python系列-并发

多进程

• python的os模块提供了fork函数，但不支持跨平台
• multiprocessing模块的Process类创建子进程支持跨平台，并且提供了更高级的封装
• 多进程共享数据可以用管道，套接字等
• multiprocessing提供了一个Queue类，基于管道和锁机制提供了多个进程共享的队列

from multiprocessing import Process
from os import getpid
from random import randint
from time import time, sleep

def download_task(filename):
    print("启动下载，进程号[%d]"%getpid())
    print("开始下载%s..."%filename)
    time_to_download = randint(5,10)
    sleep(time_to_download)
    print("%s下载完成，耗费%d秒"%filename,time_to_download)

def main():
    start = time()
    p1 = Process(target=download_task, args=("python从入门到放弃.pdf",))
    p1.start()
    p2 = Process(target=download_task, args=("996 save.pdf",))
    p2.start()
    p1.join()
    p2.join()
    end = time()
    print("总共耗费%.2f"%(end-start))

if __name__ == "__main__":
    main()

多线程

• 早期提供了thread模块(现名为_thread)实现多线程，但很多功能未实现
• 推荐使用threading模块
• 可以继承Thread类来自定义个线程类
• Lock Condition Event Semaphore和Barrier解决多线程互斥的问题

from threading import Thread
from random import randint
from time import time, sleep

def download_task(filename):
    print("开始下载%s..."%filename)
    time_to_download = randint(5,10)
    sleep(time_to_download)
    print("%s下载完成，耗费%d秒"%filename,time_to_download)

def main():
    start = time()
    p1 = Thread(target=download_task, args=("python从入门到放弃.pdf",))
    p1.start()
    p2 = Thread(target=download_task, args=("996 save.pdf",))
    p2.start()
    p1.join()
    p2.join()
    end = time()
    print("总共耗费%.2f"%(end-start))

if __name__ == "__main__":
    main()

单线程+异步I/O-------python协程

• 基于事件驱动模型
• 没有线程切换的开销
• 不需要多线程的锁机制
• 可以充分利用CPU
• 主要是通过回调或者future对象来获取任务执行结果
• asyncio模块和await和async关键字来支持异步处理

import asyncio

def num_generator(m, n):
    yield from range(m, n+1)

async def prime_filter(m, n):
    primes = []
    for i in num_generator(m,n):
        flag = True
        for j in range(2, int(i ** 0.5 + 1)):
            if i % j == 0:
                flag = False
                break
            if flag:
                primes.append(i)
    return tuple(primes)

async def square_mapper(m, n):
    squares = []
    for i in num_generator(m, n):
        squares.append(i * i)

        await asyncio.sleep(0.001)
    
    return squares

def main():
    loop = asyncio.get_event_loop()
    future = asyncio.gather(prime_filter(2,100), square_mapper(1,100))
    future.add_done_callback(lambda x: print(x.result))
    loop.run_until_complete(future)
    loop.close()

if __name__ == "__main__":
    main()