[python] 다중 처리의 공유 메모리 개체

나는 같은 문제를 겪고 그것을 해결하기 위해 약간의 공유 메모리 유틸리티 클래스를 작성했습니다.

나는 multiprocessing.RawArray(lockfree)를 사용 하고 있으며 배열에 대한 액세스가 전혀 동기화되지 않았습니다 (lockfree). 자신의 발을 쏘지 않도록 조심하십시오.

이 솔루션을 사용하면 쿼드 코어 i7에서 약 3 배의 속도 향상을 얻을 수 있습니다.

코드는 다음과 같습니다. 자유롭게 사용하고 개선하고 버그가 있으면 신고 해주세요.

'''
Created on 14.05.2013

@author: martin
'''

import multiprocessing
import ctypes
import numpy as np

class SharedNumpyMemManagerError(Exception):
    pass

'''
Singleton Pattern
'''
class SharedNumpyMemManager:    

    _initSize = 1024

    _instance = None

    def __new__(cls, *args, **kwargs):
        if not cls._instance:
            cls._instance = super(SharedNumpyMemManager, cls).__new__(
                                cls, *args, **kwargs)
        return cls._instance        

    def __init__(self):
        self.lock = multiprocessing.Lock()
        self.cur = 0
        self.cnt = 0
        self.shared_arrays = [None] * SharedNumpyMemManager._initSize

    def __createArray(self, dimensions, ctype=ctypes.c_double):

        self.lock.acquire()

        # double size if necessary
        if (self.cnt >= len(self.shared_arrays)):
            self.shared_arrays = self.shared_arrays + [None] * len(self.shared_arrays)

        # next handle
        self.__getNextFreeHdl()        

        # create array in shared memory segment
        shared_array_base = multiprocessing.RawArray(ctype, np.prod(dimensions))

        # convert to numpy array vie ctypeslib
        self.shared_arrays[self.cur] = np.ctypeslib.as_array(shared_array_base)

        # do a reshape for correct dimensions            
        # Returns a masked array containing the same data, but with a new shape.
        # The result is a view on the original array
        self.shared_arrays[self.cur] = self.shared_arrays[self.cnt].reshape(dimensions)

        # update cnt
        self.cnt += 1

        self.lock.release()

        # return handle to the shared memory numpy array
        return self.cur

    def __getNextFreeHdl(self):
        orgCur = self.cur
        while self.shared_arrays[self.cur] is not None:
            self.cur = (self.cur + 1) % len(self.shared_arrays)
            if orgCur == self.cur:
                raise SharedNumpyMemManagerError('Max Number of Shared Numpy Arrays Exceeded!')

    def __freeArray(self, hdl):
        self.lock.acquire()
        # set reference to None
        if self.shared_arrays[hdl] is not None: # consider multiple calls to free
            self.shared_arrays[hdl] = None
            self.cnt -= 1
        self.lock.release()

    def __getArray(self, i):
        return self.shared_arrays[i]

    @staticmethod
    def getInstance():
        if not SharedNumpyMemManager._instance:
            SharedNumpyMemManager._instance = SharedNumpyMemManager()
        return SharedNumpyMemManager._instance

    @staticmethod
    def createArray(*args, **kwargs):
        return SharedNumpyMemManager.getInstance().__createArray(*args, **kwargs)

    @staticmethod
    def getArray(*args, **kwargs):
        return SharedNumpyMemManager.getInstance().__getArray(*args, **kwargs)

    @staticmethod    
    def freeArray(*args, **kwargs):
        return SharedNumpyMemManager.getInstance().__freeArray(*args, **kwargs)

# Init Singleton on module load
SharedNumpyMemManager.getInstance()

if __name__ == '__main__':

    import timeit

    N_PROC = 8
    INNER_LOOP = 10000
    N = 1000

    def propagate(t):
        i, shm_hdl, evidence = t
        a = SharedNumpyMemManager.getArray(shm_hdl)
        for j in range(INNER_LOOP):
            a[i] = i

    class Parallel_Dummy_PF:

        def __init__(self, N):
            self.N = N
            self.arrayHdl = SharedNumpyMemManager.createArray(self.N, ctype=ctypes.c_double)            
            self.pool = multiprocessing.Pool(processes=N_PROC)

        def update_par(self, evidence):
            self.pool.map(propagate, zip(range(self.N), [self.arrayHdl] * self.N, [evidence] * self.N))

        def update_seq(self, evidence):
            for i in range(self.N):
                propagate((i, self.arrayHdl, evidence))

        def getArray(self):
            return SharedNumpyMemManager.getArray(self.arrayHdl)

    def parallelExec():
        pf = Parallel_Dummy_PF(N)
        print(pf.getArray())
        pf.update_par(5)
        print(pf.getArray())

    def sequentialExec():
        pf = Parallel_Dummy_PF(N)
        print(pf.getArray())
        pf.update_seq(5)
        print(pf.getArray())

    t1 = timeit.Timer("sequentialExec()", "from __main__ import sequentialExec")
    t2 = timeit.Timer("parallelExec()", "from __main__ import parallelExec")

    print("Sequential: ", t1.timeit(number=1))    
    print("Parallel: ", t2.timeit(number=1))

답변

import numpy as np
import ray

ray.init()

@ray.remote
def func(array, param):
    # Do stuff.
    return 1

array = np.ones(10**6)
# Store the array in the shared memory object store once
# so it is not copied multiple times.
array_id = ray.put(array)

result_ids = [func.remote(array_id, i) for i in range(4)]
output = ray.get(result_ids)

import numpy as np
import pickle
import ray

ray.init()

x = {i: np.ones(10**7) for i in range(20)}

# Time Ray.
%time x_id = ray.put(x)  # 2.4s
%time new_x = ray.get(x_id)  # 0.00073s

# Time pickle.
%time serialized = pickle.dumps(x)  # 2.6s
%time deserialized = pickle.loads(serialized)  # 1.9s

$ pip install brain-plasma

$ plasma_store -m 10000000 -s /tmp/plasma

from brain_plasma import Brain
brain = Brain(path='/tmp/plasma/)

brain['a'] = [1]*10000

brain['a']
# >>> [1,1,1,1,...]