canal 搭建

搭建mysql环境

  • 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

    1. [mysqld]
    2. log-bin=mysql-bin # 开启 binlog
    3. binlog-format=ROW # 选择 ROW 模式
    4. server_id=1 # 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

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

搭建canal环境

  • 下载 canal, 访问 release 页面 , 选择需要的包下载, 如以 1.0.17 版本为例

    1. wget https://github.com/alibaba/canal/releases/download/canal-1.0.17/canal.deployer-1.0.17.tar.gz

  • 解压缩

    1. mkdir /tmp/canal
    2. tar zxvf canal.deployer-$version.tar.gz -C /tmp/canal

解压完成后，进入 /tmp/canal 目录，可以看到如下结构
image.png

  • 配置修改
    • instance.properties
      1. vi conf/example/instance.properties

样例：

  1. ## mysql serverId
  2. canal.instance.mysql.slaveId = 1234
  3. #position info，需要改成自己的数据库信息
  4. canal.instance.master.address = 127.0.0.1:3306 
  5. canal.instance.master.journal.name = 
  6. canal.instance.master.position = 
  7. canal.instance.master.timestamp = 
  8. #canal.instance.standby.address = 
  9. #canal.instance.standby.journal.name =
  10. #canal.instance.standby.position = 
  11. #canal.instance.standby.timestamp = 
  12. #username/password，需要改成自己的数据库信息
  13. canal.instance.dbUsername = canal  
  14. canal.instance.dbPassword = canal
  15. canal.instance.defaultDatabaseName =
  16. canal.instance.connectionCharset = UTF-8
  17. #table regex
  18. canal.instance.filter.regex = .\*\\\\..\*

实例：

  1. #################################################
  2. ## mysql serverId , v1.0.26+ will autoGen
  3. # canal.instance.mysql.slaveId=0
  5. # enable gtid use true/false
  6. canal.instance.gtidon=false
  8. # position info
  9. canal.instance.master.address=rm-bp1r09z18z9kh8xp6.mysql.rds.aliyuncs.com:3306
  10. canal.instance.master.journal.name=
  11. canal.instance.master.position=
  12. canal.instance.master.timestamp=
  13. canal.instance.master.gtid=
  15. # rds oss binlog
  16. canal.instance.rds.accesskey=
  17. canal.instance.rds.secretkey=
  18. canal.instance.rds.instanceId=
  20. # table meta tsdb info
  21. canal.instance.tsdb.enable=true
  22. #canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
  23. #canal.instance.tsdb.dbUsername=canal
  24. #canal.instance.tsdb.dbPassword=canal
  26. #canal.instance.standby.address =
  27. #canal.instance.standby.journal.name =
  28. #canal.instance.standby.position =
  29. #canal.instance.standby.timestamp =
  30. #canal.instance.standby.gtid=
  32. # username/password
  33. # 用户名/密码
  34. canal.instance.dbUsername=zjt_lkyw_rds
  35. canal.instance.dbPassword=ZjjtGPSAL2016
  36. canal.instance.connectionCharset = UTF-8
  37. # enable druid Decrypt database password
  38. canal.instance.enableDruid=false
  39. #canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==
  41. # table regex
  42. # canal.instance.filter.regex=.*\\..*
  43. # 需要匹配的表名
  44. canal.instance.filter.regex=lkyw_rd.zjw_lkyw_gps_raw_1,lkyw_rd.zjw_lkyw_gps_raw_2,lkyw_rd.zjw_lkyw_gps_raw_3,lkyw_rd.zjw_lkyw_gps_raw_4,lkyw_rd.zjw_lkyw_gps_raw_5,lkyw_rd.zjw_lkyw_gps_raw_6,lkyw_rd.zjw_lkyw_gps_raw_7
  45. # table black regex
  46. canal.instance.filter.black.regex=
  47. # table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
  48. #canal.instance.filter.field=test1.t_product:id/subject/keywords,test2.t_company:id/name/contact/ch
  49. # table field black filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
  50. #canal.instance.filter.black.field=test1.t_product:subject/product_image,test2.t_company:id/name/contact/ch
  52. # mq config
  53. canal.mq.topic=example
  54. # dynamic topic route by schema or table regex
  55. #canal.mq.dynamicTopic=mytest1.user,mytest2\\..*,.*\\..*
  56. canal.mq.partition=0
  57. # hash partition config
  58. #canal.mq.partitionsNum=3
  59. #canal.mq.partitionHash=test.table:id^name,.*\\..*
  60. #################################################
  • 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-8，GBK , ISO-8859-1

  • 如果系统是1个 cpu，需要将 canal.instance.parser.parallel 设置为 false

    • canal.properties ```bash
      #
      ### common argument
      #

      tcp bind ip

      canal.ip = 192.168.119.17

      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

canal.zkServers =

flush data to zk

canal.zookeeper.flush.period = 1000 canal.withoutNetty = false

tcp, kafka, RocketMQ

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

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

aliyun ak/sk , support rds/mq

canal.aliyun.accessKey = canal.aliyun.secretKey =

#
### 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
#

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”

  2. <a name="Of7xL"></a>
  3. ### 启动

sh bin/startup.sh

  1. 到目前为止 canal的服务端我们已经搭建好了 但是到目前 我们只是把数据库的binlog 拉到canal中，我们还得把数据用otter去消费

sh bin/startup.sh

  2. 查看 server 日志

vi logs/canal/canal.log

  1. ```
  2. 2013-02-05 22:45:27.967 [main] INFO  com.alibaba.otter.canal.deployer.CanalLauncher - ## start the canal server.
  3. 2013-02-05 22:45:28.113 [main] INFO  com.alibaba.otter.canal.deployer.CanalController - ## start the canal server[10.1.29.120:11111]
  4. 2013-02-05 22:45:28.210 [main] INFO  com.alibaba.otter.canal.deployer.CanalLauncher - ## the canal server is running now ......

查看 instance 的日志

  1. vi logs/example/example.log
  1. 2013-02-05 22:50:45.636 [main] INFO  c.a.o.c.i.spring.support.PropertyPlaceholderConfigurer - Loading properties file from class path resource [canal.properties]
  2. 2013-02-05 22:50:45.641 [main] INFO  c.a.o.c.i.spring.support.PropertyPlaceholderConfigurer - Loading properties file from class path resource [example/instance.properties]
  3. 2013-02-05 22:50:45.803 [main] INFO  c.a.otter.canal.instance.spring.CanalInstanceWithSpring - start CannalInstance for 1-example 
  4. 2013-02-05 22:50:45.810 [main] INFO  c.a.otter.canal.instance.spring.CanalInstanceWithSpring - start successful....

写个简单的Demo 去监听mysql 数据的变动

Jar包

  1. <dependency>
  2.  <groupId>com.alibaba.otter</groupId>
  3.  <artifactId>canal.client</artifactId>
  4.  <version>1.1.3</version>
  5. </dependency>

测试代码

  1. package com.hq.eos.sync.client;
  3. import java.net.InetSocketAddress;
  4. import java.util.List;
  7. import com.alibaba.otter.canal.client.CanalConnector;
  8. import com.alibaba.otter.canal.client.CanalConnectors;
  9. import com.alibaba.otter.canal.protocol.CanalEntry.Column;
  10. import com.alibaba.otter.canal.protocol.CanalEntry.Entry;
  11. import com.alibaba.otter.canal.protocol.CanalEntry.EntryType;
  12. import com.alibaba.otter.canal.protocol.CanalEntry.EventType;
  13. import com.alibaba.otter.canal.protocol.CanalEntry.RowChange;
  14. import com.alibaba.otter.canal.protocol.CanalEntry.RowData;
  15. import com.alibaba.otter.canal.protocol.Message;
  19. public class CanalTest {
  21.  public static void main(String[] args) throws Exception {
  23.      CanalConnector connector = CanalConnectors.newSingleConnector(new InetSocketAddress("10.0.98.186", 11111), "expert", "root", "root");
  24.      connector.connect();
  25.      connector.subscribe(".*\\..*");
  26.      connector.rollback();
  28.      while (true) {
  29.          Message message = connector.getWithoutAck(100); // 获取指定数量的数据
  30.          long batchId = message.getId();
  31.          if (batchId == -1 || message.getEntries().isEmpty()) {
  32.              Thread.sleep(1000);
  33.              continue;
  34.          }
  35.      // System.out.println(message.getEntries());
  36.      printEntries(message.getEntries());
  37.      connector.ack(batchId);// 提交确认，消费成功，通知server删除数据
  38.     // connector.rollback(batchId);// 处理失败, 回滚数据，后续重新获取数据
  39.      }
  40.  }
  42.  private static void printEntries(List<Entry> entries) throws Exception {
  43.      for (Entry entry : entries) {
  44.      if (entry.getEntryType() != EntryType.ROWDATA) {
  45.      continue;
  46.      }
  48.      RowChange rowChange = RowChange.parseFrom(entry.getStoreValue());
  50.      EventType eventType = rowChange.getEventType();
  51.      System.out.println(String.format("================> binlog[%s:%s] , name[%s,%s] , eventType : %s",
  52.      entry.getHeader().getLogfileName(), entry.getHeader().getLogfileOffset(),
  53.      entry.getHeader().getSchemaName(), entry.getHeader().getTableName(), eventType));
  55.      for (RowData rowData : rowChange.getRowDatasList()) {
  56.          switch (rowChange.getEventType()) {
  57.              case INSERT:
  58.                  System.out.println("INSERT ");
  59.                  printColumns(rowData.getAfterColumnsList());
  60.                 break;
  61.              case UPDATE:
  62.                  System.out.println("UPDATE ");
  63.                  printColumns(rowData.getAfterColumnsList());
  64.                  break;
  65.              case DELETE:
  66.                  System.out.println("DELETE ");
  67.                  printColumns(rowData.getBeforeColumnsList());
  68.                  break;
  69.              default:
  70.                  break;
  71.          }
  72.      }
  73.      }
  74.  }
  76.  private static void printColumns(List<Column> columns) {
  77.      for(Column column : columns) {
  78.          System.out.println(column.getName() + " : " + column.getValue() + " update=" + column.getUpdated());
  79.      }
  80.  }
  81. }