版权声明：原创转载请注明出处，谢谢 https://blog.csdn.net/qq_21108311/article/details/85682037
之前已经构建好了datax镜像，只差最后一步，datax运行
datax的使用很简单：
python datax.py 配置文件.json以上命令就可以直接使用datax了，本次就来分解以上命令
首先python打头执行命令，datax.py是datax自带的，该可执行文件再datax的bin目录下，最后加上执行的配置文件
配置文件大体结构是：
读数据库+各种读取信息和条件
|
|
|
写数据库+各种写的信息和条件
|
|
|
加上通用设定，如一次的数据量大小等等配置文件是要用json来写的，官方有自带模板，进入到bin目录后可以通过命令查看：
python datax.py -r oraclereader -w oraclewriter2019.1.9更新
今早开始测试datax同步，经过几天的学习，对datax的使用又加深了不少理解。
datax官方自带模板，可以通过命令获得所支持的json模板
python datax.py -r mysqlreader -w mysqlwriter > mysql2mysql1.json
-r ：读的数据库模板，可以是oracle、mysql等等，但是要加上reader
-w ：写的数据库模板，同上
> 把模板格式写到一个文件上，后面是自己取的文件名本次我测试MySQL-MySQL
#在datax脚本路径查看有哪些json
[root@8ec3fabb3594 bin]# ls
datax.py dxprof.py perftrace.py
#获取模板，写入json文件
[root@8ec3fabb3594 bin]# python datax.py -r mysqlreader -w mysqlwriter > mysql2mysql1.json
#查看文件是否出现和文件模板内容
[root@8ec3fabb3594 bin]# ls
datax.py dxprof.py mysql2mysql1.json perftrace.py
[root@8ec3fabb3594 bin]# cat mysql2mysql1.json
DataX (DATAX-OPENSOURCE-3.0), From Alibaba !
Copyright (C) 2010-2017, Alibaba Group. All Rights Reserved.
Please refer to the mysqlreader document:
https://github.com/alibaba/DataX/blob/master/mysqlreader/doc/mysqlreader.md
Please refer to the mysqlwriter document:
https://github.com/alibaba/DataX/blob/master/mysqlwriter/doc/mysqlwriter.md
Please save the following configuration as a json file and use
python {DATAX_HOME}/bin/datax.py {JSON_FILE_NAME}.json
to run the job.
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"column": [],
"connection": [
{
"jdbcUrl": [],
"table": []
}
],
"password": "",
"username": "",
"where": ""
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"column": [],
"connection": [
{
"jdbcUrl": "",
"table": []
}
],
"password": "",
"preSql": [],
"session": [],
"username": "",
"writeMode": ""
}
}
}
],
"setting": {
"speed": {
"channel": ""
}
}
}
}
[root@8ec3fabb3594 bin]# ls
datax.py dxprof.py mysql2mysql1.json perftrace.py
[root@8ec3fabb3594 bin]# vi mysql2mysql1.json
之后按照模板填信息，列：
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
#最好指定同步的字段，否则会出警告，且耦合度较高，我这里测试就偷个懒
"column": ["*"],
"connection": [
{
#jdb格式就是jdbc标准格式+ip+要同步的数据库
"jdbcUrl": ["jdbc:mysql://45.59.13.2:3306/datax"],
"table": ["test"]
}
],
"password": "My@test",
"username": "root",
"where": ""
#不是所有参数必须给值，必填参数可在git上参考官方文档
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"column": ["*"],
"connection": [
{
"jdbcUrl": "jdbc:mysql://45.59.13.2:3307/datax",
"table": ["test"]
}
],
"password": "My@test",
"preSql": [],
"session": [],
"username": "root",
#模式最好指定
"writeMode": "insert"
}
}
}
],
"setting": {
"speed": {
"channel": "1"
}
}
}
}
之后直解运行datax即可：
#同步命令
[root@8ec3fabb3594 bin]# python datax.py mysql2mysql1.json
#运行日志
DataX (DATAX-OPENSOURCE-3.0), From Alibaba !
Copyright (C) 2010-2017, Alibaba Group. All Rights Reserved.
2019-01-09 02:06:26.025 [main] INFO VMInfo - VMInfo# operatingSystem class => sun.management.OperatingSystemImpl
2019-01-09 02:06:26.035 [main] INFO Engine - the machine info =>
osInfo: Oracle Corporation 1.8 25.191-b12
jvmInfo: Linux amd64 3.10.0-862.2.3.el7.x86_64
cpu num: 4
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
2019-01-09 02:06:26.061 [main] INFO Engine -
{
"content":[
{
"reader":{
"name":"mysqlreader",
"parameter":{
"column":[
"*"
],
"connection":[
{
"jdbcUrl":[
"jdbc:mysql://45.59.13.1:3306/datax"
],
"table":[
"test"
]
}
],
"password":"*******",
"username":"root",
"where":""
}
},
"writer":{
"name":"mysqlwriter",
"parameter":{
"column":[
"*"
],
"connection":[
{
"jdbcUrl":"jdbc:mysql://45.59.13.1:3307/datax",
"table":[
"test"
]
}
],
"password":"*******",
"preSql":[],
"session":[],
"username":"root",
"writeMode":"insert"
}
}
}
],
"setting":{
"speed":{
"channel":"1"
}
}
}
2019-01-09 02:06:26.085 [main] WARN Engine - prioriy set to 0, because NumberFormatException, the value is: null
2019-01-09 02:06:26.087 [main] INFO PerfTrace - PerfTrace traceId=job_-1, isEnable=false, priority=0
2019-01-09 02:06:26.088 [main] INFO JobContainer - DataX jobContainer starts job.
2019-01-09 02:06:26.090 [main] INFO JobContainer - Set jobId = 0
2019-01-09 02:06:26.595 [job-0] INFO OriginalConfPretreatmentUtil - Available jdbcUrl:jdbc:mysql://45.59.113.211:3306/datax?yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true.
2019-01-09 02:06:26.597 [job-0] WARN OriginalConfPretreatmentUtil - 您的配置文件中的列配置存在一定的风险. 因为您未配置读取数据库表的列，当您的表字段个数、类型有变动时，可能影响任务正确性甚至会运行出错。请检查您的配置并作出修改.
2019-01-09 02:06:26.911 [job-0] INFO OriginalConfPretreatmentUtil - table:[test] all columns:[
id,test
].
2019-01-09 02:06:26.911 [job-0] WARN OriginalConfPretreatmentUtil - 您的配置文件中的列配置信息存在风险. 因为您配置的写入数据库表的列为*，当您的表字段个数、类型有变动时，可能影响任务正确性甚至会运行出错。请检查您的配置并作出修改.
2019-01-09 02:06:26.913 [job-0] INFO OriginalConfPretreatmentUtil - Write data [
insert INTO %s (id,test) VALUES(?,?)
], which jdbcUrl like:[jdbc:mysql://45.59.113.211:3307/datax?yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true]
2019-01-09 02:06:26.914 [job-0] INFO JobContainer - jobContainer starts to do prepare ...
2019-01-09 02:06:26.914 [job-0] INFO JobContainer - DataX Reader.Job [mysqlreader] do prepare work .
2019-01-09 02:06:26.915 [job-0] INFO JobContainer - DataX Writer.Job [mysqlwriter] do prepare work .
2019-01-09 02:06:26.915 [job-0] INFO JobContainer - jobContainer starts to do split ...
2019-01-09 02:06:26.916 [job-0] INFO JobContainer - Job set Channel-Number to 1 channels.
2019-01-09 02:06:26.922 [job-0] INFO JobContainer - DataX Reader.Job [mysqlreader] splits to [1] tasks.
2019-01-09 02:06:26.923 [job-0] INFO JobContainer - DataX Writer.Job [mysqlwriter] splits to [1] tasks.
2019-01-09 02:06:26.945 [job-0] INFO JobContainer - jobContainer starts to do schedule ...
2019-01-09 02:06:26.950 [job-0] INFO JobContainer - Scheduler starts [1] taskGroups.
2019-01-09 02:06:26.955 [job-0] INFO JobContainer - Running by standalone Mode.
2019-01-09 02:06:26.965 [taskGroup-0] INFO TaskGroupContainer - taskGroupId=[0] start [1] channels for [1] tasks.
2019-01-09 02:06:26.973 [taskGroup-0] INFO Channel - Channel set byte_speed_limit to -1, No bps activated.
2019-01-09 02:06:26.974 [taskGroup-0] INFO Channel - Channel set record_speed_limit to -1, No tps activated.
2019-01-09 02:06:26.992 [taskGroup-0] INFO TaskGroupContainer - taskGroup[0] taskId[0] attemptCount[1] is started
2019-01-09 02:06:26.997 [0-0-0-reader] INFO CommonRdbmsReader$Task - Begin to read record by Sql: [select * from test
] jdbcUrl:[jdbc:mysql://45.59.113.211:3306/datax?yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true].
2019-01-09 02:06:27.034 [0-0-0-reader] INFO CommonRdbmsReader$Task - Finished read record by Sql: [select * from test
] jdbcUrl:[jdbc:mysql://45.59.113.211:3306/datax?yearIsDateType=false&zeroDateTimeBehavior=convertToNull&tinyInt1isBit=false&rewriteBatchedStatements=true].
2019-01-09 02:06:27.294 [taskGroup-0] INFO TaskGroupContainer - taskGroup[0] taskId[0] is successed, used[308]ms
2019-01-09 02:06:27.296 [taskGroup-0] INFO TaskGroupContainer - taskGroup[0] completed it's tasks.
2019-01-09 02:06:36.983 [job-0] INFO StandAloneJobContainerCommunicator - Total 2 records, 6 bytes | Speed 0B/s, 0 records/s | Error 0 records, 0 bytes | All Task WaitWriterTime 0.000s | All Task WaitReaderTime 0.000s | Percentage 100.00%
2019-01-09 02:06:36.983 [job-0] INFO AbstractScheduler - Scheduler accomplished all tasks.
2019-01-09 02:06:36.985 [job-0] INFO JobContainer - DataX Writer.Job [mysqlwriter] do post work.
2019-01-09 02:06:36.985 [job-0] INFO JobContainer - DataX Reader.Job [mysqlreader] do post work.
2019-01-09 02:06:36.986 [job-0] INFO JobContainer - DataX jobId [0] completed successfully.
2019-01-09 02:06:36.987 [job-0] INFO HookInvoker - No hook invoked, because base dir not exists or is a file: /data/datax/hook
2019-01-09 02:06:36.989 [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
2019-01-09 02:06:36.990 [job-0] INFO JobContainer - PerfTrace not enable!
2019-01-09 02:06:36.991 [job-0] INFO StandAloneJobContainerCommunicator - Total 2 records, 6 bytes | Speed 0B/s, 0 records/s | Error 0 records, 0 bytes | All Task WaitWriterTime 0.000s | All Task WaitReaderTime 0.000s | Percentage 100.00%
2019-01-09 02:06:36.992 [job-0] INFO JobContainer -
任务启动时刻 : 2019-01-09 02:06:26
任务结束时刻 : 2019-01-09 02:06:36
任务总计耗时 : 10s
任务平均流量 : 0B/s
记录写入速度 : 0rec/s
读出记录总数 : 2
读写失败总数 : 0
#由上可以看出，有些不严谨的会有警告弹出同理，我们可以获取Oracle-Oracle模板或者Oracle-MySQL模板等等，配置json后运行即可。