datax同步数据：数据源：hdfs，目标源：hdfs

一.配置文件hdfs-hdfs.json

{
    "job": {
        "setting": {
            "speed": {
                "channel": 3
            }
        },
        "content": [
            {
                "reader": {
                    "name": "hdfsreader",
                    "parameter": {
                        "path": "/user/anguoan/*",
                        "defaultFS": "hdfs://10.x.x.x:8020",
                        "column": [
                               {
                                "index": 0,
                                "type": "long"
                               },
                               {
                                "index": 1,
                                "type": "string"
                               },
                               {
                                "index": 2,
                                "type": "string"
                               }
                        ],
                        "fileType": "text",
                        "encoding": "UTF-8",
                        "fieldDelimiter": ","
                    }

                },
                "writer": {
                    "name": "hdfswriter",
                    "parameter": {
                        "defaultFS": "hdfs://x.x.x.x:8020",
                        "fileType": "text",
                        "path": "/user/admin/",
                        "fileName": "hdfswriter",
                        "column": [
                            {
                                "name": "col1",
                                "type": "varchar"
                            },
                            {
                                "name": "col2",
                                "type": "varchar"
                            },
                            {
                                "name": "col3",
                                "type": "varchar"
                            }
                        ],
                        "writeMode": "append",
                        "fieldDelimiter": ","
                    }
                }
            }
        ]
    }
}

二.执行脚本

datax.py hdfs-hdfs.json