Can't pickle when using multiprocessing Pool.map()

Question

I\'m trying to use multiprocessing\'s Pool.map() function to divide out work simultaneously. When I use the following code, it works fine:

Answer 1

Some limitations though to Steven Bethard's solution :

When you register your class method as a function, the destructor of your class is surprisingly called every time your method processing is finished. So if you have 1 instance of your class that calls n times its method, members may disappear between 2 runs and you may get a message malloc: *** error for object 0x...: pointer being freed was not allocated (e.g. open member file) or pure virtual method called, terminate called without an active exception (which means than the lifetime of a member object I used was shorter than what I thought). I got this when dealing with n greater than the pool size. Here is a short example :

from multiprocessing import Pool, cpu_count
from multiprocessing.pool import ApplyResult

# --------- see Stenven's solution above -------------
from copy_reg import pickle
from types import MethodType

def _pickle_method(method):
    func_name = method.im_func.__name__
    obj = method.im_self
    cls = method.im_class
    return _unpickle_method, (func_name, obj, cls)

def _unpickle_method(func_name, obj, cls):
    for cls in cls.mro():
        try:
            func = cls.__dict__[func_name]
        except KeyError:
            pass
        else:
            break
    return func.__get__(obj, cls)


class Myclass(object):

    def __init__(self, nobj, workers=cpu_count()):

        print "Constructor ..."
        # multi-processing
        pool = Pool(processes=workers)
        async_results = [ pool.apply_async(self.process_obj, (i,)) for i in range(nobj) ]
        pool.close()
        # waiting for all results
        map(ApplyResult.wait, async_results)
        lst_results=[r.get() for r in async_results]
        print lst_results

    def __del__(self):
        print "... Destructor"

    def process_obj(self, index):
        print "object %d" % index
        return "results"

pickle(MethodType, _pickle_method, _unpickle_method)
Myclass(nobj=8, workers=3)
# problem !!! the destructor is called nobj times (instead of once)

Output:

Constructor ...
object 0
object 1
object 2
... Destructor
object 3
... Destructor
object 4
... Destructor
object 5
... Destructor
object 6
... Destructor
object 7
... Destructor
... Destructor
... Destructor
['results', 'results', 'results', 'results', 'results', 'results', 'results', 'results']
... Destructor

The __call__ method is not so equivalent, because [None,...] are read from the results :

from multiprocessing import Pool, cpu_count
from multiprocessing.pool import ApplyResult

class Myclass(object):

    def __init__(self, nobj, workers=cpu_count()):

        print "Constructor ..."
        # multiprocessing
        pool = Pool(processes=workers)
        async_results = [ pool.apply_async(self, (i,)) for i in range(nobj) ]
        pool.close()
        # waiting for all results
        map(ApplyResult.wait, async_results)
        lst_results=[r.get() for r in async_results]
        print lst_results

    def __call__(self, i):
        self.process_obj(i)

    def __del__(self):
        print "... Destructor"

    def process_obj(self, i):
        print "obj %d" % i
        return "result"

Myclass(nobj=8, workers=3)
# problem !!! the destructor is called nobj times (instead of once), 
# **and** results are empty !

So none of both methods is satisfying...