We Keep Coding

how to add specific number of additional workers to an exisiting multiprocessing pool?

In below situation I've created a default pool with two workers and perform tasks. During task processing the task_queue is checked regularly so it doesn't exceeds a certain length limit and prevents up/down stream clutter. How to add dynamically more workers to reduce the task queue length?
import multiprocessing as mp
... code snippet...
def main(poolsize, start_process):
pool = mp.Pool(processes=poolsize, initializer=start_process)
done = False
task_queue = []
while True:
... snippet code : do something ...
if len(task_queue) >= 10:
... code to expand pool goes here...
if done == True:
break
.. do final something ...
if __name__ == '__main__':
# freeze_support()
poolsize = 2
main(poolsize)

To add more workers during a running pool processing job you can add below function within the while-loop:
def repopulate(pool, add_workers):
current_pool_size = len(pool._pool) # _.pool gets the current pool size.
new_pool_size = current_pool_size + add_workers
pool._processes = new_pool_size
pool._repopulate_pool()
return pool
Within the while-loop from main():
if len(task_queue) >= 10:
new_workers = 2
repopulate(poolname, new_workers)

multiprocessing.Pool with dynamic size
full example based on the answer by ZF007
import multiprocessing, time, random
def worker_function(job_id):
dt = random.randint(1, 10)
print(f"job {job_id}: sleeping for {dt} seconds")
time.sleep(dt)
return job_id * job_id
def get_job_done(job_id):
return lambda val: print(f"job {job_id}: job done: val={val}")
def grow_pool(pool, new_size, max_size=None):
new_size = min(new_size, max_size) if max_size else new_size
if new_size > pool._processes:
print(f"growing pool from {pool._processes} to {new_size}")
pool._processes = new_size
pool._repopulate_pool()
if __name__ == "__main__":
# start pool
start_workers = 1 # start N workers before demand
max_workers = 4 # run N workers on demand
pool = multiprocessing.Pool(start_workers)
# add jobs
num_jobs = 10
grow_pool(pool, num_jobs, max_workers)
for job_id in range(0, num_jobs):
job_done = get_job_done(job_id)
print(f"job {job_id}: adding job")
pool.apply_async(worker_function, args=(job_id,), callback=job_done)
# wait
pool.close()
pool.join()

Multiprocessing : use tqdm to display a progress bar

To make my code more "pythonic" and faster, I use multiprocessing and a map function to send it a) the function and b) the range of iterations.
The implanted solution (i.e., calling tqdm directly on the range tqdm.tqdm(range(0, 30))) does not work with multiprocessing (as formulated in the code below).
The progress bar is displayed from 0 to 100% (when python reads the code?) but it does not indicate the actual progress of the map function.
How can one display a progress bar that indicates at which step the 'map' function is ?
from multiprocessing import Pool
import tqdm
import time
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
p = Pool(2)
r = p.map(_foo, tqdm.tqdm(range(0, 30)))
p.close()
p.join()
Any help or suggestions are welcome...

Use imap instead of map, which returns an iterator of the processed values.
from multiprocessing import Pool
import tqdm
import time
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
with Pool(2) as p:
r = list(tqdm.tqdm(p.imap(_foo, range(30)), total=30))

Sorry for being late but if all you need is a concurrent map, I added this functionality in tqdm>=4.42.0:
from tqdm.contrib.concurrent import process_map # or thread_map
import time
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
r = process_map(_foo, range(0, 30), max_workers=2)
References: https://tqdm.github.io/docs/contrib.concurrent/ and https://github.com/tqdm/tqdm/blob/master/examples/parallel_bars.py
It supports max_workers and chunksize and you can also easily switch from process_map to thread_map.

Solution found. Be careful! Due to multiprocessing, the estimation time (iteration per loop, total time, etc.) could be unstable, but the progress bar works perfectly.
Note: Context manager for Pool is only available in Python 3.3+.
from multiprocessing import Pool
import time
from tqdm import *
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
with Pool(processes=2) as p:
max_ = 30
with tqdm(total=max_) as pbar:
for _ in p.imap_unordered(_foo, range(0, max_)):
pbar.update()

You can use p_tqdm instead.
https://github.com/swansonk14/p_tqdm
from p_tqdm import p_map
import time
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
r = p_map(_foo, list(range(0, 30)))

based on the answer of Xavi Martínez I wrote the function imap_unordered_bar. It can be used in the same way as imap_unordered with the only difference that a processing bar is shown.
from multiprocessing import Pool
import time
from tqdm import *
def imap_unordered_bar(func, args, n_processes = 2):
p = Pool(n_processes)
res_list = []
with tqdm(total = len(args)) as pbar:
for i, res in tqdm(enumerate(p.imap_unordered(func, args))):
pbar.update()
res_list.append(res)
pbar.close()
p.close()
p.join()
return res_list
def _foo(my_number):
square = my_number * my_number
time.sleep(1)
return square
if __name__ == '__main__':
result = imap_unordered_bar(_foo, range(5))

import multiprocessing as mp
import tqdm
iterable = ...
num_cpu = mp.cpu_count() - 2 # dont use all cpus.
def func():
# your logic
...
if __name__ == '__main__':
with mp.Pool(num_cpu) as p:
list(tqdm.tqdm(p.imap(func, iterable), total=len(iterable)))

For progress bar with apply_async, we can use following code as suggested in:
https://github.com/tqdm/tqdm/issues/484
import time
import random
from multiprocessing import Pool
from tqdm import tqdm
def myfunc(a):
time.sleep(random.random())
return a ** 2
pool = Pool(2)
pbar = tqdm(total=100)
def update(*a):
pbar.update()
for i in range(pbar.total):
pool.apply_async(myfunc, args=(i,), callback=update)
pool.close()
pool.join()

Here is my take for when you need to get results back from your parallel executing functions. This function does a few things (there is another post of mine that explains it further) but the key point is that there is a tasks pending queue and a tasks completed queue. As workers are done with each task in the pending queue they add the results in the tasks completed queue. You can wrap the check to the tasks completed queue with the tqdm progress bar. I am not putting the implementation of the do_work() function here, it is not relevant, as the message here is to monitor the tasks completed queue and update the progress bar every time a result is in.
def par_proc(job_list, num_cpus=None, verbose=False):
# Get the number of cores
if not num_cpus:
num_cpus = psutil.cpu_count(logical=False)
print('* Parallel processing')
print('* Running on {} cores'.format(num_cpus))
# Set-up the queues for sending and receiving data to/from the workers
tasks_pending = mp.Queue()
tasks_completed = mp.Queue()
# Gather processes and results here
processes = []
results = []
# Count tasks
num_tasks = 0
# Add the tasks to the queue
for job in job_list:
for task in job['tasks']:
expanded_job = {}
num_tasks = num_tasks + 1
expanded_job.update({'func': pickle.dumps(job['func'])})
expanded_job.update({'task': task})
tasks_pending.put(expanded_job)
# Set the number of workers here
num_workers = min(num_cpus, num_tasks)
# We need as many sentinels as there are worker processes so that ALL processes exit when there is no more
# work left to be done.
for c in range(num_workers):
tasks_pending.put(SENTINEL)
print('* Number of tasks: {}'.format(num_tasks))
# Set-up and start the workers
for c in range(num_workers):
p = mp.Process(target=do_work, args=(tasks_pending, tasks_completed, verbose))
p.name = 'worker' + str(c)
processes.append(p)
p.start()
# Gather the results
completed_tasks_counter = 0
with tqdm(total=num_tasks) as bar:
while completed_tasks_counter < num_tasks:
results.append(tasks_completed.get())
completed_tasks_counter = completed_tasks_counter + 1
bar.update(completed_tasks_counter)
for p in processes:
p.join()
return results

Based on "user17242583" answer, I created the following function. It should be as fast as Pool.map and the results are always ordered. Plus, you can pass as many parameters to your function as you want and not just a single iterable.
from multiprocessing import Pool
from functools import partial
from tqdm import tqdm
def imap_tqdm(function, iterable, processes, chunksize=1, desc=None, disable=False, **kwargs):
"""
Run a function in parallel with a tqdm progress bar and an arbitrary number of arguments.
Results are always ordered and the performance should be the same as of Pool.map.
:param function: The function that should be parallelized.
:param iterable: The iterable passed to the function.
:param processes: The number of processes used for the parallelization.
:param chunksize: The iterable is based on the chunk size chopped into chunks and submitted to the process pool as separate tasks.
:param desc: The description displayed by tqdm in the progress bar.
:param disable: Disables the tqdm progress bar.
:param kwargs: Any additional arguments that should be passed to the function.
"""
if kwargs:
function_wrapper = partial(_wrapper, function=function, **kwargs)
else:
function_wrapper = partial(_wrapper, function=function)
results = [None] * len(iterable)
with Pool(processes=processes) as p:
with tqdm(desc=desc, total=len(iterable), disable=disable) as pbar:
for i, result in p.imap_unordered(function_wrapper, enumerate(iterable), chunksize=chunksize):
results[i] = result
pbar.update()
return results
def _wrapper(enum_iterable, function, **kwargs):
i = enum_iterable[0]
result = function(enum_iterable[1], **kwargs)
return i, result

This approach simple and it works.
from multiprocessing.pool import ThreadPool
import time
from tqdm import tqdm
def job():
time.sleep(1)
pbar.update()
pool = ThreadPool(5)
with tqdm(total=100) as pbar:
for i in range(100):
pool.apply_async(job)
pool.close()
pool.join()

return value from spawned multiprocessing.process [duplicate]

In the example code below, I'd like to get the return value of the function worker. How can I go about doing this? Where is this value stored?
Example Code:
import multiprocessing
def worker(procnum):
'''worker function'''
print str(procnum) + ' represent!'
return procnum
if __name__ == '__main__':
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i,))
jobs.append(p)
p.start()
for proc in jobs:
proc.join()
print jobs
Output:
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
[<Process(Process-1, stopped)>, <Process(Process-2, stopped)>, <Process(Process-3, stopped)>, <Process(Process-4, stopped)>, <Process(Process-5, stopped)>]
I can't seem to find the relevant attribute in the objects stored in jobs.

Use shared variable to communicate. For example like this:
import multiprocessing
def worker(procnum, return_dict):
"""worker function"""
print(str(procnum) + " represent!")
return_dict[procnum] = procnum
if __name__ == "__main__":
manager = multiprocessing.Manager()
return_dict = manager.dict()
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i, return_dict))
jobs.append(p)
p.start()
for proc in jobs:
proc.join()
print(return_dict.values())

I think the approach suggested by #sega_sai is the better one. But it really needs a code example, so here goes:
import multiprocessing
from os import getpid
def worker(procnum):
print('I am number %d in process %d' % (procnum, getpid()))
return getpid()
if __name__ == '__main__':
pool = multiprocessing.Pool(processes = 3)
print(pool.map(worker, range(5)))
Which will print the return values:
I am number 0 in process 19139
I am number 1 in process 19138
I am number 2 in process 19140
I am number 3 in process 19139
I am number 4 in process 19140
[19139, 19138, 19140, 19139, 19140]
If you are familiar with map (the Python 2 built-in) this should not be too challenging. Otherwise have a look at sega_Sai's link.
Note how little code is needed. (Also note how processes are re-used).

For anyone else who is seeking how to get a value from a Process using Queue:
import multiprocessing
ret = {'foo': False}
def worker(queue):
ret = queue.get()
ret['foo'] = True
queue.put(ret)
if __name__ == '__main__':
queue = multiprocessing.Queue()
queue.put(ret)
p = multiprocessing.Process(target=worker, args=(queue,))
p.start()
p.join()
print(queue.get()) # Prints {"foo": True}
Note that in Windows or Jupyter Notebook, with multithreading you have to save this as a file and execute the file. If you do it in a command prompt you will see an error like this:
AttributeError: Can't get attribute 'worker' on <module '__main__' (built-in)>

For some reason, I couldn't find a general example of how to do this with Queue anywhere (even Python's doc examples don't spawn multiple processes), so here's what I got working after like 10 tries:
from multiprocessing import Process, Queue
def add_helper(queue, arg1, arg2): # the func called in child processes
ret = arg1 + arg2
queue.put(ret)
def multi_add(): # spawns child processes
q = Queue()
processes = []
rets = []
for _ in range(0, 100):
p = Process(target=add_helper, args=(q, 1, 2))
processes.append(p)
p.start()
for p in processes:
ret = q.get() # will block
rets.append(ret)
for p in processes:
p.join()
return rets
Queue is a blocking, thread-safe queue that you can use to store the return values from the child processes. So you have to pass the queue to each process. Something less obvious here is that you have to get() from the queue before you join the Processes or else the queue fills up and blocks everything.
Update for those who are object-oriented (tested in Python 3.4):
from multiprocessing import Process, Queue
class Multiprocessor():
def __init__(self):
self.processes = []
self.queue = Queue()
#staticmethod
def _wrapper(func, queue, args, kwargs):
ret = func(*args, **kwargs)
queue.put(ret)
def run(self, func, *args, **kwargs):
args2 = [func, self.queue, args, kwargs]
p = Process(target=self._wrapper, args=args2)
self.processes.append(p)
p.start()
def wait(self):
rets = []
for p in self.processes:
ret = self.queue.get()
rets.append(ret)
for p in self.processes:
p.join()
return rets
# tester
if __name__ == "__main__":
mp = Multiprocessor()
num_proc = 64
for _ in range(num_proc): # queue up multiple tasks running `sum`
mp.run(sum, [1, 2, 3, 4, 5])
ret = mp.wait() # get all results
print(ret)
assert len(ret) == num_proc and all(r == 15 for r in ret)

This example shows how to use a list of multiprocessing.Pipe instances to return strings from an arbitrary number of processes:
import multiprocessing
def worker(procnum, send_end):
'''worker function'''
result = str(procnum) + ' represent!'
print result
send_end.send(result)
def main():
jobs = []
pipe_list = []
for i in range(5):
recv_end, send_end = multiprocessing.Pipe(False)
p = multiprocessing.Process(target=worker, args=(i, send_end))
jobs.append(p)
pipe_list.append(recv_end)
p.start()
for proc in jobs:
proc.join()
result_list = [x.recv() for x in pipe_list]
print result_list
if __name__ == '__main__':
main()
Output:
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
['0 represent!', '1 represent!', '2 represent!', '3 represent!', '4 represent!']
This solution uses fewer resources than a multiprocessing.Queue which uses
a Pipe
at least one Lock
a buffer
a thread
or a multiprocessing.SimpleQueue which uses
a Pipe
at least one Lock
It is very instructive to look at the source for each of these types.

It seems that you should use the multiprocessing.Pool class instead and use the methods .apply() .apply_async(), map()
http://docs.python.org/library/multiprocessing.html?highlight=pool#multiprocessing.pool.AsyncResult

You can use the exit built-in to set the exit code of a process. It can be obtained from the exitcode attribute of the process:
import multiprocessing
def worker(procnum):
print str(procnum) + ' represent!'
exit(procnum)
if __name__ == '__main__':
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i,))
jobs.append(p)
p.start()
result = []
for proc in jobs:
proc.join()
result.append(proc.exitcode)
print result
Output:
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
[0, 1, 2, 3, 4]

The pebble package has a nice abstraction leveraging multiprocessing.Pipe which makes this quite straightforward:
from pebble import concurrent
#concurrent.process
def function(arg, kwarg=0):
return arg + kwarg
future = function(1, kwarg=1)
print(future.result())
Example from: https://pythonhosted.org/Pebble/#concurrent-decorators

Thought I'd simplify the simplest examples copied from above, working for me on Py3.6. Simplest is multiprocessing.Pool:
import multiprocessing
import time
def worker(x):
time.sleep(1)
return x
pool = multiprocessing.Pool()
print(pool.map(worker, range(10)))
You can set the number of processes in the pool with, e.g., Pool(processes=5). However it defaults to CPU count, so leave it blank for CPU-bound tasks. (I/O-bound tasks often suit threads anyway, as the threads are mostly waiting so can share a CPU core.) Pool also applies chunking optimization.
(Note that the worker method cannot be nested within a method. I initially defined my worker method inside the method that makes the call to pool.map, to keep it all self-contained, but then the processes couldn't import it, and threw "AttributeError: Can't pickle local object outer_method..inner_method". More here. It can be inside a class.)
(Appreciate the original question specified printing 'represent!' rather than time.sleep(), but without it I thought some code was running concurrently when it wasn't.)
Py3's ProcessPoolExecutor is also two lines (.map returns a generator so you need the list()):
from concurrent.futures import ProcessPoolExecutor
with ProcessPoolExecutor() as executor:
print(list(executor.map(worker, range(10))))
With plain Processes:
import multiprocessing
import time
def worker(x, queue):
time.sleep(1)
queue.put(x)
queue = multiprocessing.SimpleQueue()
tasks = range(10)
for task in tasks:
multiprocessing.Process(target=worker, args=(task, queue,)).start()
for _ in tasks:
print(queue.get())
Use SimpleQueue if all you need is put and get. The first loop starts all the processes, before the second makes the blocking queue.get calls. I don't think there's any reason to call p.join() too.

If you are using Python 3, you can use concurrent.futures.ProcessPoolExecutor as a convenient abstraction:
from concurrent.futures import ProcessPoolExecutor
def worker(procnum):
'''worker function'''
print(str(procnum) + ' represent!')
return procnum
if __name__ == '__main__':
with ProcessPoolExecutor() as executor:
print(list(executor.map(worker, range(5))))
Output:
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
[0, 1, 2, 3, 4]

A simple solution:
import multiprocessing
output=[]
data = range(0,10)
def f(x):
return x**2
def handler():
p = multiprocessing.Pool(64)
r=p.map(f, data)
return r
if __name__ == '__main__':
output.append(handler())
print(output[0])
Output:
[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

You can use ProcessPoolExecutor to get a return value from a function as shown below:
from concurrent.futures import ProcessPoolExecutor
def test(num1, num2):
return num1 + num2
with ProcessPoolExecutor() as executor:
feature = executor.submit(test, 2, 3)
print(feature.result()) # 5

I modified vartec's answer a bit since I needed to get the error codes from the function. (Thanks vertec!!! its an awesome trick)
This can also be done with a manager.list but I think is better to have it in a dict and store a list within it. That way, way we keep the function and the results since we can't be sure of the order in which the list will be populated.
from multiprocessing import Process
import time
import datetime
import multiprocessing
def func1(fn, m_list):
print 'func1: starting'
time.sleep(1)
m_list[fn] = "this is the first function"
print 'func1: finishing'
# return "func1" # no need for return since Multiprocess doesnt return it =(
def func2(fn, m_list):
print 'func2: starting'
time.sleep(3)
m_list[fn] = "this is function 2"
print 'func2: finishing'
# return "func2"
def func3(fn, m_list):
print 'func3: starting'
time.sleep(9)
# if fail wont join the rest because it never populate the dict
# or do a try/except to get something in return.
raise ValueError("failed here")
# if we want to get the error in the manager dict we can catch the error
try:
raise ValueError("failed here")
m_list[fn] = "this is third"
except:
m_list[fn] = "this is third and it fail horrible"
# print 'func3: finishing'
# return "func3"
def runInParallel(*fns): # * is to accept any input in list
start_time = datetime.datetime.now()
proc = []
manager = multiprocessing.Manager()
m_list = manager.dict()
for fn in fns:
# print fn
# print dir(fn)
p = Process(target=fn, name=fn.func_name, args=(fn, m_list))
p.start()
proc.append(p)
for p in proc:
p.join() # 5 is the time out
print datetime.datetime.now() - start_time
return m_list, proc
if __name__ == '__main__':
manager, proc = runInParallel(func1, func2, func3)
# print dir(proc[0])
# print proc[0]._name
# print proc[0].name
# print proc[0].exitcode
# here you can check what did fail
for i in proc:
print i.name, i.exitcode # name was set up in the Process line 53
# here will only show the function that worked and where able to populate the
# manager dict
for i, j in manager.items():
print dir(i) # things you can do to the function
print i, j

How to process input in parallel with python, but without processes?

I have a list of input data and would like to process it in parallel, but processing each takes time as network io is involved. CPU usage is not a problem.
I would not like to have the overhead of additional processes since I have a lot of things to process at a time and do not want to setup inter process communication.
# the parallel execution equivalent of this?
import time
input_data = [1,2,3,4,5,6,7]
input_processor = time.sleep
results = map(input_processor, input_data)
The code I am using makes use of twisted.internet.defer so a solution involving that is fine as well.

You can easily define Worker threads that work in parallel till a queue is empty.
from threading import Thread
from collections import deque
import time
# Create a new class that inherits from Thread
class Worker(Thread):
def __init__(self, inqueue, outqueue, func):
'''
A worker that calls func on objects in inqueue and
pushes the result into outqueue
runs until inqueue is empty
'''
self.inqueue = inqueue
self.outqueue = outqueue
self.func = func
super().__init__()
# override the run method, this is starte when
# you call worker.start()
def run(self):
while self.inqueue:
data = self.inqueue.popleft()
print('start')
result = self.func(data)
self.outqueue.append(result)
print('finished')
def test(x):
time.sleep(x)
return 2 * x
if __name__ == '__main__':
data = 12 * [1, ]
queue = deque(data)
result = deque()
# create 3 workers working on the same input
workers = [Worker(queue, result, test) for _ in range(3)]
# start the workers
for worker in workers:
worker.start()
# wait till all workers are finished
for worker in workers:
worker.join()
print(result)
As expected, this runs ca. 4 seconds.
One could also write a simple Pool class to get rid of the noise in the main function:
from threading import Thread
from collections import deque
import time
class Pool():
def __init__(self, n_threads):
self.n_threads = n_threads
def map(self, func, data):
inqueue = deque(data)
result = deque()
workers = [Worker(inqueue, result, func) for i in range(self.n_threads)]
for worker in workers:
worker.start()
for worker in workers:
worker.join()
return list(result)
class Worker(Thread):
def __init__(self, inqueue, outqueue, func):
'''
A worker that calls func on objects in inqueue and
pushes the result into outqueue
runs until inqueue is empty
'''
self.inqueue = inqueue
self.outqueue = outqueue
self.func = func
super().__init__()
# override the run method, this is starte when
# you call worker.start()
def run(self):
while self.inqueue:
data = self.inqueue.popleft()
print('start')
result = self.func(data)
self.outqueue.append(result)
print('finished')
def test(x):
time.sleep(x)
return 2 * x
if __name__ == '__main__':
data = 12 * [1, ]
pool = Pool(6)
result = pool.map(test, data)
print(result)

You can use the multiprocessing module. Without knowing more about how you want it to process, you can use a pool of workers:
import multiprocessing as mp
import time
input_processor = time.sleep
core_num = mp.cpu_count()
pool=Pool(processes = core_num)
result = [pool.apply_async(input_processor(i)) for for i in range(1,7+1) ]
result_final = [p.get() for p in results]
for n in range(1,7+1):
print n, result_final[n]
The above keeps track of the order each task is done. It also does not allow the processes to talk to each other.
Editted:
To call this as a function, you should input the input data and number of processors:
def parallel_map(processor_count, input_data):
pool=Pool(processes = processor_count)
result = [pool.apply_async(input_processor(i)) for for i in input_data ]
result_final = np.array([p.get() for p in results])
result_data = np.vstack( (input_data, result_final))
return result_data

I assume you are using Twisted. In that case, you can launch multiple deferreds and wait for the completion of all of them using DeferredList:
http://twistedmatrix.com/documents/15.4.0/core/howto/defer.html#deferredlist
If input_processor is a non-blocking call (returns deferred):
def main():
input_data = [1,2,3,4,5,6,7]
input_processor = asyn_function
for entry in input_data:
requests.append(defer.maybeDeferred(input_processor, entry))
deferredList = defer.DeferredList(requests, , consumeErrors=True)
deferredList.addCallback(gotResults)
return deferredList
def gotResults(results):
for (success, value) in result:
if success:
print 'Success:', value
else:
print 'Failure:', value.getErrorMessage()
In case input_processor is a long/blocking function, you can use deferToThread instead of maybeDeferred:
def main():
input_data = [1,2,3,4,5,6,7]
input_processor = syn_function
for entry in input_data:
requests.append(threads.deferToThread(input_processor, entry))
deferredList = defer.DeferredList(requests, , consumeErrors=True)
deferredList.addCallback(gotResults)
return deferredList

How do you pass a Queue reference to a function managed by pool.map_async()?

I want a long-running process to return its progress over a Queue (or something similar) which I will feed to a progress bar dialog. I also need the result when the process is completed. A test example here fails with a RuntimeError: Queue objects should only be shared between processes through inheritance.
import multiprocessing, time
def task(args):
count = args[0]
queue = args[1]
for i in xrange(count):
queue.put("%d mississippi" % i)
return "Done"
def main():
q = multiprocessing.Queue()
pool = multiprocessing.Pool()
result = pool.map_async(task, [(x, q) for x in range(10)])
time.sleep(1)
while not q.empty():
print q.get()
print result.get()
if __name__ == "__main__":
main()
I've been able to get this to work using individual Process objects (where I am alowed to pass a Queue reference) but then I don't have a pool to manage the many processes I want to launch. Any advise on a better pattern for this?

The following code seems to work:
import multiprocessing, time
def task(args):
count = args[0]
queue = args[1]
for i in xrange(count):
queue.put("%d mississippi" % i)
return "Done"
def main():
manager = multiprocessing.Manager()
q = manager.Queue()
pool = multiprocessing.Pool()
result = pool.map_async(task, [(x, q) for x in range(10)])
time.sleep(1)
while not q.empty():
print q.get()
print result.get()
if __name__ == "__main__":
main()
Note that the Queue is got from a manager.Queue() rather than multiprocessing.Queue(). Thanks Alex for pointing me in this direction.

Making q global works...:
import multiprocessing, time
q = multiprocessing.Queue()
def task(count):
for i in xrange(count):
q.put("%d mississippi" % i)
return "Done"
def main():
pool = multiprocessing.Pool()
result = pool.map_async(task, range(10))
time.sleep(1)
while not q.empty():
print q.get()
print result.get()
if __name__ == "__main__":
main()
If you need multiple queues, e.g. to avoid mixing up the progress of the various pool processes, a global list of queues should work (of course, each process will then need to know what index in the list to use, but that's OK to pass as an argument;-).