我想知道并行文件写入是否有效。确实，硬盘一次具有一个可用的读取头。因此，HDD可以一次执行一项任务。但是下面的测试（在python中）与我的期望相矛盾：

要复制的文件约为1 Gb

脚本1（//读取和写入同一文件10次的任务）：

#!/usr/bin/env python
from multiprocessing import Pool
def read_and_write( copy_filename ):
    with open( "/env/cns/bigtmp1/ERR000916_2.fastq", "r") as fori:
        with open( "/env/cns/bigtmp1/{}.fastq".format( copy_filename) , "w" ) as fout:
            for line in fori:
                fout.write( line + "\n" )
    return copy_filename

def main():
    f_names = [ "test_jm_{}".format(i) for i in range( 0, 10 ) ]
    pool = Pool(processes=4)
    results = pool.map( read_and_write, f_names )

if __name__ == "__main__":
    main()

脚本2（读取和写入同一文件的行10次的任务）：

#!/usr/bin/env python
def read_and_write( copy_filename ):
    with open( "/env/cns/bigtmp1/ERR000916_2.fastq", "r") as fori:
        with open( "/env/cns/bigtmp1/{}.fastq".format( copy_filename) , "w" ) as fout:
            for line in fori:
                fout.write( line + "\n" )
    return copy_filename

def main():
    f_names = [ "test_jm_{}".format(i) for i in range( 0, 10 ) ]
    for n in f_names:
        result = read_and_write( n )

if __name__ == "__main__":
    main()

脚本3（//复制同一文件10次的任务）：

#!/usr/bin/env python
from shutil import copyfile
from multiprocessing import Pool
def read_and_write( copy_filename ):
    copyfile( "/env/cns/bigtmp1/ERR000916_2.fastq", "/env/cns/bigtmp1/{}.fastq".format( copy_filename) )
    return copy_filename

def main():
    f_names = [ "test_jm_{}".format(i) for i in range( 0, 10 ) ]
    pool = Pool(processes=4)
    results = pool.map( read_and_write, f_names )

if __name__ == "__main__":
    main()

脚本4（将同一文件复制10次的任务）：

#!/usr/bin/env python
from shutil import copyfile
def read_and_write( copy_filename ):
    copyfile( "/env/cns/bigtmp1/ERR000916_2.fastq", "/env/cns/bigtmp1/{}.fastq".format( copy_filename) )
    return copy_filename

def main():
    f_names = [ "test_jm_{}".format(i) for i in range( 0, 10 ) ]
    for n in f_names:
        result = read_and_write( n )

if __name__ == "__main__":
    main()

结果：

$ # // task to read and write line by line 10 times a same file
$ time python read_write_1.py

real    1m46.484s
user    3m40.865s
sys 0m29.455s

$ rm test_jm*
$ # task to read and write line by line 10 times a same file
$ time python read_write_2.py

real    4m16.530s
user    3m41.303s
sys 0m24.032s

$ rm test_jm*
$ # // task to copy 10 times a same file
$ time python read_write_3.py

real    1m35.890s
user    0m10.615s
sys 0m36.361s


$ rm test_jm*
$ # task to copy 10 times a same file
$ time python read_write_4.py

real    1m40.660s
user    0m7.322s
sys 0m25.020s
$ rm test_jm*

这些基本结果似乎表明// io读写更有效。

谢谢你的光