact the length may end up growing as you're iterating. If you use imap exclusively, then doing something similar to your original approach will work fine:
import multiprocessing
class I(object):
def __init__(self, maxsize=0):
self.q = multiprocessing.Queue(maxsize)
def __getattr__(self, attr):
if hasattr(self.q, attr):
return getattr(self.q, attr)
def __iter__(self):
return self
def next(self):
item = self.q.get()
if item == 'Done':
raise StopIteration
return item
def thisworker(item):
if item == 1:
q.put(3)
if item == 2:
q.put('Done')
print 'got this item: %s' % item
return item
q=I()
q.put(1)
q.put(2)
q.put(5)
the_pool = multiprocessing.Pool(2) # 2 workers
print list(the_pool.imap(thisworker, q))
Output:
got this item: 1
got this item: 5
got this item: 3
got this item: 2
[1, 2, 5, 3]
I got rid of the code that worried about the length, and used delegation instead of inheritance, for better Python 3.x compatibility.
Note that my original suggestion, to use iter(q.get, <sentinel>), still works here, too, as long as you use imap instead of map.

Related

Return result of process after an exception is triggered

I have a multiprocessing setup that handles a long running task by appending all calculated values to lst. It looks roughly like this:
from multiprocessing import Pool
from time import sleep
def fun(_):
lst = [] # list that will be returned
for i in range(200):
lst.append(i)
if not i % 10:
sleep(0.1) # 'long task', cause a KeyboardInterrupt in this time
return lst
if __name__ == '__main__':
master = []
processes = 2
for result in Pool(processes).imap_unordered(fun, range(processes)):
master.append(result)
print(master)
I want to be able to cause a KeyboardInterrupt and have the processes return the list they worked on, even if they are not done yet, as each iteration just adds a new sublist.
(My actual data looks roughly like lst = ([], [[], ...], [[], ...]), every empty list contains ints only, the actual function would return lst1, lst2, lst3)
I have tried to envelop the whole main part in try: except: like so:
try:
for result in Pool(processes).imap_unordered(fun, range(processes)):
master.append(result)
except KeyboardInterrupt:
# somehow retrieve the values here
pass
I have however not come to any possible solution this way.
How can I tell the processes it's time to exit early and return me their current result?
Edit to show the actual structure:
main.py:
from other import Other
class Something:
def __init__(self):
pass # stuff here
def spawner(self):
for result in Pool(processes=self.processes).imap_unordered(self.loop, range(self.processes)):
pass # do stuff with the data
def loop(self, _):
# setup stuff
Other(setup_stuff).start()
other.py
class Other:
def __init__(self):
pass # more stuff
def start(self):
lst1, lst2, lst3 = [], [], []
for _ in range(self.episodes):
pass # do the actual computation
return lst1, lst2, lst3
Maybe you can use multiprocessing.Queue instead of a list to return variables. Set-up one queue at the beginning and all processes will write to the queue.
At the end, read all values from the queue.
from time import sleep
from multiprocessing import Pool, Queue
q = None
def set_global_data(queue):
global q
q = queue
def fun(_):
for i in range(200):
q.put_nowait(i)
if not i % 10:
sleep(0.1) # 'long task', cause a KeyboardInterrupt in this time
# nothing is returned
if __name__ == "__main__":
master = Queue()
processes = 2
try:
with Pool(processes, set_global_data, (master,)) as p:
for result in p.imap_unordered(fun, range(processes)):
pass
except KeyboardInterrupt:
pass
while not master.empty():
v = master.get_nowait()
print(v)
EDIT: With multiple files:
main.py
from other import Other
from multiprocessing import Pool, Queue
class Something:
def __init__(self):
pass # stuff here
def spawner(self):
master = Queue()
try:
with Pool(2, Something.set_global_data, (master,)) as p:
for _ in p.imap_unordered(self.loop, range(2)):
pass
except KeyboardInterrupt:
pass
while not master.empty():
v = master.get_nowait()
print(v)
def loop(self, _):
# setup stuff
Other().start()
#staticmethod
def set_global_data(queue):
Other.q = queue
s = Something()
s.spawner()
other.py
from time import sleep
class Other:
q = None
def __init__(self):
pass # more stuff
def start(self):
for i in range(200):
Other.q.put_nowait(i)
if not i % 10:
sleep(0.1)

How can you feed an iterable to multiple consumers in constant space?

How can you feed an iterable to multiple consumers in constant space?
TLDR
Write an implementation which passes the following test in CONSTANT SPACE, while
treating min, max and sum as black boxes.
def testit(implementation, N):
assert implementation(range(N), min, max, sum) == (0, N-1, N*(N-1)//2)
Discussion
We love iterators because they let us process streams of data lazily,
allowing the treatment of huge amounts of data in CONSTANT SPACE.
def source_summary(source, summary):
return summary(source)
N = 10 ** 8
print(source_summary(range(N), min))
print(source_summary(range(N), max))
print(source_summary(range(N), sum))
Each line took a few seconds to execute, but used very little memory. However,
It did require 3 separate traversals of the source. So this will not work if
your source is a network connection, data acquisition hardware, etc. unless you cache all the data somewhere, losing the CONSTANT SPACE requirement.
Here's a version which demonstrates this problem
def source_summaries(source, *summaries):
from itertools import tee
return tuple(map(source_summary, tee(source, len(summaries)),
summaries))
testit(source_summaries, N)
print('OK')
The test passes, but tee had to keep a copy of all the data, so the space usage goes up from O(1) to O(N).
How can you obtain the results in a single traversal with constant memory?
It is, of course, possible to pass the test given at the top, with O(1) space usage, by cheating:
using knowledge of the specific iterator-consumers that the test uses. But
that is not the point: source_summaries should work with any iterator
consumables such as set, collections.Counter, ''.join, including any
and all that may be written in the future. The implementation must treat them
as black boxes.
To be clear: the only knowledge available about the consumers is that each one consumes one iterable and returns one result. Using any other knowledge about the consumer is cheating.
Ideas
[EDIT: I have posted an implementation of this idea as an answer]
I can imagine a solution (which I really don't like) that uses
preemptive threading
a custom iterator linking the consumer to the source
Let's call the custom iterator link.
For each consumer, run
result = consumer(<link instance for this thread>)
<link instance for this thread>.set_result(result)
on a separate thread.
On the main thread, something along the lines of
for item in source:
for l in links:
l.push(item)
for l in links:
l.stop()
for thread in threads:
thread.join()
return tuple(link.get_result, links)
link.__next__ blocks until the link instance receives
.push(item) in which case it returns the item
.stop() in which case it raises StopIteration
The data races look like a nightmare. You'd need a queue for the pushes, and probably a sentinel object would need to be placed in the queue by link.stop() ... and a bunch of other things I'm overlooking.
I would prefer to use cooperative threading, but consumer(link) seems to be
unavoidably un-cooperative.
Do you have any less messy suggestions?
Here is an alternative implementation of your idea. It uses cooperative multi-threading. As you suggested, the key point is to use multi-threading and having the iterators __next__ method block until all threads have consumed the current iterate.
In addition, the iterator contains an (optional) buffer of constant size. With this buffer we can read the source in chunks and avoid a lot of the locking/synchronization.
My implementation also handles the case in which some consumers stop iterating before reaching the end of the iterator.
import threading
class BufferedMultiIter:
def __init__(self, source, n, bufsize = 1):
'''`source` is an iterator or iterable,
`n` is the number of threads that will interact with this iterator,
`bufsize` is the size of the internal buffer. The iterator will read
and buffer elements from `source` in chunks of `bufsize`. The bigger
the buffer is, the better the performance but also the bigger the
(constant) space requirement.
'''
self._source = iter(source)
self._n = n
# Condition variable for synchronization
self._cond = threading.Condition()
# Buffered values
bufsize = max(bufsize, 1)
self._buffer = [None] * bufsize
self._buffered = 0
self._next = threading.local()
# State variables to implement the "wait for buffer to get refilled"
# protocol
self._serial = 0
self._waiting = 0
# True if we reached the end of the source
self._stop = False
# Was the thread killed (for error handling)?
self._killed = False
def _fill_buffer(self):
'''Refill the internal buffer.'''
self._buffered = 0
while self._buffered < len(self._buffer):
try:
self._buffer[self._buffered] = next(self._source)
self._buffered += 1
except StopIteration:
self._stop = True
break
# Explicitly clear the unused part of the buffer to release
# references as early as possible
for i in range(self._buffered, len(self._buffer)):
self._buffer[i] = None
self._waiting = 0
self._serial += 1
def register_thread(self):
'''Register a thread.
Each thread that wants to access this iterator must first register
with the iterator. It is an error to register the same thread more
than once. It is an error to access this iterator with a thread that
was not registered (with the exception of calling `kill`). It is an
error to register more threads than the number that was passed to the
constructor.
'''
self._next.i = 0
def unregister_thread(self):
'''Unregister a thread from this iterator.
This should be called when a thread is done using the iterator.
It catches the case in which a consumer does not consume all the
elements from the iterator but exits early.
'''
assert hasattr(self._next, 'i')
delattr(self._next, 'i')
with self._cond:
assert self._n > 0
self._n -= 1
if self._waiting == self._n:
self._fill_buffer()
self._cond.notify_all()
def kill(self):
'''Forcibly kill this iterator.
This will wake up all threads currently blocked in `__next__` and
will have them raise a `StopIteration`.
This function should be called in case of error to terminate all
threads as fast as possible.
'''
self._cond.acquire()
self._killed = True
self._stop = True
self._cond.notify_all()
self._cond.release()
def __iter__(self): return self
def __next__(self):
if self._next.i == self._buffered:
# We read everything from the buffer.
# Wait until all other threads have also consumed the buffer
# completely and then refill it.
with self._cond:
old = self._serial
self._waiting += 1
if self._waiting == self._n:
self._fill_buffer()
self._cond.notify_all()
else:
# Wait until the serial number changes. A change in
# serial number indicates that another thread has filled
# the buffer
while self._serial == old and not self._killed:
self._cond.wait()
# Start at beginning of newly filled buffer
self._next.i = 0
if self._killed:
raise StopIteration
k = self._next.i
if k == self._buffered and self._stop:
raise StopIteration
value = self._buffer[k]
self._next.i = k + 1
return value
class NotAll:
'''A consumer that does not consume all the elements from the source.'''
def __init__(self, limit):
self._limit = limit
self._consumed = 0
def __call__(self, it):
last = None
for k in it:
last = k
self._consumed += 1
if self._consumed >= self._limit:
break
return last
def multi_iter(iterable, *consumers, **kwargs):
'''Iterate using multiple consumers.
Each value in `iterable` is presented to each of the `consumers`.
The function returns a tuple with the results of all `consumers`.
There is an optional `bufsize` argument. This controls the internal
buffer size. The bigger the buffer, the better the performance, but also
the bigger the (constant) space requirement of the operation.
NOTE: This will spawn a new thread for each consumer! The iteration is
multi-threaded and happens in parallel for each element.
'''
n = len(consumers)
it = BufferedMultiIter(iterable, n, kwargs.get('bufsize', 1))
threads = list() # List with **running** threads
result = [None] * n
def thread_func(i, c):
it.register_thread()
result[i] = c(it)
it.unregister_thread()
try:
for c in consumers:
t = threading.Thread(target = thread_func, args = (len(threads), c))
t.start()
threads.append(t)
except:
# Here we should forcibly kill all the threads but there is not
# t.kill() function or similar. So the best we can do is stop the
# iterator
it.kill()
finally:
while len(threads) > 0:
t = threads.pop(-1)
t.join()
return tuple(result)
from time import time
N = 10 ** 7
notall1 = NotAll(1)
notall1000 = NotAll(1000)
start1 = time()
res1 = (min(range(N)), max(range(N)), sum(range(N)), NotAll(1)(range(N)),
NotAll(1000)(range(N)))
stop1 = time()
print('5 iterators: %s %.2f' % (str(res1), stop1 - start1))
for p in range(5):
start2 = time()
res2 = multi_iter(range(N), min, max, sum, NotAll(1), NotAll(1000),
bufsize = 2**p)
stop2 = time()
print('multi_iter%d: %s %.2f' % (p, str(res2), stop2 - start2))
The timings are again horrible but you can see how using a constant size buffer improves things significantly:
5 iterators: (0, 9999999, 49999995000000, 0, 999) 0.71
multi_iter0: (0, 9999999, 49999995000000, 0, 999) 342.36
multi_iter1: (0, 9999999, 49999995000000, 0, 999) 264.71
multi_iter2: (0, 9999999, 49999995000000, 0, 999) 151.06
multi_iter3: (0, 9999999, 49999995000000, 0, 999) 95.79
multi_iter4: (0, 9999999, 49999995000000, 0, 999) 72.79
Maybe this can serve as a source of ideas for a good implementation.
Here is an implementation of the preemptive threading solution outlined in the original question.
[EDIT: There is a serious problem with this implementation. [EDIT, now fixed, using a solution inspired by Daniel Junglas.]
Consumers which do not iterate through the whole iterable, will cause a space leak in the queue inside Link. For example:
def exceeds_10(iterable):
for item in iterable:
if item > 10:
return True
return False
if you use this as one of the consumers and use the source range(10**6), it will stop removing items from the queue inside Link after the first 11 items, leaving approximately 10**6 items to be accumulated in the queue!
]
class Link:
def __init__(self, queue):
self.queue = queue
def __iter__(self):
return self
def __next__(self):
item = self.queue.get()
if item is FINISHED:
raise StopIteration
return item
def put(self, item):
self.queue.put(item)
def stop(self):
self.queue.put(FINISHED)
def consumer_not_listening_any_more(self):
self.__class__ = ClosedLink
class ClosedLink:
def put(self, _): pass
def stop(self) : pass
class FINISHED: pass
def make_thread(link, consumer, future):
from threading import Thread
return Thread(target = lambda: on_thread(link, consumer, future))
def on_thread(link, consumer, future):
future.set_result(consumer(link))
link.consumer_not_listening_any_more()
def source_summaries_PREEMPTIVE_THREAD(source, *consumers):
from queue import SimpleQueue as Queue
from asyncio import Future
links = tuple(Link(Queue()) for _ in consumers)
futures = tuple( Future() for _ in consumers)
threads = tuple(map(make_thread, links, consumers, futures))
for thread in threads:
thread.start()
for item in source:
for link in links:
link.put(item)
for link in links:
link.stop()
for t in threads:
t.join()
return tuple(f.result() for f in futures)
It works, but (unsirprisingly) with a horrible degradation in performance:
def time(thunk):
from time import time
start = time()
thunk()
stop = time()
return stop - start
N = 10 ** 7
t = time(lambda: testit(source_summaries, N))
print(f'old: {N} in {t:5.1f} s')
t = time(lambda: testit(source_summaries_PREEMPTIVE_THREAD, N))
print(f'new: {N} in {t:5.1f} s')
giving
old: 10000000 in 1.2 s
new: 10000000 in 30.1 s
So, even though this is a theoretical solution, it is not a practical one[*].
Consequently, I think that this approach is a dead end, unless there's a way of persuading consumer to yield cooperatively (as opposed to forcing it to yield preemptively) in
def on_thread(link, consumer, future):
future.set_result(consumer(link))
... but that seems fundamentally impossible. Would love to be proven wrong.
[*] This is actually a bit harsh: the test does absolutely nothing with trivial data; if this were part of a larger computation which performed heavy calculations on the elements, then this approach could be genuinely useful.

Threading with Decorator in Python [duplicate]

The function foo below returns a string 'foo'. How can I get the value 'foo' which is returned from the thread's target?
from threading import Thread
def foo(bar):
print('hello {}'.format(bar))
return 'foo'
thread = Thread(target=foo, args=('world!',))
thread.start()
return_value = thread.join()
The "one obvious way to do it", shown above, doesn't work: thread.join() returned None.
One way I've seen is to pass a mutable object, such as a list or a dictionary, to the thread's constructor, along with a an index or other identifier of some sort. The thread can then store its results in its dedicated slot in that object. For example:
def foo(bar, result, index):
print 'hello {0}'.format(bar)
result[index] = "foo"
from threading import Thread
threads = [None] * 10
results = [None] * 10
for i in range(len(threads)):
threads[i] = Thread(target=foo, args=('world!', results, i))
threads[i].start()
# do some other stuff
for i in range(len(threads)):
threads[i].join()
print " ".join(results) # what sound does a metasyntactic locomotive make?
If you really want join() to return the return value of the called function, you can do this with a Thread subclass like the following:
from threading import Thread
def foo(bar):
print 'hello {0}'.format(bar)
return "foo"
class ThreadWithReturnValue(Thread):
def __init__(self, group=None, target=None, name=None,
args=(), kwargs={}, Verbose=None):
Thread.__init__(self, group, target, name, args, kwargs, Verbose)
self._return = None
def run(self):
if self._Thread__target is not None:
self._return = self._Thread__target(*self._Thread__args,
**self._Thread__kwargs)
def join(self):
Thread.join(self)
return self._return
twrv = ThreadWithReturnValue(target=foo, args=('world!',))
twrv.start()
print twrv.join() # prints foo
That gets a little hairy because of some name mangling, and it accesses "private" data structures that are specific to Thread implementation... but it works.
For Python 3:
class ThreadWithReturnValue(Thread):
def __init__(self, group=None, target=None, name=None,
args=(), kwargs={}, Verbose=None):
Thread.__init__(self, group, target, name, args, kwargs)
self._return = None
def run(self):
if self._target is not None:
self._return = self._target(*self._args,
**self._kwargs)
def join(self, *args):
Thread.join(self, *args)
return self._return
FWIW, the multiprocessing module has a nice interface for this using the Pool class. And if you want to stick with threads rather than processes, you can just use the multiprocessing.pool.ThreadPool class as a drop-in replacement.
def foo(bar, baz):
print 'hello {0}'.format(bar)
return 'foo' + baz
from multiprocessing.pool import ThreadPool
pool = ThreadPool(processes=1)
async_result = pool.apply_async(foo, ('world', 'foo')) # tuple of args for foo
# do some other stuff in the main process
return_val = async_result.get() # get the return value from your function.
In Python 3.2+, stdlib concurrent.futures module provides a higher level API to threading, including passing return values or exceptions from a worker thread back to the main thread:
import concurrent.futures
def foo(bar):
print('hello {}'.format(bar))
return 'foo'
with concurrent.futures.ThreadPoolExecutor() as executor:
future = executor.submit(foo, 'world!')
return_value = future.result()
print(return_value)
Jake's answer is good, but if you don't want to use a threadpool (you don't know how many threads you'll need, but create them as needed) then a good way to transmit information between threads is the built-in Queue.Queue class, as it offers thread safety.
I created the following decorator to make it act in a similar fashion to the threadpool:
def threaded(f, daemon=False):
import Queue
def wrapped_f(q, *args, **kwargs):
'''this function calls the decorated function and puts the
result in a queue'''
ret = f(*args, **kwargs)
q.put(ret)
def wrap(*args, **kwargs):
'''this is the function returned from the decorator. It fires off
wrapped_f in a new thread and returns the thread object with
the result queue attached'''
q = Queue.Queue()
t = threading.Thread(target=wrapped_f, args=(q,)+args, kwargs=kwargs)
t.daemon = daemon
t.start()
t.result_queue = q
return t
return wrap
Then you just use it as:
#threaded
def long_task(x):
import time
x = x + 5
time.sleep(5)
return x
# does not block, returns Thread object
y = long_task(10)
print y
# this blocks, waiting for the result
result = y.result_queue.get()
print result
The decorated function creates a new thread each time it's called and returns a Thread object that contains the queue that will receive the result.
UPDATE
It's been quite a while since I posted this answer, but it still gets views so I thought I would update it to reflect the way I do this in newer versions of Python:
Python 3.2 added in the concurrent.futures module which provides a high-level interface for parallel tasks. It provides ThreadPoolExecutor and ProcessPoolExecutor, so you can use a thread or process pool with the same api.
One benefit of this api is that submitting a task to an Executor returns a Future object, which will complete with the return value of the callable you submit.
This makes attaching a queue object unnecessary, which simplifies the decorator quite a bit:
_DEFAULT_POOL = ThreadPoolExecutor()
def threadpool(f, executor=None):
#wraps(f)
def wrap(*args, **kwargs):
return (executor or _DEFAULT_POOL).submit(f, *args, **kwargs)
return wrap
This will use a default module threadpool executor if one is not passed in.
The usage is very similar to before:
#threadpool
def long_task(x):
import time
x = x + 5
time.sleep(5)
return x
# does not block, returns Future object
y = long_task(10)
print y
# this blocks, waiting for the result
result = y.result()
print result
If you're using Python 3.4+, one really nice feature of using this method (and Future objects in general) is that the returned future can be wrapped to turn it into an asyncio.Future with asyncio.wrap_future. This makes it work easily with coroutines:
result = await asyncio.wrap_future(long_task(10))
If you don't need access to the underlying concurrent.Future object, you can include the wrap in the decorator:
_DEFAULT_POOL = ThreadPoolExecutor()
def threadpool(f, executor=None):
#wraps(f)
def wrap(*args, **kwargs):
return asyncio.wrap_future((executor or _DEFAULT_POOL).submit(f, *args, **kwargs))
return wrap
Then, whenever you need to push cpu intensive or blocking code off the event loop thread, you can put it in a decorated function:
#threadpool
def some_long_calculation():
...
# this will suspend while the function is executed on a threadpool
result = await some_long_calculation()
Another solution that doesn't require changing your existing code:
import Queue # Python 2.x
#from queue import Queue # Python 3.x
from threading import Thread
def foo(bar):
print 'hello {0}'.format(bar) # Python 2.x
#print('hello {0}'.format(bar)) # Python 3.x
return 'foo'
que = Queue.Queue() # Python 2.x
#que = Queue() # Python 3.x
t = Thread(target=lambda q, arg1: q.put(foo(arg1)), args=(que, 'world!'))
t.start()
t.join()
result = que.get()
print result # Python 2.x
#print(result) # Python 3.x
It can be also easily adjusted to a multi-threaded environment:
import Queue # Python 2.x
#from queue import Queue # Python 3.x
from threading import Thread
def foo(bar):
print 'hello {0}'.format(bar) # Python 2.x
#print('hello {0}'.format(bar)) # Python 3.x
return 'foo'
que = Queue.Queue() # Python 2.x
#que = Queue() # Python 3.x
threads_list = list()
t = Thread(target=lambda q, arg1: q.put(foo(arg1)), args=(que, 'world!'))
t.start()
threads_list.append(t)
# Add more threads here
...
threads_list.append(t2)
...
threads_list.append(t3)
...
# Join all the threads
for t in threads_list:
t.join()
# Check thread's return value
while not que.empty():
result = que.get()
print result # Python 2.x
#print(result) # Python 3.x
UPDATE:
I think there's a significantly simpler and more concise way to save the result of the thread, and in a way that keeps the interface virtually identical to the threading.Thread class (please let me know if there are edge cases - I haven't tested as much as my original post below):
import threading
class ConciseResult(threading.Thread):
def run(self):
self.result = self._target(*self._args, **self._kwargs)
To be robust and avoid potential errors:
import threading
class ConciseRobustResult(threading.Thread):
def run(self):
try:
if self._target is not None:
self.result = self._target(*self._args, **self._kwargs)
finally:
# Avoid a refcycle if the thread is running a function with
# an argument that has a member that points to the thread.
del self._target, self._args, self._kwargs
Short explanation: we override only the run method of threading.Thread, and modify nothing else. This allows us to use everything else the threading.Thread class does for us, without needing to worry about missing potential edge cases such as _private attribute assignments or custom attribute modifications in the way that my original post does.
We can verify that we only modify the run method by looking at the output of help(ConciseResult) and help(ConciseRobustResult). The only method/attribute/descriptor included under Methods defined here: is run, and everything else comes from the inherited threading.Thread base class (see the Methods inherited from threading.Thread: section).
To test either of these implementations using the example code below, substitute ConciseResult or ConciseRobustResult for ThreadWithResult in the main function below.
Original post using a closure function in the init method:
Most answers I've found are long and require being familiar with other modules or advanced python features, and will be rather confusing to someone unless they're already familiar with everything the answer talks about.
Working code for a simplified approach:
import threading
class ThreadWithResult(threading.Thread):
def __init__(self, group=None, target=None, name=None, args=(), kwargs={}, *, daemon=None):
def function():
self.result = target(*args, **kwargs)
super().__init__(group=group, target=function, name=name, daemon=daemon)
Example code:
import time, random
def function_to_thread(n):
count = 0
while count < 3:
print(f'still running thread {n}')
count +=1
time.sleep(3)
result = random.random()
print(f'Return value of thread {n} should be: {result}')
return result
def main():
thread1 = ThreadWithResult(target=function_to_thread, args=(1,))
thread2 = ThreadWithResult(target=function_to_thread, args=(2,))
thread1.start()
thread2.start()
thread1.join()
thread2.join()
print(thread1.result)
print(thread2.result)
main()
Explanation:
I wanted to simplify things significantly, so I created a ThreadWithResult class and had it inherit from threading.Thread. The nested function function in __init__ calls the threaded function we want to save the value of, and saves the result of that nested function as the instance attribute self.result after the thread finishes executing.
Creating an instance of this is identical to creating an instance of threading.Thread. Pass in the function you want to run on a new thread to the target argument and any arguments that your function might need to the args argument and any keyword arguments to the kwargs argument.
e.g.
my_thread = ThreadWithResult(target=my_function, args=(arg1, arg2, arg3))
I think this is significantly easier to understand than the vast majority of answers, and this approach requires no extra imports! I included the time and random module to simulate the behavior of a thread, but they're not required to achieve the functionality asked in the original question.
I know I'm answering this looong after the question was asked, but I hope this can help more people in the future!
EDIT: I created the save-thread-result PyPI package to allow you to access the same code above and reuse it across projects (GitHub code is here). The PyPI package fully extends the threading.Thread class, so you can set any attributes you would set on threading.thread on the ThreadWithResult class as well!
The original answer above goes over the main idea behind this subclass, but for more information, see the more detailed explanation (from the module docstring) here.
Quick usage example:
pip3 install -U save-thread-result # MacOS/Linux
pip install -U save-thread-result # Windows
python3 # MacOS/Linux
python # Windows
from save_thread_result import ThreadWithResult
# As of Release 0.0.3, you can also specify values for
#`group`, `name`, and `daemon` if you want to set those
# values manually.
thread = ThreadWithResult(
target = my_function,
args = (my_function_arg1, my_function_arg2, ...)
kwargs = {my_function_kwarg1: kwarg1_value, my_function_kwarg2: kwarg2_value, ...}
)
thread.start()
thread.join()
if getattr(thread, 'result', None):
print(thread.result)
else:
# thread.result attribute not set - something caused
# the thread to terminate BEFORE the thread finished
# executing the function passed in through the
# `target` argument
print('ERROR! Something went wrong while executing this thread, and the function you passed in did NOT complete!!')
# seeing help about the class and information about the threading.Thread super class methods and attributes available:
help(ThreadWithResult)
Parris / kindall's answer join/return answer ported to Python 3:
from threading import Thread
def foo(bar):
print('hello {0}'.format(bar))
return "foo"
class ThreadWithReturnValue(Thread):
def __init__(self, group=None, target=None, name=None, args=(), kwargs=None, *, daemon=None):
Thread.__init__(self, group, target, name, args, kwargs, daemon=daemon)
self._return = None
def run(self):
if self._target is not None:
self._return = self._target(*self._args, **self._kwargs)
def join(self):
Thread.join(self)
return self._return
twrv = ThreadWithReturnValue(target=foo, args=('world!',))
twrv.start()
print(twrv.join()) # prints foo
Note, the Thread class is implemented differently in Python 3.
I stole kindall's answer and cleaned it up just a little bit.
The key part is adding *args and **kwargs to join() in order to handle the timeout
class threadWithReturn(Thread):
def __init__(self, *args, **kwargs):
super(threadWithReturn, self).__init__(*args, **kwargs)
self._return = None
def run(self):
if self._Thread__target is not None:
self._return = self._Thread__target(*self._Thread__args, **self._Thread__kwargs)
def join(self, *args, **kwargs):
super(threadWithReturn, self).join(*args, **kwargs)
return self._return
UPDATED ANSWER BELOW
This is my most popularly upvoted answer, so I decided to update with code that will run on both py2 and py3.
Additionally, I see many answers to this question that show a lack of comprehension regarding Thread.join(). Some completely fail to handle the timeout arg. But there is also a corner-case that you should be aware of regarding instances when you have (1) a target function that can return None and (2) you also pass the timeout arg to join(). Please see "TEST 4" to understand this corner case.
ThreadWithReturn class that works with py2 and py3:
import sys
from threading import Thread
from builtins import super # https://stackoverflow.com/a/30159479
_thread_target_key, _thread_args_key, _thread_kwargs_key = (
('_target', '_args', '_kwargs')
if sys.version_info >= (3, 0) else
('_Thread__target', '_Thread__args', '_Thread__kwargs')
)
class ThreadWithReturn(Thread):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self._return = None
def run(self):
target = getattr(self, _thread_target_key)
if target is not None:
self._return = target(
*getattr(self, _thread_args_key),
**getattr(self, _thread_kwargs_key)
)
def join(self, *args, **kwargs):
super().join(*args, **kwargs)
return self._return
Some sample tests are shown below:
import time, random
# TEST TARGET FUNCTION
def giveMe(arg, seconds=None):
if not seconds is None:
time.sleep(seconds)
return arg
# TEST 1
my_thread = ThreadWithReturn(target=giveMe, args=('stringy',))
my_thread.start()
returned = my_thread.join()
# (returned == 'stringy')
# TEST 2
my_thread = ThreadWithReturn(target=giveMe, args=(None,))
my_thread.start()
returned = my_thread.join()
# (returned is None)
# TEST 3
my_thread = ThreadWithReturn(target=giveMe, args=('stringy',), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=2)
# (returned is None) # because join() timed out before giveMe() finished
# TEST 4
my_thread = ThreadWithReturn(target=giveMe, args=(None,), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=random.randint(1, 10))
Can you identify the corner-case that we may possibly encounter with TEST 4?
The problem is that we expect giveMe() to return None (see TEST 2), but we also expect join() to return None if it times out.
returned is None means either:
(1) that's what giveMe() returned, or
(2) join() timed out
This example is trivial since we know that giveMe() will always return None. But in real-world instance (where the target may legitimately return None or something else) we'd want to explicitly check for what happened.
Below is how to address this corner-case:
# TEST 4
my_thread = ThreadWithReturn(target=giveMe, args=(None,), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=random.randint(1, 10))
if my_thread.isAlive():
# returned is None because join() timed out
# this also means that giveMe() is still running in the background
pass
# handle this based on your app's logic
else:
# join() is finished, and so is giveMe()
# BUT we could also be in a race condition, so we need to update returned, just in case
returned = my_thread.join()
Using Queue :
import threading, queue
def calc_square(num, out_queue1):
l = []
for x in num:
l.append(x*x)
out_queue1.put(l)
arr = [1,2,3,4,5,6,7,8,9,10]
out_queue1=queue.Queue()
t1=threading.Thread(target=calc_square, args=(arr,out_queue1))
t1.start()
t1.join()
print (out_queue1.get())
My solution to the problem is to wrap the function and thread in a class. Does not require using pools,queues, or c type variable passing. It is also non blocking. You check status instead. See example of how to use it at end of code.
import threading
class ThreadWorker():
'''
The basic idea is given a function create an object.
The object can then run the function in a thread.
It provides a wrapper to start it,check its status,and get data out the function.
'''
def __init__(self,func):
self.thread = None
self.data = None
self.func = self.save_data(func)
def save_data(self,func):
'''modify function to save its returned data'''
def new_func(*args, **kwargs):
self.data=func(*args, **kwargs)
return new_func
def start(self,params):
self.data = None
if self.thread is not None:
if self.thread.isAlive():
return 'running' #could raise exception here
#unless thread exists and is alive start or restart it
self.thread = threading.Thread(target=self.func,args=params)
self.thread.start()
return 'started'
def status(self):
if self.thread is None:
return 'not_started'
else:
if self.thread.isAlive():
return 'running'
else:
return 'finished'
def get_results(self):
if self.thread is None:
return 'not_started' #could return exception
else:
if self.thread.isAlive():
return 'running'
else:
return self.data
def add(x,y):
return x +y
add_worker = ThreadWorker(add)
print add_worker.start((1,2,))
print add_worker.status()
print add_worker.get_results()
Taking into consideration #iman comment on #JakeBiesinger answer I have recomposed it to have various number of threads:
from multiprocessing.pool import ThreadPool
def foo(bar, baz):
print 'hello {0}'.format(bar)
return 'foo' + baz
numOfThreads = 3
results = []
pool = ThreadPool(numOfThreads)
for i in range(0, numOfThreads):
results.append(pool.apply_async(foo, ('world', 'foo'))) # tuple of args for foo)
# do some other stuff in the main process
# ...
# ...
results = [r.get() for r in results]
print results
pool.close()
pool.join()
I'm using this wrapper, which comfortably turns any function for running in a Thread - taking care of its return value or exception. It doesn't add Queue overhead.
def threading_func(f):
"""Decorator for running a function in a thread and handling its return
value or exception"""
def start(*args, **kw):
def run():
try:
th.ret = f(*args, **kw)
except:
th.exc = sys.exc_info()
def get(timeout=None):
th.join(timeout)
if th.exc:
raise th.exc[0], th.exc[1], th.exc[2] # py2
##raise th.exc[1] #py3
return th.ret
th = threading.Thread(None, run)
th.exc = None
th.get = get
th.start()
return th
return start
Usage Examples
def f(x):
return 2.5 * x
th = threading_func(f)(4)
print("still running?:", th.is_alive())
print("result:", th.get(timeout=1.0))
#threading_func
def th_mul(a, b):
return a * b
th = th_mul("text", 2.5)
try:
print(th.get())
except TypeError:
print("exception thrown ok.")
Notes on threading module
Comfortable return value & exception handling of a threaded function is a frequent "Pythonic" need and should indeed already be offered by the threading module - possibly directly in the standard Thread class. ThreadPool has way too much overhead for simple tasks - 3 managing threads, lots of bureaucracy. Unfortunately Thread's layout was copied from Java originally - which you see e.g. from the still useless 1st (!) constructor parameter group.
Based of what kindall mentioned, here's the more generic solution that works with Python3.
import threading
class ThreadWithReturnValue(threading.Thread):
def __init__(self, *init_args, **init_kwargs):
threading.Thread.__init__(self, *init_args, **init_kwargs)
self._return = None
def run(self):
self._return = self._target(*self._args, **self._kwargs)
def join(self):
threading.Thread.join(self)
return self._return
Usage
th = ThreadWithReturnValue(target=requests.get, args=('http://www.google.com',))
th.start()
response = th.join()
response.status_code # => 200
join always return None, i think you should subclass Thread to handle return codes and so.
You can define a mutable above the scope of the threaded function, and add the result to that. (I also modified the code to be python3 compatible)
returns = {}
def foo(bar):
print('hello {0}'.format(bar))
returns[bar] = 'foo'
from threading import Thread
t = Thread(target=foo, args=('world!',))
t.start()
t.join()
print(returns)
This returns {'world!': 'foo'}
If you use the function input as the key to your results dict, every unique input is guaranteed to give an entry in the results
Define your target to
1) take an argument q
2) replace any statements return foo with q.put(foo); return
so a function
def func(a):
ans = a * a
return ans
would become
def func(a, q):
ans = a * a
q.put(ans)
return
and then you would proceed as such
from Queue import Queue
from threading import Thread
ans_q = Queue()
arg_tups = [(i, ans_q) for i in xrange(10)]
threads = [Thread(target=func, args=arg_tup) for arg_tup in arg_tups]
_ = [t.start() for t in threads]
_ = [t.join() for t in threads]
results = [q.get() for _ in xrange(len(threads))]
And you can use function decorators/wrappers to make it so you can use your existing functions as target without modifying them, but follow this basic scheme.
GuySoft's idea is great, but I think the object does not necessarily have to inherit from Thread and start() could be removed from interface:
from threading import Thread
import queue
class ThreadWithReturnValue(object):
def __init__(self, target=None, args=(), **kwargs):
self._que = queue.Queue()
self._t = Thread(target=lambda q,arg1,kwargs1: q.put(target(*arg1, **kwargs1)) ,
args=(self._que, args, kwargs), )
self._t.start()
def join(self):
self._t.join()
return self._que.get()
def foo(bar):
print('hello {0}'.format(bar))
return "foo"
twrv = ThreadWithReturnValue(target=foo, args=('world!',))
print(twrv.join()) # prints foo
This is a pretty old question, but I wanted to share a simple solution that has worked for me and helped my dev process.
The methodology behind this answer is the fact that the "new" target function, inner is assigning the result of the original function (passed through the __init__ function) to the result instance attribute of the wrapper through something called closure.
This allows the wrapper class to hold onto the return value for callers to access at anytime.
NOTE: This method doesn't need to use any mangled methods or private methods of the threading.Thread class, although yield functions have not been considered (OP did not mention yield functions).
Enjoy!
from threading import Thread as _Thread
class ThreadWrapper:
def __init__(self, target, *args, **kwargs):
self.result = None
self._target = self._build_threaded_fn(target)
self.thread = _Thread(
target=self._target,
*args,
**kwargs
)
def _build_threaded_fn(self, func):
def inner(*args, **kwargs):
self.result = func(*args, **kwargs)
return inner
Additionally, you can run pytest (assuming you have it installed) with the following code to demonstrate the results:
import time
from commons import ThreadWrapper
def test():
def target():
time.sleep(1)
return 'Hello'
wrapper = ThreadWrapper(target=target)
wrapper.thread.start()
r = wrapper.result
assert r is None
time.sleep(2)
r = wrapper.result
assert r == 'Hello'
As mentioned multiprocessing pool is much slower than basic threading. Using queues as proposeded in some answers here is a very effective alternative. I have use it with dictionaries in order to be able run a lot of small threads and recuperate multiple answers by combining them with dictionaries:
#!/usr/bin/env python3
import threading
# use Queue for python2
import queue
import random
LETTERS = 'abcdefghijklmnopqrstuvwxyz'
LETTERS = [ x for x in LETTERS ]
NUMBERS = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
def randoms(k, q):
result = dict()
result['letter'] = random.choice(LETTERS)
result['number'] = random.choice(NUMBERS)
q.put({k: result})
threads = list()
q = queue.Queue()
results = dict()
for name in ('alpha', 'oscar', 'yankee',):
threads.append( threading.Thread(target=randoms, args=(name, q)) )
threads[-1].start()
_ = [ t.join() for t in threads ]
while not q.empty():
results.update(q.get())
print(results)
Here is the version that I created of #Kindall's answer.
This version makes it so that all you have to do is input your command with arguments to create the new thread.
This was made with Python 3.8:
from threading import Thread
from typing import Any
def test(plug, plug2, plug3):
print(f"hello {plug}")
print(f'I am the second plug : {plug2}')
print(plug3)
return 'I am the return Value!'
def test2(msg):
return f'I am from the second test: {msg}'
def test3():
print('hello world')
def NewThread(com, Returning: bool, *arguments) -> Any:
"""
Will create a new thread for a function/command.
:param com: Command to be Executed
:param arguments: Arguments to be sent to Command
:param Returning: True/False Will this command need to return anything
"""
class NewThreadWorker(Thread):
def __init__(self, group = None, target = None, name = None, args = (), kwargs = None, *,
daemon = None):
Thread.__init__(self, group, target, name, args, kwargs, daemon = daemon)
self._return = None
def run(self):
if self._target is not None:
self._return = self._target(*self._args, **self._kwargs)
def join(self):
Thread.join(self)
return self._return
ntw = NewThreadWorker(target = com, args = (*arguments,))
ntw.start()
if Returning:
return ntw.join()
if __name__ == "__main__":
print(NewThread(test, True, 'hi', 'test', test2('hi')))
NewThread(test3, True)
You can use pool.apply_async() of ThreadPool() to return the value from test() as shown below:
from multiprocessing.pool import ThreadPool
def test(num1, num2):
return num1 + num2
pool = ThreadPool(processes=1) # Here
result = pool.apply_async(test, (2, 3)) # Here
print(result.get()) # 5
And, you can also use submit() of concurrent.futures.ThreadPoolExecutor() to return the value from test() as shown below:
from concurrent.futures import ThreadPoolExecutor
def test(num1, num2):
return num1 + num2
with ThreadPoolExecutor(max_workers=1) as executor:
future = executor.submit(test, 2, 3) # Here
print(future.result()) # 5
And, instead of return, you can use the array result as shown below:
from threading import Thread
def test(num1, num2, r):
r[0] = num1 + num2 # Instead of "return"
result = [None] # Here
thread = Thread(target=test, args=(2, 3, result))
thread.start()
thread.join()
print(result[0]) # 5
And instead of return, you can also use the queue result as shown below:
from threading import Thread
import queue
def test(num1, num2, q):
q.put(num1 + num2) # Instead of "return"
queue = queue.Queue() # Here
thread = Thread(target=test, args=(2, 3, queue))
thread.start()
thread.join()
print(queue.get()) # '5'
The shortest and simplest way I've found to do this is to take advantage of Python classes and their dynamic properties. You can retrieve the current thread from within the context of your spawned thread using threading.current_thread(), and assign the return value to a property.
import threading
def some_target_function():
# Your code here.
threading.current_thread().return_value = "Some return value."
your_thread = threading.Thread(target=some_target_function)
your_thread.start()
your_thread.join()
return_value = your_thread.return_value
print(return_value)
One usual solution is to wrap your function foo with a decorator like
result = queue.Queue()
def task_wrapper(*args):
result.put(target(*args))
Then the whole code may looks like that
result = queue.Queue()
def task_wrapper(*args):
result.put(target(*args))
threads = [threading.Thread(target=task_wrapper, args=args) for args in args_list]
for t in threads:
t.start()
while(True):
if(len(threading.enumerate()) < max_num):
break
for t in threads:
t.join()
return result
Note
One important issue is that the return values may be unorderred.
(In fact, the return value is not necessarily saved to the queue, since you can choose arbitrary thread-safe data structure )
Kindall's answer in Python3
class ThreadWithReturnValue(Thread):
def __init__(self, group=None, target=None, name=None,
args=(), kwargs={}, *, daemon=None):
Thread.__init__(self, group, target, name, args, kwargs, daemon)
self._return = None
def run(self):
try:
if self._target:
self._return = self._target(*self._args, **self._kwargs)
finally:
del self._target, self._args, self._kwargs
def join(self,timeout=None):
Thread.join(self,timeout)
return self._return
I know this thread is old.... but I faced the same problem... If you are willing to use thread.join()
import threading
class test:
def __init__(self):
self.msg=""
def hello(self,bar):
print('hello {}'.format(bar))
self.msg="foo"
def main(self):
thread = threading.Thread(target=self.hello, args=('world!',))
thread.start()
thread.join()
print(self.msg)
g=test()
g.main()
Best way... Define a global variable, then change the variable in the threaded function. Nothing to pass in or retrieve back
from threading import Thread
# global var
radom_global_var = 5
def function():
global random_global_var
random_global_var += 1
domath = Thread(target=function)
domath.start()
domath.join()
print(random_global_var)
# result: 6

multiprocessing - Pool.imap is consuming my iterator

I have an extremely huge iterator returning massive amounts of data (file contents). Consuming the iterator hence effectively eats up all my RAM in seconds. Generally, pythons multiprocessing.Pool().imap(...) claims to iterate lazily. That means that it gets a value from the iterator, passes it on to the worker and then waits for the worker to finish. This would be exactly what I want.
However, for some reason it keeps on retrieving values from the iterator, even if the maximum number of workers are already running. This is my code:
class FileNameIterator(object): # Support class for TupleIterator
def __init__(self,path):
self.scanner = scandir.scandir(path)
def __iter__(self):
return self
def next(self):
while True:
direntry = self.scanner.next()
if os.path.isfile(direntry.path):
return direntry.name
class ContentIterator(object): # Support class for TupleIterator
def __init__(self,filenameiter,path):
self.filenameiter = filenameiter
self.path = path
def __iter__(self):
return self
def next(self):
print "<iter> reading content." # TODO: remove
with open(self.path + "\\" + self.filenameiter.next()) as f:
r = f.read()
f.close()
return r
class TupleIterator(object): # Basically izip with working __len__
def __init__(self,path):
self.fnameiter = FileNameIterator(path)
self.cntiter = ContentIterator(FileNameIterator(path),path)
self.path = path
def __iter__(self):
return self
def next(self):
return self.fnameiter.next(), self.cntiter.next()
def __len__(self):
return len([name for name in os.listdir(self.path) if os.path.isfile(os.path.join(self.path, name))])
pool = ThreadPool(12) # Has same API as Pool(), but allows memory sharing
itr = TupleIterator(_path) # Basically izip with working __len__
with open(_datafile, 'w') as datafile: # Workers write results to a file
pool.imap_unordered(worker, itr,len(itr)/12) # This does not work as expected
pool.close()
pool.join()
datafile.close()
I have the workers printing a message when they start and finish, and the iterator printing when it reads a file. This shows that the iterator continuously reads files way faster than the workers can process them.
How do I fix this? Is the imap(..) function working as it should and I'm just misunderstanding how it should be working?

Python Queue.get(block=False) with non-empty Queue. Can it raise Queue.empty?

I'm using python's Queue.Queue to synchronize several threads. First, a Queue is populated with N elements, as in
N = 10
q = Queue.Queue()
for i in range(N):
q.put(i)
Then, several threads consume the elements from the queue with block=False
q.get(block=False)
My question is: can the previous call to Queue.get() raise Queue.Empty in any of the first N calls?
Thanks!
The first N calls to get() will succeed; q.get(block=False) will only raise Queue.Empty if the queue is actually empty. All the calls to get made by your threads are synchronized, so the first N threads that get the mutex used by the Queue will successfully get an item from the Queue. If you have N+1 or more threads, any get beyond the Nth will raise Queue.Empty. This is fairly easy to see for yourself by looking at the relevant parts of the Queue code, as mentioned by Eric.
class Queue:
"""Create a queue object with a given maximum size.
If maxsize is <= 0, the queue size is infinite.
"""
def __init__(self, maxsize=0):
self.maxsize = maxsize
self._init(maxsize)
self.mutex = _threading.Lock()
self.not_empty = _threading.Condition(self.mutex)
... # Stuff we don't care about
def get(self, block=True, timeout=None):
self.not_empty.acquire() # Only on thread can hold this at a time
try:
if not block:
if not self._qsize(): # If there's nothing in the Queue
raise Empty
... # Other stuff we don't care about, since you use block=False
item = self._get()
self.not_full.notify()
return item
finally:
self.not_empty.release()
def _init(self, maxsize):
self.queue = deque()
def _qsize(self, len=len):
return len(self.queue)

Categories

Resources