Canal 实现 同步 到 MySQL 从库 单表仅数据

原文：canal 实现 mysql 数据同步

admin 配置

mysql -uroot -p < /opt/module/canal/admin/conf/canal_manager.sql >> ~/execsql.log

deployer 配置

vim /opt/module/canal/deployer/conf/canal.properties

canal.serverMode = tcp

vim /opt/module/canal/deployer/conf/example/instance.properties

canal.instance.master.address=hadoop106:3306    #mysql源地址
canal.instance.dbUsername=root
canal.instance.dbPassword=root

adapter 配置

vim /opt/module/canal/adapter/conf/application.yml

①
canal.conf:
  mode: tcp #tcp kafka rocketMQ rabbitMQ
# Canal 的 deployer 服务所在的 IP 地址:11111
  canalServerHost: hadoop108:11111
#  flatMessage: true
#  mqServers 127.0.0.1:9092  #or rocketmq
#  zookeeperHosts:
  batchSize: 500
  syncBatchSize: 1000
  retries: 0

 

②
secretKey:
    srcDataSources:
      # url: jdbc:mysql://mysql源数据库IP1:3306/数据库名?useUnicode=true&characterEncoding=UTF-8&serverTimezone=GMT&useSSL=false
      url: jdbc:mysql://hadoop106:3306/FlinkEtl?useUnicode=true
      username: root
      password: root

 

③
canalAdapters:
  - instance: example # canal instance Name or mq topic name
    groups:
    - groupId: g1
      outerAdapters:
      - name: logger
      - name: rdb
        key: mysql1
        properties:
          jdbc.driverClassName: com.mysql.jdbc.Driver
　　　　　　# jdbc.url: jdbc:mysql://mysql目标地址IP2:3306/数据库名?useUnicode=true&characterEncoding=UTF-8&serverTimezone=GMT&useSSL=false
          jdbc.url: jdbc:mysql://hadoop108:3306/FlinkEtl?useUnicode=true
          jdbc.username: root
          jdbc.password: root

vim /opt/module/canal/adapter/conf/rdb/mytest_user.yml

dataSourceKey: defaultDS
destination: example
#和上面③中的该配置保持一致
groupId: g1
#和③中的该配置保持一致
outerAdapterKey: mysql1
concurrent: true
dbMapping:
  # mysql源数据库名称
  database: FlinkEtl
  # mysql源数据库下的表名称
  table: employee
  # 同步到目标数据库-数据表名称
  targetTable: employee
  targetPk:
    id: id
# 如果源表和目标表的字段结构等完全一致，直接开启此配置即可，下面的 targetColumns 注释掉，不注释以 targetColumns 为准
  mapAll: true
  # targetColumns:
  #  id:
  #  name:
  #  role_id:
  #  c_time:
  #  test1:
# 也注掉
  # etlCondition: "where c_time>={}"
  # 批量提交的大小
  # commitBatch: 3000 


## Mirror schema synchronize config
#dataSourceKey: defaultDS
#destination: example
#groupId: g1
#outerAdapterKey: mysql1
#concurrent: true
#dbMapping:
#  mirrorDb: true
#  database: mytest

 

IP1 和 IP2 上面安装的 mysql 数据库下 创建了 FlintEtl.employee 表和 FlintEtl.employee 表，

现在的需求是，数据要从  hadoop106 IP1:  FlintEtl.employee  =>  hadoop108  IP2:  FlintEtl.employee 表同步，

 SQL:

show variables like'%validate_password%';
set global validate_password_length= 4;
set global validate_password_mixed_case_count= 0;
set global validate_password_number_count= 0;
set global validate_password_special_char_count= 0;
set global validate_password_policy= 0;

create user 'canal'@'%' identified by 'canal';
grant select,replication slave, replication client on *.* to 'canal'@'%';
select * from mysql.user where user = 'canal' \G;

set global validate_password_length= 8;
set global validate_password_mixed_case_count= 1;
set global validate_password_number_count= 1;
set global validate_password_special_char_count= 1;
set global validate_password_policy= 1;


show variables like 'log_bin%';
show variables like '%binlog_format%';

drop table if exists `employee`;
create table `employee` (
`id` int(11) not null ,
`name` varchar(255) character set utf8mb4 collate utf8mb4_unicode_ci null default null,
`age` int(11) null default null,
`gender` varchar(25) character set utf8mb4 collate utf8mb4_unicode_ci null default null,
PRIMARY KEY (`id`) using btree
) engine = InnoDB character set = utf8mb4 collate = utf8mb4_unicode_ci row_format = Dynamic;

-- ----------------------------
-- Records of employee
-- ----------------------------
insert into `employee` values (1, 'lisi', 15, '男');
insert into `employee` values (2, 'zhangsan', 22, '男');
insert into `employee` values (3, 'wangwu', 35, '男');
insert into `employee` values (4, 'zhaoliu', 25, '男');
insert into `employee` values (5, 'tianqi', 32, '男');
insert into `employee` values (6, 'xiaohong', 25, '女');
insert into `employee` values (7, 'xiaohang', 15, '女');

canal 启动

sh /opt/module/canal/deployer/bin/startup.sh
vim /opt/module/canal/deployer/logs/canal/canal.log
G
sh /opt/module/canal/adaper/bin/startup.sh
vim /opt/module/canal/adaper/logs/adapter/adapter.log
G

END

 

 

===================  只单表同步数据时，配置备份   ==========================

canal.properties

#################################################
#########               common argument         #############
#################################################
# tcp bind ip
canal.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
# admin auto register
#canal.admin.register.auto = true
#canal.admin.register.cluster =
#canal.admin.register.name =

canal.zkServers =
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ, pulsarMQ
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
canal.instance.filter.dml.insert = false
canal.instance.filter.dml.update = false
canal.instance.filter.dml.delete = 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.url = jdbc:mysql://hadoop106:3306/canal_tsdb?useUnicode=true&characterEncoding=UTF-8&useSSL=false
canal.instance.tsdb.dbUsername = root
canal.instance.tsdb.dbPassword = root
# 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

#################################################
#########               destinations            #############
#################################################
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
# set this value to 'true' means that when binlog pos not found, skip to latest.
# WARN: pls keep 'false' in production env, or if you know what you want.
canal.auto.reset.latest.pos.mode = false

# 报错 com.alibaba.druid.pool.DruidDataSource
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 Properties      #############
##################################################
# aliyun ak/sk , support rds/mq
canal.aliyun.accessKey =
canal.aliyun.secretKey =
canal.aliyun.uid=

canal.mq.flatMessage = true
canal.mq.canalBatchSize = 50
canal.mq.canalGetTimeout = 100
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.accessChannel = local

canal.mq.database.hash = true
canal.mq.send.thread.size = 30
canal.mq.build.thread.size = 8

##################################################
#########                    Kafka                   #############
##################################################
kafka.bootstrap.servers = 127.0.0.1:9092
kafka.acks = all
kafka.compression.type = none
kafka.batch.size = 16384
kafka.linger.ms = 1
kafka.max.request.size = 1048576
kafka.buffer.memory = 33554432
kafka.max.in.flight.requests.per.connection = 1
kafka.retries = 0

kafka.kerberos.enable = false
kafka.kerberos.krb5.file = "../conf/kerberos/krb5.conf"
kafka.kerberos.jaas.file = "../conf/kerberos/jaas.conf"

##################################################
#########                   RocketMQ         #############
##################################################
rocketmq.producer.group = test
rocketmq.enable.message.trace = false
rocketmq.customized.trace.topic =
rocketmq.namespace =
rocketmq.namesrv.addr = 127.0.0.1:9876
rocketmq.retry.times.when.send.failed = 0
rocketmq.vip.channel.enabled = false
rocketmq.tag =

##################################################
#########                   RabbitMQ         #############
##################################################
rabbitmq.host =
rabbitmq.virtual.host =
rabbitmq.exchange =
rabbitmq.username =
rabbitmq.password =
rabbitmq.deliveryMode =


##################################################
#########                     Pulsar         #############
##################################################
pulsarmq.serverUrl =
pulsarmq.roleToken =
pulsarmq.topicTenantPrefix =

instance.properties

#################################################
## mysql serverId , v1.0.26+ will autoGen
# canal.instance.mysql.slaveId=0

# enable gtid use true/false
canal.instance.gtidon=false

# position info
canal.instance.master.address=hadoop106:3306
canal.instance.master.journal.name=
canal.instance.master.position=
canal.instance.master.timestamp=
canal.instance.master.gtid=

# rds oss binlog
canal.instance.rds.accesskey=
canal.instance.rds.secretkey=
canal.instance.rds.instanceId=

# tsdb 是为预防表结构发生变化,而在 canal 订阅 binlog 时产生问题
# canal使用数据库存储上一次的表结构信息，然后对比两次的表结构，可解决此错误。
# table meta tsdb info
canal.instance.tsdb.enable=true
#canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb?useUnicode=true&characterEncoding=UTF-8&useSSL=false
#canal.instance.tsdb.dbUsername=root
#canal.instance.tsdb.dbPassword=root
# 新增 配置文件
# 因为tsdb默认使用的是h2数据库（java内置数据库）。不增加此配置默认还是使用内置数据库，
#canal.instance.tsdb.spring.xml = classpath:spring/tsdb/mysql-tsdb.xml
#canal.instance.standby.address =
#canal.instance.standby.journal.name =
#canal.instance.standby.position =
#canal.instance.standby.timestamp =
#canal.instance.standby.gtid=

# username/password
canal.instance.dbUsername=root
canal.instance.dbPassword=root
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==

# table regex
canal.instance.filter.regex=.*\\..*
# table black regex
canal.instance.filter.black.regex=mysql\\.slave_.*
# table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.field=test1.t_product:id/subject/keywords,test2.t_company:id/name/contact/ch
# table field black filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.black.field=test1.t_product:subject/product_image,test2.t_company:id/name/contact/ch

# mq config
canal.mq.topic=example
# dynamic topic route by schema or table regex
#canal.mq.dynamicTopic=mytest1.user,topic2:mytest2\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.enableDynamicQueuePartition=false
#canal.mq.partitionsNum=3
#canal.mq.dynamicTopicPartitionNum=test.*:4,mycanal:6
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################

adapter

application.yml

server:
  port: 8081
logging:
  level:
    com.alibaba.otter.canal.client.adapter.rdb: DEBUG
spring:
  jackson:
    date-format: yyyy-MM-dd HH:mm:ss
    time-zone: GMT+8
    default-property-inclusion: non_null

canal.conf:
  mode: tcp #tcp kafka rocketMQ rabbitMQ
  # Canal 的 deployer 服务所在的 IP 地址:11111
  canalServerHost: hadoop108:11111
#  flatMessage: true
#  mqServers 127.0.0.1:9092  #or rocketmq
#  zookeeperHosts:
  batchSize: 500
  syncBatchSize: 1000
  # -1 表示无限重试
  retries: 0
  timeout:
  accessKey:
  secretKey:
  consumerProperties:
    # canal tcp consumer
    canal.tcp.server.host: 127.0.0.1:11111
    canal.tcp.zookeeper.hosts:
    canal.tcp.batch.size: 500
    canal.tcp.username:
    canal.tcp.password:
    # kafka consumer
    kafka.bootstrap.servers: 127.0.0.1:9092
    kafka.enable.auto.commit: false
    kafka.auto.commit.interval.ms: 1000
    kafka.auto.offset.reset: latest
    kafka.request.timeout.ms: 40000
    kafka.session.timeout.ms: 30000
    kafka.isolation.level: read_committed
    kafka.max.poll.records: 1000
    # rocketMQ consumer
    rocketmq.namespace:
    rocketmq.namesrv.addr: 127.0.0.1:9876
    rocketmq.batch.size: 1000
    rocketmq.enable.message.trace: false
    rocketmq.customized.trace.topic:
    rocketmq.access.channel:
    rocketmq.subscribe.filter:
    # rabbitMQ consumer
    rabbitmq.host:
    rabbitmq.virtual.host:
    rabbitmq.username:
    rabbitmq.password:
    rabbitmq.resource.ownerId:

  srcDataSources:
    defaultDS:
      url: jdbc:mysql://hadoop106:3306/FlinkEtl?useUnicode=true&characterEncoding=UTF-8&serverTimezone=GMT&useSSL=false
      username: root
      password: root
  canalAdapters:
  - instance: example # canal instance Name or mq topic name
    groups:
    - groupId: g1
      outerAdapters:
      - name: logger
      - name: rdb
        key: mysql1
        properties:
          jdbc.driverClassName: com.mysql.jdbc.Driver
          jdbc.url: jdbc:mysql://hadoop108:3306/FlinkEtl?useUnicode=true&characterEncoding=UTF-8&serverTimezone=GMT&useSSL=false
          jdbc.username: root
          jdbc.password: root
#          druid.stat.enable: false
#          druid.stat.slowSqlMillis: 1000
#      - name: rdb
#        key: oracle1
#        properties:
#          jdbc.driverClassName: oracle.jdbc.OracleDriver
#          jdbc.url: jdbc:oracle:thin:@localhost:49161:XE
#          jdbc.username: mytest
#          jdbc.password: m121212
#      - name: rdb
#        key: postgres1
#        properties:
#          jdbc.driverClassName: org.postgresql.Driver
#          jdbc.url: jdbc:postgresql://localhost:5432/postgres
#          jdbc.username: postgres
#          jdbc.password: 121212
#          threads: 1
#          commitSize: 3000
#      - name: hbase
#        properties:
#          hbase.zookeeper.quorum: 127.0.0.1
#          hbase.zookeeper.property.clientPort: 2181
#          zookeeper.znode.parent: /hbase
#      - name: es
#        hosts: 127.0.0.1:9300 # 127.0.0.1:9200 for rest mode
#        properties:
#          mode: transport # or rest
#          # security.auth: test:123456 #  only used for rest mode
#          cluster.name: elasticsearch
#      - name: kudu
#        key: kudu
#        properties:
#          kudu.master.address: 127.0.0.1 # ',' split multi address
#      - name: phoenix
#        key: phoenix
#        properties:
#          jdbc.driverClassName: org.apache.phoenix.jdbc.PhoenixDriver
#          jdbc.url: jdbc:phoenix:127.0.0.1:2181:/hbase/db
#          jdbc.username:
#          jdbc.password:

bootstrap.yml

canal:
  manager:
    jdbc:
      url: jdbc:mysql://hadoop108:3306/canal_manager?useUnicode=true&characterEncoding=UTF-8&serverTimezone=GMT&useSSL=false
      username: root
      password: root

mytest_user.yml

dataSourceKey: defaultDS
destination: example
#和上面第二步中的该配置保持一致
groupId: g1
#和第二步中的该配置保持一致
outerAdapterKey: mysql1
concurrent: true
dbMapping:
  # mysql源数据库名称
  database: FlinkEtl
  # mysql源数据库下的表名称
  table: employee
  # 同步到目标数据库-数据表名称
  targetTable: employee
  targetPk:
    id: id
# 如果源表和目标表的字段结构等完全一致，直接开启此配置即可，下面的targetColumns可以注释掉
  mapAll: true
  # targetColumns:
  #  id:
  #  name:
  #  role_id:
  #  c_time:
  #  test1:
  # 注掉
  # etlCondition: "where c_time>={}"
  # 批量提交的大小
  # commitBatch: 3000 


## Mirror schema synchronize config
#dataSourceKey: defaultDS
#destination: example
#groupId: g1
#outerAdapterKey: mysql1
#concurrent: true
#dbMapping:
#  mirrorDb: true
#  database: mytest

 =================镜像同步 配置===========================

原文：实战教程第四章4.10：如何使用 CANAL 将 MySQL 数据实时同步到 OceanBase - 知乎 (zhihu.com)

#dataSourceKey: defaultDS
#destination: example
#和上面③的该配置保持一致
#groupId: g1
#和③中的该配置保持一致
#outerAdapterKey: mysql1
#concurrent: true
#dbMapping:
  # mysql源数据库名称
  #database: FlinkEtl
  # mysql源数据库下的表名称
  #table: employee
  # 同步到目标数据库-数据表名称
  #targetTable: employee
  #targetPk:
    #id: id
# 如果源表和目标表的字段结构等完全一致，直接开启此配置即可，下面的targetColumns可以注释掉
  #mapAll: true
# 如果targetColumns也配置了映射,则以targetColumns配置为准)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
  # targetColumns:
  #  id:
  #  name:
  #  role_id:
  #  c_time:
  #  test1:
# 注掉
# etlCondition: "where c_time>={}"
# 批量提交的大小
# commitBatch: 3000 


## Mirror schema synchronize config
dataSourceKey: defaultDS
destination: example
groupId: g1
outerAdapterKey: mysql1
concurrent: true
dbMapping:
  mirrorDb: true
  database: FlinkEtl