canal实战(三)|canal数据消费到kafka
## 本文章改编于阿里开源工具Canal，原版网址 https://github.com/alibaba/canal
- canal第一辑 canal的配置安装与服务启动
- canal第二辑 canal java客户端
canal的原理我们在第一辑里已经介绍，现在我们需要把canal采集到的日志数据消费到kafka，并通过kafka把数据进行进一步入库，上云等消费操作。
首先我们把Kafka进行安装配置，涉及到的有zookeeper，kafka，有的服务器还要装java环境等，kafka的安装我之前有讲过，来，给你一个kafka实施传送站
安装配置并开启kafka后，我们需要把kafka的相关信息补充到canal配置中，以便canal可以把数据发送到kafka
- vim ./conf/example/instance.properties
#################################################
## mysql serverId , v1.0.26+ will autoGen
# canal.instance.mysql.slaveId=0
# enable gtid use true/false
canal.instance.gtidon=false
# position info
# 需要改为MySQL实例所在的的IP,若为集群以逗号分隔
canal.instance.master.address=192.168.xxx.xxx:3306
canal.instance.master.journal.name=mysql-bin.000001
canal.instance.master.position=123439266
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/hhy_test
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
# topic改为实际
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,.*\\..*
#################################################
- 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
# zookeeper的ip
canal.zkServers = 192.168.xxx.xxx
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ,这里改为kafka
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.url = jdbc:mysql://127.0.0.1:3306/hhy_test
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.xxx.xxx: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 = canal
# 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"配置好之后重新启动canal，看日志不报错的话，离成功就很近了
这里我们打开kafka的消费
bin/kafka-console-consumer.sh --bootstrap-server 192.168.xxx.xxx:9092 --topic canal --from-beginning然后运行MySQL
insert into hhy_test.canal_test VALUES(1,'test',now())这里就会在消费端看到对应的数据出来
这个时候kafka出来的数据是json格式的，我们可以在java里进行处理(好像这是下一篇kafka要讲的事情，不管了，一篇全写完了！！！)
配置kafka的依赖
org.apache.kafka
kafka-clients
1.1.0
然后直接输入kafka的java控制消费端代码，网上这一类的代码非常多
package com.hhy.kafka;
import java.util.Collections;
import java.util.Properties;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import org.apache.kafka.clients.consumer.*;
import org.apache.kafka.common.serialization.StringDeserializer;
public class Consumer {
public static void main(String[] args) {
Properties p = new Properties();
p.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "192.168.xxx.xxx:9092");
p.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
p.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
p.put(ConsumerConfig.GROUP_ID_CONFIG, "canal");
KafkaConsumer kafkaConsumer = new KafkaConsumer(p);
kafkaConsumer.subscribe(Collections.singletonList(Producer.topic));// 订阅消息
while (true) {
ConsumerRecords records = kafkaConsumer.poll(100);
for (ConsumerRecord record : records) {
String value = record.value();
JSONObject obj = JSON.parseObject(value);
if ("INSERT".equalsIgnoreCase(obj.getString("type"))
&& "hhy_test".equalsIgnoreCase(obj.getString("database"))
&& "canal_test".equalsIgnoreCase(obj.getString("table"))) {
JSONArray dataArry = obj.getJSONArray("data");
if (dataArry != null && dataArry.size() > 0) {
for (int i = 0; i < dataArry.size(); i++) {
System.out.println(dataArry.getJSONObject(i).toJSONString());
}
}
}
}
}
}
} 运行结果出现
即为正常消费