Canal
2023/8/7 18:06:08
Canal
2023/8/7 18:06:29
Canal是一种开源的数据库变更数据捕获（CDC）解决方案，用于对接不同数据库之间的数据复制和同步。它由阿里巴巴集团开发并发布，采用Java语言编写，并且基于Apache Kafka提供高性能的消息传递机制。
Canal的主要特点和功能包括：
- 数据库异构支持：Canal可以对接多种数据库，包括MySQL、Oracle、PostgreSQL等常见的关系型数据库，实现不同数据库之间的数据复制和同步。
- 实时数据捕获：Canal通过解析数据库的事务日志，实时捕获数据库的变更操作，包括插入、更新、删除等，确保将数据变更以事件的形式传递出来。
- 低延迟和高吞吐量：Canal利用Apache Kafka作为消息传递中间件，具有低延迟和高吞吐量的优势，可以有效地处理大量的数据变更。
- 灵活的数据转换：Canal支持自定义的数据转换和映射规则，可以根据需求对数据进行格式转换、字段映射、过滤等操作，实现数据在不同数据库之间的兼容性和一致性。
- 数据库拓扑监控：Canal提供了实时的数据库拓扑监控功能，可以监控数据库实例的健康状态、复制进程、延迟等信息，方便用户对数据库进行实时管理和故障排查。
- 高可靠性和容错性：Canal具有高可靠性和容错性，支持多节点部署和数据冗余，确保数据的连续可用性和数据同步的稳定性。
- 易于使用和扩展：Canal提供了简单易用的配置和管理接口，同时也支持多种开发语言的客户端接口，方便用户进行二次开发和定制化需求。
Canal在阿里巴巴内部被广泛应用于分布式系统架构、业务双写、数据统计分析等场景，它具有成熟稳定的特点，并且在开源社区中得到了广泛的关注和贡献。使用Canal可以实现数据库之间的实时数据复制和同步，满足企业对数据一致性和实时性的需求。
canal→kafka
配置参考：canal.properties
#################################################
######### common argument #############
#################################################
# tcp bind ip
canal.ip = 192.168.0.206
# 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, pulsarMQ
canal.serverMode = kafka
# kafka开启安全认证后新加的配置
canal.mq.properties.security.protocol = SASL_PLAINTEXT
canal.mq.properties.sasl.mechanism = PLAIN
canal.mq.sasl.jaas.config = org.apache.kafka.common.security.plain.PlainLoginModule required username="admin" password="admin-2019";
#canal.mq.sasl.enable=true
#canal.mq.servers = 192.168.0.131:9092,192.168.0.132:9092,192.168.0.133:9092
canal.mq.servers = 192.168.0.230:81
# 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 = 256
## 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.retries = 0
canal.mq.compressionType = none
canal.mq.acks = all
canal.mq.transaction = false
canal.mq.lingerMs = 1
canal.mq.bufferMemory = 33554432
canal.mq.batchSize = 16384
canal.mq.maxRequestSize = 1048576
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 = 192.168.0.230:81
kafka.acks = all
kafka.compression.type = none
kafka.batch.size = 16384
kafka.linger.ms = 1
kafka.max.request.size = 10485760
kafka.buffer.memory = 33554432
kafka.max.in.flight.requests.per.connection = 1
kafka.retries = 0
# kafka开启安全认证后新加的配置
kafka.sasl.jaas.config = org.apache.kafka.common.security.plain.PlainLoginModule required username='admin' password='admin-2019';
kafka.sasl.mechanism = PLAIN
kafka.security.protocol = SASL_PLAINTEXT
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 =
##################################################
######### Pulsar #############
##################################################
pulsarmq.serverUrl =
pulsarmq.roleToken =
pulsarmq.topicTenantPrefix =
