Python - 动态使用multiprocessing模块
我正在尝试开发一个包装器,用来动态使用 multiprocessing
模块。我有很多函数分散在不同的模块里,需要好好管理这些函数。我需要能够把来自任何模块的函数和它的参数传递给我的包装器。因为这些数据和函数在运行时才会知道,所以它们是依赖用户的。
下面是我想要实现的一个例子:
import sys
from multiprocessing import Process, Queue, cpu_count
def dyn():
pass
class mp():
def __init__(self, data, func, n_procs = cpu_count()):
self.data = data
self.q = Queue()
self.n_procs = n_procs
# Replace module-level 'dyn' function with the provided function
setattr(sys.modules[__name__], 'dyn', func)
# Calling dyn(...) at this point will produce the same output as
# calling func(...)
def _worker(self, *items):
data = []
for item in items:
data.append(dyn(item))
self.q.put(data)
def compute(self):
for item in self.data:
Process(target=getattr(self, '_worker'), args=item).start()
def items(self):
queue_count = self.n_procs
while queue_count > 0:
queue_count -= 1
yield self.q.get()
if __name__ == '__main__':
def work(x):
return x ** 2
# Create workers
data = [range(10)] * cpu_count()
workers = mp(data, work)
# Make the workers work
workers.compute()
# Get the data from the workers
workers_data = []
for item in workers.items():
workers_data.append(item)
print workers_data
在这个例子中,输出应该是这个格式:
[[0, 1, 4, 9, 16, 25, 36, 49, 64, 81] * n_procs]
如果你尝试运行这段代码,你会遇到一个异常,提示传递给 dyn
的参数太多了。我认为问题在于 dyn
在这个实例中被覆盖了,但当调用 Process
时,这些更改就不再存在了。
我该如何解决这个问题呢?
注意 - 这段代码需要在Windows上运行。我使用的是Python 2.7。
更新
根据我收到的评论,我决定做一些“麻烦”的事情。下面是我工作的解决方案:
import sys, re, uuid, os
from cStringIO import StringIO
from multiprocessing import Process, Queue, cpu_count
class mp():
def __init__(self, data, func, n_procs = cpu_count()):
self.data = data
self.q = Queue()
self.n_procs = n_procs
self.module = 'm' + str(uuid.uuid1()).replace('-', '')
self.file = self.module + '.py'
# Build external module
self.__func_to_module(func)
def __func_to_module(self, func):
with open(self.file, 'wb') as f:
for line in StringIO(func):
if 'def' in line:
f.write(re.sub(r'def .*\(', 'def work(', line))
else:
f.write(line)
def _worker(self, q, module, *items):
exec('from %s import work' % module)
data = []
for item in items[0]:
data.append(work(item))
q.put(data)
def compute(self):
for item in self.data:
Process(target=getattr(self, '_worker'),
args=(self.q, self.module, item)).start()
def items(self):
queue_count = self.n_procs
while queue_count > 0:
queue_count -= 1
yield self.q.get()
os.remove(self.file)
os.remove(self.file + 'c')
if __name__ == '__main__':
func = '''def func(x):
return x ** 2'''
# Create workers
data = [range(10)] * cpu_count()
workers = mp(data, func)
# Make the workers work
workers.compute()
# Get the data from the workers
workers_data = []
for item in workers.items():
workers_data.append(item)
print workers_data
1 个回答
1
在Windows系统上,每当启动一个新的进程时,模块会被重新加载,这样就会丢失对“dyn”的定义。不过,你可以通过队列传递一个函数,或者通过参数传递给进程的目标函数。
def _worker(*items, func=None, q=None):
#note that this had better be a function not a method
data = []
for item in items:
data.append(func(item))
q.put(data)
#...
Process(target=_worker, args=item, kwargs={'func':dyn, 'q':q})