Here is my script. When I run it in a shell it just hangs indefinitely whereas I would expect it to terminate cleanly.
import logging
from logging import StreamHandler
import pymsteams
import queue
import threading
import atexit
class TeamsHandler(StreamHandler):
def __init__(self, channel_url):
super().__init__()
self.channel_url = channel_url
self.queue = queue.Queue()
self.thread = threading.Thread(target=self._worker)
self.thread.start()
atexit.register(self.queue.put, None)
def _worker(self):
while True:
record = self.queue.get()
if record is None:
break
msg = self.format(record)
print(msg)
def emit(self, record):
# enqueue the record to log and return control to the caller
self.queue.put(record)
if __name__ == "__main__":
my_logger = logging.getLogger('TestLogging')
my_logger.setLevel(logging.DEBUG)
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.DEBUG)
my_logger.addHandler(console_handler)
CHANNEL_ID = "not_used_anyway"
teamshandler = TeamsHandler(CHANNEL_ID)
teamshandler.setFormatter(logging.Formatter('%(levelname)s %(message)s'))
teamshandler.setLevel(logging.DEBUG)
my_logger.addHandler(teamshandler)
for i in range(1, 2):
my_logger.error(f"this is an error [{i}]")
my_logger.info(f"this is an info [{i}]")
The None record that should be sent by atexit (line 28) never arrives so the thread stays open forever.
How to make sure that the program exits cleanly by modifying the TeamsHandler only ?
I got something working, have a look:
import queue
import threading
class Worker:
def __init__(self):
self.queue = queue.Queue()
threading.Thread(target=self._worker).start()
def _worker(self):
print("starting thread")
while True:
record = self.queue.get()
if record is None:
print("exiting")
break
print(f"Got message: {record}")
def emit(self, record):
self.queue.put(record)
class Wrapper:
def __init__(self):
self._worker = Worker()
def __del__(self):
print("Wrapper is being deleted")
self._worker.emit(None)
def emit(self, record):
self._worker.emit(record)
def main():
worker = Wrapper()
worker.emit("foo")
worker.emit("bar")
print("main exits")
if __name__ == "__main__":
main()
The point here is that when main exits, worker (which is an instance of Wrapper) goes out of scope, and its __del__ method is called, and it sends stop message to a real worker object.
The results of running this code ("Got message" lines can be in different places, of course):
starting thread
main exits
Wrapper is being deleted
Got message: foo
Got message: bar
exiting
As pointed out by avysk, the problem is likely that atexit handlers fire too late, after the waiting for the non-daemon threads is already (supposed to be) done, which leads to deadlock.
If I were you, I'd just add a call like TeamsHandler.finish() at the end of if __name__ == '__main__' block, and modify TeamsHandler along these lines (untested):
_queues = []
class TeamsHandler(StreamHandler):
def __init__(self, channel_url):
super().__init__()
self.channel_url = channel_url
self.queue = queue.Queue()
self.thread = threading.Thread(target=self._worker)
self.thread.start()
_queues.append(self.queue)
def _worker(self):
while True:
record = self.queue.get()
if record is None:
break
msg = self.format(record)
print(msg)
def emit(self, record):
# enqueue the record to log and return control to the caller
self.queue.put(record)
#staticmethod
def finish(self):
for q in _queues:
q.put(None)
del _queues[:]
In Logging Cookbook I found Logging to a single file from multiple processes, I would like to use it with multiple modules, each module is a process, do you have any idea?
I used first code in the Logging to a single file from multiple processes.
Lets say the main in module, and worker_process in another, how to do that?
main.py:
def listener_configurer():
root = logging.getLogger()
h = logging.handlers.RotatingFileHandler('mptest.log', 'a', 300, 10)
f = logging.Formatter('%(asctime)s %(processName)-10s %(name)s %(levelname)-8s %(message)s')
h.setFormatter(f)
root.addHandler(h)
def listener_process(queue, configurer):
configurer()
while True:
try:
record = queue.get()
if record is None: # We send this as a sentinel to tell the listener to quit.
break
logger = logging.getLogger(record.name)
logger.handle(record) # No level or filter logic applied - just do it!
except Exception:
import sys, traceback
print('Whoops! Problem:', file=sys.stderr)
traceback.print_exc(file=sys.stderr)
def main():
queue = multiprocessing.Queue(-1)
listener = multiprocessing.Process(target=listener_process,
args=(queue, listener_configurer))
listener.start()
workers = []
for i in range(10):
worker = worker_process.TEST(queue)
workers.append(worker)
worker.start()
for w in workers:
w.join()
queue.put_nowait(None)
listener.join()
if __name__ == '__main__':
main()
worker_process.py
def worker_configurer(queue):
h = logging.handlers.QueueHandler(queue)
root = logging.getLogger()
root.addHandler(h)
root.setLevel(logging.DEBUG)
class TEST(multiprocessing.Process):
def __init__(self, queue, func=worker_configurer):
super(TEST, self).__init__()
self.queue = queue
self.func = func
self.LEVELS = [logging.DEBUG, logging.INFO, logging.WARNING,
logging.ERROR, logging.CRITICAL]
self.LOGGERS = ['a.b.c', 'd.e.f']
self.MESSAGES = [
'Random message #1',
'Random message #2',
'Random message #3',
]
def run(self):
self.func(self.queue)
name = multiprocessing.current_process().name
print('Worker started: %s' % name)
for i in range(10):
time.sleep(random())
logger = logging.getLogger(choice(self.LOGGERS))
level = choice(self.LEVELS)
message = choice(self.MESSAGES)
logger.log(level, message)
print('Worker finished: %s' % name)
This is not work correctly, I would like to use the code (first code) in the doc with multiple modules, as I mentioned before.
I have this code that should put an event in a queue each time an external program (TCPdump) creates a *.pcap file in my directory.
My problem is that I always get an empty queue, although I got the print from process() function.
What am I doing wrong? Is the queue correctly defined and shared between the two classes?
EDIT-----------------
I maybe understood why I got an empty queue, I think it is because I'm printing the queue that I initialized before it gets filled by Handler class.
I modified my code and created two processes that should consume the same queue, but now the execution stuck on queue.put() and the thread ReadPcapFiles() stop running.
Here the updated code:
import time
import pyshark
import concurrent.futures
import threading
import logging
from queue import Queue
from multiprocessing import Process
from watchdog.observers import Observer, api
from watchdog.events import PatternMatchingEventHandler
class Handler(PatternMatchingEventHandler):
patterns = ["*.pcap", "*.pcapng"]
def __init__(self, queue):
PatternMatchingEventHandler.__init__(self)
self.queue = queue
def process(self, event):
#print(f'event type: {event.event_type} path : {event.src_path}')
self.queue.put(event.src_path)
logging.info(f"Storing message: {self.queue.qsize()}")
print("Producer queue: ", list(self.queue.queue))
#self.queue.get()
def on_created(self, event):
self.process(event)
def StartWatcher(watchdogq, event):
path = 'C:\\...'
handler = Handler(watchdogq)
observer = Observer()
while not event.is_set():
observer.schedule(handler, path, recursive=False)
print("About to start observer")
observer.start()
try:
while True:
time.sleep(1)
except Exception as error:
observer.stop()
print("Error: " + str(error))
observer.join()
def ReadPcapFiles(consumerq, event):
while not event.is_set() or not consumerq.empty():
print("Consumer queue: ", consumerq.get())
#print("Consumer queue: ", list(consumerq.queue))
# pcapfile = pyshark.FileCapture(self.queue.get())
# for packet in pcapfile:
# countPacket +=1
if __name__ == '__main__':
format = "%(asctime)s: %(message)s"
logging.basicConfig(format=format, level=logging.INFO,datefmt="%H:%M:%S")
logging.getLogger().setLevel(logging.DEBUG)
queue = Queue()
event = threading.Event()
with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
executor.submit(StartWatcher,queue, event)
executor.submit(ReadPcapFiles,queue, event)
time.sleep(0.1)
logging.info("Main: about to set event")
event.set()
OLD CODE:
import time
from queue import Queue
from watchdog.observers import Observer
from watchdog.events import PatternMatchingEventHandler
class Handler(PatternMatchingEventHandler):
patterns = ["*.pcap", "*.pcapng"]
def __init__(self, queue):
PatternMatchingEventHandler.__init__(self)
self.queue = queue
def process(self, event):
print(f'event type: {event.event_type} path : {event.src_path}')
self.queue.put(event.src_path)
def on_created(self, event):
self.process(event)
class Watcher():
def __init__(self, path):
self.queue = Queue()
self.observer = Observer()
self.handler = Handler(self.queue)
self.path = path
def start(self):
self.observer.schedule(self.handler, self.path, recursive=True)
self.observer.start()
try:
while True:
time.sleep(1)
self.queue.get()
print(list(self.queue.queue))
except Exception as error:
self.observer.stop()
print("Error: " + str(error))
self.observer.join()
if __name__ == '__main__':
watcher = Watcher('C:\\...')
watcher.start()
This is working for me (I got the main idea from this answer, thanks!) but notice that I consider this a workaround, so if someone has a better solution to this or can better explain the reason of such behavior in Python, please do not hesitate to answer!
My guess is that I had two main problems:
- I was starting Watchdog process inside another thread (and that was blocking somehow my queue consuming thread).
- Python threading does not work really in parallel and therefore starting an independent process was necessary.
Here my code:
import time
import pyshark
import threading
import logging
import os
from queue import Queue
from multiprocessing import Process, Pool
from watchdog.observers import Observer, api
from watchdog.events import PatternMatchingEventHandler
from concurrent.futures import ThreadPoolExecutor
class Handler(PatternMatchingEventHandler):
patterns = ["*.pcap", "*.pcapng"]
def __init__(self, queue):
PatternMatchingEventHandler.__init__(self)
self.queue = queue
def process(self, event):
self.queue.put(event.src_path)
logging.info(f"Storing message: {self.queue.qsize()}")
print("Producer queue: ", list(self.queue.queue))
def on_created(self, event):
#wait that the transfer of the file is finished before processing it
file_size = -1
while file_size != os.path.getsize(event.src_path):
file_size = os.path.getsize(event.src_path)
time.sleep(1)
self.process(event)
def ConsumeQueue(consumerq):
while True:
if not consumerq.empty():
pool = Pool()
pool.apply_async(ReadPcapFiles, (consumerq.get(), ))
else:
time.sleep(1)
def ReadPcapFiles(get_event):
createdFile = get_event
print(f"This is my event in ReadPacapFile {createdFile}")
countPacket = 0
bandwidth = 0
pcapfile = pyshark.FileCapture(createdFile)
for packet in pcapfile:
countPacket +=1
bandwidth = bandwidth + int(packet.length)
print(f"Packet nr {countPacket}")
print(f"Byte per second {bandwidth}")
if __name__ == '__main__':
format = "%(asctime)s: %(message)s"
logging.basicConfig(format=format, level=logging.INFO,datefmt="%H:%M:%S")
logging.getLogger().setLevel(logging.DEBUG)
queue = Queue()
path = 'C:\\...'
worker = threading.Thread(target=ConsumeQueue, args=(queue, ), daemon=True)
print("About to start worker")
worker.start()
event_handler = Handler(queue)
observer = Observer()
observer.schedule(event_handler, path, recursive=False)
print("About to start observer")
observer.start()
try:
while True:
time.sleep(1)
except Exception as error:
observer.stop()
print("Error: " + str(error))
observer.join()
There is an excellent library which provides concurrent access to the items within that queue. The queue is also persistent[file based as well as database based], so if the program crashes, you can still consume events from the point where the program crashed.
persist-queue
I have a class MyLogger for sending messages to log server by using PUBhandler.
An exception gets raised when MyLogger is instanced in LogWorker.init() method (like version 1), however, it is ok if MyLogger is instanced in LogWorker.log_worker() method (version 2).
Any suggestions would be appreciated.
import logging
from multiprocessing import Process
import os
import random
import sys
import time
import zmq
from zmq.log.handlers import PUBHandler
class MyLogger(object):
''''''
def __init__(self, port, handler=None):
self.port = port
self.handler = handler or self._construct_sock_handler()
self.logger = logging.getLogger()
self.logger.setLevel(logging.INFO)
if not self.logger.handlers:
self.logger.addHandler(self.handler)
def _construct_sock_handler(self):
context = zmq.Context()
log_sock = context.socket(zmq.PUB)
log_sock.connect("tcp://127.0.0.1:%i" % self.port)
time.sleep(0.1)
handler = PUBHandler(log_sock)
return handler
def get_logger(self):
return self.logger
def sub_logger(port, level=logging.DEBUG):
ctx = zmq.Context()
sub = ctx.socket(zmq.SUB)
sub.bind('tcp://127.0.0.1:%i' % port)
sub.setsockopt(zmq.SUBSCRIBE, "")
logging.basicConfig(level=level)
while True:
level, message = sub.recv_multipart()
if message.endswith('\n'):
# trim trailing newline, which will get appended again
message = message[:-1]
log = getattr(logging, level.lower())
log(message)
class LogWorker(object):
def __init__(self):
- pass # version 1
+ self.logger = MyLogger(port).get_logger() # version 2
def log_worker(self, port):
- self.logger = MyLogger(port).get_logger() # version 1
print "starting logger at %i with level=%s" % (os.getpid(), logging.DEBUG)
while True:
level = logging.INFO
self.logger.log(level, "Hello from %i!" % os.getpid())
time.sleep(1)
if __name__ == '__main__':
if len(sys.argv) > 1:
n = int(sys.argv[1])
else:
n = 2
port = 5555
workers = [Process(target=LogWorker().log_worker, args=(port,)) for _ in range(n)]
[w.start() for w in workers]
try:
sub_logger(port)
except KeyboardInterrupt:
pass
finally:
[ w.terminate() for w in workers ]
answer from pyzmq owner minrk:
You cannot pass zmq contexts or sockets across the fork boundary that happens when you instantiate a subprocess with multiprocessing. You have to make sure that you create your Context after you are in the subprocess.
solution:
def work():
worker = LogWorker(port)
worker.log_worker()
workers = [ Process(target=work) for _ in range(n) ]
I'm having much trouble trying to understand just how the multiprocessing queue works on python and how to implement it. Lets say I have two python modules that access data from a shared file, let's call these two modules a writer and a reader. My plan is to have both the reader and writer put requests into two separate multiprocessing queues, and then have a third process pop these requests in a loop and execute as such.
My main problem is that I really don't know how to implement multiprocessing.queue correctly, you cannot really instantiate the object for each process since they will be separate queues, how do you make sure that all processes relate to a shared queue (or in this case, queues)
My main problem is that I really don't know how to implement multiprocessing.queue correctly, you cannot really instantiate the object for each process since they will be separate queues, how do you make sure that all processes relate to a shared queue (or in this case, queues)
This is a simple example of a reader and writer sharing a single queue... The writer sends a bunch of integers to the reader; when the writer runs out of numbers, it sends 'DONE', which lets the reader know to break out of the read loop.
You can spawn as many reader processes as you like...
from multiprocessing import Process, Queue
import time
import sys
def reader_proc(queue):
"""Read from the queue; this spawns as a separate Process"""
while True:
msg = queue.get() # Read from the queue and do nothing
if msg == "DONE":
break
def writer(count, num_of_reader_procs, queue):
"""Write integers into the queue. A reader_proc() will read them from the queue"""
for ii in range(0, count):
queue.put(ii) # Put 'count' numbers into queue
### Tell all readers to stop...
for ii in range(0, num_of_reader_procs):
queue.put("DONE")
def start_reader_procs(qq, num_of_reader_procs):
"""Start the reader processes and return all in a list to the caller"""
all_reader_procs = list()
for ii in range(0, num_of_reader_procs):
### reader_p() reads from qq as a separate process...
### you can spawn as many reader_p() as you like
### however, there is usually a point of diminishing returns
reader_p = Process(target=reader_proc, args=((qq),))
reader_p.daemon = True
reader_p.start() # Launch reader_p() as another proc
all_reader_procs.append(reader_p)
return all_reader_procs
if __name__ == "__main__":
num_of_reader_procs = 2
qq = Queue() # writer() writes to qq from _this_ process
for count in [10**4, 10**5, 10**6]:
assert 0 < num_of_reader_procs < 4
all_reader_procs = start_reader_procs(qq, num_of_reader_procs)
writer(count, len(all_reader_procs), qq) # Queue stuff to all reader_p()
print("All reader processes are pulling numbers from the queue...")
_start = time.time()
for idx, a_reader_proc in enumerate(all_reader_procs):
print(" Waiting for reader_p.join() index %s" % idx)
a_reader_proc.join() # Wait for a_reader_proc() to finish
print(" reader_p() idx:%s is done" % idx)
print(
"Sending {0} integers through Queue() took {1} seconds".format(
count, (time.time() - _start)
)
)
print("")
Here's a dead simple usage of multiprocessing.Queue and multiprocessing.Process that allows callers to send an "event" plus arguments to a separate process that dispatches the event to a "do_" method on the process. (Python 3.4+)
import multiprocessing as mp
import collections
Msg = collections.namedtuple('Msg', ['event', 'args'])
class BaseProcess(mp.Process):
"""A process backed by an internal queue for simple one-way message passing.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.queue = mp.Queue()
def send(self, event, *args):
"""Puts the event and args as a `Msg` on the queue
"""
msg = Msg(event, args)
self.queue.put(msg)
def dispatch(self, msg):
event, args = msg
handler = getattr(self, "do_%s" % event, None)
if not handler:
raise NotImplementedError("Process has no handler for [%s]" % event)
handler(*args)
def run(self):
while True:
msg = self.queue.get()
self.dispatch(msg)
Usage:
class MyProcess(BaseProcess):
def do_helloworld(self, arg1, arg2):
print(arg1, arg2)
if __name__ == "__main__":
process = MyProcess()
process.start()
process.send('helloworld', 'hello', 'world')
The send happens in the parent process, the do_* happens in the child process.
I left out any exception handling that would obviously interrupt the run loop and exit the child process. You can also customize it by overriding run to control blocking or whatever else.
This is really only useful in situations where you have a single worker process, but I think it's a relevant answer to this question to demonstrate a common scenario with a little more object-orientation.
I had a look at multiple answers across stack overflow and the web while trying to set-up a way of doing multiprocessing using queues for passing around large pandas dataframes. It seemed to me that every answer was re-iterating the same kind of solutions without any consideration of the multitude of edge cases one will definitely come across when setting up calculations like these. The problem is that there is many things at play at the same time. The number of tasks, the number of workers, the duration of each task and possible exceptions during task execution. All of these make synchronization tricky and most answers do not address how you can go about it. So this is my take after fiddling around for a few hours, hopefully this will be generic enough for most people to find it useful.
Some thoughts before any coding examples. Since queue.Empty or queue.qsize() or any other similar method is unreliable for flow control, any code of the like
while True:
try:
task = pending_queue.get_nowait()
except queue.Empty:
break
is bogus. This will kill the worker even if milliseconds later another task turns up in the queue. The worker will not recover and after a while ALL the workers will disappear as they randomly find the queue momentarily empty. The end result will be that the main multiprocessing function (the one with the join() on the processes) will return without all the tasks having completed. Nice. Good luck debugging through that if you have thousands of tasks and a few are missing.
The other issue is the use of sentinel values. Many people have suggested adding a sentinel value in the queue to flag the end of the queue. But to flag it to whom exactly? If there is N workers, assuming N is the number of cores available give or take, then a single sentinel value will only flag the end of the queue to one worker. All the other workers will sit waiting for more work when there is none left. Typical examples I've seen are
while True:
task = pending_queue.get()
if task == SOME_SENTINEL_VALUE:
break
One worker will get the sentinel value while the rest will wait indefinitely. No post I came across mentioned that you need to submit the sentinel value to the queue AT LEAST as many times as you have workers so that ALL of them get it.
The other issue is the handling of exceptions during task execution. Again these should be caught and managed. Moreover, if you have a completed_tasks queue you should independently count in a deterministic way how many items are in the queue before you decide that the job is done. Again relying on queue sizes is bound to fail and returns unexpected results.
In the example below, the par_proc() function will receive a list of tasks including the functions with which these tasks should be executed alongside any named arguments and values.
import multiprocessing as mp
import dill as pickle
import queue
import time
import psutil
SENTINEL = None
def do_work(tasks_pending, tasks_completed):
# Get the current worker's name
worker_name = mp.current_process().name
while True:
try:
task = tasks_pending.get_nowait()
except queue.Empty:
print(worker_name + ' found an empty queue. Sleeping for a while before checking again...')
time.sleep(0.01)
else:
try:
if task == SENTINEL:
print(worker_name + ' no more work left to be done. Exiting...')
break
print(worker_name + ' received some work... ')
time_start = time.perf_counter()
work_func = pickle.loads(task['func'])
result = work_func(**task['task'])
tasks_completed.put({work_func.__name__: result})
time_end = time.perf_counter() - time_start
print(worker_name + ' done in {} seconds'.format(round(time_end, 5)))
except Exception as e:
print(worker_name + ' task failed. ' + str(e))
tasks_completed.put({work_func.__name__: None})
def par_proc(job_list, num_cpus=None):
# Get the number of cores
if not num_cpus:
num_cpus = psutil.cpu_count(logical=False)
print('* Parallel processing')
print('* Running on {} cores'.format(num_cpus))
# Set-up the queues for sending and receiving data to/from the workers
tasks_pending = mp.Queue()
tasks_completed = mp.Queue()
# Gather processes and results here
processes = []
results = []
# Count tasks
num_tasks = 0
# Add the tasks to the queue
for job in job_list:
for task in job['tasks']:
expanded_job = {}
num_tasks = num_tasks + 1
expanded_job.update({'func': pickle.dumps(job['func'])})
expanded_job.update({'task': task})
tasks_pending.put(expanded_job)
# Use as many workers as there are cores (usually chokes the system so better use less)
num_workers = num_cpus
# We need as many sentinels as there are worker processes so that ALL processes exit when there is no more
# work left to be done.
for c in range(num_workers):
tasks_pending.put(SENTINEL)
print('* Number of tasks: {}'.format(num_tasks))
# Set-up and start the workers
for c in range(num_workers):
p = mp.Process(target=do_work, args=(tasks_pending, tasks_completed))
p.name = 'worker' + str(c)
processes.append(p)
p.start()
# Gather the results
completed_tasks_counter = 0
while completed_tasks_counter < num_tasks:
results.append(tasks_completed.get())
completed_tasks_counter = completed_tasks_counter + 1
for p in processes:
p.join()
return results
And here is a test to run the above code against
def test_parallel_processing():
def heavy_duty1(arg1, arg2, arg3):
return arg1 + arg2 + arg3
def heavy_duty2(arg1, arg2, arg3):
return arg1 * arg2 * arg3
task_list = [
{'func': heavy_duty1, 'tasks': [{'arg1': 1, 'arg2': 2, 'arg3': 3}, {'arg1': 1, 'arg2': 3, 'arg3': 5}]},
{'func': heavy_duty2, 'tasks': [{'arg1': 1, 'arg2': 2, 'arg3': 3}, {'arg1': 1, 'arg2': 3, 'arg3': 5}]},
]
results = par_proc(task_list)
job1 = sum([y for x in results if 'heavy_duty1' in x.keys() for y in list(x.values())])
job2 = sum([y for x in results if 'heavy_duty2' in x.keys() for y in list(x.values())])
assert job1 == 15
assert job2 == 21
plus another one with some exceptions
def test_parallel_processing_exceptions():
def heavy_duty1_raises(arg1, arg2, arg3):
raise ValueError('Exception raised')
return arg1 + arg2 + arg3
def heavy_duty2(arg1, arg2, arg3):
return arg1 * arg2 * arg3
task_list = [
{'func': heavy_duty1_raises, 'tasks': [{'arg1': 1, 'arg2': 2, 'arg3': 3}, {'arg1': 1, 'arg2': 3, 'arg3': 5}]},
{'func': heavy_duty2, 'tasks': [{'arg1': 1, 'arg2': 2, 'arg3': 3}, {'arg1': 1, 'arg2': 3, 'arg3': 5}]},
]
results = par_proc(task_list)
job1 = sum([y for x in results if 'heavy_duty1' in x.keys() for y in list(x.values())])
job2 = sum([y for x in results if 'heavy_duty2' in x.keys() for y in list(x.values())])
assert not job1
assert job2 == 21
Hope that is helpful.
in "from queue import Queue" there is no module called queue, instead multiprocessing should be used. Therefore, it should look like "from multiprocessing import Queue"
Just made a simple and general example for demonstrating passing a message over a Queue between 2 standalone programs. It doesn't directly answer the OP's question but should be clear enough indicating the concept.
Server:
multiprocessing-queue-manager-server.py
import asyncio
import concurrent.futures
import multiprocessing
import multiprocessing.managers
import queue
import sys
import threading
from typing import Any, AnyStr, Dict, Union
class QueueManager(multiprocessing.managers.BaseManager):
def get_queue(self, ident: Union[AnyStr, int, type(None)] = None) -> multiprocessing.Queue:
pass
def get_queue(ident: Union[AnyStr, int, type(None)] = None) -> multiprocessing.Queue:
global q
if not ident in q:
q[ident] = multiprocessing.Queue()
return q[ident]
q: Dict[Union[AnyStr, int, type(None)], multiprocessing.Queue] = dict()
delattr(QueueManager, 'get_queue')
def init_queue_manager_server():
if not hasattr(QueueManager, 'get_queue'):
QueueManager.register('get_queue', get_queue)
def serve(no: int, term_ev: threading.Event):
manager: QueueManager
with QueueManager(authkey=QueueManager.__name__.encode()) as manager:
print(f"Server address {no}: {manager.address}")
while not term_ev.is_set():
try:
item: Any = manager.get_queue().get(timeout=0.1)
print(f"Client {no}: {item} from {manager.address}")
except queue.Empty:
continue
async def main(n: int):
init_queue_manager_server()
term_ev: threading.Event = threading.Event()
executor: concurrent.futures.ThreadPoolExecutor = concurrent.futures.ThreadPoolExecutor()
i: int
for i in range(n):
asyncio.ensure_future(asyncio.get_running_loop().run_in_executor(executor, serve, i, term_ev))
# Gracefully shut down
try:
await asyncio.get_running_loop().create_future()
except asyncio.CancelledError:
term_ev.set()
executor.shutdown()
raise
if __name__ == '__main__':
asyncio.run(main(int(sys.argv[1])))
Client:
multiprocessing-queue-manager-client.py
import multiprocessing
import multiprocessing.managers
import os
import sys
from typing import AnyStr, Union
class QueueManager(multiprocessing.managers.BaseManager):
def get_queue(self, ident: Union[AnyStr, int, type(None)] = None) -> multiprocessing.Queue:
pass
delattr(QueueManager, 'get_queue')
def init_queue_manager_client():
if not hasattr(QueueManager, 'get_queue'):
QueueManager.register('get_queue')
def main():
init_queue_manager_client()
manager: QueueManager = QueueManager(sys.argv[1], authkey=QueueManager.__name__.encode())
manager.connect()
message = f"A message from {os.getpid()}"
print(f"Message to send: {message}")
manager.get_queue().put(message)
if __name__ == '__main__':
main()
Usage
Server:
$ python3 multiprocessing-queue-manager-server.py N
N is a integer indicating how many servers should be created. Copy one of the <server-address-N> output by the server and make it the first argument of each multiprocessing-queue-manager-client.py.
Client:
python3 multiprocessing-queue-manager-client.py <server-address-1>
Result
Server:
Client 1: <item> from <server-address-1>
Gist: https://gist.github.com/89062d639e40110c61c2f88018a8b0e5
UPD: Created a package here.
Server:
import ipcq
with ipcq.QueueManagerServer(address=ipcq.Address.AUTO, authkey=ipcq.AuthKey.AUTO) as server:
server.get_queue().get()
Client:
import ipcq
client = ipcq.QueueManagerClient(address=ipcq.Address.AUTO, authkey=ipcq.AuthKey.AUTO)
client.get_queue().put('a message')
We implemented two versions of this, one a simple multi thread pool that can execute many types of callables, making our lives much easier and the second version that uses processes, which is less flexible in terms of callables and requires and extra call to dill.
Setting frozen_pool to true will freeze execution until finish_pool_queue is called in either class.
Thread Version:
'''
Created on Nov 4, 2019
#author: Kevin
'''
from threading import Lock, Thread
from Queue import Queue
import traceback
from helium.loaders.loader_retailers import print_info
from time import sleep
import signal
import os
class ThreadPool(object):
def __init__(self, queue_threads, *args, **kwargs):
self.frozen_pool = kwargs.get('frozen_pool', False)
self.print_queue = kwargs.get('print_queue', True)
self.pool_results = []
self.lock = Lock()
self.queue_threads = queue_threads
self.queue = Queue()
self.threads = []
for i in range(self.queue_threads):
t = Thread(target=self.make_pool_call)
t.daemon = True
t.start()
self.threads.append(t)
def make_pool_call(self):
while True:
if self.frozen_pool:
#print '--> Queue is frozen'
sleep(1)
continue
item = self.queue.get()
if item is None:
break
call = item.get('call', None)
args = item.get('args', [])
kwargs = item.get('kwargs', {})
keep_results = item.get('keep_results', False)
try:
result = call(*args, **kwargs)
if keep_results:
self.lock.acquire()
self.pool_results.append((item, result))
self.lock.release()
except Exception as e:
self.lock.acquire()
print e
traceback.print_exc()
self.lock.release()
os.kill(os.getpid(), signal.SIGUSR1)
self.queue.task_done()
def finish_pool_queue(self):
self.frozen_pool = False
while self.queue.unfinished_tasks > 0:
if self.print_queue:
print_info('--> Thread pool... %s' % self.queue.unfinished_tasks)
sleep(5)
self.queue.join()
for i in range(self.queue_threads):
self.queue.put(None)
for t in self.threads:
t.join()
del self.threads[:]
def get_pool_results(self):
return self.pool_results
def clear_pool_results(self):
del self.pool_results[:]
Process Version:
'''
Created on Nov 4, 2019
#author: Kevin
'''
import traceback
from helium.loaders.loader_retailers import print_info
from time import sleep
import signal
import os
from multiprocessing import Queue, Process, Value, Array, JoinableQueue, Lock,\
RawArray, Manager
from dill import dill
import ctypes
from helium.misc.utils import ignore_exception
from mem_top import mem_top
import gc
class ProcessPool(object):
def __init__(self, queue_processes, *args, **kwargs):
self.frozen_pool = Value(ctypes.c_bool, kwargs.get('frozen_pool', False))
self.print_queue = kwargs.get('print_queue', True)
self.manager = Manager()
self.pool_results = self.manager.list()
self.queue_processes = queue_processes
self.queue = JoinableQueue()
self.processes = []
for i in range(self.queue_processes):
p = Process(target=self.make_pool_call)
p.start()
self.processes.append(p)
print 'Processes', self.queue_processes
def make_pool_call(self):
while True:
if self.frozen_pool.value:
sleep(1)
continue
item_pickled = self.queue.get()
if item_pickled is None:
#print '--> Ending'
self.queue.task_done()
break
item = dill.loads(item_pickled)
call = item.get('call', None)
args = item.get('args', [])
kwargs = item.get('kwargs', {})
keep_results = item.get('keep_results', False)
try:
result = call(*args, **kwargs)
if keep_results:
self.pool_results.append(dill.dumps((item, result)))
else:
del call, args, kwargs, keep_results, item, result
except Exception as e:
print e
traceback.print_exc()
os.kill(os.getpid(), signal.SIGUSR1)
self.queue.task_done()
def finish_pool_queue(self, callable=None):
self.frozen_pool.value = False
while self.queue._unfinished_tasks.get_value() > 0:
if self.print_queue:
print_info('--> Process pool... %s' % (self.queue._unfinished_tasks.get_value()))
if callable:
callable()
sleep(5)
for i in range(self.queue_processes):
self.queue.put(None)
self.queue.join()
self.queue.close()
for p in self.processes:
with ignore_exception: p.join(10)
with ignore_exception: p.terminate()
with ignore_exception: del self.processes[:]
def get_pool_results(self):
return self.pool_results
def clear_pool_results(self):
del self.pool_results[:]
def test(eg):
print 'EG', eg
Call with either:
tp = ThreadPool(queue_threads=2)
tp.queue.put({'call': test, 'args': [random.randint(0, 100)]})
tp.finish_pool_queue()
or
pp = ProcessPool(queue_processes=2)
pp.queue.put(dill.dumps({'call': test, 'args': [random.randint(0, 100)]}))
pp.queue.put(dill.dumps({'call': test, 'args': [random.randint(0, 100)]}))
pp.finish_pool_queue()
A multi-producers and multi-consumers example, verified. It should be easy to modify it to cover other cases, single/multi producers, single/multi consumers.
from multiprocessing import Process, JoinableQueue
import time
import os
q = JoinableQueue()
def producer():
for item in range(30):
time.sleep(2)
q.put(item)
pid = os.getpid()
print(f'producer {pid} done')
def worker():
while True:
item = q.get()
pid = os.getpid()
print(f'pid {pid} Working on {item}')
print(f'pid {pid} Finished {item}')
q.task_done()
for i in range(5):
p = Process(target=worker, daemon=True).start()
# send thirty task requests to the worker
producers = []
for i in range(2):
p = Process(target=producer)
producers.append(p)
p.start()
# make sure producers done
for p in producers:
p.join()
# block until all workers are done
q.join()
print('All work completed')
Explanation:
Two producers and five consumers in this example.
JoinableQueue is used to make sure all elements stored in queue will be processed. 'task_done' is for worker to notify an element is done. 'q.join()' will wait for all elements marked as done.
With #2, there is no need to join wait for every worker.
But it is important to join wait for every producer to store element into queue. Otherwise, program exit immediately.