import threading
import requests

def send():

  r = requests.get('https://www.stackoverlow.com')

thread = []
t = threading.Thread(target=send())
thread.append(t)
t.start()

与其他提到的一样，由于GIL，CPython只能在I/O等待时使用线程。

如果您想从多个内核中获得CPU绑定任务的好处，请使用多处理：

from multiprocessing import Process

def f(name):
    print 'hello', name

if __name__ == '__main__':
    p = Process(target=f, args=('bob',))
    p.start()
    p.join()

只需注意：线程不需要队列。

这是我可以想象的最简单的例子，它显示了10个并发运行的进程。

import threading
from random import randint
from time import sleep


def print_number(number):

    # Sleeps a random 1 to 10 seconds
    rand_int_var = randint(1, 10)
    sleep(rand_int_var)
    print "Thread " + str(number) + " slept for " + str(rand_int_var) + " seconds"

thread_list = []

for i in range(1, 10):

    # Instantiates the thread
    # (i) does not make a sequence, so (i,)
    t = threading.Thread(target=print_number, args=(i,))
    # Sticks the thread in a list so that it remains accessible
    thread_list.append(t)

# Starts threads
for thread in thread_list:
    thread.start()

# This blocks the calling thread until the thread whose join() method is called is terminated.
# From http://docs.python.org/2/library/threading.html#thread-objects
for thread in thread_list:
    thread.join()

# Demonstrates that the main process waited for threads to complete
print "Done"

Python 3具有启动并行任务的功能。这使我们的工作更容易。

它有线程池和进程池。

以下内容提供了一个见解：

ThreadPoolExecutor示例（源代码）

import concurrent.futures
import urllib.request

URLS = ['http://www.foxnews.com/',
        'http://www.cnn.com/',
        'http://europe.wsj.com/',
        'http://www.bbc.co.uk/',
        'http://some-made-up-domain.com/']

# Retrieve a single page and report the URL and contents
def load_url(url, timeout):
    with urllib.request.urlopen(url, timeout=timeout) as conn:
        return conn.read()

# We can use a with statement to ensure threads are cleaned up promptly
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
    # Start the load operations and mark each future with its URL
    future_to_url = {executor.submit(load_url, url, 60): url for url in URLS}
    for future in concurrent.futures.as_completed(future_to_url):
        url = future_to_url[future]
        try:
            data = future.result()
        except Exception as exc:
            print('%r generated an exception: %s' % (url, exc))
        else:
            print('%r page is %d bytes' % (url, len(data)))

ProcessPoolExecutor（源）

import concurrent.futures
import math

PRIMES = [
    112272535095293,
    112582705942171,
    112272535095293,
    115280095190773,
    115797848077099,
    1099726899285419]

def is_prime(n):
    if n % 2 == 0:
        return False

    sqrt_n = int(math.floor(math.sqrt(n)))
    for i in range(3, sqrt_n + 1, 2):
        if n % i == 0:
            return False
    return True

def main():
    with concurrent.futures.ProcessPoolExecutor() as executor:
        for number, prime in zip(PRIMES, executor.map(is_prime, PRIMES)):
            print('%d is prime: %s' % (number, prime))

if __name__ == '__main__':
    main()

以前的解决方案都没有在我的GNU/Linux服务器上使用多个内核（我没有管理员权限）。他们只是在一个核心上跑步。

我使用较低级别的os.fork接口来派生多个进程。这是对我有用的代码：

from os import fork

values = ['different', 'values', 'for', 'threads']

for i in range(len(values)):
    p = fork()
    if p == 0:
        my_function(values[i])
        break

我想提供一个简单的例子，以及我在自己解决这个问题时发现有用的解释。

在这个答案中，您将找到一些关于Python的GIL（全局解释器锁）的信息，以及一个使用multiprocessing.dummy编写的简单日常示例，以及一些简单的基准测试。

全局解释器锁（GIL）

Python不允许真正意义上的多线程。它有一个多线程包，但是如果你想多线程来加快你的代码，那么使用它通常不是一个好主意。

Python有一个称为全局解释器锁（GIL）的构造。GIL确保在任何时候只能执行一个“线程”。一个线程获取GIL，做一些工作，然后将GIL传递给下一个线程。

这种情况发生得很快，因此在人眼看来，您的线程似乎是并行执行的，但它们实际上只是轮流使用相同的CPU内核。

所有这些GIL传递都增加了执行开销。这意味着如果你想让你的代码运行得更快，那么使用线程打包通常不是个好主意。

使用Python的线程包是有原因的。如果你想同时运行一些事情，而效率不是一个问题，那就很好，也很方便。或者，如果您运行的代码需要等待一些东西（比如一些I/O），那么这可能很有意义。但是线程库不允许您使用额外的CPU内核。

多线程可以外包给操作系统（通过执行多线程处理），以及一些调用Python代码的外部应用程序（例如，Spark或Hadoop），或者Python代码调用的一些代码（例如：您可以让Python代码调用一个C函数来完成昂贵的多线程任务）。

为什么这很重要

因为很多人在了解GIL是什么之前，会花很多时间在他们的Python多线程代码中寻找瓶颈。

一旦这些信息清楚，下面是我的代码：

#!/bin/python
from multiprocessing.dummy import Pool
from subprocess import PIPE,Popen
import time
import os

# In the variable pool_size we define the "parallelness".
# For CPU-bound tasks, it doesn't make sense to create more Pool processes
# than you have cores to run them on.
#
# On the other hand, if you are using I/O-bound tasks, it may make sense
# to create a quite a few more Pool processes than cores, since the processes
# will probably spend most their time blocked (waiting for I/O to complete).
pool_size = 8

def do_ping(ip):
    if os.name == 'nt':
        print ("Using Windows Ping to " + ip)
        proc = Popen(['ping', ip], stdout=PIPE)
        return proc.communicate()[0]
    else:
        print ("Using Linux / Unix Ping to " + ip)
        proc = Popen(['ping', ip, '-c', '4'], stdout=PIPE)
        return proc.communicate()[0]


os.system('cls' if os.name=='nt' else 'clear')
print ("Running using threads\n")
start_time = time.time()
pool = Pool(pool_size)
website_names = ["www.google.com","www.facebook.com","www.pinterest.com","www.microsoft.com"]
result = {}
for website_name in website_names:
    result[website_name] = pool.apply_async(do_ping, args=(website_name,))
pool.close()
pool.join()
print ("\n--- Execution took {} seconds ---".format((time.time() - start_time)))

# Now we do the same without threading, just to compare time
print ("\nRunning NOT using threads\n")
start_time = time.time()
for website_name in website_names:
    do_ping(website_name)
print ("\n--- Execution took {} seconds ---".format((time.time() - start_time)))

# Here's one way to print the final output from the threads
output = {}
for key, value in result.items():
    output[key] = value.get()
print ("\nOutput aggregated in a Dictionary:")
print (output)
print ("\n")

print ("\nPretty printed output: ")
for key, value in output.items():
    print (key + "\n")
    print (value)