官网地址
https://github.com/alibaba/canal
下载地址
https://github.com/alibaba/canal/releases
原理概述看官网
https://github.com/alibaba/canal/wiki

源码版本(当前最新稳定版1.1.4)

image.png

安装MySQL(建议5.7以上，这里略过..)
安装JDK1.8（这里略过..）

在mysql的安装目录修改配置

[mysqld]
#开启binlog
log-bin=mysql-bin 
#选择row模式 
binlog-format=ROW
#配置mysql replaction需要定义，不能和canal的slaveId重复 
server_id=1
#配置取出sql
binlog-rows-query-log-events=true
#设置minimal，binlog记录的只是影响后的数据，无法正常同步update
binlog_row_image=FULL

创建MySQL 用户，用于canal 可以dump mysql（canal 默认配置是canal）。

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

检查binlog是否开启
show variables like 'log_bin';
检查logformat 是否是ROW
show variables like 'binlog_format';
查看server_id
show variables like 'server_id';

下载安装canal.deployer-1.1.4.tar.gz

tar -zxvf canal.deployer-1.1.4.tar.gz -C /usr/local/canal

修改/usr/local/canal/conf/canal.properties

#################################################
#########       common argument     #############
#################################################
# tcp bind ip
#canal server绑定的本地IP信息，如果不配置，默认选择一个本机IP进行启动服务
canal.ip =
# register ip to zookeeper
canal.register.ip =
#canal server提供socket服务的端口
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 server链接zookeeper集群的链接信息
例子：127.0.0.1:2181,127.0.0.1:2182
canal.zkServers = 
# flush data to zk
#canal持久化数据到zookeeper上的更新频率，单位毫秒
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = tcp
# flush meta cursor/parse position to file
#canal持久化数据到file上的目录
canal.file.data.dir = ${canal.conf.dir}
#canal持久化数据到file上的更新频率，单位毫秒
canal.file.flush.period = 1000
## memory store RingBuffer size, should be Math.pow(2,n)
#canal内存store中可缓存buffer记录数，需要为2的指数
canal.instance.memory.buffer.size = 16384
## memory store RingBuffer used memory unit size , default 1kb
#内存记录的单位大小，默认1KB，和buffer.size组合决定最终的内存使用大小
canal.instance.memory.buffer.memunit = 1024 
## meory store gets mode used MEMSIZE or ITEMSIZE
#canal内存store中数据缓存模式
1. ITEMSIZE : 根据buffer.size进行限制，只限制记录的数量
2. MEMSIZE : 根据buffer.size * buffer.memunit的大小，限制缓存记录的大小
canal.instance.memory.batch.mode = MEMSIZE
#canal内存store中可缓存buffer记录数，需要为2的指数
canal.instance.memory.rawEntry = true

## detecing config
#是否开启心跳检查
canal.instance.detecting.enable = false
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
#心跳检查sql
canal.instance.detecting.sql = select 1
#心跳检查频率，单位秒
canal.instance.detecting.interval.time = 3
#心跳检查失败重试次数
canal.instance.detecting.retry.threshold = 3
#心跳检查失败后，是否开启自动mysql自动切换
说明：比如心跳检查失败超过阀值后，如果该配置为true，canal就会自动链到mysql备库获取binlog数据
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发生mysql切换时，在新的mysql库上查找binlog时需要往前查找的时间，单位秒
说明：mysql主备库可能存在解析延迟或者时钟不统一，需要回退一段时间，保证数据不丢
canal.instance.fallbackIntervalInSeconds = 60

# network config
#网络链接参数，SocketOptions.SO_RCVBUF
canal.instance.network.receiveBufferSize = 16384
#网络链接参数，SocketOptions.SO_SNDBUF
canal.instance.network.sendBufferSize = 16384
#网络链接参数，SocketOptions.SO_TIMEOUT
canal.instance.network.soTimeout = 30

# binlog filter config
#v1.0.25版本新增，是否启用druid的DDL parse的过滤，基于sql的完整parser可以解决之前基于正则匹配补全的问题，默认为true
canal.instance.filter.druid.ddl = true
#是否忽略DCL的query语句，比如grant/create user等
canal.instance.filter.query.dcl = false
#是否忽略DML的query语句，比如insert/update/delete table.(mysql5.6的ROW模式可以包含statement模式的query记录)
canal.instance.filter.query.dml = false
#是否忽略DDL的query语句，比如create table/alater table/drop table/rename table/create index/drop index. (目前支持的ddl类型主要为table级别的操作，create databases/trigger/procedure暂时划分为dcl类型)
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
#ddl语句是否隔离发送，开启隔离可保证每次只返回发送一条ddl数据，不和其他dml语句混合返回.(otter ddl同步使用)
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
#v1.0.25版本新增,table meta的时间序列版本的本地存储路径，默认为instance目录
canal.instance.tsdb.dir = ${canal.file.data.dir:../conf}/${canal.instance.destination:}
#v1.0.25版本新增,table meta的时间序列版本存储的数据库链接串，比如例子为本地嵌入式数据库
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 配置instance，可以配置多个用“,”分割
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 = 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"

配置instance.properties

#################################################
## mysql serverId , v1.0.26+ will autoGen
#mysql集群配置中的serverId概念，需要保证和当前mysql集群中id唯一
# canal.instance.mysql.slaveId=2222

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

# position info  mysql master链接地址 
canal.instance.master.address=192.168.1.115:3306
#mysql主库链接时起始的binlog文件
canal.instance.master.journal.name=
#mysql主库链接时起始的binlog偏移量
canal.instance.master.position=
#mysql主库链接时起始的binlog的时间戳
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
#v1.0.25版本新增,是否开启table meta的时间序列版本记录功能
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  连接数据库使用的账号密码
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/JM6LeHmiiNdH1FWgGCpUfircSw
lWKUCAwEAAQ==

# table regex  订阅库表正则（白名单表）
#mysql 数据解析关注的表，Perl正则表达式.
多个正则之间以逗号(,)分隔，转义符需要双斜杠(\\) 
常见例子：
1.  所有表：.*   or  .*\\..*
2.  canal schema下所有表： canal\\..*
3.  canal下的以canal打头的表：canal\\.canal.*
4.  canal schema下的一张表：canal.test1
5.  多个规则组合使用：canal\\..*,mysql.test1,mysql.test2 (逗号分隔)
注意：此过滤条件只针对row模式的数据有效(ps. mixed/statement因为不解析sql，所以无法准确提取tableName进行过滤)
canal.instance.filter.regex=.*\\..*
# table black regex  配置正则（黑名单表）
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=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,.*\\..*
#################################################

启动

image.png

查看日志

##tail -200f /usr/local/canal/logs/example/example.log
2020-12-21 02:47:51.308 [pool-2-thread-1] INFO  c.a.otter.canal.instance.spring.CanalInstanceWithSpring - start CannalInstance for 1-example 
2020-12-21 02:47:51.314 [pool-2-thread-1] WARN  c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table filter : ^.*\..*$
2020-12-21 02:47:51.315 [pool-2-thread-1] WARN  c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table black filter : 
2020-12-21 02:47:51.327 [pool-2-thread-1] INFO  c.a.otter.canal.instance.core.AbstractCanalInstance - subscribe filter change to .*\..*
2020-12-21 02:47:51.327 [pool-2-thread-1] WARN  c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table filter : ^.*\..*$
2020-12-21 02:47:51.327 [pool-2-thread-1] INFO  c.a.otter.canal.instance.core.AbstractCanalInstance - start successful....
2020-12-21 02:47:51.485 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN  c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - ---> begin to find start position, it will be long time for reset or first position
2020-12-21 02:47:51.529 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN  c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - prepare to find start position just last position
 {"identity":{"slaveId":-1,"sourceAddress":{"address":"docker_server","port":3306}},"postion":{"gtid":"","included":false,"journalName":"mysql-bin.000001","position":9846,"serverId":1,"timestamp":1608468374000}}
2020-12-21 02:47:51.981 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN  c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - ---> find start position successfully, EntryPosition[included=false,journalName=mysql-bin.000001,position=9846,serverId=1,gtid=,timestamp=1608468374000] cost : 479ms , the next step is binlog dump

创建canal-client服务

pom.xml引入

       <dependency>
            <groupId>com.alibaba.otter</groupId>
            <artifactId>canal.client</artifactId>
            <version>1.1.4</version>
        </dependency>

官网测试代码

public class ClientTest {
    //canal server地址
    private static String SERVER_ADDRESS="192.168.1.114";
   //服务端口
    private static int PORT = 11111;

    private static String DESTINATION="example";
    private static String USERNAME="";
    private static String PASSWORD="";

    public static void main(String[] args) {
        CanalConnector canalConnector = CanalConnectors.newSingleConnector(new InetSocketAddress(SERVER_ADDRESS,PORT),DESTINATION,USERNAME,PASSWORD);
        int emptyCount = 0;
        long batchId = 0l;
        try{
            canalConnector.connect();
            //订阅如果这里配置将覆盖服务端
            canalConnector.subscribe(".*\\..*");
            canalConnector.rollback();

            int totalEmptyCount = 1200;

            while (emptyCount < totalEmptyCount) {
                Message message = canalConnector.getWithoutAck(100); // 获取指定数量的数据
                batchId = message.getId();

                int size = message.getEntries().size();
                if (batchId == -1 || size == 0) {
                    emptyCount++;
                   // System.out.println("empty count : " + emptyCount);
                    try {
                        Thread.sleep(1000);
                    } catch (InterruptedException e) {
                    }
                } else {
                    emptyCount = 0;
                    // System.out.printf("message[batchId=%s,size=%s] \n", batchId, size);
                    printEntity(message.getEntries());
                  //  int i = 1/0;
                }
           
                canalConnector.ack(batchId); // 提交确认
                // connector.rollback(batchId); // 处理失败, 回滚数据
            }

            System.out.println("empty too many times, exit");
        }catch (Exception e){
            e.printStackTrace();
            if(batchId>0){
                canalConnector.rollback(batchId); // 处理失败, 回滚数据
            }
        }finally {
         
            canalConnector.disconnect();
        }

    }

    public static void printEntity(List<CanalEntry.Entry> list){
        for(CanalEntry.Entry entry : list){
            if(entry.getEntryType() != CanalEntry.EntryType.ROWDATA){
                continue;
            }

            try{
                CanalEntry.RowChange rowChange = CanalEntry.RowChange.parseFrom(entry.getStoreValue());
                System.out.println("sql--->"+rowChange.getSql());


                CanalEntry.EventType eventType = rowChange.getEventType();
                System.out.println(String.format("================&gt; binlog[%s:%s] , name[%s,%s] , eventType : %s",
                        entry.getHeader().getLogfileName(), entry.getHeader().getLogfileOffset(),
                        entry.getHeader().getSchemaName(), entry.getHeader().getTableName(),
                        eventType));

                for (CanalEntry.RowData rowData : rowChange.getRowDatasList()){
                    if (eventType == CanalEntry.EventType.DELETE) {
                        printColumn(rowData.getBeforeColumnsList());
                    } else if (eventType == CanalEntry.EventType.INSERT) {
                        printColumn(rowData.getAfterColumnsList());
                    } else {
                        System.out.println("-------&gt; before");
                        printColumn(rowData.getBeforeColumnsList());
                        System.out.println("-------&gt; after");
                        printColumn(rowData.getAfterColumnsList());
                    }
                }
            }catch (Exception e){
                e.printStackTrace();
            }
        }
    }

    private static void printColumn(List<CanalEntry.Column> columns) {
        for (CanalEntry.Column column : columns) {
            System.out.println(column.getName() + " : " + column.getValue() + "    update=" + column.getUpdated());
        }
    }