I want to start the ActorCore method in a seperte process and then process messages that come to that ActorCore. For some reason this code is not working.
import queue
from multiprocessing import Process
class NotMessage(Exception):
def __str__(self):
return 'NotMessage exception'
class Message(object):
def Do(self, Actor):
# Do some stuff to the actor
pass
def __str__(self):
return 'Generic message'
class StopMessage(Message):
def Do(self, Actor):
Actor.__stopped = True
def __str__(self):
return 'Stop message'
class Actor(object):
__DebugName = ''
__MsgQ = None
__stopped = False
def __init__(self, Name):
self.__DebugName = Name
self.__MsgQ = queue.Queue()
def LaunchActor(self):
p = Process(target=self.ActorCore)
p.start()
return self.__MsgQ
def ActorCore(self):
while not self.__stopped:
Msg = self.__MsgQ.get(block=True)
try:
Msg.Do(self)
print(Msg)
except NotMessage as e:
print(str(e), ' occurred in ', self.__DebugName)
def main():
joe = Actor('Joe')
msg = Message()
stop = StopMessage()
qToJoe = joe.LaunchActor()
qToJoe.put(msg)
qToJoe.put(msg)
qToJoe.put(stop)
if __name__ == '__main__':
main()
I am getting weird error when running:
Traceback (most recent call last):
File "C:/Users/plkruczp/PycharmProjects/ActorFramework/Actor/Actor.py", line 64, in <module>
main()
File "C:/Users/plkruczp/PycharmProjects/ActorFramework/Actor/Actor.py", line 58, in main
qToJoe = joe.LaunchActor()
File "C:/Users/plkruczp/PycharmProjects/ActorFramework/Actor/Actor.py", line 40, in LaunchActor
p.start()
File "C:\Program Files\Python35\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\Program Files\Python35\lib\multiprocessing\context.py", line 212, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Program Files\Python35\lib\multiprocessing\context.py", line 313, in _Popen
return Popen(process_obj)
File "C:\Program Files\Python35\lib\multiprocessing\popen_spawn_win32.py", line 66, in __init__
reduction.dump(process_obj, to_child)
File "C:\Program Files\Python35\lib\multiprocessing\reduction.py", line 59, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: can't pickle _thread.lock objects
Help please! I tried everything :(
Just use Queue instead of queue:
Remove import queue and add Queue to from multiprocessing like:
from multiprocessing import Process,Queue
then change self.__MsgQ = queue.Queue() to self.__MsgQ = Queue()
That's all you need to do to get it to work, the rest is the same for your case.
Edit, explanation:
queue.Queue is only thread-safe, and multiprocessing does actually spawn another process. Because of that, the additional multiprocessing.Queue is implemented to be also process-safe. As another option, if multithreading is wanted, the threading library can be used together with queue.Queue: https://docs.python.org/dev/library/threading.html#module-threading
Additional information:
Another parallelization option, depending on your further requirements is joblib, where the spawning can be defined to be either a process or a thread: https://joblib.readthedocs.io/
Related
I want to create a class Storage where each object has a dictionary orderbooks as a property.
I want to write on orderbooks from the main process by invoking the method write, but I want to defer this action to another process and ensuring that the dictionary orderbooks is accessible from the main process.
To do so, I create a Mananger() that I pass during the definition of the object and that is used to notify the processes about the changes of the dictionary. My code is the following:
from multiprocessing import Process, Manager
class Storage():
def __init__(self,manager):
self.manager = manager
self.orderbooks = self.manager.dict()
def store_value(self,el):
self.orderbooks[el[0]] = el[1]
def write(self,el:list):
p = Process(target=self.store_value,args=(el,))
p.start()
if __name__ == '__main__':
manager=Manager()
book1 = Storage(manager)
book1.write([0,1])
However, when I run this code, I get the following error
Traceback (most recent call last):
File "/Users/main_user/PycharmProjects/handle_queue/main.py", line 21, in <module>
book1.write([0,1])
File "/Users/main_user/PycharmProjects/handle_queue/main.py", line 13, in write
p.start()
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/popen_spawn_posix.py", line 47, in _launch
reduction.dump(process_obj, fp)
File "/Users/main_user/opt/anaconda3/envs/handle_queue/lib/python3.10/multiprocessing/reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot pickle 'weakref' object
What is wrong with my code?
Per Aaron's posted comment:
from multiprocessing import Process, Manager
class Storage():
def __init__(self, orderbooks):
self.orderbooks = orderbooks
def store_value(self, el):
self.orderbooks[el[0]] = el[1]
def write(self, el: list):
p = Process(target=self.store_value, args=(el,))
p.start()
# Ensure we do not return until store_value has
# completed updating the dictionary:
p.join()
if __name__ == '__main__':
manager = Manager()
orderbooks = manager.dict()
book1 = Storage(orderbooks)
book1.write([0, 1])
print(orderbooks)
Prints:
{0: 1}
I'm trying to decrease running time by using multiprocessing.
I got a weird error TypeError: cannot pickle 'weakref' object
I'm not quite sure why this error occurs because I also use this approach to run another program but it run normally. Can someone explain why this error occurs.
I already follow this Solution but it did not work for me.
import multiprocessing
from scipy import stats
import numpy as np
import pandas as pd
class T_TestFeature:
def __init__(self, data, classes):
self.data = data
self.classes = classes
self.manager = multiprocessing.Manager()
self.pval = self.manager.list()
def preform(self):
process = []
for i in range(10):
process.append(multiprocessing.Process(target=self.t_test, args=(i,)))
for p in process:
p.start()
for p in process:
p.join()
def t_test(self, k):
index_samples = np.array(self.data)[:,k]
rs1 = [index_samples[i] for i in range(len(index_samples)) if self.classes[i] == "Virginia"]
rs2 = [index_samples[i] for i in range(len(index_samples)) if self.classes[i] != "Virginia"]
self.pval.append(stats.ttest_ind(rs1, rs2, equal_var=False).pvalue)
def main():
df = pd.read_excel("/Users/xxx/Documents/Project/src/flattened.xlsx")
flattened = df.values.T
y = df.columns
result = T_TestFeature(flattened, y)
result.preform()
print(result.pval)
if __name__ == "__main__":
main()
Traceback (most recent call last):
File "/Users/xxx/Documents/Project/src/t_test.py", line 41, in <module>
main()
File "/Users/xxx/Documents/Project/src/t_test.py", line 37, in main
result.preform()
File "/Users/xxx/Documents/Project/src/t_test.py", line 21, in preform
p.start()
File "/Users/xxx/opt/anaconda3/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/Users/xxx/opt/anaconda3/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/Users/xxx/opt/anaconda3/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/Users/xxx/opt/anaconda3/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/Users/x/opt/anaconda3/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 47, in _xxlaunch
reduction.dump(process_obj, fp)
File "/Users/xxx/opt/anaconda3/lib/python3.9/multiprocessing/reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot pickle 'weakref' object
Here is a simpler way to reproduce your issue:
from multiprocessing import Manager, Process
class A:
def __init__(self):
self.manager = Manager()
def start(self):
print("started")
if __name__ == "__main__":
a = A()
proc = Process(target=a.start)
proc.start()
proc.join()
You cannot pickle instances containing manager objects, because they contain reference to the manager process they started (therefore, in general you can't pickle instances containing objects of class Process).
A simple fix would be to not store the manager. It will automatically be garbage collected once no references to the managed list remains:
def __init__(self, data, classes):
self.data = data
self.classes = classes
manager = multiprocessing.Manager()
self.pval = manager.list()
I have looked at this question to get started and it works just fine How can I recover the return value of a function passed to multiprocessing.Process?
But in my case I would like to write a small tool, that would connect to many computers and gather some statistics, each stat would be gathered within a Process to make it snappy. But as soon as I try to wrap up the multiprocessing command in a class for a machine then it fails.
Here is my code
import multiprocessing
import pprint
def run_task(command):
p = subprocess.Popen(command, stdout = subprocess.PIPE, universal_newlines = True, shell = False)
result = p.communicate()[0]
return result
MACHINE_NAME = "cptr_name"
A_STAT = "some_stats_A"
B_STAT = "some_stats_B"
class MachineStatsGatherer():
def __init__(self, machineName):
self.machineName = machineName
manager = multiprocessing.Manager()
self.localStats = manager.dict() # creating a shared ressource for the sub processes to use
self.localStats[MACHINE_NAME] = machineName
def gatherStats(self):
self.runInParallel(
self.GatherSomeStatsA,
self.GatherSomeStatsB,
)
self.printStats()
def printStats(self):
pprint.pprint(self.localStats)
def runInParallel(self, *fns):
processes = []
for fn in fns:
process = multiprocessing.Process(target=fn, args=(self.localStats))
processes.append(process)
process.start()
for process in processes:
process.join()
def GatherSomeStatsA(self, returnStats):
# do some remote command, simplified here for the sake of debugging
result = "Windows"
returnStats[A_STAT] = result.find("Windows") != -1
def GatherSomeStatsB(self, returnStats):
# do some remote command, simplified here for the sake of debugging
result = "Windows"
returnStats[B_STAT] = result.find("Windows") != -1
def main():
machine = MachineStatsGatherer("SOMEMACHINENAME")
machine.gatherStats()
return
if __name__ == '__main__':
main()
And here is the error message
Traceback (most recent call last):
File "C:\Users\mesirard\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 297, in _bootstrap
self.run()
File "C:\Users\mesirard\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "d:\workdir\trunks6\Tools\VTKAppTester\Utils\NXMachineMonitorShared.py", line 45, in GatherSomeStatsA
returnStats[A_STAT] = result.find("Windows") != -1
TypeError: 'str' object does not support item assignment
Process Process-3:
Traceback (most recent call last):
File "C:\Users\mesirard\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 297, in _bootstrap
self.run()
File "C:\Users\mesirard\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "d:\workdir\trunks6\Tools\VTKAppTester\Utils\NXMachineMonitorShared.py", line 50, in GatherSomeStatsB
returnStats[B_STAT] = result.find("Windows") != -1
TypeError: 'str' object does not support item assignment
The issue is coming from this line
process = multiprocessing.Process(target=fn, args=(self.localStats))
it should have a extra comma at the end of args like so
process = multiprocessing.Process(target=fn, args=(self.localStats,))
I wrote the code below:
import random, time, queue
from multiprocessing.managers import BaseManager
task_queue = queue.Queue()
result_queue = queue.Queue()
class QueueManager(BaseManager):
pass
QueueManager.register('get_task_queue', callable=lambda: task_queue)
QueueManager.register('get_result_queue', callable=lambda: result_queue)
manager = QueueManager(address=('', 5000), authkey=b'abd')
manager.start()
task = manager.get_task_queue()
result = manager.get_result_queue()
for i in range(10):
n = random.randint(0, 10000)
print('Put task %d...' % n)
task.put(n)
print('Try get result...')
for i in range(10):
r = result.get(timeout=10)
print('Result: %s' % r)
manager.shutdown()
print('master exit.')
but when it runs, I receive this error:
Traceback (most recent call last):
File "D:/PycharmProjects/test/task_master.py", line 23, in <module>
manager.start()
File "C:\Users\tang_ke\AppData\Local\Programs\Python\Python35-32\lib\multiprocessing\managers.py", line 479, in start
self._process.start()
File "C:\Users\tang_ke\AppData\Local\Programs\Python\Python35-32\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\Users\tang_ke\AppData\Local\Programs\Python\Python35-32\lib\multiprocessing\context.py", line 313, in _Popen
return Popen(process_obj)
File "C:\Users\tang_ke\AppData\Local\Programs\Python\Python35-32\lib\multiprocessing\popen_spawn_win32.py", line 66, in __init__
reduction.dump(process_obj, to_child)
File "C:\Users\tang_ke\AppData\Local\Programs\Python\Python35-32\lib\multiprocessing\reduction.py", line 59, in dump
ForkingPickler(file, protocol).dump(obj)
_pickle.PicklingError: Can't pickle <function <lambda> at 0x03A67C48>: attribute lookup <lambda> on __main__ failed
Process finished with exit code 1
I got answer in the site:讨论 - 廖雪峰的官方网站
step 1:
don't use "lambda" in "QueueManager.register",you have to replace a function,example:
def return_task_queue():
global task_queue
return task_queue
QueueManager.register('get_task_queue', callable=return_task_queue)
step 2:
you have to add IPAddress when you create "QueueManager",example:
QueueManager(address=('127.0.0.1', 5000), authkey=b'abc')
step 3:
you have to put all functions about queuemanager and task and result in a function...example:
def test():
QueueManager.register('get_task_queue', callable=return_task_queue)
QueueManager.register('get_result_queue', callable=return_result_queue)
manager = QueueManager(address=('127.0.0.1', 5000), authkey=b'abc')
manager.start()
....
and you have to use the function "test" in MAIN function,example:
if __name__ == '__main__':
test()
In following script why my callback function never get called ?
I am using a pre-created kernel to run the code and trying to get the output of it with attaching the callback for respective sockets.
from zmq.eventloop import ioloop
ioloop.install()
from zmq.eventloop.zmqstream import ZMQStream
from functools import partial
from tornado import gen
from tornado.concurrent import Future
from jupyter_client import BlockingKernelClient
from pprint import pprint
import logging, os, zmq
reply_futures = {}
context = zmq.Context()
publisher = context.socket(zmq.PUSH)
publisher.connect("tcp://127.0.0.1:5253")
def reply_callback(session, stream, msg_list):
idents, msg_parts = session.feed_identities(msg_list)
reply = session.deserialize(msg_parts)
parent_id = reply['parent_header'].get('msg_id')
reply_future = reply_futures.get(parent_id)
print("{} \n".format(reply))
if reply_future:
if "execute_reply" == reply["msg_type"]:
reply_future.set_result(reply)
publisher.send(reply)
def fv_execute():
code = 'print ("hello")'
msg_id = execute(code)
return msg_id
def get_connection_file(kernel_id):
json_file = 'kernel-{}.json'.format(kernel_id)
return os.path.join('/tmp',json_file)
def execute(code,):
kernel_id = '46459cb4-fa34-497a-8e3d-dfb3ab4476fd'
cf = get_connection_file(kernel_id)
kernel_client = BlockingKernelClient(connection_file=cf)
setup_listener(kernel_client)
msg_id = ioloop.IOLoop.current().run_sync(lambda: execute_(kernel_client,code))
return msg_id
def setup_listener(kernel_client):
shell_stream = ZMQStream(kernel_client.shell_channel.socket)
iopub_stream = ZMQStream(kernel_client.iopub_channel.socket)
shell_stream.on_recv_stream(partial(reply_callback, kernel_client.session))
iopub_stream.on_recv_stream(partial(reply_callback, kernel_client.session))
#gen.coroutine
def execute_(kernel_client, code):
msg_id = kernel_client.execute(code)
f = reply_futures[msg_id] = Future()
print("Is kernel alive: {}".format(kernel_client.is_alive()))
print(msg_id)
yield f
raise gen.Return(msg_id)
if __name__ == '__main__':
fv_execute()
here is output, the script runs forever
jupyter#albus:~/lab$ python2 iolooptest2.py
Is kernel alive: True
de3eae2e-48d3-451a-b6bc-421674bb2a35
^X^CTraceback (most recent call last):
File "iolooptest2.py", line 61, in <module>
fv_execute()
File "iolooptest2.py", line 30, in fv_execute
msg_id = execute(code)
File "iolooptest2.py", line 42, in execute
msg_id = ioloop.IOLoop.current().run_sync(lambda: execute_(kernel_client,code))
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 452, in run_sync
self.start()
File "/usr/local/lib/python2.7/dist- packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 862, in start
event_pairs = self._impl.poll(poll_timeout)
File "/usr/local/lib/python2.7/dist- packages/zmq/eventloop/ioloop.py", line 122, in poll
z_events = self._poller.poll(1000*timeout)
File "/usr/local/lib/python2.7/dist-packages/zmq/sugar/poll.py", line 99, in poll
return zmq_poll(self.sockets, timeout=timeout)
File "zmq/backend/cython/_poll.pyx", line 116, in zmq.backend.cython._poll.zmq_poll (zmq/backend/cython/_poll.c:2036)
File "zmq/backend/cython/checkrc.pxd", line 12, in zmq.backend.cython.checkrc._check_rc (zmq/backend/cython/_poll.c:2418)
KeyboardInterrupt
A slightly modified version of the code is here
https://gist.github.com/jayendra13/76a4f5726428882013ea62d94974da5c
where I pass ioloop as a argument to zmqstream, while attaching the callback, which also has a same behaviour.
Here is almost similar script which works
https://gist.github.com/jayendra13/e553fafba5398e287107e947c16988df
Adding the following two lines after the creation of kernel_client solved my issue.
kernel_client.load_connection_file()
kernel_client.start_channels()
so new execute looks like this
def execute(code,):
kernel_id = '46459cb4-fa34-497a-8e3d-dfb3ab4476fd'
cf = get_connection_file(kernel_id)
kernel_client = BlockingKernelClient(connection_file=cf)
kernel_client.load_connection_file()
kernel_client.start_channels()
setup_listener(kernel_client)
msg_id = ioloop.IOLoop.current().run_sync(lambda: execute_(kernel_client,code))
return msg_id