canal 实现mysql和oracle数据库之间增量备份

一、项目介绍

将mysql数据库的写操作同步到oracle数据库。canel利用主从复制原理将mysql数据的写操作输出到Kafka的topic里，java程序消费kafka的数据并转化成相应的sql语句，插入oracle中（这里用nginx反向代理oracle提供服务）

二、工作原理

1、mysql主从同步实现

①Master服务器上进行写操作时，会把写操作记录到本地的二进制日志文件中，本地会启动sql线程，该线程会通过网络把事件传递给slave从服务器
②Slave服务器会启动I/O thread，负责接收二进制日志事件，并写入本地的relay log中继日志
③Slave服务器启动SQL thread，负责读取中继日志中的事件，在从服务器本地执行，从而保证主、从服务器数据同步

2、canel的工作原理

①canal模拟mysql slave的交互协议，伪装自己为mysql slave，向mysql master发送dump协议
②mysql master收到dump请求，开始推送binary log给slave(也就是canal)
③canal解析binary log对象(原始为byte流)

三、数据同步

1、全量备份同步（此过程略过）

2、数据增量同步

2.1MySQL添加canel用户

GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'%' identified by 'WWW.1.com';
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'localhost' identified by 'WWW.1.com';
FLUSH PRIVILEGES;

2.2开启MySQL的binlog日志

# vi /etc/my.cnf 

[mysqld]
log-bin=mysql-bin # 开启binlog
binlog-format=ROW # 选择ROW 模式
server_id=1 # 配置MySQL replaction 需要定义，不要和canal 的slaveId 重复

2.3安装jdk(略)

2.4安装zookeeper

 2.4.1准备安装包zookeeper-3.4.11.tar.gz，解压安装

[root@localhost ~]# tar zxf zookeeper-3.4.11.tar.gz -C /usr/local/
[root@localhost ~]# cd /usr/local/zookeeper-3.4.11

2.4.2修改配置文件zoo.cfg

[root@localhost conf]# pwd
/usr/local/zookeeper-3.4.11/conf

[root@localhost conf]# cp zoo_sample.cfg  zoo.cfg

[root@localhost conf]# vim zoo.cfg

tickTime=2000
initLimit=10
syncLimit=5
dataDir=/usr/local/zookeeper-3.4.11/data
clientPort=2181
server1=192.168.174.128:2888:3888

[root@localhost]# mkdir /usr/local/zookeeper-3.4.11/data

dataDir下创建文件myid,内容配置文件中的server.n，n值对应

[root@localhost data]# echo 1 > myid
[root@localhost data]# cat myid
1

2.4.3启动zookeeper

[root@localhost bin]# /usr/local/zookeeper-3.4.11/bin/zkServer.sh start
ZooKeeper JMX enabled by default
Using config: /usr/local/zookeeper-3.4.11/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED

[root@localhost bin]# jps
2217 QuorumPeerMain
2234 Jps

2.5安装Kafka

2.5.1准备安装包kafka_2.11-1.0.0.tgz，解压安装

[root@localhost ~]# tar zxf kafka_2.11-1.0.0.tgz -C /usr/local/

 2.5.2修改配置文件config/server.properties

[root@localhost kafka_2.11-1.0.0]# vim config/server.properties

broker.id=2
listeners=PLAINTEXT://192.168.174.128:9092

advertised.listeners=PLAINTEXT://192.168.174.128:9092

num.network.threads=3
num.io.threads=8
socket.send.buffer.bytes=102400
socket.receive.buffer.bytes=102400
socket.request.max.bytes=104857600

log.dirs=/usr/local/kafka_2.11-1.0.0/kafka-logs


num.partitions=1
num.recovery.threads.per.data.dir=1
offsets.topic.replication.factor=1
transaction.state.log.replication.factor=1
transaction.state.log.min.isr=1
log.retention.hours=168
log.retention.check.interval.ms=300000


zookeeper.connect=192.168.174.128:2181
zookeeper.connection.timeout.ms=6000
group.initial.rebalance.delay.ms=0

2.5.3启动kafka

[root@localhost bin]# pwd
/usr/local/kafka_2.11-1.0.0/bin

[root@localhost bin]# ./kafka-server-start.sh  -daemon ../config/server.properties    # 注意：-daemon启动是指后台启动，调试时可以去掉该参数

[root@localhost kafka_2.11-1.0.0]# jps
2928 Kafka
2992 Jps
2217 QuorumPeerMain

2.5.4测试kafka

①首先尝试创建一个topic

[root@localhost bin]#  ./kafka-topics.sh --create --zookeeper 192.168.174.128:2181 --replication-factor 1 --partitions 1 --topic test
Created topic "test".

②查看所有的topic

[root@localhost bin]# ./kafka-topics.sh --list --zookeeper 192.168.174.128:2181
test

③启动一个consumer

[root@localhost bin]# ./kafka-console-consumer.sh --zookeeper 192.168.174.128:2181 --topic test --from-beginning

注：kafka_2.12-2.2.0版本

/kafka-console-consumer.sh --topic test --bootstrap-server [IP]:9092

④启动生产者，向consumer发送消息

[root@localhost bin]# ./kafka-console-producer.sh --broker-list 192.168.174.128:9092 --topic test

 

⑤查看创建的topic

[root@localhost bin]# ./kafka-topics.sh --describe --zookeeper 192.168.174.128:2181 --topic test
Topic:test      PartitionCount:1        ReplicationFactor:1     Configs:
        Topic: test     Partition: 0    Leader: 0       Replicas: 0     Isr: 0

2.6安装canel

2.6.1准备安装包canal.deployer-1.1.4.tar.gz，解压安装

[root@localhost ~]# tar zxf canal.deployer-1.1.4.tar.gz -C /usr/local/canel

 2.6.2修改配置文件

①修改instance.properties

[root@localhost example]# pwd
/usr/local/canel/conf/example

[root@localhost example]# vim instance.properties

#################################################
## mysql serverId , v1.0.26+ will autoGen
canal.instance.mysql.slaveId=1234   #不能与 mysql 配置中的 server_id 相同

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

# position info
canal.instance.master.address=192.168.174.128:3306
canal.instance.master.journal.name=mysql-bin.000001
canal.instance.master.position=5556        #mysql的position信息
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=WWW.1.com
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=.*\\..*
canal.instance.filter.regex=school.Student,school.Teacher,school.Course,school.Score
# 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=mytest:school
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################

 ②修改canal.properties

[root@localhost conf]# pwd
/usr/local/canel/conf

[root@localhost conf]# vim 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

#canal.zkServers =
# flush data to zk
#canal.zookeeper.flush.period = 1000   #注释掉默认的zk配置
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = kafka   #指定MQ中间件为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 = 192.168.174.128:9092   #配置kafka连接信息
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"

2.6.3启动canel

[root@localhost bin]# pwd
/usr/local/canel/bin
[root@localhost bin]# ./startup.sh     #启动
[root@localhost bin]# ./stop.sh        #停止

注：配置instance.properties的 position 如果cannal不是第一次启动需删除同级目录下的meta.dat文件，配置才会生效

2.7验证，在被监控的mysql表中写入数据，查看kafka是否有数据产生

 

 至此canel搭建已经完成，后续还需要java程序消费kafka中数据，插入oracle，因为java程序需要开发才能完成，这段保密，只提供个思路，仅供参考。