基本使用datax 将数据从mysql转入postgresql

1、安装jdk

[root@Antiy47 ~]# mkdir /usr/local/java
[root@Antiy47 ~]# tar zxvf jdk-8u211-linux-x64.tar.gz -C /usr/local/java
[root@Antiy47 ~]# rpm -e --nodeps `rpm -qa | grep java `
[root@Antiy47 ~]# alternatives --install /usr/bin/java  java  /usr/local/java/jdk1.8.0_211/bin/java  300
[root@Antiy47 ~]# alternatives --config java

2、安装mvn

[root@Antiy47 ~]# tar zxvf apache-maven-3.6.1-bin.tar.gz -C /opt
[root@Antiy47 ~]# vim /etc/profile
export JAVA_HOME=/usr/local/java/jdk1.8.0_211
export JRE_HOME=/usr/local/java/jdk1.8.0_211/jre
export PATH=$PATH:$JAVA_HOME/bin:$JRE_HOME/bin
export CLASSPATH=$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar:$JRE_HOME/lib
export MAVEN_HOME=/opt/apache-maven-3.6.1/
export PATH=$PATH:$JAVA_HOME/bin:$JRE_HOME/bin:$MAVEN_HOME/bin
[root@Antiy47 ~]# java -version
java version "1.8.0_171"
Java(TM) SE Runtime Environment (build 1.8.0_171-b11)
Java HotSpot(TM) 64-Bit Server VM (build 25.171-b11, mixed mode)
[root@Antiy47 ~]# mvn -version
Apache Maven 3.6.1 (d66c9c0b3152b2e69ee9bac180bb8fcc8e6af555; 2019-04-05T03:00:29+08:00)
Maven home: /opt/apache-maven-3.6.1
Java version: 1.8.0_211, vendor: Oracle Corporation, runtime: /usr/local/java/jdk1.8.0_211/jre
Default locale: en_US, platform encoding: UTF-8
OS name: "linux", version: "4.11.6-1.el6.elrepo.x86_64", arch: "amd64", family: "unix"

3、安装驱动

[root@Antiy47 ~]# rpm -ivh mysql-connector-java-8.0.16-1.el7.noarch.rpm 
[root@Antiy47 ~]# cp postgresql-42.2.5.jar /usr/local/java/jdk1.8.0_211/lib/

4、安装datax

[root@Antiy47 ~]# tar zxvf datax.tar.gz -C /opt/

5、测试datax

[root@Antiy47 ~]# cd /opt/datax/bin
[root@Antiy47 ~]# python datax.py ../job/job.json
最后返回
2019-06-14 00:09:44.149 [job-0] INFO  StandAloneJobContainerCommunicator - Total 100000 records, 2600000 bytes | Speed 253.91KB/s, 10000 records/s | Error 0 records, 0 bytes |  All Task WaitWriterTime 0.022s |  All Task WaitReaderTime 0.036s | Percentage 100.00%
2019-06-14 00:09:44.149 [job-0] INFO  JobContainer - 
任务启动时刻                    : 2019-06-14 00:09:34
任务结束时刻                    : 2019-06-14 00:09:44
任务总计耗时                    :                 10s
任务平均流量                    :          253.91KB/s
记录写入速度                    :          10000rec/s
读出记录总数                    :              100000
读写失败总数                    :                   0

6、从mysql导数据到postgresql
首先确认mysql与postgresql的表结构一致，其次确认pg的host登陆方法是md5

[root@Antiy47 bin]# python datax.py -r mysqlreader  -w  postgresqlwriter > myjob.json
[root@Antiy47 bin]# vim myjob.json
配置相关的jdbc url和数据库和表
{
    "job": {
        "content": [
            {
                "reader": {
                    "name": "mysqlreader", 
                    "parameter": {
                        "column": ["id","title","hosts"], 
                        "connection": [
                            {
                                "jdbcUrl": ["jdbc:mysql://127.0.0.1:3306/test?characterEncoding=utf8"], 
                                "table": ["dashboard_graph"]
                            }
                        ], 
                        "password": "123456", 
                        "username": "root", 
                        "where": ""
                    }
                }, 
                "writer": {
                    "name": "postgresqlwriter", 
                    "parameter": {
                        "column": ["id","title","hosts"],
                        "connection": [
                            {
                                "jdbcUrl": "jdbc:postgresql://127.0.0.1:5432/pgone", 
                                "table": ["t1"]
                            }
                        ], 
                        "password": "111111", 
                        "postSql": [], 
                        "preSql": [], 
                        "username": "postgres"
                    }
                }
            }
        ], 
        "setting": {
            "speed": {
                "channel": "3"
            }
        }
    }
}

导数据

[root@Antiy47 bin]# python datax.py myjob.json 

DataX (DATAX-OPENSOURCE-3.0), From Alibaba !
Copyright (C) 2010-2017, Alibaba Group. All Rights Reserved.


2019-06-13 23:51:32.463 [main] INFO  VMInfo - VMInfo# operatingSystem class => sun.management.OperatingSystemImpl
2019-06-13 23:51:32.470 [main] INFO  Engine - the machine info  => 

	osInfo:	Oracle Corporation 1.8 25.171-b11
	jvmInfo:	Linux amd64 4.11.6-1.el6.elrepo.x86_64
	cpu num:	64

	totalPhysicalMemory:	-0.00G
	freePhysicalMemory:	-0.00G
	maxFileDescriptorCount:	-1
	currentOpenFileDescriptorCount:	-1

	GC Names	[PS MarkSweep, PS Scavenge]

	MEMORY_NAME                    | allocation_size                | init_size                      
	PS Eden Space                  | 256.00MB                       | 256.00MB                       
	Code Cache                     | 240.00MB                       | 2.44MB                         
	Compressed Class Space         | 1,024.00MB                     | 0.00MB                         
	PS Survivor Space              | 42.50MB                        | 42.50MB                        
	PS Old Gen                     | 683.00MB                       | 683.00MB                       
	Metaspace                      | -0.00MB                        | 0.00MB                         


2019-06-13 23:51:32.488 [main] INFO  Engine - 
{
	"content":[
		{
			"reader":{
				"name":"mysqlreader",
				"parameter":{
					"column":[
						"id",
						"title",
						"hosts"
					],
					"connection":[
						{
							"jdbcUrl":[
								"jdbc:mysql://127.0.0.1:3306/test?characterEncoding=utf8"
							],
							"table":[
								"dashboard_graph"
							]
						}
					],
					"password":"******",
					"username":"root",
					"where":""
				}
			},
			"writer":{
				"name":"postgresqlwriter",
				"parameter":{
					"column":[
						"id",
						"title",
						"hosts"
					],
					"connection":[
						{
							"jdbcUrl":"jdbc:postgresql://127.0.0.1:5432/pgone",
							"table":[
								"t1"
							]
						}
					],
					"password":"******",
					"postSql":[],
					"preSql":[],
					"username":"postgres"
				}
			}
		}
	],
	"setting":{
		"speed":{
			"channel":"3"
		}
	}
}

2019-06-13 23:51:32.503 [main] WARN  Engine - prioriy set to 0, because NumberFormatException, the value is: null
2019-06-13 23:51:32.504 [main] INFO  PerfTrace - PerfTrace traceId=job_-1, isEnable=false, priority=0
2019-06-13 23:51:32.504 [main] INFO  JobContainer - DataX jobContainer starts job.
2019-06-13 23:51:32.506 [main] INFO  JobContainer - Set jobId = 0
2019-06-13 23:51:32.811 [job-0] INFO  OriginalConfPretreatmentUtil - Available jdbcUrl:jdbc:mysql://127.0.0.1:3306/test?characterEncoding=utf8&yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true.
2019-06-13 23:51:32.825 [job-0] INFO  OriginalConfPretreatmentUtil - table:[dashboard_graph] has columns:[id,title,hosts,counters,screen_id,timespan,graph_type,method,position,falcon_tags].
2019-06-13 23:51:32.906 [job-0] INFO  OriginalConfPretreatmentUtil - table:[t1] all columns:[
id,title,hosts
].
2019-06-13 23:51:32.915 [job-0] INFO  OriginalConfPretreatmentUtil - Write data [
INSERT INTO %s (id,title,hosts) VALUES(?,?,?)
], which jdbcUrl like:[jdbc:postgresql://127.0.0.1:5432/pgone]
2019-06-13 23:51:32.915 [job-0] INFO  JobContainer - jobContainer starts to do prepare ...
2019-06-13 23:51:32.915 [job-0] INFO  JobContainer - DataX Reader.Job [mysqlreader] do prepare work .
2019-06-13 23:51:32.916 [job-0] INFO  JobContainer - DataX Writer.Job [postgresqlwriter] do prepare work .
2019-06-13 23:51:32.916 [job-0] INFO  JobContainer - jobContainer starts to do split ...
2019-06-13 23:51:32.917 [job-0] INFO  JobContainer - Job set Channel-Number to 3 channels.
2019-06-13 23:51:32.920 [job-0] INFO  JobContainer - DataX Reader.Job [mysqlreader] splits to [1] tasks.
2019-06-13 23:51:32.921 [job-0] INFO  JobContainer - DataX Writer.Job [postgresqlwriter] splits to [1] tasks.
2019-06-13 23:51:32.938 [job-0] INFO  JobContainer - jobContainer starts to do schedule ...
2019-06-13 23:51:32.941 [job-0] INFO  JobContainer - Scheduler starts [1] taskGroups.
2019-06-13 23:51:32.943 [job-0] INFO  JobContainer - Running by standalone Mode.
2019-06-13 23:51:32.949 [taskGroup-0] INFO  TaskGroupContainer - taskGroupId=[0] start [1] channels for [1] tasks.
2019-06-13 23:51:32.953 [taskGroup-0] INFO  Channel - Channel set byte_speed_limit to -1, No bps activated.
2019-06-13 23:51:32.953 [taskGroup-0] INFO  Channel - Channel set record_speed_limit to -1, No tps activated.
2019-06-13 23:51:32.962 [taskGroup-0] INFO  TaskGroupContainer - taskGroup[0] taskId[0] attemptCount[1] is started
2019-06-13 23:51:32.964 [0-0-0-reader] INFO  CommonRdbmsReader$Task - Begin to read record by Sql: [select id,title,hosts from dashboard_graph 
] jdbcUrl:[jdbc:mysql://127.0.0.1:3306/test?characterEncoding=utf8&yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true].
2019-06-13 23:51:32.976 [0-0-0-reader] INFO  CommonRdbmsReader$Task - Finished read record by Sql: [select id,title,hosts from dashboard_graph 
] jdbcUrl:[jdbc:mysql://127.0.0.1:3306/test?characterEncoding=utf8&yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true].
2019-06-13 23:51:33.262 [taskGroup-0] INFO  TaskGroupContainer - taskGroup[0] taskId[0] is successed, used[302]ms
2019-06-13 23:51:33.263 [taskGroup-0] INFO  TaskGroupContainer - taskGroup[0] completed it's tasks.
2019-06-13 23:51:42.960 [job-0] INFO  StandAloneJobContainerCommunicator - Total 1 records, 209 bytes | Speed 20B/s, 0 records/s | Error 0 records, 0 bytes |  All Task WaitWriterTime 0.000s |  All Task WaitReaderTime 0.000s | Percentage 100.00%
2019-06-13 23:51:42.960 [job-0] INFO  AbstractScheduler - Scheduler accomplished all tasks.
2019-06-13 23:51:42.961 [job-0] INFO  JobContainer - DataX Writer.Job [postgresqlwriter] do post work.
2019-06-13 23:51:42.961 [job-0] INFO  JobContainer - DataX Reader.Job [mysqlreader] do post work.
2019-06-13 23:51:42.961 [job-0] INFO  JobContainer - DataX jobId [0] completed successfully.
2019-06-13 23:51:42.962 [job-0] INFO  HookInvoker - No hook invoked, because base dir not exists or is a file: /opt/datax/hook
2019-06-13 23:51:42.963 [job-0] INFO  JobContainer - 
	 [total cpu info] => 
		averageCpu                     | maxDeltaCpu                    | minDeltaCpu                    
		-1.00%                         | -1.00%                         | -1.00%
                        

	 [total gc info] => 
		 NAME                 | totalGCCount       | maxDeltaGCCount    | minDeltaGCCount    | totalGCTime        | maxDeltaGCTime     | minDeltaGCTime     
		 PS MarkSweep         | 0                  | 0                  | 0                  | 0.000s             | 0.000s             | 0.000s             
		 PS Scavenge          | 0                  | 0                  | 0                  | 0.000s             | 0.000s             | 0.000s             

2019-06-13 23:51:42.963 [job-0] INFO  JobContainer - PerfTrace not enable!
2019-06-13 23:51:42.963 [job-0] INFO  StandAloneJobContainerCommunicator - Total 1 records, 209 bytes | Speed 20B/s, 0 records/s | Error 0 records, 0 bytes |  All Task WaitWriterTime 0.000s |  All Task WaitReaderTime 0.000s | Percentage 100.00%
2019-06-13 23:51:42.964 [job-0] INFO  JobContainer - 
任务启动时刻                    : 2019-06-13 23:51:32
任务结束时刻                    : 2019-06-13 23:51:42
任务总计耗时                    :                 10s
任务平均流量                    :               20B/s
记录写入速度                    :              0rec/s
读出记录总数                    :                   1
读写失败总数                    :                   0