python 学习笔记7进程和线程

多进程

os 系统模块提供了进程的很多东西
os.getpid() 获取进程id
pid = os.fork() fork创建一个新的进程
父进程返回子进程id
子进程返回0

multiprocessing

multiprocessing是一个跨系统的模块,因为windows没有提供fork

from multiprocessing import Process
import os

# 子进程要执行的代码
def run_proc(name):
    print('Run child process %s (%s)...' % (name, os.getpid()))

if __name__=='__main__':
    print('Parent process %s.' % os.getpid())
    p = Process(target=run_proc, args=('test',))
    print('Child process will start.')
    p.start()
    p.join()
    print('Child process end.')

pool

from multiprocessing import Pool
import os, time, random

def long_time_task(name):
    print('Run task %s (%s)...' % (name, os.getpid()))
    start = time.time()
    time.sleep(random.random() * 3)
    end = time.time()
    print('Task %s runs %0.2f seconds.' % (name, (end - start)))

if __name__=='__main__':
    print('Parent process %s.' % os.getpid())
    p = Pool(4)
    for i in range(5):
        p.apply_async(long_time_task, args=(i,))
    print('Waiting for all subprocesses done...')
    p.close()
    p.join()
    print('All subprocesses done.')

对Pool对象调用join()方法会等待所有子进程执行完毕,调用join()之前必须先调用close(),调用close()之后就不能继续添加新的Process了。

子进程

subprocess 模块

进程间通信

from multiprocessing import Process, Queue
import os, time, random

# 写数据进程执行的代码:
def write(q):
    print('Process to write: %s' % os.getpid())
    for value in ['A', 'B', 'C']:
        print('Put %s to queue...' % value)
        q.put(value)
        time.sleep(random.random())

# 读数据进程执行的代码:
def read(q):
    print('Process to read: %s' % os.getpid())
    while True:
        value = q.get(True)
        print('Get %s from queue.' % value)

if __name__=='__main__':
    # 父进程创建Queue,并传给各个子进程:
    q = Queue()
    pw = Process(target=write, args=(q,))
    pr = Process(target=read, args=(q,))
    # 启动子进程pw,写入:
    pw.start()
    # 启动子进程pr,读取:
    pr.start()
    # 等待pw结束:
    pw.join()
    # pr进程里是死循环,无法等待其结束,只能强行终止:
    pr.terminate()

线程
Python的标准库提供了两个模块:_thread和threading,_thread是低级模块,threading是高级模块,对_thread进行了封装。绝大多数情况下,我们只需要使用threading这个高级模块。

import time, threading

# 新线程执行的代码:
def loop():
    print('thread %s is running...' % threading.current_thread().name)
    n = 0
    while n < 5:
        n = n + 1
        print('thread %s >>> %s' % (threading.current_thread().name, n))
        time.sleep(1)
    print('thread %s ended.' % threading.current_thread().name)

print('thread %s is running...' % threading.current_thread().name)
t = threading.Thread(target=loop, name='LoopThread')
t.start()
t.join()
print('thread %s ended.' % threading.current_thread().name)

Python的threading模块有个current_thread()函数,它永远返回当前线程的实例。主线程实例的名字叫MainThread,子线程的名字在创建时指定,我们用LoopThread命名子线程

Lock

balance = 0
lock = threading.Lock()

def run_thread(n):
    for i in range(100000):
        # 先要获取锁:
        lock.acquire()
        try:
            # 放心地改吧:
            change_it(n)
        finally:
            # 改完了一定要释放锁:
            lock.release()

python因为Global Interpreter Lock锁的存在。导致多多线程无法同时执行。。不过可以使用多进程克服这个问题。

ThreadLocal

每个县城有自己的对象副本

分布式进程

把任务分发到不同的机器上

import random, time, queue
from multiprocessing.managers import BaseManager

# 发送任务的队列:
task_queue = queue.Queue()
# 接收结果的队列:
result_queue = queue.Queue()

# 从BaseManager继承的QueueManager:
class QueueManager(BaseManager):
    pass

# 把两个Queue都注册到网络上, callable参数关联了Queue对象:
QueueManager.register('get_task_queue', callable=lambda: task_queue)
QueueManager.register('get_result_queue', callable=lambda: result_queue)
# 绑定端口5000, 设置验证码'abc':
manager = QueueManager(address=('', 5000), authkey=b'abc')
# 启动Queue:
manager.start()
# 获得通过网络访问的Queue对象:
task = manager.get_task_queue()
result = manager.get_result_queue()
# 放几个任务进去:
for i in range(10):
    n = random.randint(0, 10000)
    print('Put task %d...' % n)
    task.put(n)
# 从result队列读取结果:
print('Try get results...')
for i in range(10):
    r = result.get(timeout=10)
    print('Result: %s' % r)
# 关闭:
manager.shutdown()
print('master exit.')

# task_worker.py

import time, sys, queue
from multiprocessing.managers import BaseManager

# 创建类似的QueueManager:
class QueueManager(BaseManager):
    pass

# 由于这个QueueManager只从网络上获取Queue,所以注册时只提供名字:
QueueManager.register('get_task_queue')
QueueManager.register('get_result_queue')

# 连接到服务器,也就是运行task_master.py的机器:
server_addr = '127.0.0.1'
print('Connect to server %s...' % server_addr)
# 端口和验证码注意保持与task_master.py设置的完全一致:
m = QueueManager(address=(server_addr, 5000), authkey=b'abc')
# 从网络连接:
m.connect()
# 获取Queue的对象:
task = m.get_task_queue()
result = m.get_result_queue()
# 从task队列取任务,并把结果写入result队列:
for i in range(10):
    try:
        n = task.get(timeout=1)
        print('run task %d * %d...' % (n, n))
        r = '%d * %d = %d' % (n, n, n*n)
        time.sleep(1)
        result.put(r)
    except Queue.Empty:
        print('task queue is empty.')
# 处理结束:
print('worker exit.')

你可能感兴趣的:(python)