python3-----多进程、多线程、多协程

目前计算机程序一般会遇到两类I/O：硬盘I/O和网络I/O。我就针对网络I/O的场景分析下python3下进程、线程、协程效率的对比。进程采用multiprocessing.Pool进程池，线程是自己封装的进程池，协程采用gevent的库。用python3自带的urlllib.request和开源的requests做对比。代码如下：

import urllib.request
import requests
import time
import multiprocessing
import threading
import queue

def startTimer():
    return time.time()

def ticT(startTime):
    useTime = time.time() - startTime
    return round(useTime, 3)

#def tic(startTime, name):
#    useTime = time.time() - startTime
#    print('[%s] use time: %1.3f' % (name, useTime))

def download_urllib(url):
    req = urllib.request.Request(url,
            headers={'user-agent': 'Mozilla/5.0'})
    res = urllib.request.urlopen(req)
    data = res.read()
    try:
        data = data.decode('gbk')
    except UnicodeDecodeError:
        data = data.decode('utf8', 'ignore')
    return res.status, data

def download_requests(url):
    req = requests.get(url,
            headers={'user-agent': 'Mozilla/5.0'})
    return req.status_code, req.text

class threadPoolManager:
    def __init__(self,urls, workNum=10000,threadNum=20):
        self.workQueue=queue.Queue()
        self.threadPool=[]
        self.__initWorkQueue(urls)
        self.__initThreadPool(threadNum)

    def __initWorkQueue(self,urls):
        for i in urls:
            self.workQueue.put((download_requests,i))

    def __initThreadPool(self,threadNum):
        for i in range(threadNum):
            self.threadPool.append(work(self.workQueue))

    def waitAllComplete(self):
        for i in self.threadPool:
            if i.isAlive():
                i.join()

class work(threading.Thread):
    def __init__(self,workQueue):
        threading.Thread.__init__(self)
        self.workQueue=workQueue
        self.start()
    def run(self):
        while True:
            if self.workQueue.qsize():
                do,args=self.workQueue.get(block=False)
                do(args)
                self.workQueue.task_done()
            else:
                break

urls = ['http://www.ustchacker.com'] * 10
urllibL = []
requestsL = []
multiPool = []
threadPool = []
N = 20
PoolNum = 100

for i in range(N):
    print('start %d try' % i)
    urllibT = startTimer()
    jobs = [download_urllib(url) for url in urls]
    #for status, data in jobs:
    #    print(status, data[:10])
    #tic(urllibT, 'urllib.request')
    urllibL.append(ticT(urllibT))
    print('1')
    
    requestsT = startTimer()
    jobs = [download_requests(url) for url in urls]
    #for status, data in jobs:
    #    print(status, data[:10])
    #tic(requestsT, 'requests')
    requestsL.append(ticT(requestsT))
    print('2')
    
    requestsT = startTimer()
    pool = multiprocessing.Pool(PoolNum)
    data = pool.map(download_requests, urls)
    pool.close()
    pool.join()
    multiPool.append(ticT(requestsT))
    print('3')

    requestsT = startTimer()
    pool = threadPoolManager(urls, threadNum=PoolNum)
    pool.waitAllComplete()
    threadPool.append(ticT(requestsT))
    print('4')

import matplotlib.pyplot as plt
x = list(range(1, N+1))
plt.plot(x, urllibL, label='urllib')
plt.plot(x, requestsL, label='requests')
plt.plot(x, multiPool, label='requests MultiPool')
plt.plot(x, threadPool, label='requests threadPool')
plt.xlabel('test number')
plt.ylabel('time(s)')
plt.legend()
plt.show()

运行结果如下：

 

 

        从上图可以看出，python3自带的urllib.request效率还是不如开源的requests，multiprocessing进程池效率明显提升，但还低于自己封装的线程池，有一部分原因是创建、调度进程的开销比创建线程高（测试程序中我把创建的代价也包括在里面）。

在Windows上要想使用进程模块，就必须把有关进程的代码写在当前.py文件的if __name__ == ‘__main__’ :语句的下面，才能正常使用Windows下的进程模块。Unix/Linux下则不需要。

 

下面是gevent的测试代码：

import urllib.request
import requests
import time
import gevent.pool
import gevent.monkey

gevent.monkey.patch_all()

def startTimer():
    return time.time()

def ticT(startTime):
    useTime = time.time() - startTime
    return round(useTime, 3)

#def tic(startTime, name):
#    useTime = time.time() - startTime
#    print('[%s] use time: %1.3f' % (name, useTime))

def download_urllib(url):
    req = urllib.request.Request(url,
            headers={'user-agent': 'Mozilla/5.0'})
    res = urllib.request.urlopen(req)
    data = res.read()
    try:
        data = data.decode('gbk')
    except UnicodeDecodeError:
        data = data.decode('utf8', 'ignore')
    return res.status, data

def download_requests(url):
    req = requests.get(url,
            headers={'user-agent': 'Mozilla/5.0'})
    return req.status_code, req.text

urls = ['http://www.ustchacker.com'] * 10
urllibL = []
requestsL = []
reqPool = []
reqSpawn = []
N = 20
PoolNum = 100

for i in range(N):
    print('start %d try' % i)
    urllibT = startTimer()
    jobs = [download_urllib(url) for url in urls]
    #for status, data in jobs:
    #    print(status, data[:10])
    #tic(urllibT, 'urllib.request')
    urllibL.append(ticT(urllibT))
    print('1')
    
    requestsT = startTimer()
    jobs = [download_requests(url) for url in urls]
    #for status, data in jobs:
    #    print(status, data[:10])
    #tic(requestsT, 'requests')
    requestsL.append(ticT(requestsT))
    print('2')
    
    requestsT = startTimer()
    pool = gevent.pool.Pool(PoolNum)
    data = pool.map(download_requests, urls)
    #for status, text in data:
    #    print(status, text[:10])
    #tic(requestsT, 'requests with gevent.pool')
    reqPool.append(ticT(requestsT))
    print('3')
    
    requestsT = startTimer()
    jobs = [gevent.spawn(download_requests, url) for url in urls]
    gevent.joinall(jobs)
    #for i in jobs:
    #    print(i.value[0], i.value[1][:10])
    #tic(requestsT, 'requests with gevent.spawn')
    reqSpawn.append(ticT(requestsT))
    print('4')
    
import matplotlib.pyplot as plt
x = list(range(1, N+1))
plt.plot(x, urllibL, label='urllib')
plt.plot(x, requestsL, label='requests')
plt.plot(x, reqPool, label='requests geventPool')
plt.plot(x, reqSpawn, label='requests Spawn')
plt.xlabel('test number')
plt.ylabel('time(s)')
plt.legend()
plt.show()

运行结果如下：

 

        从上图可以看到，对于I/O密集型任务，gevent还是能对性能做很大提升的，由于协程的创建、调度开销都比线程小的多，所以可以看到不论使用gevent的Spawn模式还是Pool模式，性能差距不大。

        因为在gevent中需要使用monkey补丁，会提高gevent的性能，但会影响multiprocessing的运行，如果要同时使用，需要如下代码：

gevent.monkey.patch_all(thread=False, socket=False, select=False)

可是这样就不能充分发挥gevent的优势，所以不能把multiprocessing Pool、threading Pool、gevent Pool在一个程序中对比。不过比较两图可以得出结论，线程池和gevent的性能最优的，其次是进程池。附带得出个结论，requests库比urllib.request库性能要好一些哈:-)        

 

转载请注明：转自http://blog.csdn.net/littlethunder/article/details/40983031