Python多进程multiprocessing.Pool类详解

__init__(self, group=None, target=None, name=None, args=(), kwargs={})

#coding=utf-8
import multiprocessing

def do(n) :
 #获取当前线程的名字
 name = multiprocessing.current_process().name
 print name,'starting'
 print "worker ", n
 return

if __name__ == '__main__' :
 numList = []
 for i in xrange(5) :
  p = multiprocessing.Process(target=do, args=(i,))
  numList.append(p)
  p.start()
  p.join()
  print "Process end."

Process-1 starting
worker 0
Process end.
Process-2 starting
worker 1
Process end.
Process-3 starting
worker 2
Process end.
Process-4 starting
worker 3
Process end.
Process-5 starting
worker 4
Process end.

apply(func[, args=()[, kwds={}]])

apply_async(func[, args=()[, kwds={}[, callback=None]]])

map(func, iterable[, chunksize=None])

import time
from multiprocessing import Pool
def run(fn):
 #fn: 函数参数是数据列表的一个元素
 time.sleep(1)
 return fn*fn

if __name__ == "__main__":
 testFL = [1,2,3,4,5,6] 
 print 'shunxu:' #顺序执行(也就是串行执行，单进程)
 s = time.time()
 for fn in testFL:
  run(fn)

 e1 = time.time()
 print "顺序执行时间：", int(e1 - s)

 print 'concurrent:' #创建多个进程，并行执行
 pool = Pool(5) #创建拥有5个进程数量的进程池
 #testFL:要处理的数据列表，run：处理testFL列表中数据的函数
 rl =pool.map(run, testFL) 
 pool.close()#关闭进程池，不再接受新的进程
 pool.join()#主进程阻塞等待子进程的退出
 e2 = time.time()
 print "并行执行时间：", int(e2-e1)
 print rl

import time
from multiprocessing import Pool
def run(fn) :
 time.sleep(2)
 print fn
if __name__ == "__main__" :
 startTime = time.time()
 testFL = [1,2,3,4,5]
 pool = Pool(10)#可以同时跑10个进程
 pool.map(run,testFL)
 pool.close()
 pool.join()  
 endTime = time.time()
 print "time :", endTime - startTime

21

3
4
5
time : 2.51999998093

1
34

2
5
time : 2.48600006104

import os
import time
from multiprocessing import Pool

def getFile(path) :
 #获取目录下的文件list
 fileList = []
 for root, dirs, files in list(os.walk(path)) :
  for i in files :
   if i.endswith('.txt') or i.endswith('.10w') :
    fileList.append(root + "\\" + i)
 return fileList

def operFile(filePath) :
 #统计每个文件中行数和字符数，并返回
 filePath = filePath
 fp = open(filePath)
 content = fp.readlines()
 fp.close()
 lines = len(content)
 alphaNum = 0
 for i in content :
  alphaNum += len(i.strip('\n'))
 return lines,alphaNum,filePath

def out(list1, writeFilePath) :
 #将统计结果写入结果文件中
 fileLines = 0
 charNum = 0
 fp = open(writeFilePath,'a')
 for i in list1 :
  fp.write(i[2] + " 行数："+ str(i[0]) + " 字符数："+str(i[1]) + "\n")
  fileLines += i[0]
  charNum += i[1]
 fp.close()
 print fileLines, charNum

if __name__ == "__main__":
 #创建多个进程去统计目录中所有文件的行数和字符数
 startTime = time.time()
 filePath = "C:\\wcx\\a"
 fileList = getFile(filePath)
 pool = Pool(5) 
 resultList =pool.map(operFile, fileList) 
 pool.close()
 pool.join()

 writeFilePath = "c:\\wcx\\res.txt"
 print resultList
 out(resultList, writeFilePath)
 endTime = time.time()
 print "used time is ", endTime - startTime