CanalAdmin部署文档

1、下载

Releases · alibaba/canal · GitHub

2、解压

mkdir canalAdmin

tar zxvf canal.admin-1.1.6.tar.gz -C canalAdmin

3、配置修改

vim canalAdmin/conf/application.yml

配置数据库信息，address、username、password填实际使用数据库信息，database固定为canal_manager

4、初始化元数据库

mysql -h 172.16.1.186 -uroot -p123456 < canal_manager.sql

如果本地没有mysql客户端，可以将canal_manager.sql内容拷贝出来单独执行

5、启动Canal Admin

sh canalAdmin/bin/startup.sh

6、登录页面

默认端口8089，用户名admin，默认密码123456

7、集群管理->新建集群

集群名称：自定义

ZK地址：为已安装的zk集群地址

8、添加主配置参数

#################################################
######### 		common argument		#############
#################################################

canal.ip = 
canal.register.ip = 
canal.port = 11111
canal.metrics.pull.port = 11112

# 这里填写linux上安装canalServer的操作系统用户名和MD5加密的密码
canal.user = demo
canal.passwd = e369853df766fa44e1ed0ff613f563bd

# 这里填写安装canalAdmin的IP:端口
canal.admin.manager = 172.16.1.4:8089
# 默认11110，可以不改
canal.admin.port = 11110
# canalAdmin前端登录的用户名和MD5加密的密码
canal.admin.user = admin
canal.admin.passwd = 6BB4837EB74329105EE4568DDA7DC67ED2CA2AD9

canal.admin.register.auto = true
# 对应[集群管理]中创建的集群名
canal.admin.register.cluster = cluster01
# 对应[Server管理]中创建的Server名称
canal.admin.register.name = bigdata5
# 配置需要写入kafka的ZK集群
canal.zkServers = bigdata1:2181,bigdata2:2181,bigdata5:2181

# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false

# tcp, kafka, rocketMQ, rabbitMQ, pulsarMQ
canal.serverMode = kafka

# 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

canal.instance.tsdb.enable = true
#canal.instance.tsdb.dir = 
# 配置canal binlog DDL相关元数据存储的数据jdbc、用户名、密码
canal.instance.tsdb.url = jdbc:mysql://172.16.1.62:3306/canal_tsdb
canal.instance.tsdb.dbUsername = root
canal.instance.tsdb.dbPassword = Pw#123456

# 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 = 

# canalServer在linux上的配置目录
canal.conf.dir = /opt/canal.deployer-1.1.6/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 = 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集群地址
kafka.bootstrap.servers = bigdata4:9092,bigdata5:9092,bigdata6:9092
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 =

9、Server管理->新建Server

所属集群：集群管理中配置的集群

Server名称：自定义

Server IP：linux中已安装canalServer的机器IP

admin端口：默认11110

tcp端口：默认11111

metric端口：默认11112

创建后的状态为停止，需要在linux启动canalServer后，动态识别状态并关联上

10、Instance管理->新建Instance

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

# enable gtid use true/false 是否开启全局事务id
canal.instance.gtidon=false
#canal.instance.master.gtid=

# position info
# 需要同步binlog的数据库地址及端
canal.instance.master.address=172.16.1.62:3306
# 需要读取的起始的binlog文件
canal.instance.master.journal.name=mysql-bin.000001
# 需要读取的起始的binlog文件的偏移量
canal.instance.master.position=0
# 需要读取的起始的binlog的时间戳
canal.instance.master.timestamp=1655049600000

# username/password 需要同步binlog的数据库的用户名和密码
canal.instance.dbUsername=root
canal.instance.dbPassword=Pw#123456
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==

# table meta tsdb info
# 是否开启table meta的时间序列版本记录功能
canal.instance.tsdb.enable=true
# 存储canal记录表结构日志的数据库jdbc
canal.instance.tsdb.url=jdbc:mysql://172.16.1.62:3306/canal_tsdb
canal.instance.tsdb.dbUsername=root
canal.instance.tsdb.dbPassword=Pw#123456

#canal.instance.standby.address =
#canal.instance.standby.journal.name =
#canal.instance.standby.position =
#canal.instance.standby.timestamp =
#canal.instance.standby.gtid=

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

# table regex
# mysql 数据解析关注的表，Perl正则表达式， .*\\..*默认所有库所有表
canal.instance.filter.regex=testDataBase\\..*
#例子1：testA\\.test 只解析testA库test表
#例子2：.*\\.test,.*\\.testA 解析所有库test表和testA表
# table black regex
# 过滤那些不符合要求的table，这些table的数据将不会被解析和传送
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

# 指定kafka的topic
canal.mq.topic=testTopic2
# 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=true
canal.mq.partitionsNum=3
#canal.mq.dynamicTopicPartitionNum=test.*:4,mycanal:6
canal.mq.partitionHash=.*\\..*
#例子1：test\\.test:pk1^pk2 指定匹配的单表，对应的hash字段为pk1 + pk2
#例子2：.*\\..*:id 正则匹配，指定所有正则匹配的表对应的hash字段为id
#例子3：.*\\..*:$pk$ 正则匹配，指定所有正则匹配的表对应的hash字段为表主键(自动查找)
#例子4: 匹配规则啥都不写，则默认发到0这个partition上
#例子5：.*\\..* ，不指定pk信息的正则匹配，将所有正则匹配的表,对应的hash字段为表名
#例子6: test\\.test:id,.*\\..* , 针对test的表按照id散列,其余的表按照table散列
#################################################

11、安装canalServer

11.1、下载

Releases · alibaba/canal · GitHub

11.2、解压

将canal.deployer-1.1.6.tar.gz上传到/opt目录

cd /opt
tar -zxvf canal.deployer-1.1.6.tar.gz

11.3、设置配置文件

cd /opt/canal.deployer-1.1.6/conf
mv canal.properties canal.properties_bak
cp canal_local.properties canal.properties
vim canal.properties

# register ip
canal.register.ip =

# canalAdmin 的链接、端口、用户名和MD5密码
canal.admin.manager = 172.16.1.64:8089
canal.admin.port = 11110
canal.admin.user = admin
canal.admin.passwd = 6BB4837EB74329105EE4568DDA7DC67ED2CA2AD9
# admin auto register
canal.admin.register.auto = true
# 需要注册到canalAdmin的集群名，对应集群管理里面创建的集群名
canal.admin.register.cluster = cluster01
# 当前canalServer在Server管理里面创建的Server名称
canal.admin.register.name = bigdata6

11.4、启动canalServer

sh /opt/canal.deployer-1.1.6/bin/startup.sh

启动后，canalAdmin的server管理模块，对应创建的server会动态识别到，状态变为启动

12、canal Server HA 搭建

在server管理里面，创建第二个server，所属集群与第一个server相同，比如同为cluster01

创建完成后，重复步骤11，在另一台机器安装canalServer后端服务并启动

13、启动Instance实例

启动完成后，被动态分配到HA的bigdata6来执行

至此，canal HA已启动完成，可以去kafka客户端指定的topic去消费数据了