无锡做企业网站的公司,网站默认后台,各大网站提交入口网址,网络推广 深圳文章目录一、Canal介绍工作原理canal 工作原理二、下载三、安装使用Mysql准备canal 安装解压缩 canal-deployer配置修改启动查看server日志查看instance日志服务停止canal-client使用Canal Adapter数据同步Hbase数据同步ElasticSearch一、Canal介绍
早期阿里巴巴因为杭州和美国…
文章目录一、Canal介绍工作原理canal 工作原理二、下载三、安装使用Mysql准备canal 安装解压缩 canal-deployer配置修改启动查看server日志查看instance日志服务停止canal-client使用Canal Adapter数据同步Hbase数据同步ElasticSearch一、Canal介绍
早期阿里巴巴因为杭州和美国双机房部署存在跨机房同步的业务需求实现方式主要是基于业务 trigger 获取增量变更。从 2010 年开始业务逐步尝试数据库日志解析获取增量变更进行同步由此衍生出了大量的数据库增量订阅和消费业务。
基于日志增量订阅和消费的业务包括
数据库镜像数据库实时备份索引构建和实时维护(拆分异构索引、倒排索引等)业务 cache 刷新带业务逻辑的增量数据处理 当前的 canal 支持源端 MySQL 版本包括 5.1.x , 5.5.x , 5.6.x , 5.7.x , 8.0.x
工作原理 MySQL master 将数据变更写入二进制日志( binary log, 其中记录叫做二进制日志事件binary log events可以通过 show binlog events 进行查看)MySQL slave 将 master 的 binary log events 拷贝到它的中继日志(relay log)MySQL slave 重放 relay log 中事件将数据变更反映它自己的数据
canal 工作原理
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)
GitHub https://github.com/alibaba/canal
二、下载
下载地址https://github.com/alibaba/canal/tags 这里我们使用 v1.1.5版本 点击下载
网盘地址
链接: https://pan.baidu.com/s/1VjIzpb79d05CET5xEnwdEQ
提取码: h0bk 三、安装使用
Mysql准备
对于自建 MySQL , 需要先开启 Binlog 写入功能配置 binlog-format 为 ROW 模式my.cnf 中配置如下
[mysqld]
log-binmysql-bin # 开启 binlog
binlog-formatROW # 选择 ROW 模式
server_id1 # 配置 MySQL replaction 需要定义不要和 canal 的 slaveId 重复授权 canal 链接 MySQL 账号具有作为 MySQL slave 的权限, 如果已有账户可直接 grant
CREATE USER canal IDENTIFIED BY canal;
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO canal%;
-- GRANT ALL PRIVILEGES ON *.* TO canal% ;
FLUSH PRIVILEGES;canal 安装
解压缩 canal-deployer
tar -zxvf canal.deployer-1.1.5.tar.gz 解压后目录结构如下
drwxr-xr-x 2 root root 76 Sep 18 16:58 bin
drwxr-xr-x 5 root root 123 Sep 18 16:58 conf
drwxr-xr-x 2 root root 4096 Sep 18 16:58 lib
drwxrwxrwx 2 root root 6 Apr 19 16:15 logs
drwxrwxrwx 2 root root 177 Apr 19 16:15 plugin配置修改
修改 confg/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进行启动服务默认:无
canal.ip
# register ip to zookeeper
# 运行canal-server服务的主机IP可以不用配置他会自动绑定一个本机的IP
canal.register.ip
# canal-server监听的端口TCP模式下非TCP模式不监听1111端口
canal.port 11111
# canal-server metrics.pull监听的端口
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 server 链接zookeeper集群的链接信息集群模式下要配置zookeeper进行协调配置单机模式可以不用配置
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, rabbitMQ canal-server运行的模式TCP模式就是直连客户端不经过中间件。kafka和mq是消息队列的模式
canal.serverMode tcp
# flush meta cursor/parse position to file 存放数据的路径
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 下面是一些系统参数的配置包括内存、网络等
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 这里是心跳检查的配置做HA时会用到
canal.instance.detecting.enable false
#canal.instance.detecting.sql insert into retl.xdual values(1,now()) on duplicate key update xnow()
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 binlog过滤的配置指定过滤那些SQL
canal.instance.filter.druid.ddl true
# 是否忽略DCL的query语句比如grant/create user等默认false
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),默认false
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),默认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 binlog格式检测使用ROW模式非ROW模式也不会报错但是同步不到数据
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 并行解析配置如果是单个CPU就把下面这个true改为false
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_SIZE1000;MODEMYSQL;
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-server创建的实例在这里指定你要创建的实例的名字比如test1test2等逗号隔开
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 falsecanal.instance.tsdb.spring.xml classpath:spring/tsdb/h2-tsdb.xml
#canal.instance.tsdb.spring.xml classpath:spring/tsdb/mysql-tsdb.xmlcanal.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.uidcanal.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 localcanal.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 0kafka.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 修改example配置 在 confg/canal.properties配置了实例后需要在根配置的同级目录下创建该实例目录并创建文件 instance.properties。example是官方给的Demo 内容如下
#################################################
## mysql serverId , v1.0.26 will autoGen
## v1.0.26版本后会自动生成slaveId所以可以不用配置
# canal.instance.mysql.slaveId0# enable gtid use true/false
canal.instance.gtidonfalse# position info
# 数据库地址
canal.instance.master.address127.0.0.1:3306
# binlog日志名称
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
canal.instance.tsdb.enabletrue
#canal.instance.tsdb.urljdbc:mysql://127.0.0.1:3306/canal_tsdb
#canal.instance.tsdb.dbUsernamecanal
#canal.instance.tsdb.dbPasswordcanal#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.dbUsernamecanal
canal.instance.dbPasswordcanal
# canal.instance.connectionCharset 代表数据库的编码方式对应到 java 中的编码类型比如 UTF-8GBK , ISO-8859-1
canal.instance.connectionCharset UTF-8
# enable druid Decrypt database password
canal.instance.enableDruidfalse
#canal.instance.pwdPublicKeyMFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ# table regex
# 配置监听支持正则表达式
# 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)
# 这个是比较重要的参数匹配库表白名单比如我只要test库的user表的增量数据则这样写 test.user
canal.instance.filter.regex.*\\..*
# table black regex
# 配置不监听支持正则表达式
canal.instance.filter.black.regexmysql\\.slave_.*
# table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.fieldtest1.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.fieldtest1.t_product:subject/product_image,test2.t_company:id/name/contact/ch# mq config
canal.mq.topicexample
# dynamic topic route by schema or table regex
#canal.mq.dynamicTopicmytest1.user,mytest2\\..*,.*\\..*
canal.mq.partition0
# hash partition config
#canal.mq.partitionsNum3
#canal.mq.partitionHashtest.table:id^name,.*\\..*
#canal.mq.dynamicTopicPartitionNumtest.*:4,mycanal:6
#################################################
启动
sh bin/startup.sh 查看server日志
# tailf logs/canal/canal.log
2021-09-19 09:38:26.746 [main] INFO com.alibaba.otter.canal.deployer.CanalLauncher - ## set default uncaught exception handler
2021-09-19 09:38:26.793 [main] INFO com.alibaba.otter.canal.deployer.CanalLauncher - ## load canal configurations
2021-09-19 09:38:26.812 [main] INFO com.alibaba.otter.canal.deployer.CanalStarter - ## start the canal server.
2021-09-19 09:38:26.874 [main] INFO com.alibaba.otter.canal.deployer.CanalController - ## start the canal server[192.168.168.2(192.168.168.2):11111]
2021-09-19 09:38:28.240 [main] INFO com.alibaba.otter.canal.deployer.CanalStarter - ## the canal server is running now ......
查看instance日志
# tailf logs/example/example.log
2021-09-19 09:38:28.191 [main] INFO c.a.otter.canal.instance.spring.CanalInstanceWithSpring - start CannalInstance for 1-example
2021-09-19 09:38:28.202 [main] WARN c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - -- init table filter : ^.*\..*$
2021-09-19 09:38:28.202 [main] WARN c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - -- init table black filter : ^mysql\.slave_.*$
2021-09-19 09:38:28.207 [main] INFO c.a.otter.canal.instance.core.AbstractCanalInstance - start successful....服务停止
sh bin/stop.shcanal-client使用
manve引用
dependencygroupIdcom.alibaba.otter/groupIdartifactIdcanal.client/artifactIdversion1.1.0/version/dependencyClientSample.java import java.net.InetSocketAddress;
import java.util.List;import com.alibaba.otter.canal.client.CanalConnectors;
import com.alibaba.otter.canal.client.CanalConnector;
import com.alibaba.otter.canal.common.utils.AddressUtils;
import com.alibaba.otter.canal.protocol.Message;
import com.alibaba.otter.canal.protocol.CanalEntry.Column;
import com.alibaba.otter.canal.protocol.CanalEntry.Entry;
import com.alibaba.otter.canal.protocol.CanalEntry.EntryType;
import com.alibaba.otter.canal.protocol.CanalEntry.EventType;
import com.alibaba.otter.canal.protocol.CanalEntry.RowChange;
import com.alibaba.otter.canal.protocol.CanalEntry.RowData;
/*** author Jast* description* date 2021-09-19 09:43*/
public class ClientSample {public static void main(String args[]) {// 创建链接
// CanalConnector connector CanalConnectors.newSingleConnector(new InetSocketAddress(AddressUtils.getHostIp(),
// 11111), example, , );CanalConnector connector CanalConnectors.newSingleConnector(new InetSocketAddress(192.168.168.2,11111), 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(ListEntry 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(ListColumn columns) {for (Column column : columns) {System.out.println(column.getName() : column.getValue() update column.getUpdated());}}}此时数据库相关操作会在控制台输出
gt; binlog[mysql-bin.000003:834] , name[mysql,test] , eventType : CREATECanal Adapter
解压压缩包
mkdir canal-adapter tar -zxvf canal.adapter-1.1.5.tar.gz -C canal-adapter数据同步Hbase
1.修改启动器配置{canal-apapter}/conf/application.yml
server:port: 8081
logging:level:com.alibaba.otter.canal.client.adapter: DEBUGcom.alibaba.otter.canal.client.adapter.hbase: DEBUG
spring:jackson:date-format: yyyy-MM-dd HH:mm:sstime-zone: GMT8default-property-inclusion: non_null
canal.conf:# tcp kafka rocketMQ rabbitMQ canal-server运行的模式TCP模式就是直连客户端不经过中间件。kafka和mq是消息队列的模式mode: tcp
# flatMessage: truezookeeperHosts: syncBatchSize: 1retries: 0timeout: 1000accessKey:secretKey:consumerProperties:# canal tcp consumer 指定canal-server的地址和端口canal.tcp.server.host: 127.0.0.1:11111canal.tcp.zookeeper.hosts: 127.0.0.1:2181canal.tcp.batch.size: 1canal.tcp.username:canal.tcp.password:srcDataSources: # 数据源配置从哪里获取数据defaultDS: # 指定一个名字在ES的配置中会用到唯一url: jdbc:mysql://127.0.0.1:3306/test2?useUnicodetrueusername: rootpassword: *****canalAdapters:- instance: example # canal instance Name or mq topic name 指定在canal配置的实例名称groups:- groupId: g1 outerAdapters:- name: logger
# - name: rdb
# key: mysql1
# properties:
# jdbc.driverClassName: com.mysql.jdbc.Driver
# jdbc.url: jdbc:mysql://127.0.0.1:3306/mytest2?useUnicodetrue
# jdbc.username: root
# jdbc.password: 121212
# - name: rdb
# key: oracle1
# properties:
# jdbc.driverClassName: oracle.jdbc.OracleDriver
# jdbc.url: jdbc:oracle:thin:localhost:49161:XE
# jdbc.username: mytest
# jdbc.password: m121212
# - name: rdb
# key: postgres1
# properties:
# jdbc.driverClassName: org.postgresql.Driver
# jdbc.url: jdbc:postgresql://localhost:5432/postgres
# jdbc.username: postgres
# jdbc.password: 121212
# threads: 1
# commitSize: 3000- name: hbase # config目录下的子目录名称properties:hbase.zookeeper.quorum: sangfor.abdi.node3,sangfor.abdi.node2,sangfor.abdi.node1hbase.zookeeper.property.clientPort: 2181zookeeper.znode.parent: /hbase-unsecure # 这里是hbase在Zookeeper元信息的目录
# - name: es7
# hosts: 127.0.0.1:9300 # 127.0.0.1:9200 for rest mode
# properties:
# mode: transport # or rest
# # security.auth: test:123456 # only used for rest mode
# cluster.name: my_application
# - name: kudu
# key: kudu
# properties:
# kudu.master.address: 127.0.0.1 # , split multi address
注意adapter将会自动加载 conf/hbase 下的所有.yml结尾的配置文件
2.Hbase表映射文件 修改 conf/hbase/mytest_person.yml文件:
dataSourceKey: defaultDS # 对应application.yml中的datasourceConfigs下的配置
destination: example # 对应tcp模式下的canal instance或者MQ模式下的topic
groupId: # !!! 注意,同步Hbase数据这里groupId不要填写内容对应MQ模式下的groupId, 只会同步对应groupId的数据
hbaseMapping: # mysql--HBase的单表映射配置mode: STRING # HBase中的存储类型, 默认统一存为String, 可选: #PHOENIX #NATIVE #STRING # NATIVE: 以java类型为主, PHOENIX: 将类型转换为Phoenix对应的类型destination: example # 对应 canal destination/MQ topic 名称database: mytest # 数据库名/schema名table: person # 表名hbaseTable: MYTEST.PERSON # HBase表名family: CF # 默认统一Column Family名称uppercaseQualifier: true # 字段名转大写, 默认为truecommitBatch: 3000 # 批量提交的大小, ETL中用到#rowKey: id,type # 复合字段rowKey不能和columns中的rowKey并存# 复合rowKey会以 | 分隔columns: # 字段映射, 如果不配置将自动映射所有字段, # 并取第一个字段为rowKey, HBase字段名以mysql字段名为主id: ROWKE name: CF:NAMEemail: EMAIL # 如果column family为默认CF, 则可以省略type: # 如果HBase字段和mysql字段名一致, 则可以省略c_time: birthday:
注意: 如果涉及到类型转换,可以如下形式:
...columns: id: ROWKE$STRING ... type: TYPE$BYTE ...
类型转换涉及到Java类型和Phoenix类型两种, 分别定义如下:
#Java 类型转换, 对应配置 mode: NATIVE
$DEFAULT
$STRING
$INTEGER
$LONG
$SHORT
$BOOLEAN
$FLOAT
$DOUBLE
$BIGDECIMAL
$DATE
$BYTE
$BYTES
#Phoenix 类型转换, 对应配置 mode: PHOENIX
$DEFAULT 对应PHOENIX里的VARCHAR
$UNSIGNED_INT 对应PHOENIX里的UNSIGNED_INT 4字节
$UNSIGNED_LONG 对应PHOENIX里的UNSIGNED_LONG 8字节
$UNSIGNED_TINYINT 对应PHOENIX里的UNSIGNED_TINYINT 1字节
$UNSIGNED_SMALLINT 对应PHOENIX里的UNSIGNED_SMALLINT 2字节
$UNSIGNED_FLOAT 对应PHOENIX里的UNSIGNED_FLOAT 4字节
$UNSIGNED_DOUBLE 对应PHOENIX里的UNSIGNED_DOUBLE 8字节
$INTEGER 对应PHOENIX里的INTEGER 4字节
$BIGINT 对应PHOENIX里的BIGINT 8字节
$TINYINT 对应PHOENIX里的TINYINT 1字节
$SMALLINT 对应PHOENIX里的SMALLINT 2字节
$FLOAT 对应PHOENIX里的FLOAT 4字节
$DOUBLE 对应PHOENIX里的DOUBLE 8字节
$BOOLEAN 对应PHOENIX里的BOOLEAN 1字节
$TIME 对应PHOENIX里的TIME 8字节
$DATE 对应PHOENIX里的DATE 8字节
$TIMESTAMP 对应PHOENIX里的TIMESTAMP 12字节
$UNSIGNED_TIME 对应PHOENIX里的UNSIGNED_TIME 8字节
$UNSIGNED_DATE 对应PHOENIX里的UNSIGNED_DATE 8字节
$UNSIGNED_TIMESTAMP 对应PHOENIX里的UNSIGNED_TIMESTAMP 12字节
$VARCHAR 对应PHOENIX里的VARCHAR 动态长度
$VARBINARY 对应PHOENIX里的VARBINARY 动态长度
$DECIMAL 对应PHOENIX里的DECIMAL 动态长度
如果不配置将以java对象原生类型默认映射转换
3.启动服务
启动bin/startup.sh
停止bin/stop.sh
重启bin/restart.sh
日志目录logs/adapter/adapter.log 4.验证服务 往mysql插入数据
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());日志内容,可以看出我们写入的数据已获取到
2021-09-20 12:35:09.682 [pool-1-thread-1] INFO c.a.o.canal.client.adapter.logger.LoggerAdapterExample - DML: {data:[{id:2286ed67-19cc-11ec-bbe0-708cb6f5eaa6,name:2286ed83-19cc-11ec-bbe0-708cb6f5eaa6,age:2,age_2:null,message:null,insert_time:1632112508000}],database:test2,destination:example,es:1632112508000,groupId:g1,isDdl:false,old:null,pkNames:[id],sql:,table:testsync,ts:1632112509680,type:INSERT}
2021-09-20 12:35:09.689 [pool-1-thread-1] DEBUG c.a.o.c.client.adapter.hbase.service.HbaseSyncService - DML: {data:[{id:2286ed67-19cc-11ec-bbe0-708cb6f5eaa6,name:2286ed83-19cc-11ec-bbe0-708cb6f5eaa6,age:2,age_2:null,message:null,insert_time:1632112508000}],database:test2,destination:example,es:1632112508000,groupId:g1,isDdl:false,old:null,pkNames:[id],sql:,table:testsync,ts:1632112509680,type:INSERT}查看Hbase表中的数据发现写入成功
hbase(main):036:0 scan testsync,{LIMIT1}
ROW COLUMNCELL 226ba6e8-19cc-11ec-bbe0-708c columnCF:AGE, timestamp2021-09-20T12:35:08.548, value2 b6f5eaa6 226ba6e8-19cc-11ec-bbe0-708c columnCF:INSERT_TIME, timestamp2021-09-20T12:35:08.548, value2021-09-20 12:35:08.0b6f5eaa6 226ba6e8-19cc-11ec-bbe0-708c columnCF:NAME, timestamp2021-09-20T12:35:08.548, value226ba718-19cc-11ec-bbe0-708cb6f5eaa6 b6f5eaa6
1 row(s)
Took 0.0347 seconds PS: 这个环节有个问题卡住很久日志打印出数据实际Hbase就是无法成功写入。解决方法参考https://blog.csdn.net/zhangshenghang/article/details/120411341
数据同步ElasticSearch
我们接着在之前配置Hbase基础上直接修改配置实现同时同步ElasticSearch
1.修改启动器配置 {canal-apapter}/conf/application.yml
server:port: 8081
logging:level:com.alibaba.otter.canal.client.adapter: DEBUGcom.alibaba.otter.canal.client.adapter.hbase: DEBUG
spring:jackson:date-format: yyyy-MM-dd HH:mm:sstime-zone: GMT8default-property-inclusion: non_null
canal.conf:# tcp kafka rocketMQ rabbitMQ canal-server运行的模式TCP模式就是直连客户端不经过中间件。kafka和mq是消息队列的模式mode: tcp
# flatMessage: truezookeeperHosts: syncBatchSize: 1retries: 0timeout: 1000accessKey:secretKey:consumerProperties:# canal tcp consumer 指定canal-server的地址和端口canal.tcp.server.host: 127.0.0.1:11111canal.tcp.zookeeper.hosts: 127.0.0.1:2181canal.tcp.batch.size: 1canal.tcp.username:canal.tcp.password:srcDataSources: # 数据源配置从哪里获取数据defaultDS: # 指定一个名字在ES的配置中会用到唯一url: jdbc:mysql://127.0.0.1:3306/test2?useUnicodetrueusername: rootpassword: *****canalAdapters:- instance: example # canal instance Name or mq topic name 指定在canal配置的实例名称groups:- groupId: g1 outerAdapters:- name: logger
# - name: rdb
# key: mysql1
# properties:
# jdbc.driverClassName: com.mysql.jdbc.Driver
# jdbc.url: jdbc:mysql://127.0.0.1:3306/mytest2?useUnicodetrue
# jdbc.username: root
# jdbc.password: 121212
# - name: rdb
# key: oracle1
# properties:
# jdbc.driverClassName: oracle.jdbc.OracleDriver
# jdbc.url: jdbc:oracle:thin:localhost:49161:XE
# jdbc.username: mytest
# jdbc.password: m121212
# - name: rdb
# key: postgres1
# properties:
# jdbc.driverClassName: org.postgresql.Driver
# jdbc.url: jdbc:postgresql://localhost:5432/postgres
# jdbc.username: postgres
# jdbc.password: 121212
# threads: 1
# commitSize: 3000- name: hbaseproperties:hbase.zookeeper.quorum: sangfor.abdi.node3,sangfor.abdi.node2,sangfor.abdi.node1hbase.zookeeper.property.clientPort: 2181zookeeper.znode.parent: /hbase-unsecure- name: es7 # config目录下的子目录名称hosts: 192.168.168.2:9300 # 127.0.0.1:9200 for rest modeproperties:mode: transport # or rest
# # security.auth: test:123456 # only used for rest modecluster.name: my_application
# - name: kudu
# key: kudu
# properties:
# kudu.master.address: 127.0.0.1 # , split multi address
2.ElasticSearch 表映射文件
# 指定数据源这个值和adapter的application.yml文件中配置的srcDataSources值对应。
dataSourceKey: defaultDS
# 指定canal-server中配置的某个实例的名字不同实例对应不同业务
destination: example
# 组ID tcp方式这里填写空不要填写值不然可能会接收不到数据
groupId:
# ES的mapping映射
esMapping:# ES索引名称_index: testsync2# ES标示文档的唯一标示通常对应数据表中的主键ID字段_id: _id
# upsert: true
# pk: id
# 数据表每个字段映射到表中的具体名称不能重复sql: select a.id as _id, a.name,a.age,a.age_2,a.message,a.insert_time from testsync as a
# objFields:
# _labels: array:;
# etlCondition: where a.c_time{}commitBatch: 103 重启服务
bin/restart.sh写入数据
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());
INSERT INTO testsync(id,name,age,insert_time) values(UUID(),UUID(),2,now());查看adapter日志
2021-09-20 13:53:07.279 [pool-1-thread-1] INFO c.a.o.canal.client.adapter.logger.LoggerAdapterExample - DML: {data:[{id:05fabf89-19d7-11ec-bbe0-708cb6f5eaa6,name:05fabfb4-19d7-11ec-bbe0-708cb6f5eaa6,age:2,age_2:null,message:null,insert_time:1632117185000}],database:test2,destination:example,es:1632117185000,groupId:g1,isDdl:false,old:null,pkNames:[id],sql:,table:testsync,ts:1632117187278,type:INSERT}
2021-09-20 13:53:07.286 [pool-1-thread-1] DEBUG c.a.o.c.client.adapter.hbase.service.HbaseSyncService - DML: {data:[{id:05fabf89-19d7-11ec-bbe0-708cb6f5eaa6,name:05fabfb4-19d7-11ec-bbe0-708cb6f5eaa6,age:2,age_2:null,message:null,insert_time:1632117185000}],database:test2,destination:example,es:1632117185000,groupId:g1,isDdl:false,old:null,pkNames:[id],sql:,table:testsync,ts:1632117187278,type:INSERT}
2021-09-20 13:53:07.287 [pool-1-thread-1] DEBUG c.a.o.canal.client.adapter.es.core.service.ESSyncService - DML: {data:[{id:05fabf89-19d7-11ec-bbe0-708cb6f5eaa6,name:05fabfb4-19d7-11ec-bbe0-708cb6f5eaa6,age:2,age_2:null,message:null,insert_time:1632117185000}],database:test2,destination:example,es:1632117185000,groupId:g1,isDdl:false,old:null,pkNames:[id],sql:,table:testsync,ts:1632117187278,type:INSERT}
Affected indexes: testsync2 查看ElasticSearch数据 至此写入ElasticSearch、Hbase成功
