canal配置文件参数

canal.properties

• 指一些实例instance公共的配置

#################################################
#########               common argument         #############
#################################################
# tcp bind ip
canal.ip =    #server绑定的主机地址，默认为本机，127.0.0.1
# register ip to zookeeper
canal.register.ip = 
canal.port = 11111    #对外提供的socket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

canal.zkServers = master:2181    #zookeeper的集群地址及端口
# flush data to zk
canal.zookeeper.flush.period = 1000 #canal持久化数据到zookeeper上的更新频率，单位毫秒
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = kafka
# flush meta cursor/parse position to file
canal.file.data.dir = ${canal.conf.dir} ##canal持久化数据到file上的目录

canal.file.flush.period = 1000 # #canal持久化数据到file上的更新频率,单位毫秒
## memory store RingBuffer size, should be Math.pow(2,n)
canal.instance.memory.buffer.size = 16384  #canal内存store中可缓存的binglog事件的最大记录数，只能为2的整数幂，此处是2的16次方
## memory store RingBuffer used memory unit size , default 1kb
canal.instance.memory.buffer.memunit = 1024 #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
## meory store gets mode used MEMSIZE or ITEMSIZE
canal.instance.memory.batch.mode = MEMSIZE  #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.rawEntry = true

## detecing config
canal.instance.detecting.enable = false  #是否开启心跳检查
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
canal.instance.detecting.sql = select 1 #心跳检查sql
canal.instance.detecting.interval.time = 3  #心跳检查频率，单位秒
canal.instance.detecting.retry.threshold = 3 #心跳检查失败重试次数
canal.instance.detecting.heartbeatHaEnable = false #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
# support maximum transaction size, more than the size of the transaction will be cut into multiple transactions delivery
canal.instance.transaction.size =  1024  #最大事务完整解析的长度支持
超过该长度后，一个事务可能会被拆分成多次提交到canal store中，无法保证事务的完整可见性
# mysql fallback connected to new master should fallback times
canal.instance.fallbackIntervalInSeconds = 60 #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

# network config
canal.instance.network.receiveBufferSize = 16384 #网络链接参数,SocketOptions.SO_RCVBUF
canal.instance.network.sendBufferSize = 16384 #网络链接参数,SocketOptions.SO_SNDBUF
canal.instance.network.soTimeout = 30 #网络链接参数,SocketOptions.SO_TIMEOUT
# binlog filter config
canal.instance.filter.druid.ddl = true #	是否忽略ddl语句
canal.instance.filter.query.dcl = false
canal.instance.filter.query.dml = false
canal.instance.filter.query.ddl = false
canal.instance.filter.table.error = false #是否忽略binlog表结构获取失败的异常

(主要解决回溯binlog时,对应表已被删除或者表结构和binlog不一致的情况)
canal.instance.filter.rows = false #是否dml的数据变更事件

(主要针对用户只订阅ddl/dcl的操作)
canal.instance.filter.transaction.entry = false #是否忽略事务头和尾,比如针对写入kakfa的消息时，不需要写入TransactionBegin/Transactionend事件

# binlog format/image check
canal.instance.binlog.format = ROW,STATEMENT,MIXED #支持的binlog format格式列表
(otter会有支持format格式限制)
canal.instance.binlog.image = FULL,MINIMAL,NOBLOB #支持的binlog image格式列表
(otter会有支持format格式限制)

# binlog ddl isolation
canal.instance.get.ddl.isolation = false #ddl语句是否单独一个batch返回

(比如下游dml/ddl如果做batch内无序并发处理,会导致结构不一致)

# parallel parser config
canal.instance.parser.parallel = true #是否开启binlog并行解析模式
## 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 #binlog并行解析的异步ringbuffer队列
(必须为2的指数)
# table meta tsdb info
canal.instance.tsdb.enable = true  #是否开启tablemeta的tsdb能力
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 = master:9092
canal.mq.retries = 0
canal.mq.batchSize = 16384
canal.mq.maxRequestSize = 1048576
canal.mq.lingerMs = 100
canal.mq.bufferMemory = 33554432
canal.mq.canalBatchSize = 50

instance.properties

• 针对于每一个instance的配置，优先级高于cana.properties

#################################################
## 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=master: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=

# username/password
canal.instance.dbUsername=root
canal.instance.dbPassword=123456
canal.instance.connectionCharset = UTF-8
canal.instance.defaultDatabaseName = time
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUC
AwEAAQ==
# table regex
canal.instance.filter.regex=time\\..*
# table black regex
canal.instance.filter.black.regex=
# table black regex
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=test_topic10
# dynamic topic route by schema or table regex
canal.mq.dynamicTopic=time\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################