Canal学习文档+集成kafka

Canal学习文档 + kafka配置

配置文件

恢复默认配置（表结构变更可能会影响同步阻塞–解决方法：删除conf/example/目录下的h2跟meta相关文件，重启canal，期间数据会丢失需要重新插入期间数据）

instance.properties:

#############################################
## mysql serverId , v1.0.26+ will autoGen
canal.instance.mysql.slaveId=15

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

# position info
canal.instance.master.address=自己要监听数据库的地址ip:port // 127.0.0.1:3306
#canal.instance.master.address=
#canal.instance.master.address=
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 //表结构发生改变会阻塞读取binlog
canal.instance.tsdb.url=默认
canal.instance.tsdb.dbUsername=canal
canal.instance.tsdb.dbPassword=canal
canal.instance.tsdb.dit = ${canal.file.data.dir:../../conf}/${canal.instance.destination:}
canal.instance.tsdb.spring.xml=classpath:spring/tsdb/mysql-tsdb.xml
canal.instance.filter.table.error=false

#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.instance.dbPassword=
#canal.instance.dbUsername=rootadmin
#canal.instance.dbPassword=GMha28Q\#2w
#canal.instance.dbUsername=roota
#canal.instance.dbPassword=LZys8ipgzzdq2020@@
#canal.instance.dbUsername=
#canal.instance.dbPassword=tHLsenlrej6D3dot


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=abc.user
// 过滤器用于过滤被监听表，默认配置为全部监听，自定义格式为database1.table1,database2.table2
canal.instance.filter.regex=.*\\..*
# table black regex
canal.instance.filter.black.regex=
canal.instance.filter.query.dml = true
# 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

// 该条注释默认为注释掉的，网上讨论中认为要把该行注释解除
canal.instance.parser.parallelThreadSize = 16

# 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.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
canal.withoutNetty = false
# tcp, kafka, RocketMQ
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

# 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=默认即可
canal.instance.tsdb.dbUsername=
canal.instance.tsdb.dbPassword=

# 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 = false
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 = 127.0.0.1:6667
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"

Canal部署问题：

1.异步读取batchId重复消费 not firstly

串行读取

使用消息队列分发

canal+kafka客户端

pom

需要单独引入

<dependency>
			<groupId>org.apache.kafka</groupId>
			<artifactId>kafka-clients</artifactId>
			<version>1.1.1</version>
			<scope>provided</scope>
		</dependency>

获取消息的方式：

1.使用List新建下列连接对象时需要设置flatMessage为true

2.使用List 新建下列连接对象时需要设置flatMessage为false
同时在客户端当中应当在autoProperty对于kafka启动依赖注入配置中将flatmessage改成message的messageHandler

public class KafkaClientAutoConfiguration {


    private CanalKafkaProperties canalKafkaProperties;


    public KafkaClientAutoConfiguration(CanalKafkaProperties canalKafkaProperties) {
        this.canalKafkaProperties = canalKafkaProperties;
    }


//    @Bean
//    public RowDataHandler<List<Map<String, String>>> rowDataHandler() {
//        return new MapRowDataHandlerImpl(new MapColumnModelFactory());
//    }

    @Bean
    public RowDataHandler<CanalEntry.RowData> rowDataHandler() {
        return new RowDataHandlerImpl(new EntryColumnModelFactory());
    }

    @Bean
    @ConditionalOnProperty(value = CanalProperties.CANAL_ASYNC, havingValue = "true", matchIfMissing = true)
    public MessageHandler messageHandler(RowDataHandler<CanalEntry.RowData> rowDataHandler,
                                         List<EntryHandler> entryHandlers,
                                         ExecutorService executorService) {
        return new AsyncMessageHandlerImpl(entryHandlers, rowDataHandler, executorService);
    }


    @Bean
    @ConditionalOnProperty(value = CanalProperties.CANAL_ASYNC, havingValue = "false")
    public MessageHandler messageHandler(RowDataHandler<CanalEntry.RowData> rowDataHandler, List<EntryHandler> entryHandlers) {
        return new SyncMessageHandlerImpl(entryHandlers, rowDataHandler);
    }


    @Bean(initMethod = "start", destroyMethod = "stop")
    public KafkaCanalClient kafkaCanalClient(MessageHandler messageHandler) {
        return KafkaCanalClient.builder().servers(canalKafkaProperties.getServer())
                .groupId(canalKafkaProperties.getGroupId())
                .topic(canalKafkaProperties.getDestination())
                .messageHandler(messageHandler)
                .batchSize(canalKafkaProperties.getBatchSize())
                .filter(canalKafkaProperties.getFilter())
                .timeout(canalKafkaProperties.getTimeout())
                .unit(canalKafkaProperties.getUnit())
                .build();
    }

}

上面代码中将原来的List<Map<String, String> rowDataHandler注释掉了引入了message的RowDataHandler<CanalEntry.RowData> rowDataHandler()

public KafkaCanalClient build() {
            KafkaCanalConnector connector = new KafkaCanalConnector(servers, topic, partition, groupId, batchSize, false); // 最后一项为flatMessage（boolean）
            KafkaCanalClient kafkaCanalClient = new KafkaCanalClient();
            kafkaCanalClient.setMessageHandler(messageHandler);
            kafkaCanalClient.setConnector(connector);
            kafkaCanalClient.filter = this.filter;
            kafkaCanalClient.unit = this.unit;
            kafkaCanalClient.batchSize = this.batchSize;
            kafkaCanalClient.timeout = this.timeout;
            return kafkaCanalClient;
        } // 以上值需要在yml文件里进行配置

report工程

yml配置：

canal:
  server: 10.201.21.206:9092,10.201.21.207:9092,10.201.21.205:9092
  destination: amp_bis_db\\..*
  user-name: canal
  password: canal
  async: true
  group-id: canal-report
  mode: kafka // canal模式

2.读取数据库数据转化成实体的时候产生类型抓换错误“”不能转string

使用toBean，Inteager.parseInt()会导致字符串为""时报错

3.batch not exist

将scan = false

设置客户端重试机制

4.handler中如果有@DS会使得handler不被注册进canal