Develop Reference

Multiprocessing BrokenPipeError

I have a following problem. I am running a parallel task. I am getting this error:
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "eclat_model.py", line 127, in do_work
function(*args, work_queue, valid_list)
File "eclat_model.py", line 115, in eclat_parallel_helper
valid_list.extend(next_vectors)
File "<string>", line 2, in extend
File "/usr/lib/python3.8/multiprocessing/managers.py", line 834, in _callmethod
conn.send((self._id, methodname, args, kwds))
File "/usr/lib/python3.8/multiprocessing/connection.py", line 206, in send
self._send_bytes(_ForkingPickler.dumps(obj))
File "/usr/lib/python3.8/multiprocessing/connection.py", line 404, in _send_bytes
self._send(header)
File "/usr/lib/python3.8/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
BrokenPipeError: [Errno 32] Broken pipe
Relevant functions in eclat_model.py look like this:
def eclat_parallel_helper(index, bit_vectors, min_support, work_queue, valid_list):
next_vectors = []
for j in range(index + 1, len(bit_vectors)):
item_vector = bit_vectors[index][0] | bit_vectors[j][0]
transaction_vector = bit_vectors[index][1] & bit_vectors[j][1]
support = get_vector_support(transaction_vector)
if support >= min_support:
next_vectors.append((item_vector, transaction_vector, support))
if len(next_vectors) > 0:
valid_list.extend(next_vectors)
for i in range(len(next_vectors)):
work_queue.put((eclat_parallel_helper, (i, next_vectors, min_support)))
def do_work(work_queue, valid_list, not_done):
# work queue entries have the form (function, args)
while not_done.value:
try:
function, args = work_queue.get_nowait()
except QueueEmptyError:
continue
function(*args, work_queue, valid_list)
work_queue.task_done()
work_queue.close()
EDIT:
Multiprocessing part of the code is as follows: bit_vectors is a list of lists, where each entry is of the form
[items, transactions, support], where items is a bit vector encoding which items appear in the itemset, vector is a bit vector encoding which transactions the itemset appears in, and support is the number of transactions in which the itemset occurs.
from multiprocessing import Process, JoinableQueue, Manager, Value, cpu_count
def eclat_parallel(bit_vectors, min_support):
not_done = Value('i', 1)
manager = Manager()
valid_list = manager.list()
work_queue = JoinableQueue()
for i in range(len(bit_vectors)):
work_queue.put((eclat_parallel_helper, (i, bit_vectors, min_support)))
processes = []
for i in range(cpu_count()):
p = Process(target=do_work, args=(work_queue, valid_list, not_done), daemon=True)
p.start()
processes.append(p)
work_queue.join()
not_done.value = 0
work_queue.close()
valid_itemset_vectors = bit_vectors
for element in valid_list:
valid_itemset_vectors.append(element)
for p in processes:
p.join()
return valid_itemset_vectors
What does this error mean, please? Am I appending too many elements into next_vectors list?

I had the same issue, in my case just added a delay (time.sleep(0.01)) to solve it.
The problem is that the individual processes are too fast on queue that causes the error.

How to stop blocking call and exit thread gracefully in python

I have a working script which invokes multiple blocking read methods in different threads and whenever it gets data in the blocking method it puts the data in queue that will be read by task.
import asyncio
import atexit
import concurrent.futures
import threading
def blocking_read(x, loop):
while True:
print(f"blocking_read {x}")
time.sleep(1)
# implementation is wait for data and put into the queue
class Recorder():
def __init__(self):
self.count = 0
def run_reader_threads(self, thread_pool, event):
loop = asyncio.get_running_loop()
threads = []
for rx in range(2):
threads.append(loop.run_in_executor(thread_pool, blocking_read, rx, loop))
return threads
def wiatforever():
while True:
time.sleep(1)
reader_futures = []
executor = concurrent.futures.ThreadPoolExecutor()
event = threading.Event()
def main():
async def doit():
recorder_app = Recorder()
global reader_futures
reader_futures = recorder_app.run_reader_threads(executor, event)
#reader_handlers = recorder_app.create_handlers()
await wiatforever()
try:
print("RUN DO IT")
asyncio.run(doit())
except KeyboardInterrupt:
# cancel all futures but geeting exception on cancelling 1st future
reader_futures[0].cancel()
pass
#--------------------------------------------------------------------------------------------
if __name__ == '__main__':
main()
The problem is whenever I want to stop the script gracefully by cancelling all futures I am getting exception that RuntimeError: Event loop is closed
OUTPUT
RUN DO IT
blocking_read 0
blocking_read 1
blocking_read 1
blocking_read 0
blocking_read 0
blocking_read 1
^CTraceback (most recent call last):
File "/home/devuser/Desktop/rnr_crash/2trial.py", line 45, in main
asyncio.run(doit())
File "/usr/local/lib/python3.9/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 629, in run_until_complete
self.run_forever()
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 596, in run_forever
self._run_once()
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 1890, in _run_once
handle._run()
File "/usr/local/lib/python3.9/asyncio/events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "/home/devuser/Desktop/rnr_crash/2trial.py", line 41, in doit
await wiatforever()
File "/home/devuser/Desktop/rnr_crash/2trial.py", line 27, in wiatforever
time.sleep(1)
KeyboardInterrupt
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/devuser/Desktop/rnr_crash/2trial.py", line 53, in <module>
main()
File "/home/devuser/Desktop/rnr_crash/2trial.py", line 48, in main
reader_futures[0].cancel()
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 746, in call_soon
self._check_closed()
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 510, in _check_closed
raise RuntimeError('Event loop is closed')
RuntimeError: Event loop is closed
blocking_read 0
blocking_read 1
blocking_read 0
blocking_read 1
blocking_read 0
blocking_read 1
^CException ignored in: <module 'threading' from '/usr/local/lib/python3.9/threading.py'>
Traceback (most recent call last):
File "/usr/local/lib/python3.9/threading.py", line 1411, in _shutdown
atexit_call()
File "/usr/local/lib/python3.9/concurrent/futures/thread.py", line 31, in _python_exit
t.join()
File "/usr/local/lib/python3.9/threading.py", line 1029, in join
self._wait_for_tstate_lock()
File "/usr/local/lib/python3.9/threading.py", line 1045, in _wait_for_tstate_lock
elif lock.acquire(block, timeout):
KeyboardInterrupt:
so can anyone help me to find out the issue here and exit the script correctly without any exception.

Is it possible to spawn a process inside a thread in Python?

I'm wrting a program that spawns a process and restarts the process on certain conditions. For example, if a child process doesn't send data anymore to the mother process, for a certain period of time, I want the mother process to terminate the child process and restart it. I thought I could use a thread to recieve data from a child process and restart the child process, but it doesn't work the way I thought.
import numpy as np
import multiprocessing as mp
import threading
import time
from apscheduler.schedulers.background import BackgroundScheduler
pipe_in, pipe_out = mp.Pipe()
class Mother():
def __init__(self):
self.pipe_out = pipe_out
self.proc = mp.Process(target = self.test_func, args=(pipe_in, ))
self.proc.start()
self.thread = threading.Thread(target=self.thread_reciever, args=(self.pipe_out, ))
self.thread.start()
def thread_reciever(self, pipe_out):
while True:
value = pipe_out.recv()
print(value)
if value == 5:
self.proc.terminate()
time.sleep(2)
self.proc = mp.Process(target = self.test_func)
self.proc.start()
def test_func(self, pipe_in):
for i in range(10):
pipe_in.send(i)
time.sleep(1)
if __name__ == '__main__':
r = Mother()
It prints out this error.
D:\>d:\python36-32\python.exe temp06.py
0
1
2
3
4
5
Exception in thread Thread-1:
Traceback (most recent call last):
File "d:\python36-32\lib\threading.py", line 916, in _bootstrap_inner
self.run()
File "d:\python36-32\lib\threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "temp06.py", line 28, in thread_reciever
self.proc.start()
File "d:\python36-32\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "d:\python36-32\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "d:\python36-32\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "d:\python36-32\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
reduction.dump(process_obj, to_child)
File "d:\python36-32\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: can't pickle _thread.lock objects
D:\>Traceback (most recent call last):
File "<string>", line 1, in <module>
File "d:\python36-32\lib\multiprocessing\spawn.py", line 99, in spawn_main
new_handle = reduction.steal_handle(parent_pid, pipe_handle)
File "d:\python36-32\lib\multiprocessing\reduction.py", line 82, in steal_handle
_winapi.PROCESS_DUP_HANDLE, False, source_pid)
OSError: [WinError 87]
How could I start and terminate a process inside a thread? (I'm using a thread because it can synchronously recieve data from a different process) Or are there any other ways to do this job?
test_func as a global function
import numpy as np
import multiprocessing as mp
import threading
import time
from apscheduler.schedulers.background import BackgroundScheduler
pipe_in, pipe_out = mp.Pipe()
def test_func( pipe_in):
for i in range(10):
pipe_in.send(i)
time.sleep(1)
class Mother():
def __init__(self):
self.pipe_out = pipe_out
mp.freeze_support()
self.proc = mp.Process(target = test_func, args=(pipe_in, ))
self.proc.start()
self.thread = threading.Thread(target=self.thread_reciever, args=(self.pipe_out, ))
self.thread.start()
def thread_reciever(self, pipe_out):
while True:
value = pipe_out.recv()
print(value)
if value == 5:
self.proc.terminate()
time.sleep(2)
mp.freeze_support()
self.proc = mp.Process(target = test_func, args=(pipe_in,))
self.proc.start()
if __name__ == '__main__':
r = Mother()
OUTPUT
D:\> d:\python36-32\python.exe temp06.py
0
1
2
3
4
5
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "d:\python36-32\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "d:\python36-32\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
AttributeError: Can't get attribute 'test_func' on <module '__main__' (built-in)>

under windows, as there is no fork syscall, python starts a new interpreter instance, use pickle/unpickle to reconstruct execution context, but thread.Lock is not picklable. while pickling self.test_func, self.thread reference to a thread.Lock object, makes it unpicklable.
you could simply change test_func to a plain global function, without thread object reference :
self.proc = mp.Process(target = test_func, args=(pipe_in,))
...
def test_func(pipe_in):
for i in range(10):
pipe_in.send(i)
time.sleep(1)

How to return a counter dictionary from a function passed to multiprocessing?

I have a list of CSV files. I want to do a set of operations on each of them and then produce a counter dict and i want to cerate a master list containing individual counter dict from all CSV files. I want to parallelize processing each of the csv file and then return the counter dict from each file. I found a similar solution here : How can I recover the return value of a function passed to multiprocessing.Process?
I used the solution suggested by David Cullen. This solution works perfectly for strings, but when I tried to return a counter dict or a normal dict. All the CSV files are processed until the send_end.send(result) and it hangs on there forever when executed and then throws a memory error. I am running this in a Linux server with more than sufficient memory for creating the list of counter dicts.
I used the following code:
import multiprocessing
#get current working directory
cwd = os.getcwd()
#take a list of all files in cwd
files = os.listdir(cwd)
#defining the function that needs to be done on all csv files
def worker(f,send_end):
infile= open(f)
#read liens in csv file
lines = infile.readlines()
#split the lines by "," and store it in a list of lists
master_lst = [line.strip().split(“,”) for line in lines]
#extract the second field in each sublist
counter_lst = [ element[1] for element in master_lst]
print “Total elements in the list” + str(len(counter_lst))
#create a dictionary of count elements
a = Counter(counter_lst)
# return the counter dict
send_end.send(a)
def main():
jobs = []
pipe_list = []
for f in files:
if f.endswith('.csv'):
recv_end, send_end = multiprocessing.Pipe(duplex=False)
p = multiprocessing.Process(target=worker, args=(f, send_end))
jobs.append(p)
pipe_list.append(recv_end)
p.start()
for proc in jobs:
proc.join()
result_list = [x.recv() for x in pipe_list]
print len(result_list)
if __name__ == '__main__':
main()
The error that i get is the following:
Process Process-42:
Traceback (most recent call last):
File "/usr/lib64/python2.7/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
File "/usr/lib64/python2.7/multiprocessing/process.py", line 114, in run
self._target(*self._args, **self._kwargs)
File "/home/amm/python/collapse_multiprocessing_return.py", line 32, in
worker
a = Counter(counter_lst)
File "/usr/lib64/python2.7/collections.py", line 444, in __init__
self.update(iterable, **kwds)
File "/usr/lib64/python2.7/collections.py", line 526, in update
self[elem] = self_get(elem, 0) + 1
MemoryError
Process Process-17:
Traceback (most recent call last):
Process Process-6:
Traceback (most recent call last):
File "/usr/lib64/python2.7/multiprocessing/process.py", line 258, in
_bootstrap
File "/usr/lib64/python2.7/multiprocessing/process.py", line 258, in
_bootstrap
Process Process-8:
Traceback (most recent call last):
File "/usr/lib64/python2.7/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
self.run()
self.run()
File "/usr/lib64/python2.7/multiprocessing/process.py", line 114, in run
File "/usr/lib64/python2.7/multiprocessing/process.py", line 114, in run
self._target(*self._args, **self._kwargs)
File "/usr/lib64/python2.7/multiprocessing/process.py", line 114, in run
File "/home/amm/python/collapse_multiprocessing_return.py", line 32, in
worker
self._target(*self._args, **self._kwargs)
self._target(*self._args, **self._kwargs)
File "/home/amm/python/collapse_multiprocessing_return.py", line 32, in
worker
File "/home/amm/python/collapse_multiprocessing_return.py", line 32, in
worker
a = Counter(counter_lst_lst)
a = Counter(counter_lst_lst)
a = Counter(counter_lst_lst)
File "/usr/lib64/python2.7/collections.py", line 444, in __init__
File "/usr/lib64/python2.7/collections.py", line 444, in __init__
File "/usr/lib64/python2.7/collections.py", line 444, in __init__
self.update(iterable, **kwds)
File "/usr/lib64/python2.7/collections.py", line 526, in update
self[elem] = self_get(elem, 0) + 1
MemoryError
self.update(iterable, **kwds)
self.update(iterable, **kwds)
File "/usr/lib64/python2.7/collections.py", line 526, in update
File "/usr/lib64/python2.7/collections.py", line 526, in update
self[elem] = self_get(elem, 0) + 1
self[elem] = self_get(elem, 0) + 1
MemoryError
MemoryError
Process Process-10:
Traceback (most recent call last):
File "/usr/lib64/python2.7/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
File "/usr/lib64/python2.7/multiprocessing/process.py", line 114, in run
self._target(*self._args, **self._kwargs)
File "/home/amm/python/collapse_multiprocessing_return.py", line 32, in
worker
a = Counter(counter_lst)
File "/usr/lib64/python2.7/collections.py", line 444, in __init__
self.update(iterable, **kwds)
File "/usr/lib64/python2.7/collections.py", line 526, in update
self[elem] = self_get(elem, 0) + 1
MemoryError
^Z
[18]+ Stopped collapse_multiprocessing_return.py
Now instead of "a" in send_end.send(a) if i replace f, the filename. It prints the number of csv files in the directory (which is what len(result_list) does in this case). But when the counter dict "a" is returned it gets stuck forever, throwing the above error.
I would like to have the code pass the counter dict to receive end without any error/problems. Is there a work around? Could someone please suggest a possible solution?
p.s: I am new to multiprocessing module, sorry if this question sounds naive. Also, i tried the multiprocessing.Manager(), but got a similar error

Your traceback mentions Process Process-42:, so there are at least 42 processes being created. You're creating a process for every CSV file, which is not useful and is probably causing the memory error.
Your problem can be solved much more simply using multiprocessing.Pool.map. The worker function can also be shortened greatly:
def worker(f):
with open(f) as infile:
return Counter(line.strip().split(",")[1]
for line in infile)
def main():
pool = multiprocessing.Pool()
result_list = pool.map(worker, [f for f in files if f.endswith('.csv')])
Passing no arguments to the pool means it'll create as many processes as you have CPU cores. Using more may or may not increase performance.

Behavior of Manager in Multiprocessing

I cant find an explanation for this behavior in Python 3:
from multiprocessing import Process, cpu_count, freeze_support, Manager
class A:
def __init__(self):
# self._manager = Manager()
# self._list = self._manager.list()
manager = Manager()
self._list = manager.list()
def producer(self):
processes = []
cores = cpu_count()
for i in range(cores):
process = Process(target=self.worker)
process.start()
processes.append(process)
for process in processes:
process.join()
def worker(self):
print('I was called')
if __name__ == '__main__':
freeze_support()
a = A()
a.producer()
With this in __init__ :
self._manager = Manager()
self._list = self._manager.list()
I get an error OSError: handle is closed at the call process.start().
With this in __init__:
manager = Manager()
self._list = manager.list()
All seems to work.
I read https://docs.python.org/3.6/library/multiprocessing.html#sharing-state-between-processes but I can't find an explanation why an instance of a Manager() can't be a variable in the example above. My best guess is because Manager() is itself process and with a call like that target=self.worker I'm trying to break some logic in handling processes.
Question: Am I right? or I miss something?
Full Traceback:
Traceback (most recent call last):
File "G:/files-from-server/apps/test_module/test_export.py", line 27, in <module>
a.producer()
File "G:/files-from-server/apps/test_module/test_export.py", line 15, in producer
process.start()
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
reduction.dump(process_obj, to_child)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\connection.py", line 939, in reduce_pipe_connection
dh = reduction.DupHandle(conn.fileno(), access)
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\connection.py", line 170, in fileno
self._check_closed()
File "c:\users\maxim\appdata\local\programs\python\python36-32\Lib\multiprocessing\connection.py", line 136, in _check_closed
raise OSError("handle is closed")
OSError: handle is closed