近来接手一个项目,里面大量用到多线程、协程,因此顺便重新学习了。本文中大多代码是直接引用廖雪峰博客上的,为的只是以后方便找出模块的用法样例,特此声明。
名词解释
关系与背景知识
一个进程里至少有一个线程,即一个进程里可以有多个线程,由于python中的线程有GIL(global interpreter lock)锁,因此python中一个进程里的多线程不是并发执行的。
但是可以用多进程的方法进行分布式编程,也可以用协程(异步IO)提高CPU利用率,最好的搭配是多进程+多协程的方法。
当然,CPython牛逼的,可以改写GIL锁,使得python的多线程做到可以并发。
多进程的模块及其使用
- os.fork()与os.getpid(),os.getppid()
# Only works on Unix/Linux/Mac:
pid = os.fork() # create process
if pid == 0:
# when pid == 0, it's parent pid
print(os.getpid(), os.getppid())
else:
# when pid != 0, it's child pid
print(os.getpid(), pid)
- multiprocessing.Process()
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.')
- subprocess: call() and communicate() and Popen()
import subprocess
print('$ nslookup www.python.org')
r = subprocess.call(['nslookup', 'www.python.org'])
print('Exit code:', r)
print('$ nslookup')
p = subprocess.Popen(['nslookup'], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output, err = p.communicate(b'set q=mx\npython.org\nexit\n')
print(output.decode('utf-8'))
print('Exit code:', p.returncode)
- 进程间通信: queue.Queue
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()
多线程的模块及其使用
- threading, notice the join()
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)
- whitout lock
import time, threading
# 假定这是你的银行存款:
balance = 0
def change_it(n):
# 先存后取,结果应该为0:
global balance
balance = balance + n
balance = balance - n
def run_thread(n):
for i in range(100000):
change_it(n)
t1 = threading.Thread(target=run_thread, args=(5,))
t2 = threading.Thread(target=run_thread, args=(8,))
t1.start()
t2.start()
t1.join()
t2.join()
print(balance)
- with 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()
- multiprocessing.cpu_count()
import threading, multiprocessing
def loop():
x = 0
while True:
x = x ^ 1
for i in range(multiprocessing.cpu_count()):
t = threading.Thread(target=loop)
t.start()
- ThreadLocal
import threading
# 创建全局ThreadLocal对象:
local_school = threading.local()
def process_student():
# 获取当前线程关联的student:
std = local_school.student
print('Hello, %s (in %s)' % (std, threading.current_thread().name))
def process_thread(name):
# 绑定ThreadLocal的student:
local_school.student = name
process_student()
t1 = threading.Thread(target= process_thread, args=('Alice',), name='Thread-A')
t2 = threading.Thread(target= process_thread, args=('Bob',), name='Thread-B')
t1.start()
t2.start()
t1.join()
t2.join()
- 分布式进程: master
# task_master.py must be light.
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.')
- 分布式进程: worker
# task_worker.py do the heavy thing
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.')
协程的模块及其使用
- yield: can receive data(when generator.send()) and return data.
def consumer():
r = ''
while True:
n = yield r
if not n:
return
print('[CONSUMER] Consuming %s...' % n)
r = '200 OK'
def produce(c):
c.send(None)
n = 0
while n < 5:
n = n + 1
print('[PRODUCER] Producing %s...' % n)
r = c.send(n)
print('[PRODUCER] Consumer return: %s' % r)
c.close()
c = consumer()
produce(c)
- asyncio: sleep(), get_event_loop() [which is the funcs be decorate by coroutine]
import asyncio
@asyncio.coroutine
def hello():
print("Hello world!")
# 异步调用asyncio.sleep(1):
r = yield from asyncio.sleep(1)
print("Hello again!")
# 获取EventLoop:
loop = asyncio.get_event_loop()
# 执行coroutine
loop.run_until_complete(hello())
loop.close()
- asyncio: yield from [which means await this step and to do other thing]
import threading
import asyncio
@asyncio.coroutine
def hello():
print('Hello world! (%s)' % threading.currentThread())
yield from asyncio.sleep(1)
print('Hello again! (%s)' % threading.currentThread())
loop = asyncio.get_event_loop()
tasks = [hello(), hello()]
loop.run_until_complete(asyncio.wait(tasks))
loop.close() # remember to close.
- asyncio.wait([%this is a list%]), run_until_complete()
import asyncio
@asyncio.coroutine
def wget(host):
print('wget %s...' % host)
connect = asyncio.open_connection(host, 80)
reader, writer = yield from connect
header = 'GET / HTTP/1.0\r\nHost: %s\r\n\r\n' % host
writer.write(header.encode('utf-8'))
yield from writer.drain()
while True:
line = yield from reader.readline()
if line == b'\r\n':
break
print('%s header > %s' % (host, line.decode('utf-8').rstrip()))
# Ignore the body, close the socket
writer.close()
loop = asyncio.get_event_loop()
tasks = [wget(host) for host in ['www.sina.com.cn', 'www.sohu.com', 'www.163.com']]
loop.run_until_complete(asyncio.wait(tasks))
loop.close()
- async, await
@asyncio.coroutine
def hello():
print("Hello world!")
r = yield from asyncio.sleep(1)
print("Hello again!")
# asyncio.coroutine -> async def
# yield from -> await
async def hello():
print("Hello world!")
r = await asyncio.sleep(1)
print("Hello again!")
# this grammer start from python 3.5
- aiohttp? why not use flask?
import asyncio
from aiohttp import web
async def index(request):
await asyncio.sleep(0.5)
return web.Response(body=b'<h1>Index</h1>')
async def hello(request):
await asyncio.sleep(0.5)
text = '<h1>hello, %s!</h1>' % request.match_info['name']
return web.Response(body=text.encode('utf-8'))
async def init(loop):
app = web.Application(loop=loop)
app.router.add_route('GET', '/', index)
app.router.add_route('GET', '/hello/{name}', hello)
srv = await loop.create_server(app.make_handler(), '127.0.0.1', 8000)
print('Server started at http://127.0.0.1:8000...')
return srv
loop = asyncio.get_event_loop()
loop.run_until_complete(init(loop))
loop.run_forever()