历史
在内核2.6以前的调度实体都是进程，内核并没有真正支持线程。它是能过一个系统调用clone()来实现的，这个调用创建了一份调用进程的拷贝，跟fork()不同的是,这份进程拷贝完全共享了调用进程的地址空间。LinuxThread就是通过这个系统调用来提供线程在内核级的支持的(许多以前的线程实现都完全是在用户态，内核根本不知道线程的存在)。非常不幸的是，这种方法有相当多的地方没有遵循POSIX标准，特别是在信号处理，调度，进程间通信原语等方面。

很显然，为了改进LinuxThread必须得到内核的支持，并且需要重写线程库。为了实现这个需求，开始有两个相互竞争的项目：IBM启动的NGTP(Next Generation POSIX Threads)项目，以及Redhat公司的NPTL。在2003年的年中，IBM放弃了NGTP，也就是大约那时，Redhat发布了最初的NPTL。

NPTL最开始在redhat linux 9里发布，现在从RHEL3起内核2.6起都支持NPTL，并且完全成了GNU C库的一部分。

 

设计
NPTL使用了跟LinuxThread相同的办法，在内核里面线程仍然被当作是一个进程，并且仍然使用了clone()系统调用(在NPTL库里调用)。但是，NPTL需要内核级的特殊支持来实现，比如需要挂起然后再唤醒线程的线程同步原语futex.

NPTL也是一个1*1的线程库，就是说，当你使用pthread_create()调用创建一个线程后，在内核里就相应创建了一个调度实体，在linux里就是一个新进程，这个方法最大可能的简化了线程的实现。

除NPTL的1*1模型外还有一个m*n模型，通常这种模型的用户线程数会比内核的调度实体多。在这种实现里，线程库本身必须去处理可能存在的调度，这样在线程库内部的上下文切换通常都会相当的快，因为它避免了系统调用转到内核态。然而这种模型增加了线程实现的复杂性,并可能出现诸如优先级反转的问题，此外，用户态的调度如何跟内核态的调度进行协调也是很难让人满意。

from threading import Thread
import time
def sayhi(name):
    time.sleep(2)
    print(‘%s say hello‘ %name)

if __name__ == ‘__main__‘:
    t=Thread(target=sayhi,args=(‘egon‘,))
    t.start()
    print(‘主线程‘)

from threading import Thread
import time
class Sayhi(Thread):
    def __init__(self,name):
        super().__init__()
        self.name=name
    def run(self):
        time.sleep(2)
        print(‘%s say hello‘ % self.name)


if __name__ == ‘__main__‘:
    t = Sayhi(‘egon‘)
    t.start()
    print(‘主线程‘)

from threading import Thread
from multiprocessing import Process
import os

def work():
    print(‘hello‘,os.getpid())

if __name__ == ‘__main__‘:
    #part1:在主进程下开启多个线程,每个线程都跟主进程的pid一样
    t1=Thread(target=work)
    t2=Thread(target=work)
    t1.start()
    t2.start()
    print(‘主线程/主进程pid‘,os.getpid())

    #part2:开多个进程,每个进程都有不同的pid
    p1=Process(target=work)
    p2=Process(target=work)
    p1.start()
    p2.start()
    print(‘主线程/主进程pid‘,os.getpid())

from threading import Thread
from multiprocessing import Process
import os

def work():
    print(‘hello‘)

if __name__ == ‘__main__‘:
    #在主进程下开启线程
    t=Thread(target=work)
    t.start()
    print(‘主线程/主进程‘)
    ‘‘‘
    打印结果:
    hello
    主线程/主进程
    ‘‘‘

    #在主进程下开启子进程
    t=Process(target=work)
    t.start()
    print(‘主线程/主进程‘)
    ‘‘‘
    打印结果:
    主线程/主进程
    hello
    ‘‘‘

from  threading import Thread
from multiprocessing import Process
import os
def work():
    global n
    n=0

if __name__ == ‘__main__‘:
    # n=100
    # p=Process(target=work)
    # p.start()
    # p.join()
    # print(‘主‘,n) #毫无疑问子进程p已经将自己的全局的n改成了0,但改的仅仅是它自己的,查看父进程的n仍然为100


    n=1
    t=Thread(target=work)
    t.start()
    t.join()
    print(‘主‘,n) #查看结果为0,因为同一进程内的线程之间共享进程内的数据
同一进程内的线程共享该进程的数据？

#_*_coding:utf-8_*_
#!/usr/bin/env python
import multiprocessing
import threading

import socket
s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
s.bind((‘127.0.0.1‘,8080))
s.listen(5)

def action(conn):
    while True:
        data=conn.recv(1024)
        print(data)
        conn.send(data.upper())

if __name__ == ‘__main__‘:

    while True:
        conn,addr=s.accept()


        p=threading.Thread(target=action,args=(conn,))
        p.start()

#_*_coding:utf-8_*_
#!/usr/bin/env python


import socket

s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
s.connect((‘127.0.0.1‘,8080))

while True:
    msg=input(‘>>: ‘).strip()
    if not msg:continue

    s.send(msg.encode(‘utf-8‘))
    data=s.recv(1024)
    print(data)

from threading import Thread
import threading
from multiprocessing import Process
import os

def work():
    import time
    time.sleep(3)
    print(threading.current_thread().getName())


if __name__ == ‘__main__‘:
    #在主进程下开启线程
    t=Thread(target=work)
    t.start()

    print(threading.current_thread().getName())
    print(threading.current_thread()) #主线程
    print(threading.enumerate()) #连同主线程在内有两个运行的线程
    print(threading.active_count())
    print(‘主线程/主进程‘)

    ‘‘‘
    打印结果:
    MainThread
    <_MainThread(MainThread, started 140735268892672)>
    [<_MainThread(MainThread, started 140735268892672)>, <Thread(Thread-1, started 123145307557888)>]
    主线程/主进程
    Thread-1
    ‘‘‘

from threading import Thread
import time
def sayhi(name):
    time.sleep(2)
    print(‘%s say hello‘ %name)

if __name__ == ‘__main__‘:
    t=Thread(target=sayhi,args=(‘egon‘,))
    t.start()
    t.join()
    print(‘主线程‘)
    print(t.is_alive())
    ‘‘‘
    egon say hello
    主线程
    False
    ‘‘‘

#1 主进程在其代码结束后就已经算运行完毕了（守护进程在此时就被回收）,然后主进程会一直等非守护的子进程都运行完毕后回收子进程的资源(否则会产生僵尸进程)，才会结束，
#2 主线程在其他非守护线程运行完毕后才算运行完毕（守护线程在此时就被回收）。因为主线程的结束意味着进程的结束，进程整体的资源都将被回收，而进程必须保证非守护线程都运行完毕后才能结束。

from threading import Thread
import time
def sayhi(name):
    time.sleep(2)
    print(‘%s say hello‘ %name)

if __name__ == ‘__main__‘:
    t=Thread(target=sayhi,args=(‘egon‘,))
    t.setDaemon(True) #必须在t.start()之前设置
    t.start()

    print(‘主线程‘)
    print(t.is_alive())
    ‘‘‘
    主线程
    True
    ‘‘‘

from threading import Thread
import time
def foo():
    print(123)
    time.sleep(1)
    print("end123")

def bar():
    print(456)
    time.sleep(3)
    print("end456")


t1=Thread(target=foo)
t2=Thread(target=bar)

t1.daemon=True
t1.start()
t2.start()
print("main-------")

from threading import Thread
import os,time
def work():
    global n
    temp=n
    time.sleep(0.1)
    n=temp-1
if __name__ == ‘__main__‘:
    n=100
    l=[]
    for i in range(100):
        p=Thread(target=work)
        l.append(p)
        p.start()
    for p in l:
        p.join()

    print(n) #结果可能为99

from threading import Thread,Lock
import os,time
def work():
    global n
    lock.acquire()
    temp=n
    time.sleep(0.1)
    n=temp-1
    lock.release()
if __name__ == ‘__main__‘:
    lock=Lock()
    n=100
    l=[]
    for i in range(100):
        p=Thread(target=work)
        l.append(p)
        p.start()
    for p in l:
        p.join()

    print(n) #结果肯定为0，由原来的并发执行变成串行，牺牲了执行效率保证了数据安全

#不加锁:并发执行,速度快,数据不安全
from threading import current_thread,Thread,Lock
import os,time
def task():
    global n
    print(‘%s is running‘ %current_thread().getName())
    temp=n
    time.sleep(0.5)
    n=temp-1


if __name__ == ‘__main__‘:
    n=100
    lock=Lock()
    threads=[]
    start_time=time.time()
    for i in range(100):
        t=Thread(target=task)
        threads.append(t)
        t.start()
    for t in threads:
        t.join()

    stop_time=time.time()
    print(‘主:%s n:%s‘ %(stop_time-start_time,n))

‘‘‘
Thread-1 is running
Thread-2 is running
......
Thread-100 is running
主:0.5216062068939209 n:99
‘‘‘


#不加锁:未加锁部分并发执行,加锁部分串行执行,速度慢,数据安全
from threading import current_thread,Thread,Lock
import os,time
def task():
    #未加锁的代码并发运行
    time.sleep(3)
    print(‘%s start to run‘ %current_thread().getName())
    global n
    #加锁的代码串行运行
    lock.acquire()
    temp=n
    time.sleep(0.5)
    n=temp-1
    lock.release()

if __name__ == ‘__main__‘:
    n=100
    lock=Lock()
    threads=[]
    start_time=time.time()
    for i in range(100):
        t=Thread(target=task)
        threads.append(t)
        t.start()
    for t in threads:
        t.join()
    stop_time=time.time()
    print(‘主:%s n:%s‘ %(stop_time-start_time,n))

‘‘‘
Thread-1 is running
Thread-2 is running
......
Thread-100 is running
主:53.294203758239746 n:0
‘‘‘

#有的同学可能有疑问:既然加锁会让运行变成串行,那么我在start之后立即使用join,就不用加锁了啊,也是串行的效果啊
#没错:在start之后立刻使用jion,肯定会将100个任务的执行变成串行,毫无疑问,最终n的结果也肯定是0,是安全的,但问题是
#start后立即join:任务内的所有代码都是串行执行的,而加锁,只是加锁的部分即修改共享数据的部分是串行的
#单从保证数据安全方面,二者都可以实现,但很明显是加锁的效率更高.
from threading import current_thread,Thread,Lock
import os,time
def task():
    time.sleep(3)
    print(‘%s start to run‘ %current_thread().getName())
    global n
    temp=n
    time.sleep(0.5)
    n=temp-1


if __name__ == ‘__main__‘:
    n=100
    lock=Lock()
    start_time=time.time()
    for i in range(100):
        t=Thread(target=task)
        t.start()
        t.join()
    stop_time=time.time()
    print(‘主:%s n:%s‘ %(stop_time-start_time,n))

‘‘‘
Thread-1 start to run
Thread-2 start to run
......
Thread-100 start to run
主:350.6937336921692 n:0 #耗时是多么的恐怖
‘‘‘

）

from threading import Lock as Lock
import time
mutexA=Lock()
mutexA.acquire()
mutexA.acquire()
print(123)
mutexA.release()
mutexA.release()

from threading import RLock as Lock
import time
mutexA=Lock()
mutexA.acquire()
mutexA.acquire()
print(123)
mutexA.release()
mutexA.release()

import time
from threading import Thread,Lock
noodle_lock = Lock()
fork_lock = Lock()
def eat1(name):
    noodle_lock.acquire()
    print(‘%s 抢到了面条‘%name)
    fork_lock.acquire()
    print(‘%s 抢到了叉子‘%name)
    print(‘%s 吃面‘%name)
    fork_lock.release()
    noodle_lock.release()

def eat2(name):
    fork_lock.acquire()
    print(‘%s 抢到了叉子‘ % name)
    time.sleep(1)
    noodle_lock.acquire()
    print(‘%s 抢到了面条‘ % name)
    print(‘%s 吃面‘ % name)
    noodle_lock.release()
    fork_lock.release()

for name in [‘哪吒‘,‘egon‘,‘yuan‘]:
    t1 = Thread(target=eat1,args=(name,))
    t2 = Thread(target=eat2,args=(name,))
    t1.start()
    t2.start()

import time
from threading import Thread,RLock
fork_lock = noodle_lock = RLock()
def eat1(name):
    noodle_lock.acquire()
    print(‘%s 抢到了面条‘%name)
    fork_lock.acquire()
    print(‘%s 抢到了叉子‘%name)
    print(‘%s 吃面‘%name)
    fork_lock.release()
    noodle_lock.release()

def eat2(name):
    fork_lock.acquire()
    print(‘%s 抢到了叉子‘ % name)
    time.sleep(1)
    noodle_lock.acquire()
    print(‘%s 抢到了面条‘ % name)
    print(‘%s 吃面‘ % name)
    noodle_lock.release()
    fork_lock.release()

for name in [‘哪吒‘,‘egon‘,‘yuan‘]:
    t1 = Thread(target=eat1,args=(name,))
    t2 = Thread(target=eat2,args=(name,))
    t1.start()
    t2.start()

from threading import Thread,Semaphore
import threading
import time
# def func():
#     if sm.acquire():
#         print (threading.currentThread().getName() + ‘ get semaphore‘)
#         time.sleep(2)
#         sm.release()
def func():
    sm.acquire()
    print(‘%s get sm‘ %threading.current_thread().getName())
    time.sleep(3)
    sm.release()
if __name__ == ‘__main__‘:
    sm=Semaphore(5)
    for i in range(23):
        t=Thread(target=func)
        t.start()

与进程池是完全不同的概念，进程池Pool(4)，最大只能产生4个进程，而且从头到尾都只是这四个进程，不会产生新的，而信号量是产生一堆线程/进程

import threading
import time,random
from threading import Thread,Event

def conn_mysql():
    count=1
    while not event.is_set():
        if count > 3:
            raise TimeoutError(‘链接超时‘)
        print(‘<%s>第%s次尝试链接‘ % (threading.current_thread().getName(), count))
        event.wait(0.5)
        count+=1
    print(‘<%s>链接成功‘ %threading.current_thread().getName())


def check_mysql():
    print(‘\033[45m[%s]正在检查mysql\033[0m‘ % threading.current_thread().getName())
    time.sleep(random.randint(2,4))
    event.set()
if __name__ == ‘__main__‘:
    event=Event()
    conn1=Thread(target=conn_mysql)
    conn2=Thread(target=conn_mysql)
    check=Thread(target=check_mysql)

    conn1.start()
    conn2.start()
    check.start()

Python提供的Condition对象提供了对复杂线程同步问题的支持。Condition被称为条件变量，除了提供与Lock类似的acquire和release方法外，还提供了wait和notify方法。线程首先acquire一个条件变量，然后判断一些条件。如果条件不满足则wait；如果条件满足，进行一些处理改变条件后，通过notify方法通知其他线程，其他处于wait状态的线程接到通知后会重新判断条件。不断的重复这一过程，从而解决复杂的同步问题。

import threading

def run(n):
    con.acquire()
    con.wait()
    print("run the thread: %s" % n)
    con.release()

if __name__ == ‘__main__‘:

    con = threading.Condition()
    for i in range(10):
        t = threading.Thread(target=run, args=(i,))
        t.start()

    while True:
        inp = input(‘>>>‘)
        if inp == ‘q‘:
            break
        con.acquire()
        con.notify(int(inp))
        con.release()
        print(‘****‘)

import queue

q=queue.Queue()
q.put(‘first‘)
q.put(‘second‘)
q.put(‘third‘)

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(先进先出):
first
second
third
‘‘‘

import queue

q=queue.LifoQueue()
q.put(‘first‘)
q.put(‘second‘)
q.put(‘third‘)

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(后进先出):
third
second
first
‘‘‘

import queue

q=queue.PriorityQueue()
#put进入一个元组,元组的第一个元素是优先级(通常是数字,也可以是非数字之间的比较),数字越小优先级越高
q.put((20,‘a‘))
q.put((10,‘b‘))
q.put((30,‘c‘))

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(数字越小优先级越高,优先级高的优先出队):
(10, ‘b‘)
(20, ‘a‘)
(30, ‘c‘)
‘‘‘

Constructor for a priority queue. maxsize is an integer that sets the upperbound limit on the number of items that can be placed in the queue. Insertion will block once this size has been reached, until queue items are consumed. If maxsize is less than or equal to zero, the queue size is infinite.

The lowest valued entries are retrieved first (the lowest valued entry is the one returned by sorted(list(entries))[0]). A typical pattern for entries is a tuple in the form: (priority_number, data).

exception queue.Empty
Exception raised when non-blocking get() (or get_nowait()) is called on a Queue object which is empty.

exception queue.Full
Exception raised when non-blocking put() (or put_nowait()) is called on a Queue object which is full.

Queue.qsize()
Queue.empty() #return True if empty  
Queue.full() # return True if full 
Queue.put(item, block=True, timeout=None)
Put item into the queue. If optional args block is true and timeout is None (the default), block if necessary until a free slot is available. If timeout is a positive number, it blocks at most timeout seconds and raises the Full exception if no free slot was available within that time. Otherwise (block is false), put an item on the queue if a free slot is immediately available, else raise the Full exception (timeout is ignored in that case).

Queue.put_nowait(item)
Equivalent to put(item, False).

Queue.get(block=True, timeout=None)
Remove and return an item from the queue. If optional args block is true and timeout is None (the default), block if necessary until an item is available. If timeout is a positive number, it blocks at most timeout seconds and raises the Empty exception if no item was available within that time. Otherwise (block is false), return an item if one is immediately available, else raise the Empty exception (timeout is ignored in that case).

Queue.get_nowait()
Equivalent to get(False).

Two methods are offered to support tracking whether enqueued tasks have been fully processed by daemon consumer threads.

Queue.task_done()
Indicate that a formerly enqueued task is complete. Used by queue consumer threads. For each get() used to fetch a task, a subsequent call to task_done() tells the queue that the processing on the task is complete.

If a join() is currently blocking, it will resume when all items have been processed (meaning that a task_done() call was received for every item that had been put() into the queue).

Raises a ValueError if called more times than there were items placed in the queue.

Queue.join() block直到queue被消费完毕

#介绍
The ProcessPoolExecutor class is an Executor subclass that uses a pool of processes to execute calls asynchronously. ProcessPoolExecutor uses the multiprocessing module, which allows it to side-step the Global Interpreter Lock but also means that only picklable objects can be executed and returned.

class concurrent.futures.ProcessPoolExecutor(max_workers=None, mp_context=None)
An Executor subclass that executes calls asynchronously using a pool of at most max_workers processes. If max_workers is None or not given, it will default to the number of processors on the machine. If max_workers is lower or equal to 0, then a ValueError will be raised.


#用法
from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor

import os,time,random
def task(n):
    print(‘%s is runing‘ %os.getpid())
    time.sleep(random.randint(1,3))
    return n**2

if __name__ == ‘__main__‘:

    executor=ProcessPoolExecutor(max_workers=3)

    futures=[]
    for i in range(11):
        future=executor.submit(task,i)
        futures.append(future)
    executor.shutdown(True)
    print(‘+++>‘)
    for future in futures:
        print(future.result())

#介绍
ThreadPoolExecutor is an Executor subclass that uses a pool of threads to execute calls asynchronously.
class concurrent.futures.ThreadPoolExecutor(max_workers=None, thread_name_prefix=‘‘)
An Executor subclass that uses a pool of at most max_workers threads to execute calls asynchronously.

Changed in version 3.5: If max_workers is None or not given, it will default to the number of processors on the machine, multiplied by 5, assuming that ThreadPoolExecutor is often used to overlap I/O instead of CPU work and the number of workers should be higher than the number of workers for ProcessPoolExecutor.

New in version 3.6: The thread_name_prefix argument was added to allow users to control the threading.Thread names for worker threads created by the pool for easier debugging.

#用法
与ProcessPoolExecutor相同

from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor

import os,time,random
def task(n):
    print(‘%s is runing‘ %os.getpid())
    time.sleep(random.randint(1,3))
    return n**2

if __name__ == ‘__main__‘:

    executor=ThreadPoolExecutor(max_workers=3)

    # for i in range(11):
    #     future=executor.submit(task,i)

    executor.map(task,range(1,12)) #map取代了for+submit

from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor
from multiprocessing import Pool
import requests
import json
import os

def get_page(url):
    print(‘<进程%s> get %s‘ %(os.getpid(),url))
    respone=requests.get(url)
    if respone.status_code == 200:
        return {‘url‘:url,‘text‘:respone.text}

def parse_page(res):
    res=res.result()
    print(‘<进程%s> parse %s‘ %(os.getpid(),res[‘url‘]))
    parse_res=‘url:<%s> size:[%s]\n‘ %(res[‘url‘],len(res[‘text‘]))
    with open(‘db.txt‘,‘a‘) as f:
        f.write(parse_res)


if __name__ == ‘__main__‘:
    urls=[
        ‘https://www.baidu.com‘,
        ‘https://www.python.org‘,
        ‘https://www.openstack.org‘,
        ‘https://help.github.com/‘,
        ‘http://www.sina.com.cn/‘
    ]

    # p=Pool(3)
    # for url in urls:
    #     p.apply_async(get_page,args=(url,),callback=pasrse_page)
    # p.close()
    # p.join()

    p=ProcessPoolExecutor(3)
    for url in urls:
        p.submit(get_page,url).add_done_callback(parse_page) #parse_page拿到的是一个future对象obj，需要用obj.result()拿到结果