*使用canal采集mysql的binlog，输出到kafka，然后使用flinksql消费kafka，并输出到屏幕
- mysql需要开始binlog
- canal 会将数据库创建语句采集到，type为QUERY类型flink报错*
在docker中创建 myslq、zookeeper、kafka
1、mysql
sudo docker run -p 3306:3306 --name mysql \
-v /home/jaming/docker_work/mysql/conf:/etc/mysql \
-v /home/jaming/docker_work/mysql/logs:/var/log/mysql \
-v /home/jaming/docker_work/mysql/data:/var/lib/mysql \
-e MYSQL_ROOT_PASSWORD=root \
-d mysql:5.7
2、kafka、zookeeper
随便搜一个
mysql开启binlog
1、vim /home/jaming/docker_work/mysql/conf/my.cnf
[mysqld]
log-bin = /var/lib/mysql/mysql-bin.log
expire-logs-days = 14
max-binlog-size = 500M
server-id = 1
2、docker查看mysql的binlog开启是否成功
- docker exec -it mysql /bin/bash
- mysql -uroot -proot
- 执行sql语句 show variables like 'log_bin';
canal配置
版本：canal.deployer-1.1.5-SNAPSHOT.tar.gz
1、vim /home/jaming/software/canal/conf/example/instance.properties
#################################################
## mysql serverId , v1.0.26+ will autoGen
canal.instance.mysql.slaveId=1234
# enable gtid use true/false
canal.instance.gtidon=false
# position info
canal.instance.master.address=localhost: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://localhost:3306/canal
#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=mysql\\.slave_.*
# 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_mysql_dml
# 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.mq.dynamicTopicPartitionNum=test.*:4,mycanal:6
#################################################
2、vim /home/jaming/software/canal/conf/canal.properties
#################################################
######### common argument #############
#################################################
# tcp bind ip
canal.ip = 192.168.1.30
# register ip to zookeeper
canal.register.ip = 192.168.1.30
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 = 192.168.1.30:2181
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ
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 = true
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
#################################################
######### 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 Properties #############
##################################################
# aliyun ak/sk , support rds/mq
canal.aliyun.accessKey =
canal.aliyun.secretKey =
canal.aliyun.uid=
canal.mq.flatMessage = true
canal.mq.canalBatchSize = 50
canal.mq.canalGetTimeout = 100
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.accessChannel = local
canal.mq.database.hash = true
canal.mq.send.thread.size = 30
canal.mq.build.thread.size = 8
##################################################
######### Kafka #############
##################################################
kafka.bootstrap.servers = 192.168.1.30:9092
kafka.acks = all
kafka.compression.type = none
kafka.batch.size = 16384
kafka.linger.ms = 1
kafka.max.request.size = 1048576
kafka.buffer.memory = 33554432
kafka.max.in.flight.requests.per.connection = 1
kafka.retries = 0
kafka.kerberos.enable = false
kafka.kerberos.krb5.file = "../conf/kerberos/krb5.conf"
kafka.kerberos.jaas.file = "../conf/kerberos/jaas.conf"
##################################################
######### RocketMQ #############
##################################################
rocketmq.producer.group = test
rocketmq.enable.message.trace = false
rocketmq.customized.trace.topic =
rocketmq.namespace =
rocketmq.namesrv.addr = 127.0.0.1:9876
rocketmq.retry.times.when.send.failed = 0
rocketmq.vip.channel.enabled = false
##################################################
######### RabbitMQ #############
##################################################
rabbitmq.host =
rabbitmq.virtual.host =
rabbitmq.exchange =
rabbitmq.username =
rabbitmq.password =
启动mysql、zookeeper、kafka
略。。。。
编写程序
- pom.xml
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>${flink.version}</version>
<!-- <scope>provided</scope>-->
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<!-- <scope>provided</scope>-->
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<!-- <scope>provided</scope>-->
</dependency>
<!-- Add connector dependencies here. They must be in the default scope (compile). -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- Add logging framework, to produce console output when running in the IDE. -->
<!-- These dependencies are excluded from the application JAR by default. -->
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-statebackend-rocksdb_2.11</artifactId>
<version>${flink.version}</version>
<!-- <scope>provided</scope>-->
</dependency>
<!-- <dependency>-->
<!-- <groupId>org.apache.flink</groupId>-->
<!-- <artifactId>flink-sql-connector-hive-3.1.2_${scala.binary.version}</artifactId>-->
<!-- <version>${flink.version}</version>-->
<!-- </dependency>-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-parquet_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-api-java-bridge_2.11</artifactId>
<version>1.12.0</version>
<!-- <scope>provided</scope>-->
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-planner-blink_2.11</artifactId>
<version>1.12.0</version>
<!-- <scope>provided</scope>-->
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_2.11</artifactId>
<version>1.12.0</version>
<!-- <scope>provided</scope>-->
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-json</artifactId>
<version>1.12.0</version>
<!-- <scope>provided</scope>-->
</dependency>
- code
package com.jaming.flinktest.table;
import com.jaming.flinktest.bean.Stu;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.EnvironmentSettings;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
public class TestMysql {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
EnvironmentSettings settings = EnvironmentSettings.newInstance().inStreamingMode().useBlinkPlanner().build();
StreamTableEnvironment tenv = StreamTableEnvironment.create(env, settings);
String kafka_table = " CREATE TABLE canal_table ( `id` INT, `myname` STRING" +
") WITH ( " +
" 'connector' = 'kafka', " +
" 'topic' = 'canal_mysql_dml', " +
" 'properties.bootstrap.servers' = 'localhost:9092', " +
" 'properties.group.id' = 'testGroup', " +
" 'scan.startup.mode' = 'earliest-offset', " +
" 'format' = 'canal-json'" +
")";
tenv.executeSql(kafka_table);
Table table = tenv.sqlQuery("select * from canal_table");
DataStream<Tuple2<Boolean, Stu>> dataStream = tenv.toRetractStream(table, Stu.class);
dataStream.print();
env.execute();
}
}
package com.jaming.flinktest.bean;
import java.io.Serializable;
public class Stu implements Serializable {
int id;
String myname;
public int getId() {
return id;
}
public void setId(int id) {
this.id = id;
}
public String getMyname() {
return myname;
}
public void setMyname(String myname) {
this.myname = myname;
}
@Override
public String toString() {
return "Stu{" +
"id=" + id +
", myname='" + myname + '\'' +
'}';
}
}
向表中插入数据、更新数据，显示结果
7> (true,Stu{id=2, myname='aaa'})
7> (false,Stu{id=2, myname='aaa'})
7> (true,Stu{id=2, myname='bbb'})
7> (true,Stu{id=3, myname='333333'})
