1. 简介:


canal [kə'næl],译意为水道/管道/沟渠,主要用途是基于 MySQL 数据库增量日志解析,提供增量数据订阅和消费
早期阿里巴巴因为杭州和美国双机房部署,存在跨机房同步的业务需求,实现方式主要是基于业务 trigger 获取增量变更。从 2010 年开始,业务逐步尝试数据库
志解析获取增量变更进行同步,由此衍生出了大量的数据库增量订阅和消费业务。
基于日志增量订阅和消费的业务包括
1.数据库镜像
2.数据库实时备份
3.索引构建和实时维护(拆分异构索引、倒排索引等)
4.业务 cache 刷新
5.带业务逻辑的增量数据处理


1.1 官网地址


https://github.com/alibaba/canal


2.架构





canal1.1.5 配置kafka_canal


canal.png


3.canal 工作原理





canal1.1.5 配置kafka_canal_02


canal 工作原理.png


4 canal 部署所需要的组件


搭建一套可以用的组件需要部署MySQL、Zookeeper、Kafka和Canal四个中间件的实例


5. mysql 安装省略(参考博客上的安装即可)

5.1 为canal -admin 创建用户


CREATE USER canaladmin IDENTIFIED BY 'Canaladmin%123';
GRANT ALL ON canal_manager.* TO 'canaladmin'@'%';
FLUSH PRIVILEGES;


5.1 为canal 创建用户:


CREATE USER canal IDENTIFIED BY 'Canal%123';
GRANT ALL PRIVILEGES ON *.* TO 'canal'@'%' ;
FLUSH PRIVILEGES;


5.3 mysql 的配置:

打开mysql 的配置文件:

vi /etc/my.cnf


server-id=1
log-bin=mysql-bin
binlog-format=ROW
binlog-ignore-db=information_schema
binlog-ignore-db=mysql
binlog-ignore-db=performance_schema
binlog-ignore-db=sys

log-binbinlog/var/lib/mysql
server-id使ip
binlog-ignore-db
binlog-do-db


6. canal 安装

下载地址:


https://github.com/alibaba/canal/releases


canal1.1.5 配置kafka_canal_03


6.1 下载解压安装


[root@dbos-bigdata-test005 canal]# ll
total 8
drwxr-xr-x 6 root root 4096 Oct 11 16:37 admin
drwxr-xr-x 7 root root 4096 Oct 11 16:38 deployer
[root@dbos-bigdata-test005 canal]# pwd
/data/canal
[root@dbos-bigdata-test005 canal]#


6.2 配置环境变量


#set default jdk1.8 env
export JAVA_HOME=/usr/java/jdk1.8.0_181-cloudera
export JRE_HOME=/usr/java/jdk1.8.0_181-cloudera/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export HADOOP_CONF_DIR=/etc/hadoop/conf
export HADOOP_CLASSPATH=`hadoop classpath`
export HBASE_CONF_DIR=/etc/hbase/conf
export FLINK_HOME=/opt/flink
export HIVE_HOME=/opt/cloudera/parcels/CDH-6.3.0-1.cdh6.3.0.p0.1279813/lib/hive
export HIVE_CONF_DIR=/etc/hive/conf
export M2_HOME=/usr/local/maven/apache-maven-3.5.4
#canal的配置
export CANAL_ADMIN_HOME=/data/canal/admin
export CANAL_SERVER_HOME=/data/canal/deployer
export PATH=${JAVA_HOME}/bin:${JRE_HOME}/bin:${FLINK_HOME}/bin:${M2_HOME}/bin:${HIVE_HOME}/bin:${CANAL_SERVER_HOME}/bin:${CANAL_ADMIN_HOME}/bin:PATH


6.3 配置canal -admin

进入到canaladmin 目录的conf 目录中


vim /data/canal/admin/conf/application.yml


修改内容如下:


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

spring.datasource:
address: 172.16.12.16:3306
database: canal_manager
username: canaladmin
password: Canaladmin%123
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: admin


导入canal-admin的sql 脚本


1.mysql  
mysql> use mysql;
Reading table information for completion of table and column names
You can turn off this feature to get a quicker startup with -A

Database changed
mysql> source /root/canal_manager.sql


启动canal-admin


/data/canal/admin/bin
[root@dbos-bigdata-test005 bin]# pwd
/data/canal/admin/bin
[root@dbos-bigdata-test005 bin]# ll
total 20
-rw-r--r-- 1 root root 6 Oct 12 14:23 admin.pid
-rwxr-xr-x 1 root root 205 Apr 19 15:48 restart.sh
-rwxr-xr-x 1 root root 747 Apr 19 15:48 startup.bat
-rwxr-xr-x 1 root root 2047 Apr 19 15:48 startup.sh
-rwxr-xr-x 1 root root 1362 Apr 19 15:48 stop.sh
[root@dbos-bigdata-test005 bin]# ./startup.sh


访问地址:

http://172.16.12.16:8089/ 默认登录 admin/123456

canal1.1.5 配置kafka_canal_04


7. 配置canaldeployer


[root@dbos-bigdata-test005 conf]# pwd
/data/canal/deployer/conf
[root@dbos-bigdata-test005 conf]# ll
total 28
-rwxrwxrwx 1 root root 319 Apr 19 15:48 canal_local.properties
-rwxrwxrwx 1 root root 6379 Oct 12 14:55 canal.properties
drwxrwxrwx 2 root root 4096 Oct 12 15:09 example
-rwxrwxrwx 1 root root 3437 Apr 19 15:48 logback.xml
drwxrwxrwx 2 root root 4096 Oct 11 16:38 metrics
drwxrwxrwx 3 root root 4096 Oct 11 16:38 spring


打开canal.properties 文件:


[root@dbos-bigdata-test005 conf]# cat canal.properties 
#################################################
######### common argument #############
#################################################
# tcp bind ip
canal.ip =
# register ip to zookeeper
canal.register.ip = 172.16.12.11:2181,172.16.12.12:2181,172.16.12.13:2181
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%123
# 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

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 = 172.16.12.11:9092,172.16.12.12:9092,172.16.12.13:9092
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 =


配置实例文件


[root@dbos-bigdata-test005 example]# pwd
/data/canal/deployer/conf/example
[root@dbos-bigdata-test005 example]# ll
total 28
-rw-r--r-- 1 root root 20480 Oct 12 15:10 h2.mv.db
-rwxrwxrwx 1 root root 2112 Oct 12 14:57 instance.properties
-rw-r--r-- 1 root root 42 Oct 12 15:09 meta.dat


编辑内容:


#################################################
## 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=172.16.12.16:3306
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=

# 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
canal.instance.dbPassword=Canal%123
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,mytest2\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#canal.mq.dynamicTopicPartitionNum=test.*:4,mycanal:6
#################################################


7.1 启动


[root@slave01 bin]# pwd
/opt/module/canal/canaldeployer/bin
[root@slave01 bin]# ll
20
-rw-r--r-- 1 root root 6 2 14 01:25 canal.pid
-rwxr-xr-x 1 root root 58 2 14 00:45 restart.sh
-rwxr-xr-x 1 root root 1181 2 14 00:45 startup.bat
-rwxr-xr-x 1 root root 3167 2 14 00:45 startup.sh
-rwxr-xr-x 1 root root 1356 2 14 00:45 stop.sh
[root@slave01 bin]#
[root@slave01 bin]# ./startup.sh

canal1.1.5 配置kafka_canal_05

添加服务器之后就是部署完成了。