Python并发多线程的具体操作步骤

#方式一
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')

# 方式二
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('ly')
    t.start()
    print('主线程')

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():
    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():
    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

# -*- coding: UTF-8 -*-
#!/usr/bin/env python3

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 python3

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
msg_l=[]
format_l=[]
def talk():
    while True:
        msg=input('>>: ').strip()
        if not msg:continue
        msg_l.append(msg)

def format_msg():
    while True:
        if msg_l:
            res=msg_l.pop()
            format_l.append(res.upper())

def save():
    while True:
        if format_l:
            with open('db.txt','a',encoding='utf-8') as f:
                res=format_l.pop()
                f.write('%s\n' %res)

if __name__ == '__main__':
    t1=Thread(target=talk)
    t2=Thread(target=format_msg)
    t3=Thread(target=save)
    t1.start()
    t2.start()
    t3.start()

Thread实例对象的方法
  # isAlive(): 返回线程是否活动的。
  # getName(): 返回线程名。
  # setName(): 设置线程名。

threading模块提供的一些方法：
  # threading.currentThread(): 返回当前的线程变量。
  # threading.enumerate(): 返回一个包含正在运行的线程的list。正在运行指线程启动后、结束前，不包括启动前和终止后的线程。
  # threading.activeCount(): 返回正在运行的线程数量，与len(threading.enumerate())有相同的结果。
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=('ly',))
    t.start()
    t.join()
    print('主线程')
    print(t.is_alive())
    '''
    ly 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=('ly',))
    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-------")

'''
定义：
In CPython, the global interpreter lock, or GIL, is a mutex that prevents multiple 
native threads from executing Python bytecodes at once. This lock is necessary mainly 

because CPython's memory management is not thread-safe. (However, since the GIL 
exists, other features have grown to depend on the guarantees that it enforces.)
'''

结论：在Cpython解释器中，同一个进程下开启的多线程，同一时刻只能有一个线程执行，无法利用多核优势

'''
# 验证python test.py只会产生一个进程
# test.py内容
import os,time
print(os.getpid())
time.sleep(1000)
'''
python3 test.py 
# 在windows下
tasklist |findstr python

# 在linux下
ps aux |grep python

from multiprocessing import Process
from threading import Thread
import os,time
def work():
    res=0
    for i in range(100000000):
        res*=i

if __name__ == '__main__':
    l=[]
    print(os.cpu_count()) # 本机为4核
    start=time.time()
    for i in range(4):
        p=Process(target=work) # 耗时5s多
        p=Thread(target=work)  # 耗时18s多
        l.append(p)
        p.start()
    for p in l:
        p.join()
    stop=time.time()
    print('run time is %s' %(stop-start))

from multiprocessing import Process
from threading import Thread
import threading
import os,time
def work():
    time.sleep(2)
    print('===>')

if __name__ == '__main__':
    l=[]
    print(os.cpu_count()) # 本机为4核
    start=time.time()
    for i in range(400):
        # p=Process(target=work) # 耗时12s多,大部分时间耗费在创建进程上
        p=Thread(target=work)    # 耗时2s多
        l.append(p)
        p.start()
    for p in l:
        p.join()
    stop=time.time()
    print('run time is %s' %(stop-start))

/ Python/ceval.c /*
...
static volatile int gil_drop_request = 0;

因为Python解释器帮你自动定期进行内存回收，你可以理解为python解释器里有一个独立的线程，每过一段时间它起wake up做一次全局轮询看看哪些内存数据是可以被清空的，此时你自己的程序里的线程和py解释器自己的线程是并发运行的，假设你的线程删除了一个变量，py解释器的垃圾回收线程在清空这个变量的过程中的clearing时刻，可能一个其它线程正好又重新给这个还没来及得清空的内存空间赋值了，结果就有可能新赋值的数据被删除了，为了解决类似的问题，python解释器简单粗暴的加了锁，即当一个线程运行时，其它人都不能动，这样就解决了上述的问题，  这可以说是Python早期版本的遗留问题。
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

import threading

R=threading.Lock()

R.acquire()
'''
对公共数据的操作
'''
R.release()
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 Thread,Lock
import time
mutexA=Lock()
mutexB=Lock()

class MyThread(Thread):
    def run(self):
        self.func1()
        self.func2()
    def func1(self):
        mutexA.acquire()
        print('\033[41m%s 拿到A锁\033[0m' %self.name)

        mutexB.acquire()
        print('\033[42m%s 拿到B锁\033[0m' %self.name)
        mutexB.release()

        mutexA.release()

    def func2(self):
        mutexB.acquire()
        print('\033[43m%s 拿到B锁\033[0m' %self.name)
        time.sleep(2)

        mutexA.acquire()
        print('\033[44m%s 拿到A锁\033[0m' %self.name)
        mutexA.release()

        mutexB.release()

if __name__ == '__main__':
    for i in range(10):
        t=MyThread()
        t.start()

'''
Thread-1 拿到A锁
Thread-1 拿到B锁
Thread-1 拿到B锁
Thread-2 拿到A锁
然后就卡住，死锁了
'''

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()

event.isSet()：返回event的状态值；

event.wait()：如果 event.isSet()==False将阻塞线程；

event.set()： 设置event的状态值为True，所有阻塞池的线程激活进入就绪状态， 等待操作系统调度；

event.clear()：恢复event的状态值为False。

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

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()
def condition_func():

    ret = False
    inp = input('>>>')
    if inp == '1':
        ret = True

    return ret

def run(n):
    con.acquire()
    con.wait_for(condition_func)
    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()

from threading import Timer

def hello():
    print("hello, world")

t = Timer(1, hello)
t.start()  # after 1 seconds, "hello, world" will be printed

from threading import Timer
import random,time

class Code:
    def __init__(self):
        self.make_cache()

    def make_cache(self,interval=5):
        self.cache=self.make_code()
        print(self.cache)
        self.t=Timer(interval,self.make_cache)
        self.t.start()

    def make_code(self,n=4):
        res=''
        for i in range(n):
            s1=str(random.randint(0,9))
            s2=chr(random.randint(65,90))
            res+=random.choice([s1,s2])
        return res

    def check(self):
        while True:
            inp=input('>>: ').strip()
            if inp.upper() ==  self.cache:
                print('验证成功',end='\n')
                self.t.cancel()
                break

if __name__ == '__main__':
    obj=Code()
    obj.check()

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.

构造一个优先级队列,其中maxsize是一个整数,用于设置可以放入队列的项目数量的上限.一旦达到这个上限，插入就会阻塞，直到队列中有项目被消耗。如果maxsize小于或等于0，则队列长度为无穷大。

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).

首先检索最低值的条目(最低值的条目是指列表经过排序后取到的索引为0的那个元素,一般条目是(优先级数字,数据)这种元组的形式

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

当表示非阻塞的get()或get_nowait()在一个空的队列对象中被调用时,会抛出异常

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

当表示非阻塞的put()或put_nowait()在一个满的队列对象中被调用时,会抛出异常

Queue.qsize()
Queue.empty() #return True if empty  

当队列为空返回True

Queue.full() # return True if full 

当队列为满返回True

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).

将一个项放入队列。如果可选参数block为true并且timeout为None(默认值)，则在必要时阻塞，直到有空闲槽可用。如果参数timeout是一个正数，它最多阻塞timeout秒，如果在这段时间内没有可用的空闲槽，则会引发Full异常。否则(block为false)，如果有空闲槽可用，则将一个项目放入队列中，否则引发Full异常(在这种情况下，timeout被忽略)。

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).

从队列中移除并返回一个项。如果可选参数block为true并且timeout为None(默认值)，则在必要时阻塞，直到有可用的项。如果timeout为正数，则最多阻塞timeout秒，如果在该时间内没有可用项，则抛出Empty异常。否则(block为false)，如果一个项目可用，则返回那个项目，否则引发Empty异常(在这种情况下，timeout被忽略)。

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.

提供了两种方法来支持追踪进入队列的任务是否已被生产者的守护线程完全处理。

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.

假定先前进入队列的任务已完成。并且被队列生产者使用。对于每个用于获取任务的get()，后续对task_done()的调用都会告诉队列任务的处理已经完成。

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).

如果join()当前正被阻塞，它将在所有项都被处理完时恢复(这意味着对于每个已经put()到队列中的项都接收到task_done()调用)。

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

如果调用次数超过放入队列的项数，将引发ValueError。

Queue.join() 

阻塞,直到queue被消费完毕

# 1 介绍
concurrent.futures模块提供了高度封装的异步调用接口
ThreadPoolExecutor：线程池，提供异步调用
ProcessPoolExecutor: 进程池，提供异步调用
Both implement the same interface, which is defined by the abstract Executor class.

# 2 基本方法
# submit(fn, *args, **kwargs)
异步提交任务

# map(func, *iterables, timeout=None, chunksize=1) 
取代for循环submit的操作

# shutdown(wait=True) 
相当于进程池的pool.close()+pool.join()操作
wait=True，等待池内所有任务执行完毕回收完资源后才继续
wait=False，立即返回，并不会等待池内的任务执行完毕
但不管wait参数为何值，整个程序都会等到所有任务执行完毕
submit和map必须在shutdown之前

# result(timeout=None)
取得结果

# add_done_callback(fn)
回调函数

# 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.

ProcessPoolExecutor类是Executor的子类，它使用一个进程池来异步执行调用。ProcessPoolExecutor会调用多进程模块，这允许它避开全局解释器锁，但也意味着只能执行和返回可pickle的对象。

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.
能够异步调用数量不超过参数max_workers的子进程,如果max_workers为None或未给出，则默认值为机器上的处理器数。如果max_workers小于或等于0，则会抛出异常ValueError

# 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())

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
回调函数
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