python `hdfs`模块中client.upload()的连接问题

如何解决python `hdfs`模块中client.upload()的连接问题

我想通过python模块hdfs将文件上传到我的hdfs。我的 hadoop 在 docker-compose 中运行，我想上传大约 800,000 个文件到 hdfs。

代码就像

#!/home/fengnx/anaconda3/bin/python

from tqdm import tqdm
from hdfs import *
import os

class pyhdfs(object):
    """docstring for pyhdfs"""
    def __init__(self,ip,port):
        self.ip = ip
        self.port = port
        self.url = 'http://'+self.ip+':'+self.port
        self.client = Client(self.url)
    def mkdir(self,dirname,permission=''):
        if permission:
            permission = int(permission)
        else:
            permission = 644
        self.client.makedirs(dirname,permission = permission)
    def rmdir(self,dirname):
        self.client.delete(dirname,True)
    def upload(self,filename):
        self.client.upload(dirname,filename)
    def download(self,filename,download_filename):
        self.client.download(filename,download_filename)
    def cat(self,filename):
        with self.client.read(filename) as f:
            return f.read()

class file_file(object):
    """docstring for file_file"""
    def __init__(self,work_dir):
        self.work_dir=work_dir
        self.all_files = []
    def get_all_files(self):
        for parent,dirnames,filenames in os.walk(self.work_dir):
            for filename in filenames:
                file_path = os.path.join(parent,filename)
                self.all_files.append(file_path)
        return self.all_files

if __name__ == '__main__':
    a = pyhdfs('127.0.0.1','9870')
    a.mkdir('/ddbs')
    files = file_file('../articles')
    all_files = files.get_all_files()
    for file in tqdm(all_files):
        #print(file)
        a.upload('/ddbs',file)

但我得到了 urllib3.exceptions.NewConnectionError: <urllib3.connection.httpconnection object at 0x7fd9844da7f0>: Failed to establish a new connection: [Errno 22] Invalid argument 的 a.upload('/ddbs',file)。

docker-compose.yml 是：

version: "3"

services:
  namenode:
    image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
    container_name: namenode
    restart: always
    ports:
      - 9870:9870
      - 9000:9000
    volumes:
      - hadoop_namenode:/hadoop/dfs/name
    environment:
      - CLUSTER_NAME=test
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.2

  datanode1:
    image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
    container_name: datanode1
    restart: always
    hostname: 172.21.0.3
    volumes:
      - hadoop_datanode1:/hadoop/dfs/data
    environment:
      SERVICE_PRECONDITION: "namenode:9870"
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.3

  datanode2:
    image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
    container_name: datanode2
    restart: always
    hostname: 172.21.0.4
    volumes:
      - hadoop_datanode2:/hadoop/dfs/data
    environment:
      SERVICE_PRECONDITION: "namenode:9870"
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.4

  resourcemanager:
    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.2.1-java8
    container_name: resourcemanager
    restart: always
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864"
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.5

  nodemanager1:
    image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.2.1-java8
    container_name: nodemanager
    restart: always
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.6

  historyserver:
    image: bde2020/hadoop-historyserver:2.0.0-hadoop3.2.1-java8
    container_name: historyserver
    restart: always
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
    volumes:
      - hadoop_historyserver:/hadoop/yarn/timeline
    env_file:
      - ./hadoop.env
    networks:
      hadoopnet:
        ipv4_address: 172.21.0.7

volumes:
  hadoop_namenode:
  hadoop_datanode1:
  hadoop_datanode2:
  hadoop_historyserver:

networks:
  hadoopnet:
    driver: bridge
    ipam:
      driver: default
      config:
      -
        subnet: 172.21.0.0/24