CC00008.bdpositions——|Hadoop&实时数仓.V08|——|项目.v08|Canal同步业务数据|Canal部署|

一、Canal 安装说明

### --- Canal 安装说明

~~~     单机模式，也可以将Canal搭建集群模式。
~~~     如果要搭建集群模式，可将Canal目录分发给其他虚拟机，然后在各节点中分别启动Canal。
~~~     这种Zookeeper为观察者监控的模式，
~~~     只能实现高可用，而不是负载均衡，
~~~     即同一时间点只有一个canal-server节点能够监控某个数据源，
~~~     只要这个节点能够正常工作，那么其他监控这个数据源的canal-server只能做stand-by，
~~~     直到工作节点停掉，其他canal-server节点才能抢占。

二、canal部署

### --- 下载Canal版本包

~~~     # 下载：https://github.com/alibaba/canal/releases
~~~     # 把下载的Canal.deployer-1.1.4.tar.gz拷贝到linux,解压缩(路径可自行调整)
[root@hadoop02 software]# wget -c https://github.com/alibaba/canal/releases/download/canal-1.1.4/canal.deployer-1.1.4.tar.gz
~~~     # OR 
[root@hadoop02 software]# wget -c https://github.com/alibaba/canal/releases/download/canal-1.1.5/canal.deployer-1.1.5.tar.gz

### --- 解压canal版本包

~~~     # 解压canal版本包
[root@hadoop02 ~]# mkdir /opt/yanqi/servers/canal
[root@hadoop02 software]# tar -zxvf canal.deployer-1.1.4.tar.gz -C ../servers/canal/

### --- canal目录结构

~~~     # canal目录结构
[root@hadoop02 ~]# ll /opt/yanqi/servers/canal/
bin
conf
lib
logs

二、修改canal配置文件

### --- 修改canal.properties配置文件

~~~     # 修改conf/canal.properties
~~~     # 这个文件是canal的基本通用配置，主要关心一下端口号，不改的话默认就是11111
~~~     # 修改内容如下：(zk和kafka地址根据个人事迹情况调整，以下不再复述)
[root@hadoop02 ~]# vim /opt/yanqi/servers/canal/conf/canal.properties
~~~ 第20行: 配置zookeeper地址
canal.zkServers = hadoop01:2181,hadoop02:2181,hadoop03:2181
~~~ 第25行：tcp, kafka, RocketMQ
canal.serverMode = kafka
~~~ 第116行：配置kafka地址
canal.mq.servers = hadoop01:9092,hadoop02:9092,hadoop03:9092

### --- 修改instance.properties配置文件

~~~     # 修改conf/example/instance.properties 这个文件是针对要追踪的MySQL的实例配置
[root@hadoop02 ~]# vim /opt/yanqi/servers/canal/conf/example/instance.properties 
~~~ 第9行：配置MySQL数据库所在的主机
canal.instance.master.address=hadoop03:3306
~~~ 第33~34行：username/password，配置数据库用户和密码
canal.instance.dbUsername=canal
canal.instance.dbPassword=canal
~~~ 第50行：mq config,对应Kafka主题：
canal.mq.topic=canal

三、启动canal服务

### --- 启动Canal

~~~     # 启动canal服务
[root@hadoop02 ~]# sh /opt/yanqi/servers/canal/bin/startup.sh

~~~     # 查看canal进程

[root@hadoop02 ~]# jps
11151 CanalLauncher

### --- 关闭Canal

~~~     # 停止canal服务
[root@hadoop02 ~]# sh /opt/yanqi/servers/canal/bin/stop.sh

附录一：canal.properties完整配置文件：

[root@hadoop02 ~]# cat /opt/yanqi/servers/canal/conf/canal.properties
 
 ~~~完整配置文件
#################################################
#########       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

canal.zkServers = hadoop01:2181,hadoop02:2181,hadoop03:2181
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ
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

# 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
# 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 = hadoop01:9092,hadoop02:9092,hadoop03:9092
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"

附录二：instance.properties完整配置文件：

[root@hadoop02 ~]# cat /opt/yanqi/servers/canal/conf/example/instance.properties
 
~~~完整配置文件
#################################################
## 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=hadoop03:3306
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
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=
# 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=canal
# 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,.*\\..*
#################################################