一、目标：异库单表实时表同步

canal实验版本：v1.1.4

1.1 canal组件资源分配

1.2 canal.adaptor中源、目标配置说明

二、canal server端

2.1 主配置文件

cd /data/canal.deployer-for-rdb-1.1.4/conf

canal.properties

#################################################
#########               common argument         #############
#################################################
# tcp bind ip
canal.ip = cdh03_ip
# register ip to zookeeper
canal.register.ip =
canal.port = 11111
canal.metrics.pull.port = 11112
# canal instance user/passwd
# canal.user = canal
# canal.passwd = E3619321C1A937C46A0D8BD1DAC39F93B27D4458

# canal admin config
#canal.admin.manager = 127.0.0.1:8089
canal.admin.port = 11110
canal.admin.user = admin
canal.admin.passwd = 4ACFE3202A5FF5CF467898FC58AAB1D615029441

canal.zkServers = cdh03:2181,cdh04:2181,cdh05:2181
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = tcp
# flush meta cursor/parse position to file
canal.file.data.dir = ${canal.conf.dir}
canal.file.flush.period = 1000
## memory store RingBuffer size, should be Math.pow(2,n)
canal.instance.memory.buffer.size = 16384
## memory store RingBuffer used memory unit size , default 1kb
canal.instance.memory.buffer.memunit = 1024 
## meory store gets mode used MEMSIZE or ITEMSIZE
canal.instance.memory.batch.mode = MEMSIZE
canal.instance.memory.rawEntry = true

## detecing config
canal.instance.detecting.enable = false
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
canal.instance.detecting.sql = select 1
canal.instance.detecting.interval.time = 3
canal.instance.detecting.retry.threshold = 3
canal.instance.detecting.heartbeatHaEnable = false

# support maximum transaction size, more than the size of the transaction will be cut into multiple transactions delivery
canal.instance.transaction.size =  1024
# mysql fallback connected to new master should fallback times
canal.instance.fallbackIntervalInSeconds = 60

# network config
canal.instance.network.receiveBufferSize = 16384
canal.instance.network.sendBufferSize = 16384
canal.instance.network.soTimeout = 30

# binlog filter config
canal.instance.filter.druid.ddl = true
canal.instance.filter.query.dcl = false
canal.instance.filter.query.dml = false
canal.instance.filter.query.ddl = false
canal.instance.filter.table.error = false
canal.instance.filter.rows = false
canal.instance.filter.transaction.entry = false

# binlog format/image check
canal.instance.binlog.format = ROW,STATEMENT,MIXED 
canal.instance.binlog.image = FULL,MINIMAL,NOBLOB

# binlog ddl isolation
canal.instance.get.ddl.isolation = false

# parallel parser config
canal.instance.parser.parallel = true
## concurrent thread number, default 60% available processors, suggest not to exceed Runtime.getRuntime().availableProcessors()
#canal.instance.parser.parallelThreadSize = 16
## disruptor ringbuffer size, must be power of 2
canal.instance.parser.parallelBufferSize = 256

# table meta tsdb info
canal.instance.tsdb.enable = true
canal.instance.tsdb.dir = ${canal.file.data.dir:../conf}/${canal.instance.destination:}
canal.instance.tsdb.url = jdbc:h2:${canal.instance.tsdb.dir}/h2;CACHE_SIZE=1000;MODE=MYSQL;
canal.instance.tsdb.dbUsername = canal
canal.instance.tsdb.dbPassword = canal
# dump snapshot interval, default 24 hour
canal.instance.tsdb.snapshot.interval = 24
# purge snapshot expire , default 360 hour(15 days)
canal.instance.tsdb.snapshot.expire = 360

# aliyun ak/sk , support rds/mq
canal.aliyun.accessKey =
canal.aliyun.secretKey =

#################################################
#########               destinations            #############
#################################################
#canal.destinations = example,db_hk_apollo,db_hk_katrina,db_hk_saasv1
canal.destinations = example
# conf root dir
canal.conf.dir = ../conf
# auto scan instance dir add/remove and start/stop instance
canal.auto.scan = true
canal.auto.scan.interval = 5

canal.instance.tsdb.spring.xml = classpath:spring/tsdb/h2-tsdb.xml
#canal.instance.tsdb.spring.xml = classpath:spring/tsdb/mysql-tsdb.xml

canal.instance.global.mode = spring
canal.instance.global.lazy = false
canal.instance.global.manager.address = ${canal.admin.manager}
#canal.instance.global.spring.xml = classpath:spring/memory-instance.xml
canal.instance.global.spring.xml = classpath:spring/file-instance.xml
#canal.instance.global.spring.xml = classpath:spring/default-instance.xml

##################################################
#########                    MQ                      #############
##################################################
canal.mq.servers = cdh03:9092,cdh04:9092,cdh05:9092 
canal.mq.retries = 0
canal.mq.batchSize = 16384
canal.mq.maxRequestSize = 1048576
canal.mq.lingerMs = 100
canal.mq.bufferMemory = 33554432
canal.mq.canalBatchSize = 50
canal.mq.canalGetTimeout = 100
canal.mq.flatMessage = true
canal.mq.compressionType = none
canal.mq.acks = all
#canal.mq.properties. =
canal.mq.producerGroup = test
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.accessChannel = local
# aliyun mq namespace
#canal.mq.namespace =

##################################################
#########     Kafka Kerberos Info    #############
##################################################
canal.mq.kafka.kerberos.enable = false
canal.mq.kafka.kerberos.krb5FilePath = "../conf/kerberos/krb5.conf"
canal.mq.kafka.kerberos.jaasFilePath = "../conf/kerberos/jaas.conf"

2.1 子配置文件

cd /data/canal.deployer-for-rdb-1.1.4/conf/example

instance.properties

  1 #################################################
  2 ## mysql serverId , v1.0.26+ will autoGen
  3 canal.instance.mysql.slaveId=1234
  4 
  5 # enable gtid use true/false
  6 canal.instance.gtidon=false
  7 
  8 # position info
  9 canal.instance.master.address=111.111.111.111:3306 #待监听的源数据库ip+port
 10 canal.instance.master.journal.name=
 11 canal.instance.master.position=
 12 canal.instance.master.timestamp=
 13 canal.instance.master.gtid=
 14 
 15 # rds oss binlog
 16 canal.instance.rds.accesskey=
 17 canal.instance.rds.secretkey=
 18 canal.instance.rds.instanceId=
 19 
 20 # table meta tsdb info
 21 canal.instance.tsdb.enable=true
 22 #canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
 23 #canal.instance.tsdb.dbUsername=canal
 24 #canal.instance.tsdb.dbPassword=canal
 25 
 26 #canal.instance.standby.address =
 27 #canal.instance.standby.journal.name =
 28 #canal.instance.standby.position =
 29 #canal.instance.standby.timestamp =
 30 #canal.instance.standby.gtid=
 31 
 32 # username/password
 33 canal.instance.dbUsername=canal
 34 canal.instance.dbPassword=canal
 35 canal.instance.connectionCharset = UTF-8
 36 # enable druid Decrypt database password
 37 canal.instance.enableDruid=false
 38 #canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==
 39 
 40 # table regex
 41 #canal.instance.filter.regex=.*\\..*
 42 canal.instance.filter.regex=rtdw_test_gmall\\..*
 43 # table black regex
 44 canal.instance.filter.black.regex=
 45 # table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
 46 #canal.instance.filter.field=test1.t_product:id/subject/keywords,test2.t_company:id/name/contact/ch
 47 # table field black filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
 48 #canal.instance.filter.black.field=test1.t_product:subject/product_image,test2.t_company:id/name/contact/ch
 49 
 50 # mq config
 51 canal.mq.topic=binlog_rtdw_test_gmall
 52 # dynamic topic route by schema or table regex
 53 #canal.mq.dynamicTopic=mytest1.user,mytest2\\..*,.*\\..*
 54 canal.mq.partition=0
 55 # hash partition config
 56 #canal.mq.partitionsNum=3
 57 #canal.mq.partitionHash=test.table:id^name,.*\\..*
 58 #################################################

三、canal adaptor端

3.1 主配置文件

cd /data/canal.adapter-1.1.4/conf

application.yml

  1 server:
  2   port: 8091
  3 spring:
  4   jackson:
  5     date-format: yyyy-MM-dd HH:mm:ss
  6     time-zone: GMT+8
  7     default-property-inclusion: non_null
  8 
  9 canal.conf:
 10   mode: tcp # tcp方式监听DBMS binlog变化，其他可选项：kafka rocketMQ 
 11   canalServerHost: cdh03_ip:11111
 12 #  zookeeperHosts: slave1:2181
 13 #  mqServers: 127.0.0.1:9092 #or rocketmq
 14 #  flatMessage: true
 15   batchSize: 500
 16   syncBatchSize: 1000
 17   retries: 0
 18   timeout:
 19   accessKey:
 20   secretKey:
 21   srcDataSources: # Mysql source address
 22     defaultDS:
 23       url: jdbc:mysql://111.111.111.111:3306/rtdw_test_gmall?useUnicode=true # 源库
 24       username: root
 25       password: password
 26   canalAdapters: # 列表格式
 27   - instance: example # canal instance Name or mq topic name:【实例名，需与canal.deployer中配置项“canal.destinations”的value保持严格一致】
 28     groups:
 29     - groupId: g1 #组ID
 30       outerAdapters:
 31       - name: logger
 32       - name: rdb
 33         key: mysql1 #后续根据此key进行溯源
 34         properties:
 35           jdbc.driverClassName: com.mysql.jdbc.Driver
 36           jdbc.url: jdbc:mysql://222.222.222.222:3306/rtdw_test_gmall2?useUnicode=true
 37           jdbc.username: root
 38           jdbc.password: password
 39 #      - name: rdb
 40 #        key: oracle1
 41 #        properties:
 42 #          jdbc.driverClassName: oracle.jdbc.OracleDriver
 43 #          jdbc.url: jdbc:oracle:thin:@localhost:49161:XE
 44 #          jdbc.username: mytest
 45 #          jdbc.password: m121212
 46 #      - name: rdb
 47 #        key: postgres1
 48 #        properties:
 49 #          jdbc.driverClassName: org.postgresql.Driver
 50 #          jdbc.url: jdbc:postgresql://localhost:5432/postgres
 51 #          jdbc.username: postgres
 52 #          jdbc.password: 121212
 53 #          threads: 1
 54 #          commitSize: 3000
 55 #      - name: hbase
 56 #        properties:
 57 #          hbase.zookeeper.quorum: 127.0.0.1
 58 #          hbase.zookeeper.property.clientPort: 2181
 59 #          zookeeper.znode.parent: /hbase
 60 #      - name: es
 61 #        hosts: 127.0.0.1:9300 # 127.0.0.1:9200 for rest mode
 62 #        properties:
 63 #          mode: transport # or rest
 64 #          # security.auth: test:123456 #  only used for rest mode
 65 #          cluster.name: elasticsearch

3.2 子配置文件

adapter模块是通过热加载rdb⽬录下的yml配置⽂件来做到同步数据到指定数据库的目的，所以这块需要引用此前主配置文件中定义的canal服务端信息 和 数据源信息。

cd /data/canal.adapter-1.1.4/conf/rdb/

mytest_user.yml

  1 dataSourceKey: defaultDS	# 源数据源的key, 对应上面配置的srcDataSources中的值
  2 destination: example		# cannal的instance或者MQ的topic
  3 groupId: g1					# 对应MQ模式下的groupId, 只会同步对应groupId的数据
  4 outerAdapterKey: mysql1		# adapter key, 对应上面主配置文件中canalAdapters的key
  5 concurrent: true			# 是否按主键hash并行同步, 并行同步的表必须保证主键不会更改及主键不能为其他同步表的外键!!
  6 dbMapping:					# 源库表 与 目标库表 的mapping关系
  7   database: rtdw_test_gmall	# 源数据源的database/shcema
  8   table: holiday_info							# 源数据源表名
  9   targetTable: rtdw_test_gmall2.holiday_info	# 目标数据源的库名.表名
 10   targetPk:										# 主键映射
 11     holiday_id: holiday_id						# 如果是复合主键可以换行映射多个
 12   mapAll: true									# 是否整表映射, 要求源表和目标表字段名一模一样 (如果targetColumns也配置了映射,则以targetColumns配置为准)
 13 #  targetColumns:	# 字段映射, 格式: 目标表字段: 源表字段, 如果字段名一样源表字段名可不填
 14 #    id:
 15 #    name:
 16 #    role_id:
 17 #    c_time:
 18 #    test1:
 19 #  etlCondition: "where c_time>={}"
 20 #  commitBatch: 3000 # 批量提交的大小
 21 
 22 
 23 ## Mirror schema synchronize config
 24 #dataSourceKey: defaultDS
 25 #destination: example
 26 #groupId: g1
 27 #outerAdapterKey: mysql1
 28 #concurrent: true
 29 #dbMapping:
 30 #  mirrorDb: true
 31 #  database: mytest

四、注意事项

1、源库中的DDL，如 CREATE / DROP / ALTER 等操作，均支持实时同步至目标库。
2、对于源、目标库中的同一张表，默认源端的insert操作可以在目标端replay成功，而目标表中如果没有对应的记录，那么在源表端进行update、delete操作时，不会在目标端生成对应的数据条目。
3、源端数据库的CURD操作均可以抓取到，但为了保持数据同步操作， 需要进行目标端的数据库进行初始化操作，即将源库表dump出来一份schema和数据，然后再目标端replay。之后源端的update、delete操作可以实时同步到目标库。