Threading with Decorator in Python [duplicate] - python

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

Related

Python Multiprocessing Pool as Decorator

I'm working on code where I frequently have to use python's multiprocessing Pool class. This results in a ton of code that looks like this:
import time
from multiprocessing import Pool
from functools import partial
def test_func(x):
time.sleep(1)
return x
def test_func_parallel(iterable, processes):
p = Pool(processes=processes)
output = p.map(test_func, iterable)
p.close()
return output
This can be made more general:
def parallel(func, iterable, **kwargs):
func = partial(func, **kwargs)
p = Pool(processes=6)
out = p.map(func, iterable)
p.close()
return out
This works, but adding a parallel wrapper to every other function complicates the code. What I'd really like is to get this working as a decorator. Something like this:
def parallel(num_processes):
def parallel_decorator(func, num_processes=num_processes):
def parallel_wrapper(iterable, **kwargs):
func = partial(func, **kwargs)
p = Pool(processes=num_processes)
output = p.map(func, iterable)
p.close()
return output
return parallel_wrapper
return parallel_decorator
Which could be used as follows:
#parallel(6)
def test_func(x):
time.sleep(1)
return x
This fails for pickle reasons
Can't pickle <function test1 at 0x117473268>: it's not the same object as __main__.test1
I've read a few posts on related issues, but they all implement a solution where the multiprocessing is executed outside the decorator. Does anyone know a way to make this work?
If you don't mind to not use the syntactic sugar for decorators (# symbol), something like this should work:
import functools
import time
from multiprocessing import Pool
def parallel(func=None, **options):
if func is None:
return functools.partial(parallel, **options)
def wrapper(iterable, **kwargs):
processes = options["processes"]
with Pool(processes) as pool:
result = pool.map(func, iterable)
return result
return wrapper
def test(i):
time.sleep(1)
print(f"{i}: {i * i}")
test_parallel = parallel(test, processes=6)
def main():
test_parallel(range(10))
if __name__ == "__main__":
main()
I have the same problem. It revolves around how Pool() objects are implemented. So, it is going to work fine with a normal wrapper but not with a Decorator. The workaround is to define your own Pool()-like implementation using Process().
This can be very tricky to optimize but if you are a Decorator enthusiast here is a (dirty) example:
# something to do
args = range(10)
def parallel(function):
""" An alternative implementation to
multiprocessing.Pool().map() using
multiprocessing.Process(). """
def interfacer(args):
""" The wrapper function. """
# required libraries
from multiprocessing import (Queue, Process)
from os import cpu_count
# process control
## maximum number of processes required
max_processes = len(args)
## maximum numer of processes running
max_threads = cpu_count() - 1
""" Since there is no Pool() around
we need to take care of the processes
ourselves. If there is nothing for a
processes to do, it is going to await
for an input, if there are too many of
them, the processor shall suffer. """
# communications
## things to do
inbasket = Queue()
## things done
outbasket = Queue()
""" I am thinking asynchronouly,
there is probably a better way of
doing this. """
# populate inputs
for each in args:
## put arguments into the basket
inbasket.put(each)
def doer():
""" Feeds the targeted/decorated
'function' with data from the baskets and
collets the results.
This blind function helps the
implementation to generalize over any
iterable. """
outbasket.put(function(inbasket.get()))
return(True)
def run(processes = max_threads):
""" Create a certain number of
Process()s and runs each one.
There is room for improvements here. """
# the process pool
factory = list()
# populate the process pool
for each in range(processes):
factory.append(Process(target = doer))
# execute in process pool
for each in factory:
each.start()
each.join()
each.close()
return(True)
""" Now we need to manage the processes,
and prevent them for overwhelm the CPU.
That is the tricky part that Pool() does
so well. """
while max_processes:
# as long as there is something to do
if (max_processes - max_threads) >= 0:
run(max_threads)
max_processes -= max_threads
else:
# play it safe
run(1)
max_processes -= 1
# undo the queue and give me back the list of 'dones'
return([outbasket.get() for each in range(outbasket.qsize())])
return(interfacer)
#parallel
def test(x):
return(x**2)
print(test(args))
Probably this code is inefficient, but gives an idea.

Decorator for Multiprocessing Lock crashes on runtime

Iam trying Multiprocessing and tried using Locks with decorator for ease but it crashes on run-time
def lock_dec(func):
def wrapper(*args , **kwargs):
Lock().acquire()
func(args)
Lock().release()
return wrapper
is the decorator
#lock_dec
def add_no_lock(total):
for i in range(100):
time.sleep(0.01)
total.value += 5
this is the function
add_process = Process(target = add_no_lock , args = (total , ))
add_process.start()
i'am getting this error but i am not able to debug the code
Can't pickle local object 'lock_dec.<locals>.wrapper
EDIT after 24 hrs attempt and debugging ive found a solution by using decorators with arguments
def loc_dec_parent(*args , **kwargs):
def lock_dec(func):
#wraps(func)
def wrapper(*arg , **kwarg):
kwargs['lock'].acquire()
try:
func(*arg)
finally:
kwargs['lock'].release()
return wrapper
return lock_dec
and function is
#loc_dec_parent(lock = Lock())
def add_no_lock(total):
for i in range(100):
time.sleep(0.01)
total.value += 5
this works for me
A recent post of yours drew my attention to this post. You solution is not ideal in that it does not allow arbitrary arguments to be passed to the wrapped function (right now it would not support keyword arguments). Your decorator function only needs one argument, i.e. the lock to be used, and you shouldn't care whether it is passed as a keyword argument or not. You can also simplify your code by using a context manager for the lock:
from functools import wraps
from multiprocessing import Lock
def loc_dec_parent(lock=Lock()):
def lock_dec(func):
#wraps(func)
def wrapper(*args , **kwargs):
with lock:
func(*args, **kwargs)
return wrapper
return lock_dec
the_lock = Lock()
#loc_dec_parent(the_lock)
def foo(*args, **kwargs):
print('args:')
for arg in args:
print('\t', arg)
print('kwargs:')
for k, v in kwargs.items():
print('\t', k, '->', v)
foo(1, 2, x=3, lock=4)
Prints:
args:
1
2
kwargs:
x -> 3
lock -> 4
But there is still a problem with the decorator conceptually when actually used in actual multiprocessing under Windows or any platform that creates new processes using spawn:
from functools import wraps
from multiprocessing import Lock, Process
import time
def loc_dec_parent(lock=Lock()):
def lock_dec(func):
#wraps(func)
def wrapper(*args , **kwargs):
with lock:
func(*args, **kwargs)
return wrapper
return lock_dec
lock = Lock()
#loc_dec_parent(lock=lock)
def foo():
for i in range(3):
time.sleep(1)
print(i, flush=True)
#loc_dec_parent(lock=lock)
def bar():
for i in range(3):
time.sleep(1)
print(i, flush=True)
if __name__ == '__main__':
p1 = Process(target=foo)
p2 = Process(target=bar)
p1.start()
p2.start()
p1.join()
p2.join()
Prints:
0
0
1
1
2
2
The locking does not work! We should have seen the following it were working:
0
1
2
0
1
2
This is because to implement the creation of each new subprocess a new Python interpreter is launched in the new process's address space and the source is re-executed from the top before control is passed to the target of the Process instance. This means that in each new process's address space a new distinct Lock instance is being created and the decorators are being re-executed.
The main process should be creating a single Lock instance which it then passes to each process as an argument. In this way you can be sure that each process is dealing with the same Lock instance.
In short, a multiprocessor.Lock is a bad candidate for such a decorator if you wish to support all platforms.
Update
To emulate Java's synchronized methods, then you should ensure that you have a single Lock instance that is used by all decorated functions and methods. For this you want to use a decorator implemented as a class. Also, don't forget that the wrapper function should return any possible return value that the wrapped function/method returns.
This must run on a platform using fork to create new processes:
from functools import wraps
from multiprocessing import Lock, Process
import time
class Synchronized():
the_lock = Lock() # class instance
def __call__(self, func):
#wraps(func)
def decorated(*args, **kwargs):
with self.the_lock:
return func(*args, **kwargs)
return decorated
#Synchronized()
def foo():
for i in range(3):
time.sleep(1)
print(i, flush=True)
class MyClass:
#Synchronized()
def bar(self):
for i in range(3):
time.sleep(1)
print(i, flush=True)
if __name__ == '__main__':
p1 = Process(target=foo)
p2 = Process(target=MyClass().bar)
p1.start()
p2.start()
p1.join()
p2.join()

Python make each lock in multithread

I'm considering how to make several locks for each thread.
I have 3 threads right now.
A : main thread(data sending)
B : data receiving thread
C : data sending every 2 sec thread
I don't want to stop B(receiving thread) except sending time.
How can I use Lock between A,B and between A,C easily!!...
class A:
def __init__():
self._A_B_lock = RLock()
self._A_C_lock = RLock()
self._B = threading.Thread(target=B_receiving_thread, args=(self._A_B_lock,) ... ).start()
self._C = threading.Thread(target=C_sending_2sec_thread, args=(self._A_C_lock,) ... ).start()
def sending():
with A_B_lock:
sending_data()
def B_receiving_thread(self,A_B_lock):
while(1):
with A_B_lock:
receiving_data()
#do something
def C_sending_2sec_thread(self,A_C_lock):
while(1):
with A_C_lock:
self.sending()
# actually I want to make decorator with A_C_lock, I have so many functions.
def so_many_functions():
with self.A_C_lock:
#do important thing
This code doesn’t work..
A decorator is a good idea. You could use this
def decorator(*locks):
def _decorator(func):
def inner_function(*args, **kwargs):
for lock in locks:
lock.acquire()
value = func(*args, **kwargs)
for lock in locks:
lock.release()
return value
return inner_function
return _decorator
And then you decorate each function, and pass as parameter all the locks that that function will need to make his job without interfeering others. Like this,
lock1 = threading.Lock()
lock2 = threading.Lock()
#decorator(lock1, lock2)
def f1(word):
for char in word:
print(char)
'''DO STUFF'''
#decorator(lock1, lock2)
def f2(word):
for char in word:
print(char)
'''
DO STUFF
'''
t1 = threading.Thread(target=f1, args=('Hello ',))
t2 = threading.Thread(target=f2, args=('world',))
t1.start()
t2.start()
Thats just a dummy example, but you can easily apply it to your code. Good thing about it, is that you can easily choose wich locks you want to use for each different function.
Hope it helps

Can I pass a method to apply_async or map in python multiprocessing?

How can I get the following to work? The main point is that I want to run a method (and not a function) asynchronously.
from multiprocessing import Pool
class Async:
def __init__(self, pool):
self.pool = pool
self.run()
def run(self):
p.apply_async(self.f, (10, ))
def f(self, x):
print x*x
if __name__ == '__main__':
p = Pool(5)
a = Async(p)
p.close()
p.join()
This prints nothing.
The problem appears to be due to the fact that multiprocessing needs to pickle self.f while bound methods are not picklable. There is a discussion on how to solve the problem here.
The apply_async apparently creates an exception which is put inside the future returned. That's why nothing is printed. If a get is executed on the future, then the exception is raised.
Its definitely possible to thread class methods using a threadpool in python 2 - the following programme did what I would expect.
#!/usr/bin/env python
from multiprocessing.pool import ThreadPool
class TestAsync():
def __init__(self):
pool = ThreadPool(processes = 2)
async_completions = []
for a in range(2):
async_completions.append(pool.apply_async(self.print_int, ( a,)))
for completion in async_completions:
res = completion.get()
print("res = %d" % res)
def print_int(self, value):
print(value)
return (value*10)
a = TestAsync()

Start python Process with output and timeout

I'm trying to find the way to start a new Process and get its output if it takes less than X seconds. If the process takes more time I would like to ignore the Process result, kill the Process and carry on.
I need to basically add the timer to the code below. Now sure if there's a better way to do it, I'm open to a different and better solution.
from multiprocessing import Process, Queue
def f(q):
# Ugly work
q.put(['hello', 'world'])
if __name__ == '__main__':
q = Queue()
p = Process(target=f, args=(q,))
p.start()
print q.get()
p.join()
Thanks!
You may find the following module useful in your case:
Module
#! /usr/bin/env python3
"""Allow functions to be wrapped in a timeout API.
Since code can take a long time to run and may need to terminate before
finishing, this module provides a set_timeout decorator to wrap functions."""
__author__ = 'Stephen "Zero" Chappell ' \
'<stephen.paul.chappell#atlantis-zero.net>'
__date__ = '18 December 2017'
__version__ = 1, 0, 1
__all__ = [
'set_timeout',
'run_with_timeout'
]
import multiprocessing
import sys
import time
DEFAULT_TIMEOUT = 60
def set_timeout(limit=None):
"""Return a wrapper that provides a timeout API for callers."""
if limit is None:
limit = DEFAULT_TIMEOUT
_Timeout.validate_limit(limit)
def wrapper(entry_point):
return _Timeout(entry_point, limit)
return wrapper
def run_with_timeout(limit, polling_interval, entry_point, *args, **kwargs):
"""Execute a callable object and automatically poll for results."""
engine = set_timeout(limit)(entry_point)
engine(*args, **kwargs)
while engine.ready is False:
time.sleep(polling_interval)
return engine.value
def _target(queue, entry_point, *args, **kwargs):
"""Help with multiprocessing calls by being a top-level module function."""
# noinspection PyPep8,PyBroadException
try:
queue.put((True, entry_point(*args, **kwargs)))
except:
queue.put((False, sys.exc_info()[1]))
class _Timeout:
"""_Timeout(entry_point, limit) -> _Timeout instance"""
def __init__(self, entry_point, limit):
"""Initialize the _Timeout instance will all needed attributes."""
self.__entry_point = entry_point
self.__limit = limit
self.__queue = multiprocessing.Queue()
self.__process = multiprocessing.Process()
self.__timeout = time.monotonic()
def __call__(self, *args, **kwargs):
"""Begin execution of the entry point in a separate process."""
self.cancel()
self.__queue = multiprocessing.Queue(1)
self.__process = multiprocessing.Process(
target=_target,
args=(self.__queue, self.__entry_point) + args,
kwargs=kwargs
)
self.__process.daemon = True
self.__process.start()
self.__timeout = time.monotonic() + self.__limit
def cancel(self):
"""Terminate execution if possible."""
if self.__process.is_alive():
self.__process.terminate()
#property
def ready(self):
"""Property letting callers know if a returned value is available."""
if self.__queue.full():
return True
elif not self.__queue.empty():
return True
elif self.__timeout < time.monotonic():
self.cancel()
else:
return False
#property
def value(self):
"""Property that retrieves a returned value if available."""
if self.ready is True:
valid, value = self.__queue.get()
if valid:
return value
raise value
raise TimeoutError('execution timed out before terminating')
#property
def limit(self):
"""Property controlling what the timeout period is in seconds."""
return self.__limit
#limit.setter
def limit(self, value):
self.validate_limit(value)
self.__limit = value
#staticmethod
def validate_limit(value):
"""Verify that the limit's value is not too low."""
if value <= 0:
raise ValueError('limit must be greater than zero')
To use, see the following example that demonstrates its usage:
Example
from time import sleep
def main():
timeout_after_four_seconds = timeout(4)
# create copies of a function that have a timeout
a = timeout_after_four_seconds(do_something)
b = timeout_after_four_seconds(do_something)
c = timeout_after_four_seconds(do_something)
# execute the functions in separate processes
a('Hello', 1)
b('World', 5)
c('Jacob', 3)
# poll the functions to find out what they returned
results = [a, b, c]
polling = set(results)
while polling:
for process, name in zip(results, 'abc'):
if process in polling:
ready = process.ready
if ready is True: # if the function returned
print(name, 'returned', process.value)
polling.remove(process)
elif ready is None: # if the function took too long
print(name, 'reached timeout')
polling.remove(process)
else: # if the function is running
assert ready is False, 'ready must be True, False, or None'
sleep(0.1)
print('Done.')
def do_something(data, work):
sleep(work)
print(data)
return work
if __name__ == '__main__':
main()
Does the process you are running involve a loop?
If so you can get the timestamp prior to starting the loop and include an if statement within the loop with an sys.exit(); command terminating the script if the current timestamp differs from the recorded start time stamp by more than x seconds.
All you need to adapt the queue example from the docs to your case is to pass the timeout to the q.get() call and terminate the process on timeout:
from Queue import Empty
...
try:
print q.get(timeout=timeout)
except Empty: # no value, timeout occured
p.terminate()
q = None # the queue might be corrupted after the `terminate()` call
p.join()
Using a Pipe might be more lightweight otherwise the code is the same (you could use .poll(timeout), to find out whether there is a data to receive).

Categories

Resources