Develop Reference

Copying contexvars.Context between tasks

I have a program (an ASGI server) that is structured roughly like this:
import asyncio
import contextvars
ctxvar = contextvars.ContextVar("ctx")
async def lifepsan():
ctxvar.set("spam")
async def endpoint():
assert ctxvar.get() == "spam"
async def main():
ctx = contextvars.copy_context()
task = asyncio.create_task(lifepsan())
await task
task = asyncio.create_task(endpoint())
await task
asyncio.run(main())
Because the lifespan event / endpoints are run in tasks, they can't share contextvars.
This is by design: tasks copy the context before executing, so lifespan can't set ctxvar properly.
This is the desired behavior for endpoints, but I would like for execution to appear like this (from a user's perspective):
async def lifespan():
ctxvar.set("spam")
await endpoint()
In other words, the endpoints are executed in their own independent context, but within the context of the lifespan.
I tried to get this to work by using contextlib.copy_context():
import asyncio
import contextvars
ctxvar = contextvars.ContextVar("ctx")
async def lifepsan():
ctxvar.set("spam")
print("set")
async def endpoint():
print("get")
assert ctxvar.get() == "spam"
async def main():
ctx = contextvars.copy_context()
task = ctx.run(asyncio.create_task, lifepsan())
await task
endpoint_ctx = ctx.copy()
task = endpoint_ctx.run(asyncio.create_task, endpoint())
await task
asyncio.run(main())
As well as:
async def main():
ctx = contextvars.copy_context()
task = asyncio.create_task(ctx.run(lifespan))
await task
endpoint_ctx = ctx.copy()
task = asyncio.create_task(endpoint_ctx.run(endpoint))
await task
However it seems that contextvars.Context.run does not work this way (I guess the context is bound when the coroutine is created but not when it is executed).
Is there a simple way to achieve the desired behavior, without restructuring how the tasks are being created or such?

Here's what I came up with, inspired by PEP 555 and asgiref:
from contextvars import Context, ContextVar, copy_context
from typing import Any
def _set_cvar(cvar: ContextVar, val: Any):
cvar.set(val)
class CaptureContext:
def __init__(self) -> None:
self.context = Context()
def __enter__(self) -> "CaptureContext":
self._outer = copy_context()
return self
def sync(self):
final = copy_context()
for cvar in final:
if cvar not in self._outer:
# new contextvar set
self.context.run(_set_cvar, cvar, final.get(cvar))
else:
final_val = final.get(cvar)
if self._outer.get(cvar) != final_val:
# value changed
self.context.run(_set_cvar, cvar, final_val)
def __exit__(self, *args: Any):
self.sync()
def restore_context(context: Context) -> None:
"""Restore `context` to the current Context"""
for cvar in context.keys():
try:
cvar.set(context.get(cvar))
except LookupError:
cvar.set(context.get(cvar))
Usage:
import asyncio
import contextvars
ctxvar = contextvars.ContextVar("ctx")
async def lifepsan(cap: CaptureContext):
with cap:
ctxvar.set("spam")
async def endpoint():
assert ctxvar.get() == "spam"
async def main():
cap = CaptureContext()
await asyncio.create_task(lifepsan(cap))
restore_context(cap.context)
task = asyncio.create_task(endpoint())
await task
asyncio.run(main())
The sync() method is provided in case the task is long-running and you need to capture the context before it finishes. A somewhat contrived example:
import asyncio
import contextvars
ctxvar = contextvars.ContextVar("ctx")
async def lifepsan(cap: CaptureContext, event: asyncio.Event):
with cap:
ctxvar.set("spam")
cap.sync()
event.set()
await asyncio.sleep(float("inf"))
async def endpoint():
assert ctxvar.get() == "spam"
async def main():
cap = CaptureContext()
event = asyncio.Event()
asyncio.create_task(lifepsan(cap, event))
await event.wait()
restore_context(cap.context)
task = asyncio.create_task(endpoint())
await task
asyncio.run(main())
I think it would still be much nicer if contextvars.Context.run worked with coroutines.

This feature will be supported in Python 3.11: https://github.com/python/cpython/issues/91150
You will be able to write:
async def main():
ctx = contextvars.copy_context()
task = asyncio.create_task(lifepsan(), context=ctx)
await task
endpoint_ctx = ctx.copy()
task = asyncio.create_task(endpoint(), context=endpoint_ctx)
await task
In the meantime, in current Python versions you will need a backport of this feature. I can't think of a good one, but a bad one is here.

Convert third party library to asyncio

I have a third party library (in this case azure-cosmos) that is performing slow blocking operations. I'd like to use this with the asyncio library to leverage a degree of parallelism where I can start up another request as one is waiting for us data.
I've looked around online but been unable to find a concrete answer as to how to perform this wrapping of the external library; is it as easy as:
def external_sync_method(*args, **kwargs):
...
async def my_async_code():
args_list = [...]
return await asyncio.gather(*(external_sync_method(*args) for args in args_list))

Asynchronously run function func in a separate thread.
python >= 3.9
https://docs.python.org/3/library/asyncio-task.html#asyncio.to_thread
async def my_async_code():
args_list = [...]
return await asyncio.gather(
*(
asyncio.to_thread(external_sync_method, *args)
for args in args_list
)
)
python < 3.9
https://docs.python.org/3/library/asyncio-eventloop.html#asyncio.loop.run_in_executor
async def run_sync_method(func, *args, **kwargs):
loop = asyncio.get_running_loop()
func_call = functools.partial(func, *args, **kwargs)
return await loop.run_in_executor(None, func_call)
async def my_async_code():
args_list = [...]
return await asyncio.gather(
*(
run_sync_method(external_sync_method, *args)
for args in args_list
)
)

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

Does calling thread.join() blocks the event loop in an asynchronous context?

I'm implementing a web API using aiohttp, deployed using gunicorn with UVloop enabled --worker-class aiohttp.GunicornUVLoopWebWorker. Therefore, my code always runs in an asynchronous context. I had the ideia of implementing parallel jobs in the handling of requests for better performance.
I'm not using asyncio because i want Parallelism, not Concurrency.
I'm aware of multiprocessing and the GIL problem in python. But joining a process also applies to my question.
Here is an example:
from aiohttp.web import middleware
#middleware
async def context_init(request, handler):
request.context = {}
request.context['threads'] = []
ret = await handler(request)
for thread in request.context['threads']:
thread.join()
return ret
Taking into account that thread.join() or process.join() blocks the current thread, this will block the event loop (As far as my knowledge goes). How can I join asynchronously? What I want can be represented figuratively as this: await thread.join() or await process.join().
Update:
Thanks to #user4815162342 I was able to write proper code for my project:
Middleware:
from aiohttp.web import middleware
from util.process_session import ProcessSession
#middleware
async def context_init(request, handler):
request.context = {}
request.context['process_session'] = ProcessSession()
request.context['processes'] = {}
ret = await handler(request)
await request.context['process_session'].wait_for_all()
return ret
Util:
import asyncio
import concurrent.futures
from functools import partial
class ProcessSession():
def __init__(self):
self.loop = asyncio.get_running_loop()
self.pool = concurrent.futures.ProcessPoolExecutor()
self.futures = []
async def wait_for_all(self):
await asyncio.wait(self.futures)
def add_process(self, f, *args, **kwargs):
ret = self.loop.run_in_executor(self.pool, partial(f, *args, **kwargs))
self.futures.append(ret)
return ret
class ProcessBase():
def __init__(self, process_session, f, *args, **kwargs):
self.future = process_session.add_process(f, *args, **kwargs)
async def wait(self):
await asyncio.wait([self.future])
return self.future.result()

Answering your question: Yes, it does block the event loop.
I found that ThreadPoolExecutor works pretty well on this situations.
from util.process_session import ProcessSession
from concurrent.futures.thread import ThreadPoolExecutor
import asyncio
from aiohttp.web import middleware
#middleware
async def context_init(request, handler):
request.context = {}
request.context['threads'] = []
ret = await handler(request)
with ThreadPoolExecutor(1) as executor:
await asyncio.get_event_loop().run_in_executor(executor,
functools.partial(join_threads, data={
'threads': request.context['threads']
}))
return ret
def join_threads(threads):
for t in threads:
t.join()

I found a solution using multiprocesses. It can be done using a Pool. The standard lib provides some "async" methods (It's not really async, it just separates the initialization of the process from the process' output): apply_async
Using a simple async wrapper, I managed to deliver what I wanted:
from multiprocessing import Pool
from async_converter import sync_to_async
import asyncio
def f(x):
i = 0
while i < 10000000 * x:
i = i + 1
print("Finished: " + str(x))
return i
async def run():
print("Started with run")
with Pool(processes=4) as pool: # start 4 worker processes
result1 = pool.apply_async(f, (10,)) # evaluate "f(10)" asynchronously
result2 = pool.apply_async(f, (2,))
res1 = await sync_to_async(result1.get)()
print(res1)
res2 = await sync_to_async(result2.get)()
print(res2)
async def dummy(output):
print(output)
async def main():
# Schedule three calls *concurrently*:
await asyncio.gather(
run(),
dummy("Nice"),
dummy("Async"),
dummy("Loop"),
dummy("Perfect"),
dummy("Dummy1"),
dummy("Dummy2"),
dummy("Dummy3"),
dummy("Dummy4"),
dummy("Dummy5"),
dummy("Dummy6"),
dummy("Dummy7"),
dummy("Dummy8"),
dummy("Dummy9"),
dummy("Dummy10"),
)
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
loop.close()
outputs:
Perfect
Dummy6
Nice
Dummy1
Dummy7
Started with run
Dummy2
Dummy8
Dummy3
Dummy9
Async
Dummy4
Dummy10
Loop
Dummy5
Finished: 2
Finished: 10
100000000
20000000
Parallelism with asyncio :)

Method chaining with asyncio coroutines

I want to implement method chaining, but not for usual functions - for asyncio coroutines.
import asyncio
class Browser:
#asyncio.coroutine
def go(self):
# some actions
return self
#asyncio.coroutine
def click(self):
# some actions
return self
"Intuitive" way to call chain wouldn't work, because single method returns coroutine (generator), not self:
#asyncio.coroutine
def main():
br = yield from Browser().go().click() # this will fail
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
Correct way to call chain is:
br = yield from (yield from Browser().go()).click()
But it looks ugly and becomes unreadable when chain grows.
Is there any way to do this better? Any ideas are welcome.

I created solution, that do a job close to the needed. Idea is to use wrapper for Browser() which uses __getattr__ and __call__ to collect action (like getting attribute or call) and return self to catch next one action. After all actions collected, we "catch" yiled from wrapper using __iter__ and process all collected actions.
import asyncio
def chain(obj):
"""
Enables coroutines chain for obj.
Usage: text = yield from chain(obj).go().click().attr
Note: Returns not coroutine, but object that can be yield from.
"""
class Chain:
_obj = obj
_queue = []
# Collect getattr of call to queue:
def __getattr__(self, name):
Chain._queue.append({'type': 'getattr', 'name': name})
return self
def __call__(self, *args, **kwargs):
Chain._queue.append({'type': 'call', 'params': [args, kwargs]})
return self
# On iter process queue:
def __iter__(self):
res = Chain._obj
while Chain._queue:
action = Chain._queue.pop(0)
if action['type'] == 'getattr':
res = getattr(res, action['name'])
elif action['type'] == 'call':
args, kwargs = action['params']
res = res(*args, **kwargs)
if asyncio.iscoroutine(res):
res = yield from res
return res
return Chain()
Usage:
class Browser:
#asyncio.coroutine
def go(self):
print('go')
return self
#asyncio.coroutine
def click(self):
print('click')
return self
def text(self):
print('text')
return 5
#asyncio.coroutine
def main():
text = yield from chain(Browser()).go().click().go().text()
print(text)
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
Output:
go
click
go
text
5
Note, that chain() doesn't return real coroutine, but object that can be used like coroutine on yield from. We should wrap result of chain() to get normal coroutine, which can be passed to any asyncio function that requires coroutine:
#asyncio.coroutine
def chain_to_coro(chain):
return (yield from chain)
#asyncio.coroutine
def main():
ch = chain(Browser()).go().click().go().text()
coro = chain_to_coro(ch)
results = yield from asyncio.gather(*[coro], return_exceptions=True)
print(results)
Output:
go
click
go
text
[5]

It's still not particularly pretty, but you could implement a chain function that scales a little bit better:
import asyncio
#asyncio.coroutine
def chain(obj, *funcs):
for f, *args in funcs:
meth = getattr(obj, f) # Look up the method on the object
obj = yield from meth(*args)
return obj
class Browser:
#asyncio.coroutine
def go(self, x, y):
return self
#asyncio.coroutine
def click(self):
return self
#asyncio.coroutine
def main():
#br = yield from (yield from Browser().go(3, 4)).click()
br = yield from chain(Browser(),
("go", 3, 4),
("click",))
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
The idea is to pass tuples in a (method_name, arg1, arg2, argX) format to the chain function, rather than actually chaining the method calls themselves. You can just pass the method names directly if you don't need to support passing arguments to any of the methods in the chain.