我正在启动3个进程,我希望他们将一个字符串放入一个共享数组,在与进程(i)对应的索引处。
查看下面的代码,生成的输出是:
['test 0', None, None]
['test 1', 'test 1', None]
['test 2', 'test 2', 'test 2']
为什么'test 0'被test 1
覆盖,test 1
被test 2
覆盖?
我想要的是(顺序并不重要):
['test 0', None, None]
['test 0', 'test 1', None]
['test 0', 'test 1', 'test 2']
代码:
#!/usr/bin/env python
import multiprocessing
from multiprocessing import Value, Lock, Process, Array
import ctypes
from ctypes import c_int, c_char_p
class Consumer(multiprocessing.Process):
def __init__(self, task_queue, result_queue, arr, lock):
multiprocessing.Process.__init__(self)
self.task_queue = task_queue
self.result_queue = result_queue
self.arr = arr
self.lock = lock
def run(self):
proc_name = self.name
while True:
next_task = self.task_queue.get()
if next_task is None:
self.task_queue.task_done()
break
answer = next_task(arr=self.arr, lock=self.lock)
self.task_queue.task_done()
self.result_queue.put(answer)
return
class Task(object):
def __init__(self, i):
self.i = i
def __call__(self, arr=None, lock=None):
with lock:
arr[self.i] = "test %d" % self.i
print arr[:]
def __str__(self):
return 'ARC'
def run(self):
print 'IN'
if __name__ == '__main__':
tasks = multiprocessing.JoinableQueue()
results = multiprocessing.Queue()
arr = Array(ctypes.c_char_p, 3)
lock = multiprocessing.Lock()
num_consumers = multiprocessing.cpu_count() * 2
consumers = [Consumer(tasks, results, arr, lock) for i in xrange(num_consumers)]
for w in consumers:
w.start()
for i in xrange(3):
tasks.put(Task(i))
for i in xrange(num_consumers):
tasks.put(None)
我正在运行Python 2.7.3(Ubuntu)
答案 0 :(得分:5)
此问题与this one类似。在那里,J.F。Sebastian推测将arr[i]
点arr[i]
分配给一个只对进行赋值的子进程有意义的内存地址。其他子进程在查看该地址时检索垃圾。
至少有两种方法可以避免这个问题。一种是使用multiprocessing.manager
列表:
import multiprocessing as mp
class Consumer(mp.Process):
def __init__(self, task_queue, result_queue, lock, lst):
mp.Process.__init__(self)
self.task_queue = task_queue
self.result_queue = result_queue
self.lock = lock
self.lst = lst
def run(self):
proc_name = self.name
while True:
next_task = self.task_queue.get()
if next_task is None:
self.task_queue.task_done()
break
answer = next_task(lock = self.lock, lst = self.lst)
self.task_queue.task_done()
self.result_queue.put(answer)
return
class Task(object):
def __init__(self, i):
self.i = i
def __call__(self, lock, lst):
with lock:
lst[self.i] = "test {}".format(self.i)
print([lst[i] for i in range(3)])
if __name__ == '__main__':
tasks = mp.JoinableQueue()
results = mp.Queue()
manager = mp.Manager()
lst = manager.list(['']*3)
lock = mp.Lock()
num_consumers = mp.cpu_count() * 2
consumers = [Consumer(tasks, results, lock, lst) for i in xrange(num_consumers)]
for w in consumers:
w.start()
for i in xrange(3):
tasks.put(Task(i))
for i in xrange(num_consumers):
tasks.put(None)
tasks.join()
另一种方法是使用具有固定大小的共享数组,例如mp.Array('c', 10)
。
import multiprocessing as mp
class Consumer(mp.Process):
def __init__(self, task_queue, result_queue, arr, lock):
mp.Process.__init__(self)
self.task_queue = task_queue
self.result_queue = result_queue
self.arr = arr
self.lock = lock
def run(self):
proc_name = self.name
while True:
next_task = self.task_queue.get()
if next_task is None:
self.task_queue.task_done()
break
answer = next_task(arr = self.arr, lock = self.lock)
self.task_queue.task_done()
self.result_queue.put(answer)
return
class Task(object):
def __init__(self, i):
self.i = i
def __call__(self, arr, lock):
with lock:
arr[self.i].value = "test {}".format(self.i)
print([a.value for a in arr])
if __name__ == '__main__':
tasks = mp.JoinableQueue()
results = mp.Queue()
arr = [mp.Array('c', 10) for i in range(3)]
lock = mp.Lock()
num_consumers = mp.cpu_count() * 2
consumers = [Consumer(tasks, results, arr, lock) for i in xrange(num_consumers)]
for w in consumers:
w.start()
for i in xrange(3):
tasks.put(Task(i))
for i in xrange(num_consumers):
tasks.put(None)
tasks.join()
我推测,当mp.Array(ctypes.c_char_p, 3)
没有时,这是有效的,因为mp.Array('c', 10)
具有固定大小,因此内存地址永远不会改变,而mp.Array(ctypes.c_char_p, 3)
具有可变大小,所以将arr[i]
分配给更大的字符串时,内存地址可能会发生变化。
也许这就是the docs在发表声明时发出的警告,
虽然可以将指针存储在共享内存中,但请记住 这将引用特定地址空间中的位置 处理。但是,指针很可能在无效中 第二个进程的上下文,并尝试取消引用指针 第二个过程可能会导致崩溃。