Canal-admin1.1.6 部署 （mysql数据同步ES案例）

一、安装canal-admin

1. 下载canal-admin

github下载地址: wget https://github.com/alibaba/canal/releases/download/canal-1.1.6/canal.admin-1.1.6.tar.gz

2. 配置conf/application.yml

需要将conf/canal_manager.sql 导入到配置的数据库中

server:
  port: 8089
spring:
  jackson:
    date-format: yyyy-MM-dd HH:mm:ss
    time-zone: GMT+8

spring.datasource:
  address: 127.0.0.1:6033
  database: canal_manage
  username: canal_manage
  password: canal_manage
  driver-class-name: com.mysql.jdbc.Driver
  url: jdbc:mysql://${spring.datasource.address}/${spring.datasource.database}?useUnicode=true&characterEncoding=UTF-8&useSSL=false
  hikari:
    maximum-pool-size: 30
    minimum-idle: 1

canal:
  adminUser: admin
  adminPasswd: 123456

3. 登录canal-admin 创建集群

3.1 创建集群

3.2 修改主配置文件

访问127.0.0.1:8089 访问canal-admin管理页面
主配置>载入模版>保存 不需要做修改

#################################################
######### 		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
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.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

#################################################
######### 		destinations		#############
#################################################
canal.destinations = 
# 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

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 = manager
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 = 127.0.0.1:6667
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 =

二、部署canal-deployer

1. 下载canal-deployer

github下载地址: wget https://github.com/alibaba/canal/releases/download/canal-1.1.6/canal.adapter-1.1.6.tar.gz

2. 修改conf/canal_local.properties配置文件

# register ip
canal.register.ip = 127.0.0.1

# canal admin config
canal.admin.manager = 127.0.0.1:8089
canal.admin.port = 11110
canal.admin.user = admin
canal.admin.passwd = 6BB4837EB74329105EE4568DDA7DC67ED2CA2AD9
# admin auto register
canal.admin.register.auto = true
canal.admin.register.cluster = test
canal.admin.register.name = test_001

注： canal.admin.passwd 这个参数去数据库查看 canal_user 表中对应passwd字段值

3. 启动canal-deployer 在canal-admin中注册

bin/startup.sh local

在canal-admin web页面中查看注册canal-deployer

4. 在canal-admin中新建instance实例

instance管理>新建实例

#################################################
## 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=127.0.0.1:3306  ## 修改数据地址
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=

# table meta tsdb info
canal.instance.tsdb.enable=true
#canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
#canal.instance.tsdb.dbUsername=canal
#canal.instance.tsdb.dbPassword=canal

#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=canal      #添加数据账号密码
canal.instance.dbPassword=canal      #添加数据账号密码
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=.*\\..*   #添加监听库/表名 例： test\\.test
# table black regex
canal.instance.filter.black.regex=
# 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,mytest2\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################

三、部署canal-adapter

1. 下载canal-adapter

github下载地址: wget https://github.com/alibaba/canal/releases/download/canal1.1.6/canal.deployer-1.1.6.tar.gz

2. 配置conf/application.yml

server:
  port: 8081
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
  flatMessage: true
  zookeeperHosts:
  syncBatchSize: 1000
  retries: -1
  timeout:
  accessKey:
  secretKey:
  consumerProperties:
    # canal tcp consumer
    canal.tcp.server.host: 127.0.0.1:11111
    canal.tcp.zookeeper.hosts: zookeeper02.dev.harsons.local:2181,zookeeper01.dev.harsons.local:2181,zookeeper03.dev.harsons.local:2181
    canal.tcp.batch.size: 500
    canal.tcp.username:
    canal.tcp.password:

  srcDataSources:
    test1DS:
      url: jdbc:mysql://127.0.0.1:3306/ebc_biz_product_test?useUnicode=true
      username: canal
      password: canal
      maxActive: 100 #同步的进程数量
    test2DS:
      url: jdbc:mysql://127.0.0.1:3306/ebc_biz_product_dev?useUnicode=true
      username: canal
      password: canal
      maxActive: 100
  canalAdapters:
  - instance: test1  # canal instance Name or mq topic name
    groups:
    - groupId: g1
      outerAdapters:
      - name: logger
      - name: es7
        hosts: elasticsearch01:9200
        properties:
          mode: rest   #transport # or rest
          security.auth: elastic:test  #  only used for rest mode
          cluster.name: test
  - instance: test2  # canal instance Name or mq topic name
    groups:
    - groupId: g2
      outerAdapters:
      - name: logger
      - name: es7
        hosts: elasticsearch02:9200
        properties:
          mode: rest   #transport # or rest
          security.auth: elastic:test  #  only used for rest mode
          cluster.name: test

注： 可以添加多个库多个表实例通过groupId: g2 区分
instance: test2 对应canal-admin中instance名称

3. 修改conf/bootstrap.yml配置文件

canal:
  manager:
    jdbc:
      url: jdbc:mysql://127.0.0.1:3306/harsons_canal_es?useUnicode=true&characterEncoding=UTF-8
      username: canal
      password: canal

4. 添加conf/es7/test.yaml 查询sql

dataSourceKey: testDS    # conf/application.yml 中srcDataSources:
destination: test         #canal-admin 中 instance名称
groupId: g2
esMapping:
  _index: canal_product
  _id: id
  sql: "SELECT
  p.id,
  p.title,
  p.sub_title,
  p.price,
  p.pic
  p.update_time
FROM product p"
  etlCondition: "where p.update_time>={}"
  commitBatch: 30

注意：数据库名不可添加 `` 或者其他引号 不然会出现不自动同步数据的问题。

5. 创建索引

在es中创建索引

put /canal_product
{
    "mappings":{
        "properties":{
            "id":{
                "type":"text"
            },
            "title":{
                "type":"text"
            },
            "sub_title":{
                "type":"text"
            },
            "price":{
                "type":"text"
            },
            "update_time":{
                "type":"double"
            }
        }
    }
}

6. 全量同步数据至es

curl http://127.0.0.1:8081/etl/es7/test.yml -X POST