Canal基础

Canal模拟MySQL Slave的交互协议伪装自己为MySQL Slave，向MySQL Master发送Dump协议MySQL Master收到Dump请求，开始推送Binary Log给Slave即Canal，Canal解析Binary Log对象，原始为byte流。

安装配置

cd /usr/local
mkdir canal
tar -zxvf canal.deployer-1.1.5.tar.gz
vim conf/example/instance.properties

# 修改mysql配置
vim /etc/my.cnf
log-bin=mysql-bin  # 添加这一行就ok 
binlog-format=ROW  # 选择row模式 
server-id=1        # 配置mysql replaction需要定义，不能和canal的slaveId重复
binlog-do-db=micromall

# 执行mysql 创建canal用户
create user canal identified by 'canal';
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'%';
FLUSH PRIVILEGES;
# 查看是否授权成功
select * from user where user='canal' 

# 启动canal
cd bin
./startup.sh

基础配置

修改instance.properties配置文件

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

#canal.instance.standby.address =
#canal.instance.standby.journal.name =
#canal.instance.standby.position =
#canal.instance.standby.timestamp =
#canal.instance.standby.gtid=

# 数据库username/password
canal.instance.dbUsername=root
canal.instance.dbPassword=root
canal.instance.connectionCharset = UTF-8
canal.instance.defaultDatabaseName=eleven
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==

# table regex
# canal.instance.filter.regex=.*\\..*
# 配置表
canal.instance.filter.regex=micromall.pms_product,micromall.sms_flash_promotion_product_relation
# 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
# 消息队列Topic
canal.mq.topic=productDetailChange
# 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

修改canal.properties配置文件

#################################################
######### 		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
# admin auto register
#canal.admin.register.auto = true
#canal.admin.register.cluster =
#canal.admin.register.name =

canal.zkServers =
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ
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
canal.instance.filter.dml.insert = false
canal.instance.filter.dml.update = false
canal.instance.filter.dml.delete = 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
# set this value to 'true' means that when binlog pos not found, skip to latest.
# WARN: pls keep 'false' in production env, or if you know what you want.
canal.auto.reset.latest.pos.mode = false

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 = 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"

##################################################
######### 		    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
rocketmq.tag = 

##################################################
######### 		    RabbitMQ	     #############
##################################################
rabbitmq.host =
rabbitmq.virtual.host =
rabbitmq.exchange =
rabbitmq.username =
rabbitmq.password =
rabbitmq.deliveryMode =

Canal内部原理

Canal源码入口AbstractEventParser的start方法

• server代表一个canal运行实例，对应于一个jvm
• instance对应于一个数据队列 （1个server对应1..n个instance)
• eventParser (数据源接入，模拟slave协议和master进行交互，协议解析)
• eventSink (Parser和Store链接器，进行数据过滤，加工，分发的工作)
• eventStore (数据存储)
• metaManager (增量订阅&消费信息管理器)

Canal集群高可用

Canal的HA分为Canal Server和Canal Client两部分实现，整个HA机制的控制主要是依赖了Zookeeper的几个特性，watcher和EPHEMERAL节点和session生命周期绑定。

• Canal Server：为了减少对MySQL Dump的请求，不同Server上的instance要求同一时间只能有一个处于Running，其他的处于Standby状态
• Canal Client：为了保证有序性，一份instance同一时间只能由一个Canal Client进行get/ack/rollback操作，否则客户端接收无法保证有序

Canal Server要启动某个Canal instance时都先向Zookeeper进行一次尝试启动判断，创建EPHEMERAL临时节点，谁创建成功就允许谁启动

创建Zookeeper节点成功后，对应的Canal Server就启动对应的Canal instance，没有创建成功的Canal instance就会处于Standby状态

一旦Zookeeper发现Canal Server A创建的节点消失后，立即通知其他的Canal Server再次进行步骤1的操作，重新选出一个Canal Server启动instance.

Canal Client每次进行connect时，会首先向Zookeeper询问当前是谁启动了Canal instance，然后和其建立链接，一旦链接不可用，会重新尝试connect.

Canal Client的方式和Canal Server方式类似，也是利用Zookeeper的抢占EPHEMERAL节点的方式进行控制。

使用

<dependency>
    <groupId>com.alibaba.otter</groupId>
    <artifactId>canal.client</artifactId>
    <version>1.1.3</version>
</dependency>

@Component
@RocketMQMessageListener(topic = "${rocketmq.canal.topic}", consumerGroup = "${rocketmq.canal.group}")
public class RefreshCacheListener implements RocketMQListener<FlatMessage> {
    @Autowired
    private RedisOpsUtil redisOpsUtil;
    private final static String PRODUCT = "pms_product";
    private final static String SKU = "pms_sku_stock";
    @Override
    public void onMessage(FlatMessage flatMessage) {
        //修改后的新记录
        List<Map<String, String>> records = flatMessage.getData();
        //修改前的数据
        List<Map<String, String>> old = flatMessage.getOld();
    }
}

public class SimpleCanalClientExample {
    public static void main(String args[]) {
        // 创建链接
        CanalConnector connector = CanalConnectors.newSingleConnector(new InetSocketAddress("127.0.0.1", 11111), "example", "", "");
        int batchSize = 1000;
        int emptyCount = 0;
        try {
            connector.connect();
            connector.subscribe(".*\\..*");
            connector.rollback();
            int totalEmptyCount = 120;
            while (emptyCount < totalEmptyCount) {
                Message message = connector.getWithoutAck(batchSize); // 获取指定数量的数据
                long 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);
                    printEntry(message.getEntries());
                }

                connector.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");
        } finally {
            connector.disconnect();
        }
    }

    private static void printEntry(List<Entry> entrys) {
        for (Entry entry : entrys) {
            if (entry.getEntryType() == EntryType.TRANSACTIONBEGIN || entry.getEntryType() == EntryType.TRANSACTIONEND) {
                continue;
            }
            RowChange rowChage = null;
            try {
                rowChage = RowChange.parseFrom(entry.getStoreValue());
            } catch (Exception e) {
                throw new RuntimeException("ERROR ## parser of eromanga-event has an error , data:" + entry.toString(), e);
            }
            EventType eventType = rowChage.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 (RowData rowData : rowChage.getRowDatasList()) {
                if (eventType == EventType.DELETE) {
                    printColumn(rowData.getBeforeColumnsList());
                } else if (eventType == EventType.INSERT) {
                    printColumn(rowData.getAfterColumnsList());
                } else {
                    System.out.println("-------&gt; before");
                    printColumn(rowData.getBeforeColumnsList());
                    System.out.println("-------&gt; after");
                    printColumn(rowData.getAfterColumnsList());
                }
            }
        }
    }

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