60%的人不懂Python进程Process，你懂吗？

 

前言
本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。
作者：蒋狗 

 

新手注意：如果你python基础学的不够扎实，遇问题没人解答？可以看我的最新入门到实战教程复习下再来

基本使用

运用多进程时，将方法放在main()中，否则会出现异常警告。

process() 基本使用：与thread()类似。

pool() 基本使用：

其中map方法用起来和内置的map函数一样，却有多进程的支持。

from multiprocessing import pool
pool = pool(2)
pool.map(fib, [35] * 2)

multiprocessing.dummy 模块：

multiprocessing.dummy replicates the api of multiprocessing but is no more than a wrapper around the threading module.

对于以上部分知识点，没有实际运用过，只是单纯了解并编写demo进行了练习，理解没有很透彻。

# -*- coding: utf-8 -*-
from multiprocessing import process, pool
from multiprocessing.dummy import pool as dummypool
import time
import datetime

def log_time(methond_name):
    def decorator(f):
        def wrapper(*args, **kwargs):
            start_time = time.time()
            res = f(*args, **kwargs)
            end_time = time.time()
            print('%s cost %ss' % (methond_name, (end_time - start_time)))
            return res
        return wrapper
    return decorator

def fib(n):
    if n <=2 :
        return 1
    return fib(n-1) + fib(n-2)

@log_time('single_process')
def single_process():
    fib(33)
    fib(33)

@log_time('multi_process')
def multi_process():
    jobs = []
    for _ in range(2):
        p = process(target=fib, args=(33, ))
        p.start()
        jobs.append(p)
    for j in jobs:
        j.join()


@log_time('pool_process')
def pool_process():
    pool = pool(2)
    pool.map(fib, [33]*2)


@log_time('dummy_pool')
def dummy_pool():
    pool = dummypool(2)
    pool.map(fib, [33]*2)


if __name__ == '__main__':
    single_process()
    multi_process()
    pool_process()
    dummy_pool()

 

---

基于pipe的parmap

理解稍有困难。注意：如果你python基础不够扎实，可以看我的最新入门到实战教程复习

---

队列

实现生产消费者模型，一个队列存放任务，一个队列存放结果。 
multiprocessing模块下也有queue，但不提供task_done()和join()方法。故利用queue存放结果，joinablequeue() 来存放任务。

仿照的demo，一个消费者进程和一个生产者进程：

# -*- coding: utf-8 -*-
from multiprocessing import process, queue, joinablequeue
import time
import random

def double(n):
    return n * 2 

def producer(name, task_q):
    while 1:
        n = random.random()
        if n > 0.8:  # 大于0.8时跳出
            task_q.put(none)
            print('%s break.' % name)
            break
        print('%s produce %s.' % (name, n))
        task_q.put((double, n))


def consumer(name, task_q, result_q):
    while 1:
        task = task_q.get()
        if task is none:
            print('%s break.' % name)
            break
        func, arg = task
        res = func(arg)
        time.sleep(0.5)  # 阻塞
        task_q.task_done()
        result_q.put(res)
        print('%s consume %s, result %s' % (name, arg, res))

def run():
    task_q = joinablequeue()
    result_q = queue()
    processes = []
    p1 = process(name='p1', target=producer, args=('p1', task_q))
    c1 = process(name='c1', target=consumer, args=('c1', task_q, result_q))
    p1.start()
    c1.start()
    processes.append(p1)
    processes.append(c1)

    # join()阻塞主进程
    for p in processes:
        p.join()

    # 子进程结束后，输出result中的值
    while 1:
        if result_q.empty():
            break
        result = result_q.get()
        print('result is: %s' % result)

if __name__ == '__main__':
    run()

如果存在多个consumer()进程，只会有一个consumer()进程能取出none并break，其他的则会在task_q.get()一直挂起，尝试在consumer()方法中添加超时退出。

import queue

def consumer(name, task_q, result_q):
    while 1:
        try:
            task = task_q.get(1)  # 1s
        except queue.empty:
            print('%s time out, break.' % name)
        if task is none:
            print('%s break.' % name)
            break
        func, arg = task
        res = func(arg)
        time.sleep(0.5)  # 阻塞
        task_q.task_done()
        result_q.put(res)
        print('%s consume %s, result %s' % (name, arg, res))

---

共享内存

利用sharedctypes中的array, value来共享内存。 
下例为仿照。

# -*- coding: utf-8 -*-

from pprint import pprint

# 共享内存
from multiprocessing import sharedctypes, process, lock
from ctypes import structure, c_bool, c_double

pprint(sharedctypes.typecode_to_type)

lock = lock()


class point(structure):
    _fields_ = [('x', c_double), ('y', c_double)]  # _fields_


def modify(n, b, s, arr, a):
    n.value **= 2
    b.value = true
    s.value = s.value.upper()
    arr[0] = 10
    for a in a:
        a.x **= 2
        a.y **= 2

if __name__ == '__main__':

    n = sharedctypes.value('i', 7)
    b = sharedctypes.value(c_bool, false, lock=false)
    s = sharedctypes.array('c', b'hello world', lock=lock)  # bytes
    arr = sharedctypes.array('i', range(5), lock=true)
    a = sharedctypes.array(point, [(1.875, -6.25), (-5.75, 2.0)], lock=lock)
    p = process(target=modify, args=(n, b, s, arr, a))
    p.start()
    p.join()
    print(n.value)
    print(b.value)
    print(s.value)
    print(arr[:])
    print([(a.x, a.y) for a in a])

实际项目中利用value来监测子进程的任务状态， 并通过memcached来存储更新删除。

# -*- coding: utf-8 -*-

from multiprocessing import process, value
import time
import datetime
import random


finished = 3
failed = 4
inprocess = 2
waiting = 1

def execute_method(status, process):
    time.sleep(1)
    status.value = inprocess  # test
    time.sleep(1)
    status.value = finished  # test
    time.sleep(0.5)

def run(execute_code):
    status = value('i', waiting )
    process = value('f', 0.0)
    # mem_cache.set('%s_status' % execute_code, status.value, 0)
    # mem_cache.set('%s_process' % execute_code, process .value, 0)
    p = process(target=execute_method, args=(status, process))
    p.start()
    start_time = datetime.datetime.now()
    while true:
        print(status.value)
        now_time = datetime.datetime.now()
        if (now_time - start_time).seconds > 30:  # 超过30sbreak
            # mem_cache.delete('%s_status' % execute_code)
            # mem_cache.delete('%s_process' % execute_code)
            print('execute failed')
            p.terminate()
            break
        if status.value == 3:
            # mem_cache.delete('%s_status' % execute_code)
            # mem_cache.delete('%s_process' % execute_code)
            print('end execute')
            break
        else:
            # mem_cache.set('%s_status' % execute_code, status.value, 0)
            # mem_cache.set('%s_process' % execute_code, process .value, 0)
            print('waiting or executing')
        time.sleep(0.5)
    p.join()

---

服务进程

下例为仿照博客中的服务进程的例子，简单的展示了manager的常见的共享方式。

一个multiprocessing.manager对象会控制一个服务器进程，其他进程可以通过代理的方式来访问这个服务器进程。 常见的共享方式有以下几种： 
1. namespace。创建一个可分享的命名空间。 
2. value/array。和上面共享ctypes对象的方式一样。 
dict/list。创建一个可分享的 
3. dict/list，支持对应数据结构的方法。 
4. condition/event/lock/queue/semaphore。创建一个可分享的对应同步原语的对象。

# -*- coding: utf-8 -*-
from multiprocessing import manager, process

def modify(ns, lproxy, dproxy):
    ns.name = 'new_name'
    lproxy.append('new_value')
    dproxy['new'] = 'new_value'

def run():
    # 数据准备
    manager = manager()
    ns = manager.namespace()
    ns.name = 'origin_name'
    lproxy = manager.list()
    lproxy.append('origin_value')
    dproxy = manager.dict()
    dproxy['origin'] = 'origin_value'

    # 子进程
    p = process(target=modify, args=(ns, lproxy, dproxy))
    p.start()
    print(p.pid)
    p.join()

    print('ns.name: %s' % ns.name)
    print('lproxy: %s' % lproxy)
    print('dproxy: %s' % dproxy)

if __name__ == '__main__':
    run()

上例主要是展示了manager中的共享对象类型和代理，查看源码知是通过register()方法。

multiprocessing/managers.py:

#
# definition of syncmanager
#

class syncmanager(basemanager):
    '''
    subclass of `basemanager` which supports a number of shared object types.

    the types registered are those intended for the synchronization
    of threads, plus `dict`, `list` and `namespace`.

    the `multiprocessing.manager()` function creates started instances of
    this class.
    '''

syncmanager.register('queue', queue.queue)
syncmanager.register('joinablequeue', queue.queue)
syncmanager.register('event', threading.event, eventproxy)
syncmanager.register('lock', threading.lock, acquirerproxy)
syncmanager.register('rlock', threading.rlock, acquirerproxy)
syncmanager.register('semaphore', threading.semaphore, acquirerproxy)
syncmanager.register('boundedsemaphore', threading.boundedsemaphore,
                     acquirerproxy)
syncmanager.register('condition', threading.condition, conditionproxy)
syncmanager.register('barrier', threading.barrier, barrierproxy)
syncmanager.register('pool', pool.pool, poolproxy)
syncmanager.register('list', list, listproxy)
syncmanager.register('dict', dict, dictproxy)
syncmanager.register('value', value, valueproxy)
syncmanager.register('array', array, arrayproxy)
syncmanager.register('namespace', namespace, namespaceproxy)

# types returned by methods of poolproxy
syncmanager.register('iterator', proxytype=iteratorproxy, create_method=false)
syncmanager.register('asyncresult', create_method=false)

除了在子进程中，还可利用manager()来在不同进程间通信，如下面的分布式进程简单实现。

---

分布进程

和上例的主要区别是，非子进程间进行通信。

manager_server.py:

# -*- coding: utf-8 -*-

from multiprocessing.managers import basemanager

host = '127.0.0.1'
port = 8080
authkey = b'python'

shared_list = []

class servermanager(basemanager):
    pass

servermanager.register('get_list', callable=lambda: shared_list)
server_manager = servermanager(address=(host, port), authkey=authkey)
server = server_manager.get_server()
server.serve_forever()

manager_client.py

# -*- coding: utf-8 -*-

from multiprocessing.managers import basemanager

host = '127.0.0.1'
port = 8080
authkey = b'python'

class clientmanager(basemanager):
    pass

clientmanager.register('get_list')
client_manager = clientmanager(address=(host, port), authkey=authkey)
client_manager.connect()

l = client_manager.get_list()
print(l)

l.append('new_value')
print(l)

运行多次后，shared_list中会不断添加new_value。

仿照廖雪峰教程上的分布式进程加以适当修改。

manager_server.py:

# -*- coding: utf-8 -*-

from multiprocessing.managers import basemanager
from multiprocessing import condition, value
import queue

host = '127.0.0.1'
port = 8080
authkey = b'python'


task_q = queue.queue(10)
result_q = queue.queue(20)
cond = condition()
done = value('i', 0)

def double(n):
    return n * 2

class servermanager(basemanager):
    pass

servermanager.register('get_task_queue', callable=lambda: task_q)
servermanager.register('get_result_queue', callable=lambda: result_q)
servermanager.register('get_cond', callable=lambda: cond)
servermanager.register('get_done', callable=lambda: done)
servermanager.register('get_double', callable=double)

server_manager = servermanager(address=(host, port), authkey=authkey)
server = server_manager.get_server()

print('start server')
server.serve_forever(

manager_producer.py:

# -*- coding: utf-8 -*-

from multiprocessing.managers import basemanager
import random
import time

host = '127.0.0.1'
port = 8080
authkey = b'python'

class producermanager(basemanager):
    pass

producermanager.register('get_task_queue')
producermanager.register('get_cond')
producermanager.register('get_done')
producer_manager = producermanager(address=(host, port), authkey=authkey)

producer_manager.connect()
task_q  = producer_manager.get_task_queue()
cond = producer_manager.get_cond()
# done = producer_manager.get_done()
count = 20  # 最多有20个任务

while count > 0:
    if cond.acquire():
        if not task_q.full():
            n = random.randint(0, 10)
            task_q.put(n)
            print("producer:deliver one, now tasks:%s" % task_q.qsize())
            cond.notify()
            count -= 1
            time.sleep(0.5)
        else:
            print("producer:already full, stop deliver, now tasks:%s" % task_q.qsize())
            cond.wait() 
        cond.release()
# done.value = 1
print('producer break')

manager_consumer.py:

# -*- coding: utf-8 -*-

from multiprocessing.managers import basemanager

host = '127.0.0.1'
port = 8080
authkey = b'python'

class consumermanager(basemanager):
    pass

consumermanager.register('get_task_queue')
consumermanager.register('get_result_queue')
consumermanager.register('get_cond')
# consumermanager.register('get_done')
consumermanager.register('get_double')

consumer_manager = consumermanager(address=(host, port), authkey=authkey)
consumer_manager.connect()

task_q = consumer_manager.get_task_queue()
result_q = consumer_manager.get_result_queue()
cond = consumer_manager.get_cond()
# done = consumer_manager.get_done()

while 1:
    if result_q.full():
        print('result queue is full')
        break
    if cond.acquire():
        if not task_q.empty():
            arg = task_q.get()
            res = consumer_manager.get_double(arg)
            print("consumer:consume one, now tasks:%s" % task_q.qsize())
            result_q.put(res)
            cond.notify()
        else:
            print("consumer:only 0, stop consume, products")
            cond.wait()
        cond.release()

while 1:
    if result_q.empty():
        break
    result = result_q.get()
    print('result is: %s' % result)