多线程文件复制比多核 CPU 上的单线程慢得多

I assume this is an I/O bound task, so multithreading should help the operation speed.

守则:

    import Queue
    import threading
    import cStringIO 
    import os
    import shutil
    import timeit  # time the code exec with gc disable
    import glob    # file wildcards list, glob.glob('*.py')
    import profile # 

    fileQueue = Queue.Queue() # global
    srcPath  = 'C:\temp'
    destPath = 'D:\temp'
    tcnt = 0
    ttotal = 0

    def CopyWorker():
        while True:
            fileName = fileQueue.get()
            fileQueue.task_done()
            shutil.copy(fileName, destPath)
            #tcnt += 1
            print 'copied: ', tcnt, ' of ', ttotal

    def threadWorkerCopy(fileNameList):
        print 'threadWorkerCopy: ', len(fileNameList)
        ttotal = len(fileNameList)
        for i in range(4):
            t = threading.Thread(target=CopyWorker)
            t.daemon = True
            t.start()
        for fileName in fileNameList:
            fileQueue.put(fileName)
        fileQueue.join()

    def sequentialCopy(fileNameList):
        #around 160.446 seconds, 152 seconds
        print 'sequentialCopy: ', len(fileNameList)
        cnt = 0
        ctotal = len(fileNameList)
        for fileName in fileNameList:
            shutil.copy(fileName, destPath)
            cnt += 1
            print 'copied: ', cnt, ' of ', ctotal

    def main():
        print 'this is main method'
        fileCount = 0
        fileList = glob.glob(srcPath + '\' + '*.csv')
        #sequentialCopy(fileList)
        threadWorkerCopy(fileList)

    if __name__ == '__main__':
        profile.run('main()')

解决方案

当然慢.硬盘驱动器必须不断地在文件之间寻找.您认为多线程会使这项任务更快的信念是完全没有道理的.限制速度是您可以从磁盘读取数据或将数据写入磁盘的速度，从一个文件到另一个文件的每次寻道都会浪费本可以用于传输数据的时间.