无法在Python的multiprocessing Pool.apply_async()中pickle <type 'instancemethod'>

Question

我想运行类似这样的代码：

from multiprocessing  import Pool
import time
import random

class Controler(object):
    def __init__(self):
        nProcess = 10
        pages = 10
        self.__result = []
        self.manageWork(nProcess,pages)

def BarcodeSearcher(x):
    return x*x

def resultCollector(self,result):
    self.__result.append(result)

def manageWork(self,nProcess,pages):
    pool = Pool(processes=nProcess)
    for pag in range(pages):
        pool.apply_async(self.BarcodeSearcher, args = (pag, ), callback = self.resultCollector)

    print self.__result

if __name__ == '__main__':
    Controler()

但是运行后出现了这个错误：

   Exception in thread Thread-1:
Traceback (most recent call last):
  File "C:\Python26\lib\threading.py", line 522, in __bootstrap_inner
    self.run()
  File "C:\Python26\lib\threading.py", line 477, in run
    self.__target(*self.__args, **self.__kwargs)
  File "C:\python26\lib\multiprocessing\pool.py", line 225, in _handle_tasks
    put(task)
PicklingError: Can't pickle <type 'instancemethod'>: attribute lookup __builtin__.instancemethod failed

我看过一些帖子（帖子1， 帖子2）来解决我的问题。我想要类似于第二个帖子中Mike McKern的解决方案，但不想使用pathos库。

Answer 1

这个方法是可行的，使用了 copy_reg，这是你提供的第一个链接中 Alex Martelli 提出的建议：

import copy_reg
import types
import multiprocessing


def _pickle_method(m):
    if m.im_self is None:
        return getattr, (m.im_class, m.im_func.func_name)
    else:
        return getattr, (m.im_self, m.im_func.func_name)

copy_reg.pickle(types.MethodType, _pickle_method)


class Controler(object):
    def __init__(self):
        nProcess = 10
        pages = 10
        self.__result = []
        self.manageWork(nProcess, pages)

    def BarcodeSearcher(self, x):
        return x*x

    def resultCollector(self, result):
        self.__result.append(result)

    def manageWork(self, nProcess, pages):
        pool = multiprocessing.Pool(processes=nProcess)
        for pag in range(pages):
            pool.apply_async(self.BarcodeSearcher, args=(pag,),
                             callback=self.resultCollector)
        pool.close()
        pool.join()

        print(self.__result)

if __name__ == '__main__':
    Controler()