目前計算機程序一般會遇到兩類I/O：硬盤I/O和網絡I/O。我就針對網絡I/O的場景分析下python3下進程、線程、協程效率的對比。進程采用multiprocessing.Pool進程池，線程是自己封裝的進程池，協程采用gevent的庫。用python3自帶的urlllib.request和開源的requests做對比。代碼如下：

importurllib.requestimportrequestsimporttimeimportmultiprocessingimportthreadingimportqueuedefstartTimer():returntime.time()defticT(startTime):

useTime= time.time() -startTimereturn round(useTime, 3)#def tic(startTime, name):#useTime = time.time() - startTime#print('[%s] use time: %1.3f' % (name, useTime))

defdownload_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')exceptUnicodeDecodeError:

data= data.decode('utf8', 'ignore')returnres.status, datadefdownload_requests(url):

req=requests.get(url,

headers={'user-agent': 'Mozilla/5.0'})returnreq.status_code, req.textclassthreadPoolManager: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 inurls:

self.workQueue.put((download_requests,i))def __initThreadPool(self,threadNum):for i inrange(threadNum):

self.threadPool.append(work(self.workQueue))defwaitAllComplete(self):for i inself.threadPool:ifi.isAlive():

i.join()classwork(threading.Thread):def __init__(self,workQueue):

threading.Thread.__init__(self)

self.workQueue=workQueue

self.start()defrun(self):whileTrue:ifself.workQueue.qsize():

do,args=self.workQueue.get(block=False)

do(args)

self.workQueue.task_done()else:breakurls= ['http://www.ustchacker.com'] * 10urllibL=[]

requestsL=[]

multiPool=[]

threadPool=[]

N= 20PoolNum= 100

for i inrange(N):print('start %d try' %i)

urllibT=startTimer()

jobs= [download_urllib(url) for url inurls]#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 inurls]#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')importmatplotlib.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()

運行結果如下：

從上圖可以看出，python3自帶的urllib.request效率還是不如開源的requests，multiprocessing進程池效率明顯提升，但還低于自己封裝的線程池，有一部分原因是創建、調度進程的開銷比創建線程高(測試程序中我把創建的代價也包括在里面)。

在Windows上要想使用進程模塊，就必須把有關進程的代碼寫在當前.py文件的if __name__ == ‘__main__’ :語句的下面，才能正常使用Windows下的進程模塊。Unix/Linux下則不需要。

下面是gevent的測試代碼：

importurllib.requestimportrequestsimporttimeimportgevent.poolimportgevent.monkey

gevent.monkey.patch_all()defstartTimer():returntime.time()defticT(startTime):

useTime= time.time() -startTimereturn round(useTime, 3)#def tic(startTime, name):#useTime = time.time() - startTime#print('[%s] use time: %1.3f' % (name, useTime))

defdownload_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')exceptUnicodeDecodeError:

data= data.decode('utf8', 'ignore')returnres.status, datadefdownload_requests(url):

req=requests.get(url,

headers={'user-agent': 'Mozilla/5.0'})returnreq.status_code, req.text

urls= ['http://www.ustchacker.com'] * 10urllibL=[]

requestsL=[]

reqPool=[]

reqSpawn=[]

N= 20PoolNum= 100

for i inrange(N):print('start %d try' %i)

urllibT=startTimer()

jobs= [download_urllib(url) for url inurls]#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 inurls]#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 inurls]

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')importmatplotlib.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()

運行結果如下：

從上圖可以看到，對于I/O密集型任務，gevent還是能對性能做很大提升的，由于協程的創建、調度開銷都比線程小的多，所以可以看到不論使用gevent的Spawn模式還是Pool模式，性能差距不大。

因為在gevent中需要使用monkey補丁，會提高gevent的性能，但會影響multiprocessing的運行，如果要同時使用，需要如下代碼：

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

可是這樣就不能充分發揮gevent的優勢，所以不能把multiprocessing Pool、threading Pool、gevent Pool在一個程序中對比。不過比較兩圖可以得出結論，線程池和gevent的性能最優的，其次是進程池。附帶得出個結論，requests庫比urllib.request庫性能要好一些哈:-)

總結

以上是生活随笔為你收集整理的python3多线程协程_python3-----多进程、多线程、多协程的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。