Is it possible to set maxtasksperchild for a threadpool? - python

After encountering some probable memory leaks in a long running multi threaded script I found out about maxtasksperchild, which can be used in a Multi process pool like this:
import multiprocessing
with multiprocessing.Pool(processes=32, maxtasksperchild=x) as pool:
pool.imap(function,stuff)
Is something similar possible for the Threadpool (multiprocessing.pool.ThreadPool)?

As the answer by noxdafox said, there is no way in the parent class, you can use threading module to control the max number of tasks per child. As you want to use multiprocessing.pool.ThreadPool, threading module is similar, so...
def split_processing(yourlist, num_splits=4):
'''
yourlist = list which you want to pass to function for threading.
num_splits = control total units passed.
'''
split_size = len(yourlist) // num_splits
threads = []
for i in range(num_splits):
start = i * split_size
end = len(yourlist) if i+1 == num_splits else (i+1) * split_size
threads.append(threading.Thread(target=function, args=(yourlist, start, end)))
threads[-1].start()
# wait for all threads to finish
for t in threads:
t.join()
Lets say
yourlist has 100 items, then
if num_splits = 10; then threads = 10, each thread has 10 tasks.
if num_splits = 5; then threads = 5, each thread has 20 tasks.
if num_splits = 50; then threads = 50, each thread has 2 tasks.
and vice versa.

Looking at multiprocessing.pool.ThreadPool implementation it becomes evident that the maxtaskperchild parameter is not propagated to the parent multiprocessing.Pool class. The multiprocessing.pool.ThreadPool implementation has never been completed, hence it lacks few features (as well as tests and documentation).
The pebble package implements a ThreadPool which supports workers restart after a given amount of tasks have been processed.

I wanted a ThreadPool that will run a new task as soon as another task in the pool completes (i.e. maxtasksperchild=1). I decided to write a small "ThreadPool" class that creates a new thread for every task. As soon a task in the pool completes, another thread is created for the next value in the iterable passed to the map method. The map method blocks until all values in the passed iterable have been processed and their threads returned.
import threading
class ThreadPool():
def __init__(self, processes=20):
self.processes = processes
self.threads = [Thread() for _ in range(0, processes)]
def get_dead_threads(self):
dead = []
for thread in self.threads:
if not thread.is_alive():
dead.append(thread)
return dead
def is_thread_running(self):
return len(self.get_dead_threads()) < self.processes
def map(self, func, values):
attempted_count = 0
values_iter = iter(values)
# loop until all values have been attempted to be processed and
# all threads are finished running
while (attempted_count < len(values) or self.is_thread_running()):
for thread in self.get_dead_threads():
try:
# run thread with the next value
value = next(values_iter)
attempted_count += 1
thread.run(func, value)
except StopIteration:
break
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, exc_tb):
pass
class Thread():
def __init__(self):
self.thread = None
def run(self, target, *args, **kwargs):
self.thread = threading.Thread(target=target,
args=args,
kwargs=kwargs)
self.thread.start()
def is_alive(self):
if self.thread:
return self.thread.is_alive()
else:
return False
You can use it like this:
def run_job(self, value, mp_queue=None):
# do something with value
value += 1
with ThreadPool(processes=2) as pool:
pool.map(run_job, [1, 2, 3, 4, 5])

Related

Python dynamic MultiThread with Queue - Class

I have been struggling to implement a proper dynamic multi-thread system until now. The idea is to spin up multiple new pools of sub-threads from the main (each pool have its own number of threads and queue size) to run functions and the user can define if the main should wait for the sub-thread to finish up or just move to the next line after starting the thread. This multi-thread logic will help to extract data in parallel and at a fast frequency.
The solution to my issue is shared below for everyone who wants it. If you have any doubts and questions, please let me know.
# -*- coding: utf-8 -*-
"""
Created on Mon Jul 5 00:00:51 2021
#author: Tahasanul Abraham
"""
#%% Initialization of Libraries
import sys, os, inspect
currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0,parentdir)
parentdir_1up = os.path.dirname(parentdir)
sys.path.insert(0,parentdir_1up)
from queue import Queue
from threading import Thread, Lock
class Worker(Thread):
def __init__(self, tasks):
Thread.__init__(self)
self.tasks = tasks
self.daemon = True
self.lock = Lock()
self.start()
def run(self):
while True:
func, args, kargs = self.tasks.get()
try:
if func.lower() == "terminate":
break
except:
try:
with self.lock:
func(*args, **kargs)
except Exception as exception:
print(exception)
self.tasks.task_done()
class ThreadPool:
def __init__(self, num_threads, num_queue=None):
if num_queue is None or num_queue < num_threads:
num_queue = num_threads
self.tasks = Queue(num_queue)
self.threads = num_threads
for _ in range(num_threads): Worker(self.tasks)
# This function can be called to terminate all the worker threads of the queue
def terminate(self):
self.wait_completion()
for _ in range(self.threads): self.add_task("terminate")
return None
# This function can be called to add new work to the queue
def add_task(self, func, *args, **kargs):
self.tasks.put((func, args, kargs))
# This function can be called to wait till all the workers are done processing the pending works. If this function is called, the main will not process any new lines unless all the workers are done with the pending works.
def wait_completion(self):
self.tasks.join()
# This function can be called to check if there are any pending/running works in the queue. If there are any works pending, the call will return Boolean True or else it will return Boolean False
def is_alive(self):
if self.tasks.unfinished_tasks == 0:
return False
else:
return True
#%% Standalone Run
if __name__ == "__main__":
import time
def test_return(x,d):
print (str(x) + " - pool completed")
d[str(x)] = x
time.sleep(5)
# 2 thread and 10000000000 FIFO queues
pool = ThreadPool(2,1000000000)
r ={}
for i in range(10):
pool.add_task(test_return, i, r)
print (str(i) + " - pool added")
print ("Waiting for completion")
pool.wait_completion()
print ("pool done")
# 1 thread and 2 FIFO queues
pool = ThreadPool(1,2)
r ={}
for i in range(10):
pool.add_task(test_return, i, r)
print (str(i) + " - pool added")
print ("Waiting for completion")
pool.wait_completion()
print ("pool done")
# 2 thread and 1 FIFO queues
pool = ThreadPool(2,1)
r ={}
for i in range(10):
pool.add_task(test_return, i, r)
print (str(i) + " - pool added")
print ("Waiting for completion")
pool.wait_completion()
print ("pool done")
Making a new Pool
Using the above classes, one can make a pool of their own choise with the number of parallel threads they want and the size of the queue. Example of creating a pool of 10 threads with 200 queue size.
pool = ThreadPool(10,200)
Adding work to Pool
Once a pool is created, one can use that pool.add_task to do sub-routine works. In my example version i used the pool to call a function and its arguments. Example, I called the test_return fucntion with its arguments i and r.
pool.add_task(test_return, i, r)
Waiting for the pool to complete its work
If a pool is given some work to do, the user can either move to other code lines or wait for the pool to finish its work before the next lines ar being read. To wait for the pool to finish the work and then return back, a call for wait_completion is required. Example:
pool.wait_completion()
Terminate and close down the pool threads
Once the requirement of the pool threads are done, it is possible to terminate and close down the pool threads to save up memory and release the blocked threads. This can be done by calling the following function.
pool.terminate()
Checking if there are any pending works from the pool
There is a function that can be called to check if there are any pending/running works in the queue. If there are any works pending, the call will return Boolean True, or else it will return Boolean False. To check if the pool is working or not call the folling function.
pool.is_alive()

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

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

How can you code a nested concurrency in python?

My code has the following scheme:
class A():
def evaluate(self):
b = B()
for i in range(30):
b.run()
class B():
def run(self):
pass
if __name__ == '__main__':
a = A()
for i in range(10):
a.evaluate()
And I want to have two level of concurrency, the first one is on the evaluate method and the second one is on the run method (nested concurrency). The question is how to introduce this concurrency using the Pool class of the multiprocessing module? Should I pass explicitly number of cores?. The solution should not create processes greater than number of multiprocessing.cpu_count().
note: assume that number of cores is greater than 10 .
Edit:
I have seen a lot of comments that say that python does not have true concurrency due to GIL, this is true for python multi-threading but for multiprocessing this is not quit correct look here, also I have timed it also this article did, and the results show that it can go faster than sequential execution.
Your comment touches on a possible solution. In order to have "nested" concurrency you could have 2 separate pools. This would result in a "flat" structure program instead of a nest program. Additionally, it decouples A from B, A now knows nothing about b it just publishes to a generic queue. The example below uses a single process to illustrate wiring up concurrent workers communicating across an asynchronous queue but it could easily be replaced with a pool:
import multiprocessing as mp
class A():
def __init__(self, in_q, out_q):
self.in_q = in_q
self.out_q = out_q
def evaluate(self):
"""
Reads from input does work and process output
"""
while True:
job = self.in_q.get()
for i in range(30):
self.out_q.put(i)
class B():
def __init__(self, in_q):
self.in_q = in_q
def run(self):
"""
Loop over queue and process items, optionally configure
with another queue to "sink" the processing pipeline
"""
while True:
job = self.in_q.get()
if __name__ == '__main__':
# create the queues to wire up our concurrent worker pools
A_q = mp.Queue()
AB_q = mp.Queue()
a = A(in_q=A_q, out_q=AB_q)
b = B(in_q=AB_q)
p = mp.Process(target=a.evaluate)
p.start()
p2 = mp.Process(target=b.run)
p2.start()
for i in range(10):
A_q.put(i)
p.join()
p2.join()
This is a common pattern in golang.

Python 3 Limit count of active threads (finished threads do not quit)

I want to limit the number of active threads. What i have seen is, that a finished thread stays alive and does not exit itself, so the number of active threads keep growing until an error occours.
The following code starts only 8 threads at a time but they stay alive even when they finished. So the number keeps growing:
class ThreadEx(threading.Thread):
__thread_limiter = None
__max_threads = 2
#classmethod
def max_threads(cls, thread_max):
ThreadEx.__max_threads = thread_max
ThreadEx.__thread_limiter = threading.BoundedSemaphore(value=ThreadEx.__max_threads)
def __init__(self, target=None, args:tuple=()):
super().__init__(target=target, args=args)
if not ThreadEx.__thread_limiter:
ThreadEx.__thread_limiter = threading.BoundedSemaphore(value=ThreadEx.__max_threads)
def run(self):
ThreadEx.__thread_limiter.acquire()
try:
#success = self._target(*self._args)
#if success: return True
super().run()
except:
pass
finally:
ThreadEx.__thread_limiter.release()
def call_me(test1, test2):
print(test1 + test2)
time.sleep(1)
ThreadEx.max_threads(8)
for i in range(0, 99):
t = ThreadEx(target=call_me, args=("Thread count: ", str(threading.active_count())))
t.start()
Due to the for loop, the number of threads keep growing to 99.
I know that a thread has done its work because call_me has been executed and threading.active_count() was printed.
Does somebody know how i make sure, a finished thread does not stay alive?
This may be a silly answer but to me it looks you are trying to reinvent ThreadPool.
from multiprocessing.pool import ThreadPool
from time import sleep
p = ThreadPool(8)
def call_me(test1):
print(test1)
sleep(1)
for i in range(0, 99):
p.apply_async(call_me, args=(i,))
p.close()
p.join()
This will ensure only 8 concurrent threads are running your function at any point of time. And if you want a bit more performance, you can import Pool from multiprocessing and use that. The interface is exactly the same but your pool will now be subprocesses instead of threads, which usually gives a performance boost as GIL does not come in the way.
I have changed the class according to the help of Hannu.
I post it for reference, maybe it's useful for others that come across this post:
import threading
from multiprocessing.pool import ThreadPool
import time
class MultiThread():
__thread_pool = None
#classmethod
def begin(cls, max_threads):
MultiThread.__thread_pool = ThreadPool(max_threads)
#classmethod
def end(cls):
MultiThread.__thread_pool.close()
MultiThread.__thread_pool.join()
def __init__(self, target=None, args:tuple=()):
self.__target = target
self.__args = args
def run(self):
try:
result = MultiThread.__thread_pool.apply_async(self.__target, args=self.__args)
return result.get()
except:
pass
def call_me(test1, test2):
print(test1 + test2)
time.sleep(1)
return 0
MultiThread.begin(8)
for i in range(0, 99):
t = MultiThread(target=call_me, args=("Thread count: ", str(threading.active_count())))
t.run()
MultiThread.end()
The maximum of threads is 8 at any given time determined by the method begin.
And also the method run returns the result of your passed function if it returns something.
Hope that helps.

Thread Getting Stuck At Join

I'm running a thread pool that is giving a random bug. Sometimes it works, sometimes it gets stuck at the pool.join part of this code. I've been at this several days, yet cannot find any difference between when it works or when it gets stuck. Please help...
Here's the code...
def run_thread_pool(functions_list):
# Make the Pool of workers
pool = ThreadPool() # left blank to default to machine number of cores
pool.map(run_function, functions_list)
# close the pool and wait for the work to finish
pool.close()
pool.join()
return
Similarly, this code is also randomly getting stuck at q.join(:
def run_queue_block(methods_list, max_num_of_workers=20):
from views.console_output_handler import add_to_console_queue
'''
Runs methods on threads. Stores method returns in a list. Then outputs that list
after all methods in the list have been completed.
:param methods_list: example ((method name, args), (method_2, args), (method_3, args)
:param max_num_of_workers: The number of threads to use in the block.
:return: The full list of returns from each method.
'''
method_returns = []
log = StandardLogger(logger_name='run_queue_block')
# lock to serialize console output
lock = threading.Lock()
def _output(item):
# Make sure the whole print completes or threads can mix up output in one line.
with lock:
if item:
add_to_console_queue(item)
msg = threading.current_thread().name, item
log.log_debug(msg)
return
# The worker thread pulls an item from the queue and processes it
def _worker():
log = StandardLogger(logger_name='_worker')
while True:
try:
method, args = q.get() # Extract and unpack callable and arguments
except:
# we've hit a nonetype object.
break
if method is None:
break
item = method(*args) # Call callable with provided args and store result
method_returns.append(item)
_output(item)
q.task_done()
num_of_jobs = len(methods_list)
if num_of_jobs < max_num_of_workers:
max_num_of_workers = num_of_jobs
# Create the queue and thread pool.
q = Queue()
threads = []
# starts worker threads.
for i in range(max_num_of_workers):
t = threading.Thread(target=_worker)
t.daemon = True # thread dies when main thread (only non-daemon thread) exits.
t.start()
threads.append(t)
for method in methods_list:
q.put(method)
# block until all tasks are done
q.join()
# stop workers
for i in range(max_num_of_workers):
q.put(None)
for t in threads:
t.join()
return method_returns
I never know when it's going to work. It works most the time, but most the time is not good enough. What might possibly cause a bug like this?
You have to call shutdown on the concurrent.futures.ThreadPoolExecutor object. Then return the result of pool.map.
def run_thread_pool(functions_list):
# Make the Pool of workers
pool = ThreadPool() # left blank to default to machine number of cores
result = pool.map(run_function, functions_list)
# close the pool and wait for the work to finish
pool.shutdown()
return result
I've simplified your code without a Queue object and daemon Thread. Check if it fits your requirement.
def run_queue_block(methods_list):
from views.console_output_handler import add_to_console_queue
'''
Runs methods on threads. Stores method returns in a list. Then outputs that list
after all methods in the list have been completed.
:param methods_list: example ((method name, args), (method_2, args), (method_3, args)
:param max_num_of_workers: The number of threads to use in the block.
:return: The full list of returns from each method.
'''
method_returns = []
log = StandardLogger(logger_name='run_queue_block')
# lock to serialize console output
lock = threading.Lock()
def _output(item):
# Make sure the whole print completes or threads can mix up output in one line.
with lock:
if item:
add_to_console_queue(item)
msg = threading.current_thread().name, item
log.log_debug(msg)
return
# The worker thread pulls an item from the queue and processes it
def _worker(method, *args, **kwargs):
log = StandardLogger(logger_name='_worker')
item = method(*args, **kwargs) # Call callable with provided args and store result
with lock:
method_returns.append(item)
_output(item)
threads = []
# starts worker threads.
for method, args in methods_list:
t = threading.Thread(target=_worker, args=(method, args))
t.start()
threads.append(t)
# stop workers
for t in threads:
t.join()
return method_returns
To allow your queue to join in your second example, you need to ensure that all tasks are removed from the queue.
So in your _worker function, mark tasks as done even if they could not be processed, otherwise the queue will never be emptied, and your program will hang.
def _worker():
log = StandardLogger(logger_name='_worker')
while True:
try:
method, args = q.get() # Extract and unpack callable and arguments
except:
# we've hit a nonetype object.
q.task_done()
break
if method is None:
q.task_done()
break
item = method(*args) # Call callable with provided args and store result
method_returns.append(item)
_output(item)
q.task_done()

Categories

Resources