使用canal 監聽mysql binlog獲取增量數據

配置mysql 

sudo vi /etc/my.cnf
[mysqld]
log-bin=/var/lib/mysql/mysql-bin
binlog-format=ROW
server_id=1

添加canal用戶，修改權限

CREATE USER canal IDENTIFIED BY 'canal';
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'%';
FLUSH PRIVILEGES;

重啓mysql

sudo service mysqld restart

查看log_bin

show variables like '%log_bin%';

下載canal

[hdfs@node1 software]$ wget https://github.com/alibaba/canal/releases/download/canal-1.1.4/canal.deployer-1.1.4.tar.gz

解壓

mkdir /opt/module/canal
tar -zxvf /opt/software/canal.deployer-1.1.4.tar.gz -C /opt/module/canal

修改配置文件

vi /opt/module/canal/conf/example/instance.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=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=


# username/password
canal.instance.dbUsername=root
canal.instance.dbPassword=123456
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==


# table regex
canal.instance.filter.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=canaltest
# 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,.*\\..*
#################################################

vi /opt/module/canal/conf/canal.properties

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


canal.zkServers =
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = kafka
# 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 = node1:9092,node2:9092,node3:9092
canal.mq.retries = 0
canal.mq.batchSize = 16384
canal.mq.maxRequestSize = 1048576
canal.mq.lingerMs = 100
canal.mq.bufferMemory = 33554432
canal.mq.canalBatchSize = 50
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"

創建測試表並插入數據

CREATE TABLE Test.users(
id INT(10) PRIMARY KEY AUTO_INCREMENT,
NAME VARCHAR(256),
create_time BIGINT,
modified_time BIGINT
);

INSERT INTO  Test.users  VALUES(1,'zhangsan',UNIX_TIMESTAMP(),UNIX_TIMESTAMP());

開啓canel

/opt/module/canel/bin/startup.sh

查看kakfa topic

/opt/module/kafka_2.11-0.11.0.3/bin/kafka-topics.sh --list --zookeeper node1:2181

canaltest已經創建

消費數據

/opt/module/kafka_2.11-0.11.0.3/bin/kafka-console-consumer.sh --bootstrap-server node1:9092 --topic canaltest --from-beginning

mysql插入新數據

INSERT INTO  Test.users  VALUES(2,'lisi',UNIX_TIMESTAMP(),UNIX_TIMESTAMP());

kafka消費insert數據

{"data":[{"id":"2","name":"lisi","create_time":"1590308068","modified_time":"1590308068"}],"database":"Test","es":1590308068000,"id":9,"isDdl":false,"mysqlType":{"id":"int(10)","name":"varchar(256)","create_time":"bigint","modified_time":"bigint"},"old":null,"pkNames":["id"],"sql":"","sqlType":{"id":4,"name":12,"create_time":-5,"modified_time":-5},"table":"users","ts":1590308068312,"type":"INSERT"}

mysql修改數據

UPDATE Test.users  SET NAME='lisi_1',modified_time=UNIX_TIMESTAMP() WHERE NAME='lisi'

kafka消費update數據

{"data":[{"id":"2","name":"lisi_1","create_time":"1590308068","modified_time":"1590308148"}],"database":"Test","es":1590308148000,"id":10,"isDdl":false,"mysqlType":{"id":"int(10)","name":"varchar(256)","create_time":"bigint","modified_time":"bigint"},"old":[{"name":"lisi","modified_time":"1590308068"}],"pkNames":["id"],"sql":"","sqlType":{"id":4,"name":12,"create_time":-5,"modified_time":-5},"table":"users","ts":1590308148207,"type":"UPDATE"}

mysql刪除數據

delete from Test.users where name='lisi_1'

kafka消費delete數據

{"data":[{"id":"2","name":"lisi_1","create_time":"1590308068","modified_time":"1590308148"}],"database":"Test","es":1590308267000,"id":11,"isDdl":false,"mysqlType":{"id":"int(10)","name":"varchar(256)","create_time":"bigint","modified_time":"bigint"},"old":null,"pkNames":["id"],"sql":"","sqlType":{"id":4,"name":12,"create_time":-5,"modified_time":-5},"table":"users","ts":1590308267592,"type":"DELETE"}

總結

在生產環境中，用sqoop或者datax將數據從同步到數據倉庫中，我們往往通過modified_time，create_time或者主鍵這些索引這些時間來限制條件，導入T-1天一整天的離線數據。但是實際生產過程中會有一些表會沒有這些字段來判斷哪些是增量數據，這時候就可以通過讀取binlog中的logtime的來獲取增量數據。在一些複雜的業務場景，由於服務器壓力或者網絡延遲的問題往往會導致有些數據寫入延遲，會使凌晨12點數據產生數據漂移，及前一天的數據由於寫入過慢致使其漂移到後一天，這時候需要同時利用modified_time和binlog 的log_time獲取兩張表然後全表關聯獲取當時完整數據。