python - Pydoop 卡在 HDFS 文件的 readline 上

Question

我正在读取目录中所有文件的第一行，在本地它工作正常，但在 EMR 上，此测试在卡在大约 200-300 个文件时失败。ps -eLF 还显示子项增加到 3000，甚至在第 200 行打印。

这是 EMR 读取最大字节数的一些错误吗？pydoop版本pydoop==0.12.0

import os
import sys
import shutil
import codecs
import pydoop.hdfs as hdfs


def prepare_data(hdfs_folder):
    folder = "test_folder"
    copies_count = 700
    src_file = "file"

    #1) create a folder
    if os.path.exists(folder):
        shutil.rmtree(folder)
    os.makedirs(folder)

    #2) create XXX copies of file in folder
    for x in range(0, copies_count):
        shutil.copyfile(src_file, folder+"/"+src_file+"_"+str(x))

    #3) copy folder to hdfs
    #hadoop fs -copyFromLocal test_folder/ /maaz/test_aa
    remove_command = "hadoop fs -rmr "+ hdfs_folder
    print remove_command
    os.system(remove_command)
    command = "hadoop fs -copyFromLocal "+folder+" "+ hdfs_folder
    print command
    os.system(command)

def main(hdfs_folder):
    try:
        conn_hdfs = hdfs.fs.hdfs()
        if conn_hdfs.exists(hdfs_folder):
            items_list = conn_hdfs.list_directory(hdfs_folder)
            for item in items_list:
                if not item["kind"] == "file":
                    continue
                file_name = item["name"]
                print "validating file : %s" % file_name

                try:
                    file_handle = conn_hdfs.open_file(file_name)
                    file_line = file_handle.readline()
                    print file_line
                    file_handle.close()
                except Exception as exp:
                    print '####Exception \'%s\' in reading file %s' % (str(exp), file_name)
                    file_handle.close()
                    continue

        conn_hdfs.close()

    except Exception as e:
        print "####Exception \'%s\' in validating files!" % str(e)



if __name__ == '__main__':

    hdfs_path = '/abc/xyz'
    prepare_data(hdfs_path)

    main(hdfs_path)

Answer 1

我建议使用 subprocess 模块来读取第一行，而不是 pydoop 的 conn_hdfs.open_file

import subprocess
cmd='hadoop fs -cat {f}|head -1'.format(f=file_name)
process=subprocess.Popen(cmd, shell=True,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
stdout, stderr=process.communicate()
if stderr!='':
    file_line=stdout.split('\n')[0]
else:
     print "####Exception '{e}' in reading file {f}".format(f=file_name,e=stdout)
     continue