Python multiprocessing - probably failure when method name pass to Process - python

I have problem with multiprocessing. Under you have the code (he's in couple of class and files, but i simplified it).
I suppose, that problem lies in pass method name which I want to multiply in multiprocessing.
Informations:
"args" is a list like as [(0,1),(1,2),(2,3)] so single "arg" like as (0,1)
This two files are in totally other calatogs
!!First file!!
from ... import EF
from ... import someclass
class performs():
def action():
for i, arg in enumerate(args):
data.append(EF(self.method,list(arg),i))
someclass.create_processes(*data)
def method(self,fa,la):
...
!!second file!!
from multiprocessing import Process,Event
class EF(object):
def __init__(self,name,args=list(),proc=1):
self.name=name
self.args=args
self.proc=proc
class someclass:
#staticmethod
def create_processes(*functions):
processes=dict()
for function in functions:
process=Process(target=function.name,args=function.args)
process.start()
processes[process.pid]=process
for process in processes.values():
process.join()
When I'm debugging, error comes, when program performing this instruction "process.start()"
Console:
File "C:\Python32\lib\multiprocessing\forking.py", line 371, in main
self = load(from_parent)
AttributeError: 'performs' object has no attribute 'function'
or in other situation
File "C:\Python32\lib\multiprocessing\process.py", line 267, in _bootstrap
self.run()
File "C:\Python32\lib\multiprocessing\process.py", line 116, in run
self._target(*self._args, **self._kwargs)
File "...\performs.py", line 88, in method
...
I don't know it's important, but I have 64bit system, and installed Python and accesories for 32 bit

The comment box is too small for this, but it seems like your code is working fine. I tested it by copying it in two files (like your environment), but it of course also works in a single file. That file you can find below: it is working as expected (save for the print statements output being mixed up, but that is to be expected).
So, most likely, your issue lies elsewhere? The error seems to indicate perhaps some inclusion order, like stated in this question?
from multiprocessing import Process,Event
class EF:
def __init__(self, name, args=list(), proc=1):
self.name = name
self.args = args
self.proc = proc
class someclass:
#staticmethod
def create_processes(*functions):
processes=dict()
for function in functions:
process=Process(target=function.name,args=function.args)
process.start()
processes[process.pid]=process
for process in processes.values():
process.join()
class performs:
def action(self, args):
data = []
for i, arg in enumerate(args):
data.append(EF(self.mult, list(arg), i))
someclass.create_processes(*data)
def mult(self,fa,la):
print '%d x %d = %d' % (fa, la, fa * la)
if __name__ == '__main__':
p = performs()
p.action([(x, x+1) for x in xrange(10)])

Related

Multi-processing with decorated methods - the parameter is incorrect

I'm trying to use multi-processing on windows 10 with Python 3.10.1.
If the method has a decoration, then this code fails:
from multiprocessing import Process
def profiler(func):
def wrap(*args, **kwargs):
result = func(*args, **kwargs)
return result
return wrap
#profiler
def go_around(num):
print(num)
if __name__ == '__main__':
p = Process(target=go_around, args=(1,))
p.start()
p.join()
I'm getting this error:
File "", line 1, in
File "C:\Python\Python310\lib\multiprocessing\spawn.py", line 102, in spawn_main
source_process = _winapi.OpenProcess(
OSError: [WinError 87] The parameter is incorrect
Note that this used to work on python 2.7.
Any ideas why this is happening and how to fix it?
python pickling needs to pull the original function in order to re-construct the decorated function, and it's no longer in the namespace (because it's already been decorated.) using the decorator functools.wraps on the wrapped function stores a copy of the original function in the __dict__ of the new function so it can be accessed later. There's some edge cases where this may not work (classes..) but for simple decorators, it should work:
from multiprocessing import Process
import functools
def profiler(func):
#functools.wraps(func)
def wrap(*args, **kwargs):
result = func(*args, **kwargs)
print("I profiled your function for you :)")
return result
return wrap
#profiler
def go_around(num):
print(num)
if __name__ == '__main__':
p = Process(target=go_around, args=(1,))
p.start()
p.join()
This answer discusses things a bit further..

Python multiprocess with importlib modules

Good day to you,
Today I was moving code from threading to multiprocess. Everything seemed okay, until I got The following error:
Error
Traceback (most recent call last):
File "run.py", line 93, in <module>
main()
File "run.py", line 82, in main
emenu.executemenu(components, _path)
File "/home/s1810979/paellego/lib/execute/execute_menu.py", line 29, in executemenu
e.executeall(installed, _path)
File "/home/s1810979/paellego/lib/execute/execute.py", line 153, in executeall
pool.starmap(phase2, args)
File "/usr/lib64/python3.4/multiprocessing/pool.py", line 268, in starmap
return self._map_async(func, iterable, starmapstar, chunksize).get()
File "/usr/lib64/python3.4/multiprocessing/pool.py", line 608, in get
raise self._value
File "/usr/lib64/python3.4/multiprocessing/pool.py", line 385, in _handle_tasks
put(task)
File "/usr/lib64/python3.4/multiprocessing/connection.py", line 206, in send
self._send_bytes(ForkingPickler.dumps(obj))
File "/usr/lib64/python3.4/multiprocessing/reduction.py", line 50, in dumps
cls(buf, protocol).dump(obj)
_pickle.PicklingError: Can't pickle <class 'module'>: attribute lookup module on builtins failed
Code
execute.py
def executeall(components, _path):
args = []
manager = multiprocessing.Manager()
q = manager.Queue()
resultloc = '/some/result.log'
for component in components:
for apkpath, resultpath in zip(execonfig.apkpaths, execonfig.resultpaths):
args.append((component,apkpath,resultpath,q,)) #Args for subprocesses
cores = askcores()
with multiprocessing.Pool(processes=cores) as pool:
watcher = pool.apply_async(lgr.log, (resultloc+'/results.txt', q,))
pool.starmap(phase2, args)
component.py
class Component(object):
def __init__(self, installmodule, runmodule, installerloc, installationloc, dependencyloc):
self.installmodule = installmodule
self.runmodule = runmodule
self.installerloc = installerloc
self.installationloc = installationloc
self.dependencyloc = dependencyloc
self.config = icnf.Installconfiguration(installerloc+'/conf.conf')
#lots of functions...
installconfig.py
class State(Enum):
BEGIN=0 #Look for units
UNIT=1 #Look for unit keypairs
KEYPAIR=3
class Phase(Enum):
NONE=0
DEPS=1
PKGS=2
class Installconfiguration(object):
def __init__(self, config):
dictionary = self.reader(config) #Fill a dictionary
#dictionary (key:Phase, value: (dictionary key: str, job))
self.deps = dictionary[Phase.DEPS]
self.pkgs = dictionary[Phase.PKGS]
job.py
class Job(object):
def __init__(self, directory=None, url=None):
self.directory = directory if directory else ''
self.url = url if url else ''
As you can see, I pass a component as argument to function phase2(component, str, str, multiprocess.manager.Queue()).
The second and third argument of the constructor of component are modules imported with importlib.
What I tried
I am new to python, but not to programming. Here is what I tried:
Because the error itself did not point out what the problem was exactly, I tried removing args to find out which can't be pickled: Remove component, and everything works fine, so this appears to be the cause for trouble. However, I need this object passed to my processes.
I searched around the internet for hours, but did not find anything but basic tutorials about multiprocessing, and explanations about how pickle works. I did find this saying it should work, but not on windows or something. However, it does not work on Unix (which I use)
My ideas
As I understood it, nothing suggests I cannot send a class containing two importlib modules. I do not know what the exact problem is with component class, but importlib module as members are the only non-regular things. This is why I believe the problem occurs here.
Question
Do you know why a class containing modules is unsuitable for 'pickling'? How can one get a better idea why and where Can't pickle <class 'module'> errors occur?
More code
Full source code for this can be found on https://github.com/Sebastiaan-Alvarez-Rodriguez/paellego
Questions to me
Please leave comments requesting clarifications/more code snippets/??? if you would like me to edit this question
A last request
I would like solutions to use python standard library only, python 3.3 preferably. Also, a requirement of my code is that it runs on Unix systems.
Thanks in advance
Edit
As requested, here is a minimal example which greatly simplifies the problem:
main.py (you could execute as python main.py foo)
#!/usr/bin/env python
import sys
import importlib
import multiprocessing
class clazz(object):
def __init__(self, moduly):
self.moduly = moduly
def foopass(self, stringy):
self.moduly.foo(stringy)
def barpass(self, stringy, numbery):
self.moduly.bar(stringy)
print('Second argument: '+str(numbery))
def worker(clazzy, numbery):
clazzy.barpass('wow', numbery)
def main():
clazzy = clazz(importlib.import_module(sys.argv[1]))
clazzy.foopass('init')
args = [(clazzy, 2,)]
with multiprocessing.Pool(processes=2) as pool:
pool.starmap(worker, args)
if __name__ == "__main__":
main()
foo.py (needs to be in same directory for above call suggestion):
#!/usr/bin/env python
globaly = 0
def foo(stringy):
print('foo '+stringy)
global globaly
globaly = 5
def bar(stringy):
print('bar '+stringy)
print(str(globaly))
This gives error upon running: TypeError: can't pickle module objects
Now we know that pickling module objects is (sadly) not possible.
In order to get rid of the error, let clazz not take a module as attribute, however convenient, but let it take "modpath", which is the required string for importlib to import the module specified by user.
It looks like this (foo.py remains exactly the same as above):
#!/usr/bin/env python
import sys
import importlib
import multiprocessing
class clazz(object):
def __init__(self, modpathy):
self.modpathy = modpathy
def foopass(self, stringy):
moduly = importlib.import_module(self.modpathy)
moduly.foo(stringy)
def barpass(self, stringy, numbery):
moduly = importlib.import_module(self.modpathy)
moduly.bar(stringy)
print('Second argument: '+str(numbery))
def worker(clazzy, number):
clazzy.barpass('wow', number)
def main():
clazzy = clazz(sys.argv[1])
clazzy.foopass('init')
args = [(clazzy, 2,)]
with multiprocessing.Pool(processes=2) as pool:
pool.starmap(worker, args)
if __name__ == "__main__":
main()
If you require that your globals, such as globaly, are guaranteed to maintain state, then you need to pass a mutable object (e.g. list, dictionary) to hold this data, thanks #DavisHerring:
Module attributes are called “global variables” in Python, but they are no more persistent or accessible than any other data. Why not just use dictionaries?
The example code would look like this:
#!/usr/bin/env python
import sys
import importlib
import multiprocessing
class clazz(object):
def __init__(self, modpathy):
self.modpathy = modpathy
self.dictionary = {}
def foopass(self, stringy):
moduly = importlib.import_module(self.modpathy)
moduly.foo(stringy, self.dictionary)
def barpass(self, stringy, numbery):
moduly = importlib.import_module(self.modpathy)
moduly.bar(stringy, self.dictionary)
print('Second argument: '+str(numbery))
def worker(clazzy, number):
clazzy.barpass('wow', number)
def main():
clazzy = clazz(sys.argv[1])
clazzy.foopass('init')
args = [(clazzy, 2,)]
with multiprocessing.Pool(processes=2) as pool:
pool.starmap(worker, args)
if __name__ == "__main__":
main()
foo.py (no more globals):
#!/usr/bin/env python
def foo(stringy, dictionary):
print('foo '+stringy)
globaly = 5
dictionary['globaly'] = globaly
def bar(stringy, dictionary):
print('bar '+stringy)
globaly = dictionary['globaly']
print(str(globaly))
This way you can work around the problem without annoying can't pickle ... errors, and while maintaining states

missing 1 required positional argument in click CLI

I've written a CLI with click originally as a module and it worked fine. But since my project got bigger I now need to have attributes the CLI can work with, so I tried to turn it into a class, but I'm running into an error doing it. My code is like the following:
import click
import click_repl
import os
from prompt_toolkit.history import FileHistory
class CLI:
def __init__(self):
pass
#click.group(invoke_without_command=True)
#click.pass_context
def cli(self, ctx):
if ctx.invoked_subcommand is None:
ctx.invoke(self.repl)
#cli.command()
def foo(self):
print("foo")
#cli.command()
def repl(self):
prompt_kwargs = {
'history': FileHistory(os.path.expanduser('~/.repl_history'))
}
click_repl.repl(click.get_current_context(), prompt_kwargs)
def main(self):
while True:
try:
self.cli(obj={})
except SystemExit:
pass
if __name__ == "__main__":
foo = CLI()
foo.main()
Without all the selfs and the class CLI: the CLI is working as expected, but as a class it runs into an error: TypeError: cli() missing 1 required positional argument: 'ctx' I don't understand why this happens. As far as I know calling self.cli() should pass self automatically, thus obj={} should be passed as ctx.obj, so it shouldn't make any difference to cli if it's wrapped in a class or not.
Can someone explain to me, why this happens and more important, how I can fix it?
In case it's relevant here is the complete error stack trace:
Traceback (most recent call last):
File "C:/Users/user/.PyCharmCE2018.2/config/scratches/exec.py", line
37, in <module>
foo.main()
File "C:/Users/user/.PyCharmCE2018.2/config/scratches/exec.py", line
30, in main
self.cli(obj={})
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site- packages\click\core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site-packages\click\core.py", line 717, in main
rv = self.invoke(ctx)
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site-packages\click\core.py", line 1114, in invoke
return Command.invoke(self, ctx)
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site-packages\click\core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site-packages\click\core.py", line 555, in invoke
return callback(*args, **kwargs)
File "C:\Users\user\AppData\Local\Programs\Python\Python37\lib\site-packages\click\decorators.py", line 17, in new_func
return f(get_current_context(), *args, **kwargs)
TypeError: cli() missing 1 required positional argument: 'ctx'
EDIT: The problem seems to be the pass_context call. Usually pass_context would provide the current context as first parameter to the function, so that obj={} would be passed to the context instance. But since I wrapped the click-group into a class, the first spot is taken by the self-reference, so that the current context can't be passed to the function. Any ideas of how to work around that?
I tried changing def cli() the following way:
#click.group(invoke_without_command=True)
def cli(self):
ctx = click.get_current_context()
ctx.obj = {}
if ctx.invoked_subcommand is None:
ctx.invoke(self.repl)
So I don't pass the context by call avoiding a conflict with self, but if I try to run this with self.cli() error TypeError: cli() missing 1 required positional argument: 'self' happens.
Calling it with self.cli(self) runs into TypeError: 'CLI' object is not iterable
I am afraid the click library is not designed to work as a class. Click makes use of decorators. Don't take decorators too lightly. Decorators literally take your function as argument and return a different function.
For example:
#cli.command()
def foo(self):
Is something in line of
foo = cli.command()(foo)
So, I am afraid that click has not support to decorate functions bound to classes, but can only decorate functions that are unbound. So, basically the solution to your answer is, don't use a class.
You might be wondering how to organize your code now. Most languages present you the class as an unit of organization.
Python however goes one step further and gives you modules as well. Basically a file is a module and within this file everything you put in there is automatically associated with that file as a module.
So, just name a file cli.py and create your attributes as global variables. This might give you other problems, since you cannot alter global variables in a function scope, but you can use a class to contain your variables instead.
class Variables:
pass
variables = Variables()
variables.something = "Something"
def f():
variables.something = "Nothing"

Sending arguments to Python threads blocks other threads

Consider this test application for passing arguments to Python threads:
#!/usr/bin/python3
from pprint import pprint
import signal
import sys
import threading
class CallThreads(threading.Thread):
def __init__(self, target, *args):
self._target = target
threading.Thread.__init__(self)
target(*args)
def main(argv):
phrases = ['hello', 'goodbye']
num = 0
for phrase in phrases:
num += 1
thread_handler = CallThreads(someFunction, phrase, num)
thread_handler.daemon = True
thread_handler.start()
return True
def someFunction(a, b):
print("Hi: "+str(a)+" and "+str(b))
return True
def signal_handler(signal, frame):
print(["Got SIGINT!"])
sys.exit(0)
if __name__ == '__main__':
signal.signal(signal.SIGINT, signal_handler)
main(sys.argv)
In it's current state, it seems as though the for phrase in phrases loop is waiting for the thread to finish before starting another thread. That is, if someFunction() takes a long time to complete, then the then next thread will not start until the previous thread returns. Why is this, and how can I work around it while still sending arguments to the threads?
Edit:
I've tried saving the args array in self._args in the constructor, and then calling self._target(*self._args) or self._target(self._args) in def run (self):. This actually works in Python 2, but not in Python 3. What should I do?
Edit:
It seems that the problem is that in Python 3, the run method cannot access the private variables. That is, for the following improved code:
def __init__(self, target, *args):
self._args = args
threading.Thread.__init__(self)
def run(self):
someFunction(*self._args)
Note the following output:
Exception in thread Thread-1:
Traceback (most recent call last):
File "/usr/lib/python3.3/threading.py", line 639, in _bootstrap_inner
self.run()
File "./test.py", line 19, in run
someFunction(*self._args)
TypeError: someFunction() missing 2 required positional arguments: 'a' and 'b'
And adding a pprint(self._args) to the run() method indeed shows that the tuple returned is empty. However, changing the variables to non-private works! The following code runs fine:
def __init__(self, target, *args):
self.target = target
self.args = args
threading.Thread.__init__(self)
def run(self):
self.target(*self.args)
Therefore, I can use the application with public variables in Python 3. However, is there any way to use private variables in the CallThreads class, as in Python 2?
Thanks!
The problem is that you call target(args) on the constructor of CallThreads.
Therefore the following call blocks until CallThreads.__init__() is finished:
thread_handler = CallThreads(someFunction, phrase, num)
Update:
One possibility could be the following:
class CallThreads(threading.Thread):
def __init__(self, *args):
self._args = args
threading.Thread.__init__(self)
def run(self):
someFunction(*self._args)

Python multiprocessing PicklingError: Can't pickle <type 'function'>

I am sorry that I can't reproduce the error with a simpler example, and my code is too complicated to post. If I run the program in IPython shell instead of the regular Python, things work out well.
I looked up some previous notes on this problem. They were all caused by using pool to call function defined within a class function. But this is not the case for me.
Exception in thread Thread-3:
Traceback (most recent call last):
File "/usr/lib64/python2.7/threading.py", line 552, in __bootstrap_inner
self.run()
File "/usr/lib64/python2.7/threading.py", line 505, in run
self.__target(*self.__args, **self.__kwargs)
File "/usr/lib64/python2.7/multiprocessing/pool.py", line 313, in _handle_tasks
put(task)
PicklingError: Can't pickle <type 'function'>: attribute lookup __builtin__.function failed
I would appreciate any help.
Update: The function I pickle is defined at the top level of the module. Though it calls a function that contains a nested function. i.e, f() calls g() calls h() which has a nested function i(), and I am calling pool.apply_async(f). f(), g(), h() are all defined at the top level. I tried simpler example with this pattern and it works though.
Here is a list of what can be pickled. In particular, functions are only picklable if they are defined at the top-level of a module.
This piece of code:
import multiprocessing as mp
class Foo():
#staticmethod
def work(self):
pass
if __name__ == '__main__':
pool = mp.Pool()
foo = Foo()
pool.apply_async(foo.work)
pool.close()
pool.join()
yields an error almost identical to the one you posted:
Exception in thread Thread-2:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 552, in __bootstrap_inner
self.run()
File "/usr/lib/python2.7/threading.py", line 505, in run
self.__target(*self.__args, **self.__kwargs)
File "/usr/lib/python2.7/multiprocessing/pool.py", line 315, in _handle_tasks
put(task)
PicklingError: Can't pickle <type 'function'>: attribute lookup __builtin__.function failed
The problem is that the pool methods all use a mp.SimpleQueue to pass tasks to the worker processes. Everything that goes through the mp.SimpleQueue must be pickable, and foo.work is not picklable since it is not defined at the top level of the module.
It can be fixed by defining a function at the top level, which calls foo.work():
def work(foo):
foo.work()
pool.apply_async(work,args=(foo,))
Notice that foo is pickable, since Foo is defined at the top level and foo.__dict__ is picklable.
I'd use pathos.multiprocesssing, instead of multiprocessing. pathos.multiprocessing is a fork of multiprocessing that uses dill. dill can serialize almost anything in python, so you are able to send a lot more around in parallel. The pathos fork also has the ability to work directly with multiple argument functions, as you need for class methods.
>>> from pathos.multiprocessing import ProcessingPool as Pool
>>> p = Pool(4)
>>> class Test(object):
... def plus(self, x, y):
... return x+y
...
>>> t = Test()
>>> p.map(t.plus, x, y)
[4, 6, 8, 10]
>>>
>>> class Foo(object):
... #staticmethod
... def work(self, x):
... return x+1
...
>>> f = Foo()
>>> p.apipe(f.work, f, 100)
<processing.pool.ApplyResult object at 0x10504f8d0>
>>> res = _
>>> res.get()
101
Get pathos (and if you like, dill) here:
https://github.com/uqfoundation
When this problem comes up with multiprocessing a simple solution is to switch from Pool to ThreadPool. This can be done with no change of code other than the import-
from multiprocessing.pool import ThreadPool as Pool
This works because ThreadPool shares memory with the main thread, rather than creating a new process- this means that pickling is not required.
The downside to this method is that python isn't the greatest language with handling threads- it uses something called the Global Interpreter Lock to stay thread safe, which can slow down some use cases here. However, if you're primarily interacting with other systems (running HTTP commands, talking with a database, writing to filesystems) then your code is likely not bound by CPU and won't take much of a hit. In fact I've found when writing HTTP/HTTPS benchmarks that the threaded model used here has less overhead and delays, as the overhead from creating new processes is much higher than the overhead for creating new threads and the program was otherwise just waiting for HTTP responses.
So if you're processing a ton of stuff in python userspace this might not be the best method.
As others have said multiprocessing can only transfer Python objects to worker processes which can be pickled. If you cannot reorganize your code as described by unutbu, you can use dills extended pickling/unpickling capabilities for transferring data (especially code data) as I show below.
This solution requires only the installation of dill and no other libraries as pathos:
import os
from multiprocessing import Pool
import dill
def run_dill_encoded(payload):
fun, args = dill.loads(payload)
return fun(*args)
def apply_async(pool, fun, args):
payload = dill.dumps((fun, args))
return pool.apply_async(run_dill_encoded, (payload,))
if __name__ == "__main__":
pool = Pool(processes=5)
# asyn execution of lambda
jobs = []
for i in range(10):
job = apply_async(pool, lambda a, b: (a, b, a * b), (i, i + 1))
jobs.append(job)
for job in jobs:
print job.get()
print
# async execution of static method
class O(object):
#staticmethod
def calc():
return os.getpid()
jobs = []
for i in range(10):
job = apply_async(pool, O.calc, ())
jobs.append(job)
for job in jobs:
print job.get()
I have found that I can also generate exactly that error output on a perfectly working piece of code by attempting to use the profiler on it.
Note that this was on Windows (where the forking is a bit less elegant).
I was running:
python -m profile -o output.pstats <script>
And found that removing the profiling removed the error and placing the profiling restored it. Was driving me batty too because I knew the code used to work. I was checking to see if something had updated pool.py... then had a sinking feeling and eliminated the profiling and that was it.
Posting here for the archives in case anybody else runs into it.
Can't pickle <type 'function'>: attribute lookup __builtin__.function failed
This error will also come if you have any inbuilt function inside the model object that was passed to the async job.
So make sure to check the model objects that are passed doesn't have inbuilt functions. (In our case we were using FieldTracker() function of django-model-utils inside the model to track a certain field). Here is the link to relevant GitHub issue.
This solution requires only the installation of dill and no other libraries as pathos
def apply_packed_function_for_map((dumped_function, item, args, kwargs),):
"""
Unpack dumped function as target function and call it with arguments.
:param (dumped_function, item, args, kwargs):
a tuple of dumped function and its arguments
:return:
result of target function
"""
target_function = dill.loads(dumped_function)
res = target_function(item, *args, **kwargs)
return res
def pack_function_for_map(target_function, items, *args, **kwargs):
"""
Pack function and arguments to object that can be sent from one
multiprocessing.Process to another. The main problem is:
«multiprocessing.Pool.map*» or «apply*»
cannot use class methods or closures.
It solves this problem with «dill».
It works with target function as argument, dumps it («with dill»)
and returns dumped function with arguments of target function.
For more performance we dump only target function itself
and don't dump its arguments.
How to use (pseudo-code):
~>>> import multiprocessing
~>>> images = [...]
~>>> pool = multiprocessing.Pool(100500)
~>>> features = pool.map(
~... *pack_function_for_map(
~... super(Extractor, self).extract_features,
~... images,
~... type='png'
~... **options,
~... )
~... )
~>>>
:param target_function:
function, that you want to execute like target_function(item, *args, **kwargs).
:param items:
list of items for map
:param args:
positional arguments for target_function(item, *args, **kwargs)
:param kwargs:
named arguments for target_function(item, *args, **kwargs)
:return: tuple(function_wrapper, dumped_items)
It returs a tuple with
* function wrapper, that unpack and call target function;
* list of packed target function and its' arguments.
"""
dumped_function = dill.dumps(target_function)
dumped_items = [(dumped_function, item, args, kwargs) for item in items]
return apply_packed_function_for_map, dumped_items
It also works for numpy arrays.
A quick fix is to make the function global
from multiprocessing import Pool
class Test:
def __init__(self, x):
self.x = x
#staticmethod
def test(x):
return x**2
def test_apply(self, list_):
global r
def r(x):
return Test.test(x + self.x)
with Pool() as p:
l = p.map(r, list_)
return l
if __name__ == '__main__':
o = Test(2)
print(o.test_apply(range(10)))
Building on #rocksportrocker solution,
It would make sense to dill when sending and RECVing the results.
import dill
import itertools
def run_dill_encoded(payload):
fun, args = dill.loads(payload)
res = fun(*args)
res = dill.dumps(res)
return res
def dill_map_async(pool, fun, args_list,
as_tuple=True,
**kw):
if as_tuple:
args_list = ((x,) for x in args_list)
it = itertools.izip(
itertools.cycle([fun]),
args_list)
it = itertools.imap(dill.dumps, it)
return pool.map_async(run_dill_encoded, it, **kw)
if __name__ == '__main__':
import multiprocessing as mp
import sys,os
p = mp.Pool(4)
res = dill_map_async(p, lambda x:[sys.stdout.write('%s\n'%os.getpid()),x][-1],
[lambda x:x+1]*10,)
res = res.get(timeout=100)
res = map(dill.loads,res)
print(res)
As #penky Suresh has suggested in this answer, don't use built-in keywords.
Apparently args is a built-in keyword when dealing with multiprocessing
class TTS:
def __init__(self):
pass
def process_and_render_items(self):
multiprocessing_args = [{"a": "b", "c": "d"}, {"e": "f", "g": "h"}]
with ProcessPoolExecutor(max_workers=10) as executor:
# Using args here is fine.
future_processes = {
executor.submit(TTS.process_and_render_item, args)
for args in multiprocessing_args
}
for future in as_completed(future_processes):
try:
data = future.result()
except Exception as exc:
print(f"Generated an exception: {exc}")
else:
print(f"Generated data for comment process: {future}")
# Dont use 'args' here. It seems to be a built-in keyword.
# Changing 'args' to 'arg' worked for me.
def process_and_render_item(arg):
print(arg)
# This will print {"a": "b", "c": "d"} for the first process
# and {"e": "f", "g": "h"} for the second process.
PS: The tabs/spaces maybe a bit off.

Categories