I test python multiprocessing and write simple program:
from multiprocessing import Process
from time import sleep
def f(name):
print 'hello', name
x=1
while True:
x+=1
sleep(1)
print 'subprocess '+str(x)
if x==10:
quit()
if __name__ == '__main__':
p = Process(target=f, args=('bob',))
p.start()
x=1
while True:
x+=1
sleep(0.1)
print 'main process '+str(x)
if x==100:
quit()
Its work, but I has little error:
Traceback (most recent call last):
File "ttt.py", line 17, in <module>
p.start()
File "/usr/lib64/python2.6/multiprocessing/process.py", line 104, in start
self._popen = Popen(self)
File "/usr/lib64/python2.6/multiprocessing/forking.py", line 99, in __init__
code = process_obj._bootstrap()
File "/usr/lib64/python2.6/multiprocessing/process.py", line 242, in _bootstrap
sys.stderr.write(e.args[0] + '\n')
TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'
Use sys.exit() instead of quit(). The latter is meant to be used only in the interactive interpreter.
As Kevin noted, you can use return in f to exit the function normally. This would be perhaps more appropriate.
Related
I'm writing a script for comparing many DNA genomes with each other, and I'm trying to use multiprocessing to have it run faster. All the processes are appending to a common list, genome_score_avgs.
This is my main process:
if __name__ == "__main__":
start = time.perf_counter()
with Manager() as manager:
genome_score_avgs = manager.list()
processes = [Process(target=compareGenomes, args=(chunk, genome_score_avgs,)) for chunk in divideGenomes('TEST_DIR')]
for p in processes:
p.start()
for p in processes:
p.join()
print(genome_score_avgs)
print(*createTimeline(genome_score_avgs), sep='\n')
print(f'Finished in {time.perf_counter() - start} seconds')
This is the error that I'm getting:
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/managers.py", line 801, in _callmethod
conn = self._tls.connection
AttributeError: 'ForkAwareLocal' object has no attribute 'connection'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/ayushpal/Coding/PythonStuff/C4DInter/main.py", line 59, in <module>
print(*createTimeline(genome_score_avgs), sep='\n')
File "/Users/ayushpal/Coding/PythonStuff/C4DInter/main.py", line 42, in createTimeline
min_score = min(score_avgs, key=lambda x: x[2])
File "<string>", line 2, in __getitem__
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/managers.py", line 805, in _callmethod
self._connect()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/managers.py", line 792, in _connect
conn = self._Client(self._token.address, authkey=self._authkey)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/connection.py", line 507, in Client
c = SocketClient(address)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/connection.py", line 635, in SocketClient
s.connect(address)
FileNotFoundError: [Errno 2] No such file or directory
<ListProxy object, typeid 'list' at 0x7fc04ea36bb0; '__str__()' failed>
I read in a similar Stack Overflow question that the main process is ending earlier than the other processes, which destroys the shared list, and that I should use p.join() for all the processes. This is what I'm doing , however, it's still giving the same error. What should I do?
EDIT 1:
this is the code for CompareGenomes():
def compareGenomes(genome_pairings, genome_score_avgs):
scores = []
for genome1, genome2 in genome_pairings:
print(genome1, genome2)
for i, seq in enumerate(genome1.protein_seqs):
for j, seq2 in enumerate(genome2.protein_seqs[i::]):
alignment = align.globalxx(seq, seq2)
scores.append(alignment)
top_scores = []
for i in range(len(genome1.protein_seqs)):
top_scores.append(max(scores, key=lambda x: x[0][2] / len(x[0][1])))
scores.remove(max(scores, key=lambda x: x[0][2] / len(x[0][1])))
avg_score = sum([i[0][2] / len(i[0][1]) for i in top_scores]) / len(top_scores)
with open(f'alignments/{genome1.name}x{genome2.name}.txt', 'a') as file:
file.writelines([format_alignment(*i[0]) for i in top_scores])
genome_score_avgs.append((genome1, genome2, avg_score))
The error is happening because you are using the managed list after you have closed the manager. Once that happens, the process that the manager spawns is closed as well, and therefore your managed list will no longer work. You need to use the list inside the with block like below:
if __name__ == "__main__":
start = time.perf_counter()
with Manager() as manager:
genome_score_avgs = manager.list()
processes = [Process(target=compareGenomes, args=(chunk, genome_score_avgs,)) for chunk in divideGenomes('TEST_DIR')]
for p in processes:
p.start()
for p in processes:
p.join()
print(genome_score_avgs)
print(*createTimeline(genome_score_avgs), sep='\n')
print(f'Finished in {time.perf_counter() - start} seconds')
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 have a python program like below.
from multiprocessing import Lock, Process, Queue, current_process
import time
lock = Lock()
def do_job(tasks_to_accomplish, tasks_that_are_done):
while not tasks_to_accomplish.empty():
task = tasks_to_accomplish.get()
print(task)
lock.acquire()
tasks_that_are_done.put(task + ' is done by ' + current_process().name)
lock.release()
time.sleep(1)
return True
def main():
number_of_task = 10
number_of_processes = 4
tasks_to_accomplish = Queue()
tasks_that_are_done = Queue()
processes = []
for i in range(number_of_task):
tasks_to_accomplish.put("Task no " + str(i))
# creating processes
for w in range(number_of_processes):
p = Process(target=do_job, args=(tasks_to_accomplish, tasks_that_are_done))
processes.append(p)
p.start()
# completing process
for p in processes:
p.join()
# print the output
while not tasks_that_are_done.empty():
print(tasks_that_are_done.get())
return True
if __name__ == '__main__':
main()
Sometimes program run perfectly but sometimes it gets stuck and doesn't complete. When quit manually, it produces following error.
$ python3 multiprocessing_example.py
Task no 0
Task no 1
Task no 2
Task no 3
Task no 4
Task no 5
Task no 6
Task no 7
Task no 8
Task no 9
^CProcess Process-1:
Traceback (most recent call last):
File "multiprocessing_example.py", line 47, in <module>
main()
File "multiprocessing_example.py", line 37, in main
p.join()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/process.py", line 121, in join
res = self._popen.wait(timeout)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/popen_fork.py", line 51, in wait
return self.poll(os.WNOHANG if timeout == 0.0 else 0)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/popen_fork.py", line 29, in poll
pid, sts = os.waitpid(self.pid, flag)
KeyboardInterrupt
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/process.py", line 249, in _bootstrap
self.run()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "multiprocessing_example.py", line 9, in do_job
task = tasks_to_accomplish.get()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/queues.py", line 94, in get
res = self._recv_bytes()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/connection.py", line 216, in recv_bytes
buf = self._recv_bytes(maxlength)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/connection.py", line 407, in _recv_bytes
buf = self._recv(4)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/connection.py", line 379, in _recv
chunk = read(handle, remaining)
KeyboardInterrupt
Can someone tell me what is the issue with the program? I am using python 3.6.
Note: Lock is not needed around a Queue.
lock.acquire()
tasks_that_are_done.put(task + ' is done by ' + current_process().name)
lock.release()
Queue
The Queue class in this module implements all the required locking semantics.
Question: ... what is the issue with the program?
You are using Queue.empty() and Queue.get(),
such leads to Deadlock on calling join() because there is no guarantee that the empty() State don't change until get()
was reaching.
Deadlock prone:
while not tasks_to_accomplish.empty():
task = tasks_to_accomplish.get()
Instead of using empty/get, Pair use for instance:
import queue
while True:
try:
task = tasks_to_accomplish.get_nowait()
except queue.Empty:
break
else:
# Handle task here
...
tasks_to_accomplish.task_done()
So in those past days I have been trying to figure out how to even start getting at thread and I finally got it to work! The issue I am having now is that I want them to run simultaneously. I'm hearing different things such as GIL won't work. Some say it works with multiprocessing etc etc.. However I turned here to see if its possible and whats the say to do it?
Basically my code looks right now like this:
The code with Thread
def start(config):
NameUrl = config["Url"]
myNote = config["My-Note"]
checkoutNames(Nameurl, MyNote)
if __name__ == '__main__':
with open('config.json', 'r', encoding='UTF-8') as json_data:
config = json.load(json_data)
threads = []
for i, e in enumerate(config):
threads.append(threading.Thread(target=start, args=(config[i] or e)))
As you can see in if __name__ == '__main__': That's where the thread is at this moment. However what this does at this moment is that it first does thread 1, when its done it turns to thread 2 and goes on like that and my wish is to turn it into concurrently/simultaneously if that is even possible?
EDIT
CODE
if __name__ == '__main__':
with open('config.json', 'r', encoding='UTF-8') as json_data:
config = json.load(json_data)
jobs = []
for i, e in enumerate(config):
c = (config[i] or e)
p = multiprocessing.Process(target=start, args=(c))
jobs.append(p)
p.start()
The error iam getting with the code above:
[<Process(Process-1, initial)>]
<Process(Process-1, initial)>
{'Email': '123o#gmail.com', 'PersonNumber': '4234', 'ZipCode': '1241234', 'Name': 'Guess', 'LastName': 'TheyKnow'}
[<Process(Process-1, started)>, <Process(Process-2, initial)>]
<Process(Process-2, initial)>
{'Email': 'Hello#hotmail.com', 'PersonNumber': '1234', 'ZipCode': '56431', 'Name': 'Stack', 'LastName': 'Overflow'}
Process Process-1:
Traceback (most recent call last):
File "C:\Users\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py", line 249, in _bootstrap
self.run()
File "C:\Users\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py", line 93, in run
self._target(*self._args, **self._kwargs)
TypeError: start() takes 1 positional argument but 16 were given
Process Process-2:
Traceback (most recent call last):
File "C:\Users\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py", line 249, in _bootstrap
self.run()
File "C:\Users\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py", line 93, in run
self._target(*self._args, **self._kwargs)
TypeError: start() takes 1 positional argument but 16 were given
I think you need to fix the args parameter:
...
jobs = []
for i, e in enumerate(config):
c = (config[i] or e)
p = multiprocessing.Process(target=start, args=(c,))
jobs.append(p)
p.start()
Note the syntax used in the args parameter:
args=(c,)) # <=== (c,) means that we are assigning the tuple (c,) to args
# which gets translated into start(c)
Have a look at this code :
import threading
import time
def my_inline_function(number):
#do some stuff
download_thread = threading.Thread(target=function_that_writes, args=number)
download_thread.start()
#continue doing stuff
i = 0
while(i < 10000):
print str(i) + " : Main thread"
time.sleep(1)
i = i + 1
def function_that_writes(number):
i = number
file = open("dummy.txt", 'w')
while (i < 10000):
string = str(i) + " : child thread"
file.write(string)
time.sleep(1)
file.close()
my_inline_function(5)
function_that_writes(5)
With does my_inline_function(), which starts a thread, not create a file?
But when I am calling a function_that_writes(...) directly, which is not running in a thread, it is able to create a file.
Why am I getting this behaviour?
You need to supply your argument as a tuple args=(number,):
download_thread = threading.Thread(target=function_that_writes, args=(number,))
The exception is pretty clear here:
Exception in thread Thread-1:
Traceback (most recent call last):
File "/Users/mike/anaconda/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/Users/mike/anaconda/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
TypeError: function_that_writes() argument after * must be an iterable, not int