Python 多进程、多线程效率比较

Python 界有条不成文的准则： 计算密集型任务适合多进程，IO 密集型任务适合多线程。本篇来做个比较。

一般来讲多线程相对于多进程有优点，由于建立一个进程开销比较大，然而由于在 python 中有 GIL 这把大锁的存在，致使执行计算密集型任务时多线程实际只能是单线程。并且因为线程之间切换的开销致使多线程每每比实际的单线程还要慢，因此在 python 中计算密集型任务一般使用多进程，由于各个进程有各自独立的 GIL，互不干扰。

而在 IO 密集型任务中，CPU 时常处于等待状态，操做系统须要频繁与外界环境进行交互，如读写文件，在网络间通讯等。在这期间 GIL 会被释放，于是就可使用真正的多线程。

以上是理论，下面作一个简单的模拟测试： 大量计算用 math.sin() + math.cos() 来代替，IO 密集型用 time.sleep() 来模拟。 在 Python 中有多种方式能够实现多进程和多线程，这里一并归入看看是否有效率差别：

1. 多进程： joblib.multiprocessing, multiprocessing.Pool, multiprocessing.apply_async, concurrent.futures.ProcessPoolExecutor
2. 多线程： joblib.threading, threading.Thread, concurrent.futures.ThreadPoolExecutor

from multiprocessing import Pool
from threading import Thread
from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor
import time, os, math
from joblib import Parallel, delayed, parallel_backend


def f_IO(a):  # IO 密集型
    time.sleep(5)

def f_compute(a):  # 计算密集型
    for _ in range(int(1e7)):
        math.sin(40) + math.cos(40)
    return

def normal(sub_f):
    for i in range(6):
        sub_f(i)
    return

def joblib_process(sub_f):
    with parallel_backend("multiprocessing", n_jobs=6):
        res = Parallel()(delayed(sub_f)(j) for j in range(6))
    return


def joblib_thread(sub_f):
    with parallel_backend('threading', n_jobs=6):
        res = Parallel()(delayed(sub_f)(j) for j in range(6))
    return

def mp(sub_f):
    with Pool(processes=6) as p:
        res = p.map(sub_f, list(range(6)))
    return

def asy(sub_f):
    with Pool(processes=6) as p:
        result = []
        for j in range(6):
            a = p.apply_async(sub_f, args=(j,))
            result.append(a)
        res = [j.get() for j in result]

def thread(sub_f):
    threads = []
    for j in range(6):
        t = Thread(target=sub_f, args=(j,))
        threads.append(t)
        t.start()
    for t in threads:
        t.join()

def thread_pool(sub_f):
    with ThreadPoolExecutor(max_workers=6) as executor:
        res = [executor.submit(sub_f, j) for j in range(6)]

def process_pool(sub_f):
    with ProcessPoolExecutor(max_workers=6) as executor:
        res = executor.map(sub_f, list(range(6)))

def showtime(f, sub_f, name):
    start_time = time.time()
    f(sub_f)
    print("{} time: {:.4f}s".format(name, time.time() - start_time))

def main(sub_f):
    showtime(normal, sub_f, "normal")
    print()
    print("------ 多进程 ------")
    showtime(joblib_process, sub_f, "joblib multiprocess")
    showtime(mp, sub_f, "pool")
    showtime(asy, sub_f, "async")
    showtime(process_pool, sub_f, "process_pool")
    print()
    print("----- 多线程 -----")
    showtime(joblib_thread, sub_f, "joblib thread")
    showtime(thread, sub_f, "thread")
    showtime(thread_pool, sub_f, "thread_pool")


if __name__ == "__main__":
    print("----- 计算密集型 -----")
    sub_f = f_compute
    main(sub_f)
    print()
    print("----- IO 密集型 -----")
    sub_f = f_IO
    main(sub_f)

结果：

----- 计算密集型 -----
normal time: 15.1212s

------ 多进程 ------
joblib multiprocess time: 8.2421s
pool time: 8.5439s
async time: 8.3229s
process_pool time: 8.1722s

----- 多线程 -----
joblib thread time: 21.5191s
thread time: 21.3865s
thread_pool time: 22.5104s



----- IO 密集型 -----
normal time: 30.0305s

------ 多进程 ------
joblib multiprocess time: 5.0345s
pool time: 5.0188s
async time: 5.0256s
process_pool time: 5.0263s

----- 多线程 -----
joblib thread time: 5.0142s
thread time: 5.0055s
thread_pool time: 5.0064s

上面每一方法都统一建立6个进程/线程，结果是计算密集型任务中速度：多进程 > 单进程/线程 > 多线程， IO 密集型任务速度： 多线程 > 多进程 > 单进程/线程。

/