基于kafka的接口平台（数据库源MySQL同步增删改日志到kafka）

canal 模拟 MySQL slave 的交互协议，伪装自己为 MySQL slave ，向 MySQL master 发送dump 协议。MySQL master 收到 dump 请求，开始推送 binary log 给 slave (即 canal )。canal 解析 binary log 对象(原始为 byte 流)

一、搭建 canal-server
1，创建安装文件夹
mkdir canal-server
2，安装canal-server
tar zxvf canal.deployer-1.1.4.tar.gz -C canal-server
3，修改配置
cd /root/canal-server/conf
vi canal.properties

---

#register ip
canal.register.ip =
#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 =

---

4,启动canal-server
cd /root/canal-server/bin
./startup.sh
二、搭建canal-admin
1，创建安装文件夹
mkdir canal-admin
2，安装canal-admin
tar zxvf canal.admin-1.1.4.tar.gz -C canal-admin
3，登录mysql
mysql -h127.1 -uroot -p
4，初始化表结构
source conf/canal_manager.sql
5，修改配置文件 application.yml
server:
port: 8089
spring:
jackson:
date-format: yyyy-MM-dd HH:mm:ss
time-zone: GMT+8
spring.datasource:
address: 127.0.0.1:3306
database: canal_manager
username: root
password: 18632925029+
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
6，启动canal-admin
三、配置MySQL
1，创建canal用户，并开启对应权限
CREATE USER canal IDENTIFIED BY ‘canal’;
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON . TO ‘canal’@’%’;
FLUSH PRIVILEGES;
2，修改配置
vi /etc/my.cnf
#加入以下内容
server_id=1
log_bin = mysql-bin
binlog_format = ROW
expire_logs_days = 30
#重启mysql服务
systemctl restart mysqld #或重启docker容器、
四、配置连接
1,登录http://127.0.0.1:8089用户名admin 密码 123456 点击配置

2,修改server配置如下(红色为更改项)
#################################################
######### 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
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 =
#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 = 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 #############
##################################################
canal.mq.servers = 127.0.0.1:9092
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”

3，新建instace配置
#################################################
##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
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=root
canal.instance.dbPassword=18632925029+
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=lihao.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=oracle_test
#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,.\…
#################################################
五、测试
1，对数据库lihao.test做增、改、删操作，同步消费kafka

2，同步消费kafka
docker exec kafka kafka-console-consumer.sh --bootstrap-server 172.21.0.11:9092 --from-beginning --topic oracle_test

3，消费数据格式
INSERT INTO lihao.test (id, code, name) VALUES (‘333’, ‘aaa’, ‘AA’);

UPDATE lihao.test SET code = ‘eee’ WHERE ID = 333

DELETE FROM lihao.test WHERE id = 333

六、后续
当我们订阅的表的增删改的消息实时同步到kafak后，我们的应用再去消费该数据进行自己相应的逻辑处理即可