在下面的示例代码中,我想恢复函数worker
的返回值。我该怎么做呢?这个值存储在哪里?
示例代码:
import multiprocessing
def worker(procnum):
'''worker function'''
print str(procnum) + ' represent!'
return procnum
if __name__ == '__main__':
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i,))
jobs.append(p)
p.start()
for proc in jobs:
proc.join()
print jobs
输出:
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
[<Process(Process-1, stopped)>, <Process(Process-2, stopped)>, <Process(Process-3, stopped)>, <Process(Process-4, stopped)>, <Process(Process-5, stopped)>]
我似乎无法在jobs
中存储的对象中找到相关属性。
提前致谢, BLZ
答案 0 :(得分:117)
使用shared variable进行通信。例如:
import multiprocessing
def worker(procnum, return_dict):
'''worker function'''
print str(procnum) + ' represent!'
return_dict[procnum] = procnum
if __name__ == '__main__':
manager = multiprocessing.Manager()
return_dict = manager.dict()
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i,return_dict))
jobs.append(p)
p.start()
for proc in jobs:
proc.join()
print return_dict.values()
答案 1 :(得分:51)
我认为@sega_sai建议的方法更好。但它确实需要一个代码示例,所以这里是:
import multiprocessing
from os import getpid
def worker(procnum):
print 'I am number %d in process %d' % (procnum, getpid())
return getpid()
if __name__ == '__main__':
pool = multiprocessing.Pool(processes = 3)
print pool.map(worker, range(5))
将打印返回值:
I am number 0 in process 19139
I am number 1 in process 19138
I am number 2 in process 19140
I am number 3 in process 19139
I am number 4 in process 19140
[19139, 19138, 19140, 19139, 19140]
如果您熟悉map
(内置Python 2),这应该不会太具挑战性。否则请查看sega_Sai's link。
请注意需要的代码很少。 (还要注意如何重复使用进程)。
答案 2 :(得分:16)
此示例显示如何使用multiprocessing.Pipe实例列表从任意数量的进程返回字符串:
import multiprocessing
def worker(procnum, send_end):
'''worker function'''
result = str(procnum) + ' represent!'
print result
send_end.send(result)
def main():
jobs = []
pipe_list = []
for i in range(5):
recv_end, send_end = multiprocessing.Pipe(False)
p = multiprocessing.Process(target=worker, args=(i, send_end))
jobs.append(p)
pipe_list.append(recv_end)
p.start()
for proc in jobs:
proc.join()
result_list = [x.recv() for x in pipe_list]
print result_list
if __name__ == '__main__':
main()
<强>输出:强>
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
['0 represent!', '1 represent!', '2 represent!', '3 represent!', '4 represent!']
此解决方案使用的资源少于使用
的multiprocessing.Queue或使用
的multiprocessing.SimpleQueue查看每种类型的来源非常有启发性。
答案 3 :(得分:10)
您似乎应该使用multiprocessing.Pool类并使用方法.apply()。apply_async(),map()
http://docs.python.org/library/multiprocessing.html?highlight=pool#multiprocessing.pool.AsyncResult
答案 4 :(得分:10)
对于正在寻求如何使用Process
从Queue
获取价值的其他人:
import multiprocessing
ret = {'foo': False}
def worker(queue):
ret = queue.get()
ret['foo'] = True
queue.put(ret)
if __name__ == '__main__':
queue = multiprocessing.Queue()
queue.put(ret)
p = multiprocessing.Process(target=worker, args=(queue,))
p.start()
print queue.get() # Prints {"foo": True}
p.join()
答案 5 :(得分:9)
您可以使用内置的exit
来设置流程的退出代码。它可以从流程的exitcode
属性中获取:
import multiprocessing
def worker(procnum):
print str(procnum) + ' represent!'
exit(procnum)
if __name__ == '__main__':
jobs = []
for i in range(5):
p = multiprocessing.Process(target=worker, args=(i,))
jobs.append(p)
p.start()
result = []
for proc in jobs:
proc.join()
result.append(proc.exitcode)
print result
<强>输出:强>
0 represent!
1 represent!
2 represent!
3 represent!
4 represent!
[0, 1, 2, 3, 4]
答案 6 :(得分:9)
出于某种原因,我无法找到一个如何使用Queue
在任何地方执行此操作的一般示例(即使Python的doc示例也不会产生多个进程),所以这就是我在10次尝试后工作的内容:
def add_helper(queue, arg1, arg2): # the func called in child processes
ret = arg1 + arg2
queue.put(ret)
def multi_add(): # spawns child processes
q = Queue()
processes = []
rets = []
for _ in range(0, 100):
p = Process(target=add_helper, args=(q, 1, 2))
processes.append(p)
p.start()
for p in processes:
ret = q.get() # will block
rets.append(ret)
for p in processes:
p.join()
return rets
Queue
是一个阻塞的,线程安全的队列,可用于存储子进程的返回值。所以你必须将队列传递给每个进程。这里不太明显的是,在get()
join
之前你必须从队列中Process
,否则队列会填满并阻止所有事情。
更新:
from multiprocessing import Process, Queue
class Multiprocessor():
def __init__(self):
self.processes = []
self.queue = Queue()
@staticmethod
def _wrapper(func, queue, args, kwargs):
ret = func(*args, **kwargs)
queue.put(ret)
def run(self, func, *args, **kwargs):
args2 = [func, self.queue, args, kwargs]
p = Process(target=self._wrapper, args=args2)
self.processes.append(p)
p.start()
def wait(self):
rets = []
for p in self.processes:
ret = self.queue.get()
rets.append(ret)
for p in self.processes:
p.join()
return rets
# tester
if __name__ == "__main__":
mp = Multiprocessor()
num_proc = 64
for _ in range(num_proc): # queue up multiple tasks running `sum`
mp.run(sum, [1, 2, 3, 4, 5])
ret = mp.wait() # get all results
print(ret)
assert len(ret) == num_proc and all(r == 15 for r in ret)
答案 7 :(得分:2)
如果您使用的是Python 3,则可以使用concurrent.futures.ProcessPoolExecutor
作为便捷的抽象方法:
<com.google.android.material.textfield.TextInputLayout
android:layout_width="0dip"
android:layout_weight="0.4"
android:id="@+id/tilFPCode"
app:errorTextAppearance="@style/style_EditText_ErrorStyle"
app:hintTextAppearance="@style/style_EditText_HintStyle"
android:layout_height="wrap_content">
<com.google.android.material.textfield.TextInputEditText
android:layout_width="match_parent"
android:layout_height="wrap_content"
android:maxLines="1"
android:maxLength="5"
android:id="@+id/etFPCode"
android:imeOptions="actionDone"
android:inputType="textCapCharacters"
android:textAllCaps="true"
android:hint="@string/forgot_sec_code_hint"
style="@style/style_EditText"/>
</com.google.android.material.textfield.TextInputLayout>
输出:
from concurrent.futures import ProcessPoolExecutor
def worker(procnum):
'''worker function'''
print(str(procnum) + ' represent!')
return procnum
if __name__ == '__main__':
with ProcessPoolExecutor() as executor:
print(list(executor.map(worker, range(5))))
答案 8 :(得分:1)
pebble软件包利用multiprocessing.Pipe
有一个很好的抽象,这使得这一过程非常简单:
from pebble import concurrent
@concurrent.process
def function(arg, kwarg=0):
return arg + kwarg
future = function(1, kwarg=1)
print(future.result())
答案 9 :(得分:1)
我想简化从上面复制的最简单的示例,在Py3.6上为我工作。最简单的是multiprocessing.Pool
:
import multiprocessing
import time
def worker(x):
time.sleep(1)
return x
pool = multiprocessing.Pool()
print(pool.map(worker, range(10)))
您可以使用Pool(processes=5)
来设置池中的进程数。但是,它默认为CPU计数,因此对于CPU绑定任务,将其留空。 (无论如何,受I / O约束的任务通常无论如何都适合线程,因为线程大多在等待,因此可以共享一个CPU内核。)Pool
也适用于chunking optimization。
(请注意,worker方法不能嵌套在方法中。我最初在对pool.map
进行调用的方法内定义了worker方法,以使其全部独立,但随后这些进程无法t导入它,并抛出“ AttributeError:无法腌制本地对象external_method..inner_method”。更多here。它可以在一个类中。)
Py3的ProcessPoolExecutor
也是两行(.map
返回一个生成器,因此您需要list()
):
from concurrent.futures import ProcessPoolExecutor
with ProcessPoolExecutor() as executor:
print(list(executor.map(worker, range(10))))
使用普通的Process
是:
import multiprocessing
import time
def worker(x, queue):
time.sleep(1)
queue.put(x)
queue = multiprocessing.SimpleQueue()
tasks = range(10)
for task in tasks:
multiprocessing.Process(target=worker, args=(task, queue,)).start()
for _ in tasks:
print(queue.get())
如果您只需要put
和get
,请使用SimpleQueue
。第一个循环开始所有进程,然后第二个循环进行阻塞的queue.get
调用。我认为也没有任何理由致电p.join()
。
答案 10 :(得分:0)
我修改了vartec的答案,因为我需要从函数中获取错误代码。 (谢谢椎骨!它是一个很棒的技巧)
这也可以使用manager.list
完成,但我认为最好将它放在dict中并在其中存储列表。这样,我们保持功能和结果的方式,因为我们无法确定列表的填充顺序。
from multiprocessing import Process
import time
import datetime
import multiprocessing
def func1(fn, m_list):
print 'func1: starting'
time.sleep(1)
m_list[fn] = "this is the first function"
print 'func1: finishing'
# return "func1" # no need for return since Multiprocess doesnt return it =(
def func2(fn, m_list):
print 'func2: starting'
time.sleep(3)
m_list[fn] = "this is function 2"
print 'func2: finishing'
# return "func2"
def func3(fn, m_list):
print 'func3: starting'
time.sleep(9)
# if fail wont join the rest because it never populate the dict
# or do a try/except to get something in return.
raise ValueError("failed here")
# if we want to get the error in the manager dict we can catch the error
try:
raise ValueError("failed here")
m_list[fn] = "this is third"
except:
m_list[fn] = "this is third and it fail horrible"
# print 'func3: finishing'
# return "func3"
def runInParallel(*fns): # * is to accept any input in list
start_time = datetime.datetime.now()
proc = []
manager = multiprocessing.Manager()
m_list = manager.dict()
for fn in fns:
# print fn
# print dir(fn)
p = Process(target=fn, name=fn.func_name, args=(fn, m_list))
p.start()
proc.append(p)
for p in proc:
p.join() # 5 is the time out
print datetime.datetime.now() - start_time
return m_list, proc
if __name__ == '__main__':
manager, proc = runInParallel(func1, func2, func3)
# print dir(proc[0])
# print proc[0]._name
# print proc[0].name
# print proc[0].exitcode
# here you can check what did fail
for i in proc:
print i.name, i.exitcode # name was set up in the Process line 53
# here will only show the function that worked and where able to populate the
# manager dict
for i, j in manager.items():
print dir(i) # things you can do to the function
print i, j
答案 11 :(得分:0)
一个简单的解决方案:
import multiprocessing
output=[]
data = range(0,10)
def f(x):
return x**2
def handler():
p = multiprocessing.Pool(64)
r=p.map(f, data)
return r
if __name__ == '__main__':
output.append(handler())
print(output[0])
输出:
[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]