DataX部署及使用

https://github.com/alibaba/DataX

基础依赖 : python2
解压后运行自检脚本：

./bin/datax.py  ./job/job.json

出现如下界面代表OK

编辑 mysql2hdfs.json 文件

cd datax/job
vim mysql2hdfs.json

{
    "job": {
        "content": [
            {
                "reader": {
                    "name": "mysqlreader", 
                    "parameter": {
                        "column": [
                            "id",
                            "arth_type",
                            "content"
                        ], 
                        "connection": [
                            {
                                "jdbcUrl": [
                                    "jdbc:mysql://10.20.8.86:13306/test_db"
                                ], 
                                "table": [
                                    "test_in"
                                ]
                            }
                        ], 
                        "password": "123456", 
                        "username": "clj"
                    }
                }, 
                "writer": {
                    "name": "hdfswriter", 
                    "parameter": {
                        "column": [
                            {
                                "name":"id",
                                "type":"int"
                            },
                            {
                                "name":"arth_type",
                                "type":"string"
                            },
							{
                                "name":"content",
                                "type":"string"
                            }
                        ], 
                        "defaultFS": "hdfs://sentiment", 
						"hadoopConfig":{
						  "dfs.nameservices": "sentiment",
						  "dfs.ha.namenodes.sentiment": "namenode1,namenode2",
						  "dfs.namenode.rpc-address.sentiment.namenode1": "clj-mr-m1:8020",
						  "dfs.namenode.rpc-address.sentiment.namenode2": "clj-mr-m2:8020",
						  "dfs.client.failover.proxy.provider.sentiment": "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider"
						},
                        "fieldDelimiter": "t", 
                        "fileName": "keyword.txt", 
                        "fileType": "text", 
                        "path": "/datax/test_in", 
                        "writeMode": "append"
                    }
                }
            }
        ], 
        "setting": {
            "speed": {
                "channel": "3"
            }
        }
    }
}

注意点：
如果mysql版本比较高，需要更换驱动包，路径如下：

 plugin/reader/mysqlreader/libs/

hdfswriter需要预选创建hive外部表

create external table test_in(
 `id` bigint,
 `arth_type` string,
 `content` string
)
stored as textfile 
LOCATION 
'/datax/test_in';

高可用hdfs注意如下配置：

"defaultFS": "hdfs://sentiment", 
"hadoopConfig":{
  "dfs.nameservices": "sentiment",
  "dfs.ha.namenodes.sentiment": "namenode1,namenode2",
  "dfs.namenode.rpc-address.sentiment.namenode1": "clj-mr-m1:8020",
  "dfs.namenode.rpc-address.sentiment.namenode2": "clj-mr-m2:8020",
  "dfs.client.failover.proxy.provider.sentiment": "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider"
},

同步完成标志：