Canal介绍和使用指南

mysql> show variables like 'log_bin';
+---------------+-------+
| Variable_name | Value |
+---------------+-------+
| log_bin       | ON    |
+---------------+-------+

mysql> show variables like 'binlog_format';
+---------------+-------+
| Variable_name | Value |
+---------------+-------+
| binlog_format | ROW   |
+---------------+-------+

CREATE USER canal IDENTIFIED BY 'canal';  
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'%';
-- GRANT ALL PRIVILEGES ON *.* TO 'canal'@'%' ;
FLUSH PRIVILEGES;

bin
conf
lib
logs

#################################################
## 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

docker pull canal/canal-server:latest

git clone git@github.com:alibaba/canal.git
cd canal/docker && sh build.sh

docker run -d --name canal-server -p 11111:11111 canal/canal-server

docker exec -it canal-server /bin/bash

vi canal-server/conf/example/instance.properties

docker container restart canal-server

package main

import (
	"fmt"
	"time"

	pbe "github.com/Q1mi/canal-go/protocol/entry"

	"github.com/Q1mi/canal-go/client"
	"google.golang.org/protobuf/proto"
)

// canal-go client demo

func main() {
	// 连接canal-server
	// 请修改为你的 canal-server 配置
	connector := client.NewSimpleCanalConnector(
		"127.0.0.1", 11111, "", "", "example", 60000, 60*60*1000)
	err := connector.Connect()
	if err != nil {
		panic(err)
	}

	// mysql 数据解析关注的表，Perl正则表达式.
	err = connector.Subscribe(".*\\..*")
	if err != nil {
		fmt.Printf("connector.Subscribe failed, err:%v\n", err)
		panic(err)
	}

	// 消费消息
	for {
		message, err := connector.Get(100, nil, nil)
		if err != nil {
			fmt.Printf("connector.Get failed, err:%v\n", err)
			continue
		}
		batchId := message.Id
		if batchId == -1 || len(message.Entries) <= 0 {
			time.Sleep(time.Second)
			fmt.Println("===暂无数据===")
			continue
		}
		printEntry(message.Entries)
	}
}

func printEntry(entries []*pbe.Entry) {
	for _, entry := range entries {
		// 忽略事务开启和事务关闭类型
		if entry.GetEntryType() == pbe.EntryType_TRANSACTIONBEGIN ||
			entry.GetEntryType() == pbe.EntryType_TRANSACTIONEND {
			continue
		}
		// RowChange对象，包含了一行数据变化的所有特征
		rowChange := new(pbe.RowChange)
		// protobuf解析
		err := proto.Unmarshal(entry.GetStoreValue(), rowChange)
		if err != nil {
			fmt.Printf("proto.Unmarshal failed, err:%v\n", err)
		}
		if rowChange == nil {
			continue
		}
		// 获取并打印Header信息
		header := entry.GetHeader()
		fmt.Printf("binlog[%s : %d], name[%s,%s], eventType: %s\n",
			header.GetLogfileName(),
			header.GetLogfileOffset(),
			header.GetSchemaName(),
			header.GetTableName(),
			header.GetEventType(),
		)
		//判断是否为DDL语句
		if rowChange.GetIsDdl() {
			fmt.Printf("isDdl:true, sql:%v\n", rowChange.GetSql())
		}

		// 获取操作类型：insert/update/delete等
		eventType := rowChange.GetEventType()
		for _, rowData := range rowChange.GetRowDatas() {
			if eventType == pbe.EventType_DELETE {
				printColumn(rowData.GetBeforeColumns())
			} else if eventType == pbe.EventType_INSERT || eventType == pbe.EventType_UPDATE {
				printColumn(rowData.GetAfterColumns())
			} else {
				fmt.Println("---before---")
				printColumn(rowData.GetBeforeColumns())
				fmt.Println("---after---")
				printColumn(rowData.GetAfterColumns())
			}
		}
	}
}

func printColumn(columns []*pbe.Column) {
	for _, col := range columns {
		fmt.Printf("%s:%s  updated=%v\n", col.GetName(), col.GetValue(), col.GetUpdated())
	}
}

#  按需修改成自己的数据库信息
#################################################
...
canal.instance.master.address=127.0.0.1:3306
# username/password,数据库的用户名和密码
...
canal.instance.dbUsername = canal
canal.instance.dbPassword = canal
...
# mq config
# 设置默认的topic
canal.mq.topic=example
# 针对库名或者表名发送动态topic
#canal.mq.dynamicTopic=mytest,.*,mytest.user,mytest\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#库名.表名: 唯一主键，多个表之间用逗号分隔
#canal.mq.partitionHash=mytest.person:id,mytest.role:id
#################################################

# ...
# 可选项: tcp(默认), kafka,RocketMQ,rabbitmq,pulsarmq
canal.serverMode = kafka
# ...

# 是否为flat json格式对象
canal.mq.flatMessage = true
# Canal的batch size, 默认50K, 由于kafka最大消息体限制请勿超过1M(900K以下)
canal.mq.canalBatchSize = 50
# Canal get数据的超时时间, 单位: 毫秒, 空为不限超时
canal.mq.canalGetTimeout = 100
canal.mq.accessChannel = local

...

##################################################
#########                    Kafka                   #############
##################################################
# 此处配置修改为你的Kafka环境地址
kafka.bootstrap.servers = 127.0.0.1:9092
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

# sasl demo
# kafka.sasl.jaas.config = org.apache.kafka.common.security.scram.ScramLoginModule required \\n username=\"alice\" \\npassword="alice-secret\";
# kafka.sasl.mechanism = SCRAM-SHA-512
# kafka.security.protocol = SASL_PLAINTEXT