文章目录
DataX的安装
DataX不需要依赖其他服务，直接上传、解压、安装、配置环境变量（/etc/profile））即可
DataX的使用
stream2stream
编写配置文件stream2stream.json
# stream2stream.json
{
"job": {
"content": [
{
"reader": {
"name": "streamreader",
"parameter": {
"sliceRecordCount": 10,
"column": [
{
"type": "long",
"value": "10"
},
{
"type": "string",
"value": "hello，你好，世界-DataX"
}
]
}
},
"writer": {
"name": "streamwriter",
"parameter": {
"encoding": "UTF-8",
"print": true
}
}
}
],
"setting": {
"speed": {
"channel": 5
}
}
}
}
执行同步任务
datax.py stream2stream.json
执行结果
mysql2mysql
需要新建student2数据库，并创建student表
编写配置文件mysql2mysql.json
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"splitPk": "age",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"writeMode": "insert",
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"preSql": [
"truncate student"
],
"connection": [
{
"jdbcUrl": "jdbc:mysql://master:3306/student2?useUnicode=true&characterEncoding=utf8",
"table": [
"student"
]
}
]
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
执行同步任务
datax.py mysql2mysql.json
mysql2hdfs
写hive跟hdfs时一样的
编写配置文件mysql2hdfs.json
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"splitPk": "age",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"defaultFS": "hdfs://master:9000",
"fileType": "text",
"path": "/user/hive/warehouse/datax.db/students",
"fileName": "student",
"column": [
{
"name": "id",
studen "type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "INT"
},
{
"name": "gender",
"type": "string"
},
{
"name": "clazz",
"type": "string"
},
{
"name": "last_mod",
"type": "string"
}
],
"writeMode": "append",
"fieldDelimiter": ","
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
hbase2mysql
{
"job": {
"content": [
{
"reader": {
"name": "hbase11xreader",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master:2181"
},
"table": "student",
"encoding": "utf-8",
"mode": "normal",
"column": [
{
"name": "rowkey",
"type": "string"
},
{
"name": "cf1:name",
"type": "string"
},
{
"name": "cf1:age",
"type": "string"
},
{
"name": "cf1:gender",
"type": "string"
},
{
"name": "cf1:clazz",
"type": "string"
}
],
"range": {
"startRowkey": "",
"endRowkey": "",
"isBinaryRowkey": false
}
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"writeMode": "insert",
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz"
],
"preSql": [
"truncate student2"
],
"connection": [
{
"jdbcUrl": "jdbc:mysql://master:3306/student2?useUnicode=true&characterEncoding=utf8",
"table": [
"student2"
]
}
]
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
mysql2hbase
mysql中的score表需将cource_id改为course_id，并将student_id、course_id设为主键，并将所有字段的类型改为int
hbase需先创建score表：create ‘score’,‘cf1’
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"student_id",
"course_id",
"score"
],
"splitPk": "course_id",
"connection": [
{
"table": [
"score"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "hbase11xwriter",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master:2181"
},
"table": "score",
"mode": "normal",
"rowkeyColumn": [
{
"index":0,
"type":"string"
},
{
"index":-1,
"type":"string",
"value":"_"
},
{
"index":1,
"type":"string"
}
],
"column": [
{
"index":2,
"name": "cf1:score",
"type": "int"
}
],
"encoding": "utf-8"
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
mysql2Phoenix
在Phoenix中创建STUDENT表
CREATE TABLE IF NOT EXISTS STUDENT (
ID VARCHAR NOT NULL PRIMARY KEY,
NAME VARCHAR,
AGE BIGINT,
GENDER VARCHAR ,
CLAZZ VARCHAR
);
编写配置文件MySQLToPhoenix.json
{
"job": {
"setting": {
"speed": {
"channel": 3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz"
],
"splitPk": "id",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student?useSSL=false"
]
}
]
}
},
"writer": {
"name": "hbase11xsqlwriter",
"parameter": {
"batchSize": "256",
"column": [
"ID",
"NAME",
"AGE",
"GENDER",
"CLAZZ"
],
"hbaseConfig": {
"hbase.zookeeper.quorum": "master,node1,node2",
"zookeeper.znode.parent": "/hbase"
},
"nullMode": "skip",
"table": "STUDENT"
}
}
}
]
}
}
HDFSToHBase
将students.txt数据上传至HDFS的
/data/student1/目录在HBase中创建datax表：
create 'datax','cf1'
{
"job": {
"setting": {
"speed": {
"channel": 3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [
{
"reader": {
"name": "hdfsreader",
"parameter": {
"path": "/data/student1/",
"defaultFS": "hdfs://master:9000",
"column": [
{
"index": 0,
"type": "string"
},
{
"index": 1,
"type": "string"
},
{
"index": 2,
"type": "string"
},
{
"index": 3,
"type": "string"
},
{
"index": 4,
"type": "string"
},
{
"index": 5,
"type": "string"
}
],
"fileType": "text",
"encoding": "UTF-8",
"fieldDelimiter": ","
}
},
"writer": {
"name": "hbase11xwriter",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master,node1,node2"
},
"table": "datax",
"mode": "normal",
"rowkeyColumn": [
{
"index": 0,
"type": "string"
},
{
"index": -1,
"type": "string",
"value": "_"
},
{
"index": 1,
"type": "string"
}
],
"column": [
{
"index": 2,
"name": "cf1:age",
"type": "string"
},
{
"index": 3,
"name": "cf1:gender",
"type": "string"
},
{
"index": 4,
"name": "cf1:clazz",
"type": "string"
},
{
"index": 5,
"name": "cf1:ts",
"type": "string"
}
],
"versionColumn": {
"index": 5
},
"encoding": "utf-8"
}
}
}
]
}
}
FlinkX的安装与简单使用
FlinkX的安装
安装unzip：yum install unzip
1、上传并解压
unzip flinkx-1.10.zip -d /usr/local/soft/
2、配置环境变量
3、给bin/flinkx这个文件加上执行权限
chmod a+x flinkx
4、修改配置文件，设置运行端口
vim flinkconf/flink-conf.yaml
## web服务端口，不指定的话会随机生成一个
rest.bind-port: 8888
FlinkX的简单使用
MySQLToHDFS
- 配置文件
{
"job": {
"content": [
{
"reader": {
"parameter": {
"username": "root",
"password": "123456",
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://master:3306/student?characterEncoding=utf8"
],
"table": [
"student"
]
}
],
"column": [
"*"
],
"customSql": "",
"where": "clazz = '理科二班'",
"splitPk": "",
"queryTimeOut": 1000,
"requestAccumulatorInterval": 2
},
"name": "mysqlreader"
},
"writer": {
"name": "hdfswriter",
"parameter": {
"path": "hdfs://master:9000/data/flinkx/student",
"defaultFS": "hdfs://master:9000",
"column": [
{
"name": "col1",
"index": 0,
"type": "string"
},
{
"name": "col2",
"index": 1,
"type": "string"
},
{
"name": "col3",
"index": 2,
"type": "string"
},
{
"name": "col4",
"index": 3,
"type": "string"
},
{
"name": "col5",
"index": 4,
"type": "string"
},
{
"name": "col6",
"index": 5,
"type": "string"
}
],
"fieldDelimiter": ",",
"fileType": "text",
"writeMode": "overwrite"
}
}
}
],
"setting": {
"restore": {
"isRestore": false,
"isStream": false
},
"errorLimit": {},
"speed": {
"channel": 1
}
}
}
}
- 启动任务
flinkx -mode local -job /usr/local/soft/flinkx-1.10/job/mysqlToHDFS.json -pluginRoot /usr/local/soft/flinkx-1.10/syncplugins/ -flinkconf /usr/local/soft/flinkx-1.10/flinkconf/
- 监听日志
flinkx 任务启动后，会在执行命令的目录下生成一个nohup.out文件
tail -f nohup.out
- 通过web界面查看任务运行情况
http://master:8888
MySQLToHive
- 配置文件
{
"job": {
"content": [
{
"reader": {
"parameter": {
"username": "root",
"password": "123456",
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://master:3306/student?characterEncoding=utf8"
],
"table": [
"student"
]
}
],
"column": [
"*"
],
"customSql": "",
"where": "clazz = '文科二班'",
"splitPk": "id",
"queryTimeOut": 1000,
"requestAccumulatorInterval": 2
},
"name": "mysqlreader"
},
"writer": {
"name": "hivewriter",
"parameter": {
"jdbcUrl": "jdbc:hive2://master:10000/testflinkx",
"username": "",
"password": "",
"fileType": "text",
"fieldDelimiter": ",",
"writeMode": "overwrite",
"compress": "",
"charsetName": "UTF-8",
"maxFileSize": 1073741824,
"tablesColumn": "{\"student\":[{\"key\":\"id\",\"type\":\"string\"},{\"key\":\"name\",\"type\":\"string\"},{\"key\":\"age\",\"type\":\"string\"}]}",
"defaultFS": "hdfs://master:9000"
}
}
}
],
"setting": {
"restore": {
"isRestore": false,
"isStream": false
},
"errorLimit": {},
"speed": {
"channel": 3
}
}
}
}
- 在hive中创建testflinkx数据库，并创建student分区表
create database testflinkx;
use testflinkx;
CREATE TABLE `student`(
`id` string,
`name` string,
`age` string)
PARTITIONED BY (
`pt` string)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
- 启动hiveserver2
# 第一种方式：
hiveserver2
# 第二种方式:
hive --service hiveserver2
- 启动任务
flinkx -mode local -job /usr/local/soft/flinkx-1.10/jsonConf/mysqlToHive.json -pluginRoot /usr/local/soft/flinkx-1.10/syncplugins/ -flinkconf /usr/local/soft/flinkx-1.10/flinkconf/
- 查看日志及运行情况同上
MySQLToHBase
- 配置文件
{
"job": {
"content": [
{
"reader": {
"parameter": {
"username": "root",
"password": "123456",
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://master:3306/student?characterEncoding=utf8"
],
"table": [
"score"
]
}
],
"column": [
"*"
],
"customSql": "",
"splitPk": "student_id",
"queryTimeOut": 1000,
"requestAccumulatorInterval": 2
},
"name": "mysqlreader"
},
"writer": {
"name": "hbasewriter",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.property.clientPort": "2181",
"hbase.rootdir": "hdfs://master:9000/hbase",
"hbase.cluster.distributed": "true",
"hbase.zookeeper.quorum": "master,node1,node2",
"zookeeper.znode.parent": "/hbase"
},
"table": "testFlinkx",
"rowkeyColumn": "$(cf1:student_id)_$(cf1:course_id)",
"column": [
{
"name": "cf1:student_id",
"type": "string"
},
{
"name": "cf1:course_id",
"type": "string"
},
{
"name": "cf1:score",
"type": "string"
}
]
}
}
}
],
"setting": {
"restore": {
"isRestore": false,
"isStream": false
},
"errorLimit": {},
"speed": {
"channel": 3
}
}
}
}
- 启动hbase 并创建testflinkx表
create 'testFlinkx','cf1'
- 启动任务
flinkx -mode local -job /usr/local/soft/flinkx-1.10/jsonConf/mysqlToHBase.json -pluginRoot /usr/local/soft/flinkx-1.10/syncplugins/ -flinkconf /usr/local/soft/flinkx-1.10/flinkconf/
- 查看日志及运行情况同上
MySQLToMySQL
- 配置文件
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"column": [
{
"name": "id",
"type": "int"
},
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "int"
},
{
"name": "gender",
"type": "string"
},
{
"name": "clazz",
"type": "string"
}
],
"username": "root",
"password": "123456",
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://master:3306/student?useSSL=false"
],
"table": [
"student"
]
}
]
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"username": "root",
"password": "123456",
"connection": [
{
"jdbcUrl": "jdbc:mysql://master:3306/student?useSSL=false",
"table": [
"student2"
]
}
],
"writeMode": "insert",
"column": [
{
"name": "id",
"type": "int"
},
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "int"
},
{
"name": "gender",
"type": "string"
},
{
"name": "clazz",
"type": "string"
}
]
}
}
}
],
"setting": {
"speed": {
"channel": 1,
"bytes": 0
}
}
}
}