import random
import queue as Queue
import _thread as Thread
a = Queue.Queue()
def af():
while True:
a.put(random.randint(0,1000))
def bf():
while True:
if (not a.empty()): print (a.get())
def main():
Thread.start_new_thread(af, ())
Thread.start_new_thread(bf, ())
return
if __name__ == "__main__":
main()
the above code works fine with extreme high CPU usage, i tried to use multiprocessing with no avail. i have tried
def main():
multiprocessing.Process(target=af).run()
multiprocessing.Process(target=bf).run()
and
def main():
manager = multiprocessing.Manager()
a = manager.Queue()
pool = multiprocessing.Pool()
pool.apply_async(af)
pool.apply_async(bf)
both not working, can anyone please help me? thanks a bunch ^_^
def main():
multiprocessing.Process(target=af).run() # will not return
multiprocessing.Process(target=bf).run()
The above code does not work because af does not return; no chance to call bf. You need to separate run call to start/join so that both can run in parallel. (+ to make them share manage.Queue)
To make the second code work, you need to pass a (manager.Queue object) to functions. Otherwise they will use Queue.Queue global object which is not shared between processes; need to modify af, bf to accepts a, and main to pass a.
def af(a):
while True:
a.put(random.randint(0, 1000))
def bf(a):
while True:
print(a.get())
def main():
manager = multiprocessing.Manager()
a = manager.Queue()
pool = multiprocessing.Pool()
proc1 = pool.apply_async(af, [a])
proc2 = pool.apply_async(bf, [a])
# Wait until process ends. Uncomment following line if there's no waiting code.
# proc1.get()
# proc2.get()
In the first alternative main you use Process, but the method you should call to start the activity is not run(), as one would think, but rather start(). You will want to follow that up with appropriate join() statements. Following the information in multiprocessing (available here: https://docs.python.org/2/library/multiprocessing.html), here is a working sample:
import random
from multiprocessing import Process, Queue
def af(q):
while True:
q.put(random.randint(0,1000))
def bf(q):
while True:
if not q.empty():
print (q.get())
def main():
a = Queue()
p = Process(target=af, args=(a,))
c = Process(target=bf, args=(a,))
p.start()
c.start()
p.join()
c.join()
if __name__ == "__main__":
main()
To add to the accepted answer, in the original code:
while True:
if not q.empty():
print (q.get())
q.empty() is being called every time which is unnecessary since q.get() if the queue is empty will wait until something is available here documentation.
Similar answer here
I assume that this could affect the performance since calling the .empty() every iteration should consume more resources (it should be more noticeable if Thread was used instead of Process because Python Global Interpreter Lock (GIL))
I know it's an old question but hope it helps!
Related
I've read that it's considered bad practice to kill a thread. (Is there any way to kill a Thread?) There are a LOT of answers there, and I'm wondering if even using a thread in the first place is the right answer for me.
I have a bunch multiprocessing.Processes. Essentially, each Process is doing this:
while some_condition:
result = self.function_to_execute(i, **kwargs_i)
# outQ is a multiprocessing.queue shared between all Processes
self.outQ.put(Result(i, result))
Problem is... I need a way to interrupt function_to_execute, but can't modify the function itself. Initially, I was thinking simply process.terminate(), but that appears to be unsafe with multiprocessing.queue.
Most likely (but not guaranteed), if I need to kill a thread, the 'main' program is going to be done soon. Is my safest option to do something like this? Or perhaps there is a more elegant solution than using a thread in the first place?
def thread_task():
while some_condition:
result = self.function_to_execute(i, **kwargs_i)
if (this_thread_is_not_daemonized):
self.outQ.put(Result(i, result))
t = Thread(target=thread_task)
t.start()
if end_early:
t.daemon = True
I believe the end result of this is that the Process that spawned the thread will continue to waste CPU cycles on a task I no longer care about the output for, but if the main program finishes, it'll clean up all my memory nicely.
The main problem with daemonizing a thread is that the main program could potentially continue for 30+ minutes even when I don't care about the output of that thread anymore.
From the threading docs:
If you want your threads to stop gracefully, make them non-daemonic
and use a suitable signalling mechanism such as an Event
Here is a contrived example of what I was thinking - no idea if it mimics what you are doing or can be adapted for your situation. Another caveat: I've never written any real concurrent code.
Create an Event object in the main process and pass it all the way to the thread.
Design the thread so that it loops until the Event object is set. Once you don't need the processing anymore SET the Event object in the main process. No need to modify the function being run in the thread.
from multiprocessing import Process, Queue, Event
from threading import Thread
import time, random, os
def f_to_run():
time.sleep(.2)
return random.randint(1,10)
class T(Thread):
def __init__(self, evt,q, func, parent):
self.evt = evt
self.q = q
self.func = func
self.parent = parent
super().__init__()
def run(self):
while not self.evt.is_set():
n = self.func()
self.q.put(f'PID {self.parent}-{self.name}: {n}')
def f(T,evt,q,func):
pid = os.getpid()
t = T(evt,q,func,pid)
t.start()
t.join()
q.put(f'PID {pid}-{t.name} is alive - {t.is_alive()}')
q.put(f'PID {pid}:DONE')
return 'foo done'
if __name__ == '__main__':
results = []
q = Queue()
evt = Event()
# two processes each with one thread
p= Process(target=f, args=(T, evt, q, f_to_run))
p1 = Process(target=f, args=(T, evt, q, f_to_run))
p.start()
p1.start()
while len(results) < 40:
results.append(q.get())
print('.',end='')
print('')
evt.set()
p.join()
p1.join()
while not q.empty():
results.append(q.get_nowait())
for thing in results:
print(thing)
I initially tried to use threading.Event but the multiprocessing module complained that it couldn't be pickled. I was actually surprised that the multiprocessing.Queue and multiprocessing.Event worked AND could be accessed by the thread.
Not sure why I started with a Thread subclass - I think I thought it would be easier to control/specify what happens in it's run method. But it can be done with a function also.
from multiprocessing import Process, Queue, Event
from threading import Thread
import time, random
def f_to_run():
time.sleep(.2)
return random.randint(1,10)
def t1(evt,q, func):
while not evt.is_set():
n = func()
q.put(n)
def g(t1,evt,q,func):
t = Thread(target=t1,args=(evt,q,func))
t.start()
t.join()
q.put(f'{t.name} is alive - {t.is_alive()}')
return 'foo'
if __name__ == '__main__':
q = Queue()
evt = Event()
p= Process(target=g, args=(t1, evt, q, f_to_run))
p.start()
time.sleep(5)
evt.set()
p.join()
I'm struggling to get my head around multiprocessing and passing a global True/False variable into my function.
After get_data() finishes I want the analysis() function to start and process the data, while fetch() continues running. How can I make this work? TIA
import multiprocessing
ready = False
def fetch():
global ready
get_data()
ready = True
return
def analysis():
analyse_data()
if __name__ == '__main__':
p1 = multiprocessing.Process(target=fetch)
p2 = multiprocessing.Process(target=analysis)
p1.start()
if ready:
p2.start()
You should run the two processes and use a shared queue to exchange information between them, such as signaling the completion of an action in one of the processes.
Also, you need to have a join() statement to properly wait for completion of the processes you spawn.
from multiprocessing import Process, Queue
import time
def get_data(q):
#Do something to get data
time.sleep(2)
#Put an event in the queue to signal that get_data has finished
q.put('message from get_data to analyse_data')
def analyse_data(q):
#waiting for get_data to finish...
msg = q.get()
print msg #Will print 'message from get_data to analyse_data'
#get_data has finished
if __name__ == '__main__':
#Create queue for exchanging messages between processes
q = Queue()
#Create processes, and send the shared queue to them
processes = [Process(target=get_data,args(q,)),Process(target=analyse_data,args=(q,))]
#Start processes
for p in processes:
p.start()
#Wait until all processes complete
for p in processes:
p.join()
You example won't work for a few reasons :
Process cannot share a piece of memory with each other (you can't change the global in one process and see the change in the other)
Even if you could change the global value, you are checking it too fast and most likely it won't change in time
Read https://docs.python.org/3/library/ipc.html for more possibilities for inter-process-communications
I'm running python 2.7.3 and I noticed the following strange behavior. Consider this minimal example:
from multiprocessing import Process, Queue
def foo(qin, qout):
while True:
bar = qin.get()
if bar is None:
break
qout.put({'bar': bar})
if __name__ == '__main__':
import sys
qin = Queue()
qout = Queue()
worker = Process(target=foo,args=(qin,qout))
worker.start()
for i in range(100000):
print i
sys.stdout.flush()
qin.put(i**2)
qin.put(None)
worker.join()
When I loop over 10,000 or more, my script hangs on worker.join(). It works fine when the loop only goes to 1,000.
Any ideas?
The qout queue in the subprocess gets full. The data you put in it from foo() doesn't fit in the buffer of the OS's pipes used internally, so the subprocess blocks trying to fit more data. But the parent process is not reading this data: it is simply blocked too, waiting for the subprocess to finish. This is a typical deadlock.
There must be a limit on the size of queues. Consider the following modification:
from multiprocessing import Process, Queue
def foo(qin,qout):
while True:
bar = qin.get()
if bar is None:
break
#qout.put({'bar':bar})
if __name__=='__main__':
import sys
qin=Queue()
qout=Queue() ## POSITION 1
for i in range(100):
#qout=Queue() ## POSITION 2
worker=Process(target=foo,args=(qin,))
worker.start()
for j in range(1000):
x=i*100+j
print x
sys.stdout.flush()
qin.put(x**2)
qin.put(None)
worker.join()
print 'Done!'
This works as-is (with qout.put line commented out). If you try to save all 100000 results, then qout becomes too large: if I uncomment out the qout.put({'bar':bar}) in foo, and leave the definition of qout in POSITION 1, the code hangs. If, however, I move qout definition to POSITION 2, then the script finishes.
So in short, you have to be careful that neither qin nor qout becomes too large. (See also: Multiprocessing Queue maxsize limit is 32767)
I had the same problem on python3 when tried to put strings into a queue of total size about 5000 cahrs.
In my project there was a host process that sets up a queue and starts subprocess, then joins. Afrer join host process reads form the queue. When subprocess producess too much data, host hungs on join. I fixed this using the following function to wait for subprocess in the host process:
from multiprocessing import Process, Queue
from queue import Empty
def yield_from_process(q: Queue, p: Process):
while p.is_alive():
p.join(timeout=1)
while True:
try:
yield q.get(block=False)
except Empty:
break
I read from queue as soon as it fills so it never gets very large
I was trying to .get() an async worker after the pool had closed
indentation error outside of a with block
i had this
with multiprocessing.Pool() as pool:
async_results = list()
for job in jobs:
async_results.append(
pool.apply_async(
_worker_func,
(job,),
)
)
# wrong
for async_result in async_results:
yield async_result.get()
i needed this
with multiprocessing.Pool() as pool:
async_results = list()
for job in jobs:
async_results.append(
pool.apply_async(
_worker_func,
(job,),
)
)
# right
for async_result in async_results:
yield async_result.get()
I am new to multiprocessing
I have run example code for two 'highly recommended' multiprocessing examples given in response to other stackoverflow multiprocessing questions. Here is an example of one (which i dare not run again!)
test2.py (running from pydev)
import multiprocessing
class MyFancyClass(object):
def __init__(self, name):
self.name = name
def do_something(self):
proc_name = multiprocessing.current_process().name
print(proc_name, self.name)
def worker(q):
obj = q.get()
obj.do_something()
queue = multiprocessing.Queue()
p = multiprocessing.Process(target=worker, args=(queue,))
p.start()
queue.put(MyFancyClass('Fancy Dan'))
# Wait for the worker to finish
queue.close()
queue.join_thread()
p.join()
When I run this my computer slows down imminently. It gets incrementally slower. After some time I managed to get into the task manager only to see MANY MANY python.exe under the processes tab. after trying to end process on some, my mouse stopped moving. It was the second time i was forced to reboot.
I am too scared to attempt a third example...
running - Intel(R) Core(TM) i7 CPU 870 # 2.93GHz (8 CPUs), ~2.9GHz on win7 64
If anyone know what the issue is and can provide a VERY SIMPLE example of multiprocessing (send a string too a multiprocess, alter it and send it back for printing) I would be very grateful.
From the docs:
Make sure that the main module can be safely imported by a new Python
interpreter without causing unintended side effects (such a starting a
new process).
Thus, on Windows, you must wrap your code inside a
if __name__=='__main__':
block.
For example, this sends a string to the worker process, the string is reversed and the result is printed by the main process:
import multiprocessing as mp
def worker(inq,outq):
obj = inq.get()
obj = obj[::-1]
outq.put(obj)
if __name__=='__main__':
inq = mp.Queue()
outq = mp.Queue()
p = mp.Process(target=worker, args=(inq,outq))
p.start()
inq.put('Fancy Dan')
# Wait for the worker to finish
p.join()
result = outq.get()
print(result)
Because of the way multiprocessing works on Windows (child processes import the __main__ module) the __main__ module cannot actually run anything when imported -- any code that should execute when run directly must be protected by the if __name__ == '__main__' idiom. Your corrected code:
import multiprocessing
class MyFancyClass(object):
def __init__(self, name):
self.name = name
def do_something(self):
proc_name = multiprocessing.current_process().name
print(proc_name, self.name)
def worker(q):
obj = q.get()
obj.do_something()
if __name__ == '__main__':
queue = multiprocessing.Queue()
p = multiprocessing.Process(target=worker, args=(queue,))
p.start()
queue.put(MyFancyClass('Fancy Dan'))
# Wait for the worker to finish
queue.close()
queue.join_thread()
p.join()
Might I suggest this link? It's using threads, instead of multiprocessing, but many of the principles are the same.
I need to do a blocking xmlrpc call from my python script to several physical server simultaneously and perform actions based on response from each server independently.
To explain in detail let us assume following pseudo code
while True:
response=call_to_server1() #blocking and takes very long time
if response==this:
do that
I want to do this for all the servers simultaneously and independently but from same script
Use the threading module.
Boilerplate threading code (I can tailor this if you give me a little more detail on what you are trying to accomplish)
def run_me(func):
while not stop_event.isSet():
response= func() #blocking and takes very long time
if response==this:
do that
def call_to_server1():
#code to call server 1...
return magic_server1_call()
def call_to_server2():
#code to call server 2...
return magic_server2_call()
#used to stop your loop.
stop_event = threading.Event()
t = threading.Thread(target=run_me, args=(call_to_server1))
t.start()
t2 = threading.Thread(target=run_me, args=(call_to_server2))
t2.start()
#wait for threads to return.
t.join()
t2.join()
#we are done....
You can use multiprocessing module
import multiprocessing
def call_to_server(ip,port):
....
....
for i in xrange(server_count):
process.append( multiprocessing.Process(target=call_to_server,args=(ip,port)))
process[i].start()
#waiting process to stop
for p in process:
p.join()
You can use multiprocessing plus queues. With one single sub-process this is the example:
import multiprocessing
import time
def processWorker(input, result):
def remoteRequest( params ):
## this is my remote request
return True
while True:
work = input.get()
if 'STOP' in work:
break
result.put( remoteRequest(work) )
input = multiprocessing.Queue()
result = multiprocessing.Queue()
p = multiprocessing.Process(target = processWorker, args = (input, result))
p.start()
requestlist = ['1', '2']
for req in requestlist:
input.put(req)
for i in xrange(len(requestlist)):
res = result.get(block = True)
print 'retrieved ', res
input.put('STOP')
time.sleep(1)
print 'done'
To have more the one sub-process simply use a list object to store all the sub-processes you start.
The multiprocessing queue is a safe object.
Then you may keep track of which request is being executed by each sub-process simply storing the request associated to a workid (the workid can be a counter incremented when the queue get filled with new work). Usage of multiprocessing.Queue is robust since you do not need to rely on stdout/err parsing and you also avoid related limitation.
Then, you can also set a timeout on how long you want a get call to wait at max, eg:
import Queue
try:
res = result.get(block = True, timeout = 10)
except Queue.Empty:
print error
Use twisted.
It has a lot of useful stuff for work with network. It is also very good at working asynchronously.