官網(wǎng)地址
https://github.com/alibaba/canal
下載地址
https://github.com/alibaba/canal/releases
原理概述看官網(wǎng)
https://github.com/alibaba/canal/wiki
源碼版本(當(dāng)前最新穩(wěn)定版1.1.4)
image.png
安裝MySQL(建議5.7以上，這里略過(guò)..)
安裝JDK1.8（這里略過(guò)..）
在mysql的安裝目錄修改配置
[mysqld]
#開啟binlog
log-bin=mysql-bin
#選擇row模式
binlog-format=ROW
#配置mysql replaction需要定義，不能和canal的slaveId重復(fù)
server_id=1
#配置取出sql
binlog-rows-query-log-events=true
#設(shè)置minimal，binlog記錄的只是影響后的數(shù)據(jù)，無(wú)法正常同步update
binlog_row_image=FULL
創(chuàng)建MySQL 用戶，用于canal 可以dump mysql（canal 默認(rèn)配置是canal）。
CREATE USER canal IDENTIFIED BY 'canal';
GRANT SELECT ,REPLICATION SLAVE,REPLICATION CLIENT ON *.* TO 'canal'@'%';
FLUSH PRIVILEGES;
檢查binlog是否開啟
show variables like 'log_bin';
檢查logformat 是否是ROW
show variables like 'binlog_format';
查看server_id
show variables like 'server_id';
下載安裝canal.deployer-1.1.4.tar.gz
tar -zxvf canal.deployer-1.1.4.tar.gz -C /usr/local/canal
修改/usr/local/canal/conf/canal.properties
#################################################
######### common argument #############
#################################################
# tcp bind ip
#canal server綁定的本地IP信息，如果不配置，默認(rèn)選擇一個(gè)本機(jī)IP進(jìn)行啟動(dòng)服務(wù)
canal.ip =
# register ip to zookeeper
canal.register.ip =
#canal server提供socket服務(wù)的端口
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 server鏈接zookeeper集群的鏈接信息
例子：127.0.0.1:2181,127.0.0.1:2182
canal.zkServers =
# flush data to zk
#canal持久化數(shù)據(jù)到zookeeper上的更新頻率，單位毫秒
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, RocketMQ
canal.serverMode = tcp
# flush meta cursor/parse position to file
#canal持久化數(shù)據(jù)到file上的目錄
canal.file.data.dir = ${canal.conf.dir}
#canal持久化數(shù)據(jù)到file上的更新頻率，單位毫秒
canal.file.flush.period = 1000
## memory store RingBuffer size, should be Math.pow(2,n)
#canal內(nèi)存store中可緩存buffer記錄數(shù)，需要為2的指數(shù)
canal.instance.memory.buffer.size = 16384
## memory store RingBuffer used memory unit size , default 1kb
#內(nèi)存記錄的單位大小，默認(rèn)1KB，和buffer.size組合決定最終的內(nèi)存使用大小
canal.instance.memory.buffer.memunit = 1024
## meory store gets mode used MEMSIZE or ITEMSIZE
#canal內(nèi)存store中數(shù)據(jù)緩存模式
1. ITEMSIZE : 根據(jù)buffer.size進(jìn)行限制，只限制記錄的數(shù)量
2. MEMSIZE : 根據(jù)buffer.size * buffer.memunit的大小，限制緩存記錄的大小
canal.instance.memory.batch.mode = MEMSIZE
#canal內(nèi)存store中可緩存buffer記錄數(shù)，需要為2的指數(shù)
canal.instance.memory.rawEntry = true
## detecing config
#是否開啟心跳檢查
canal.instance.detecting.enable = false
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
#心跳檢查sql
canal.instance.detecting.sql = select 1
#心跳檢查頻率，單位秒
canal.instance.detecting.interval.time = 3
#心跳檢查失敗重試次數(shù)
canal.instance.detecting.retry.threshold = 3
#心跳檢查失敗后，是否開啟自動(dòng)mysql自動(dòng)切換
說(shuō)明：比如心跳檢查失敗超過(guò)閥值后，如果該配置為true，canal就會(huì)自動(dòng)鏈到mysql備庫(kù)獲取binlog數(shù)據(jù)
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發(fā)生mysql切換時(shí)，在新的mysql庫(kù)上查找binlog時(shí)需要往前查找的時(shí)間，單位秒
說(shuō)明：mysql主備庫(kù)可能存在解析延遲或者時(shí)鐘不統(tǒng)一，需要回退一段時(shí)間，保證數(shù)據(jù)不丟
canal.instance.fallbackIntervalInSeconds = 60
# network config
#網(wǎng)絡(luò)鏈接參數(shù)，SocketOptions.SO_RCVBUF
canal.instance.network.receiveBufferSize = 16384
#網(wǎng)絡(luò)鏈接參數(shù)，SocketOptions.SO_SNDBUF
canal.instance.network.sendBufferSize = 16384
#網(wǎng)絡(luò)鏈接參數(shù)，SocketOptions.SO_TIMEOUT
canal.instance.network.soTimeout = 30
# binlog filter config
#v1.0.25版本新增，是否啟用druid的DDL parse的過(guò)濾，基于sql的完整parser可以解決之前基于正則匹配補(bǔ)全的問題，默認(rèn)為true
canal.instance.filter.druid.ddl = true
#是否忽略DCL的query語(yǔ)句，比如grant/create user等
canal.instance.filter.query.dcl = false
#是否忽略DML的query語(yǔ)句，比如insert/update/delete table.(mysql5.6的ROW模式可以包含statement模式的query記錄)
canal.instance.filter.query.dml = false
#是否忽略DDL的query語(yǔ)句，比如create table/alater table/drop table/rename table/create index/drop index. (目前支持的ddl類型主要為table級(jí)別的操作，create databases/trigger/procedure暫時(shí)劃分為dcl類型)
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
#ddl語(yǔ)句是否隔離發(fā)送，開啟隔離可保證每次只返回發(fā)送一條ddl數(shù)據(jù)，不和其他dml語(yǔ)句混合返回.(otter ddl同步使用)
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
#v1.0.25版本新增,table meta的時(shí)間序列版本的本地存儲(chǔ)路徑，默認(rèn)為instance目錄
canal.instance.tsdb.dir = ${canal.file.data.dir:../conf}/${canal.instance.destination:}
#v1.0.25版本新增,table meta的時(shí)間序列版本存儲(chǔ)的數(shù)據(jù)庫(kù)鏈接串，比如例子為本地嵌入式數(shù)據(jù)庫(kù)
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 配置instance，可以配置多個(gè)用“,”分割
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"
配置instance.properties
#################################################
## mysql serverId , v1.0.26+ will autoGen
#mysql集群配置中的serverId概念，需要保證和當(dāng)前mysql集群中id唯一
# canal.instance.mysql.slaveId=2222
# enable gtid use true/false
canal.instance.gtidon=false
# position info mysql master鏈接地址
canal.instance.master.address=192.168.1.115:3306
#mysql主庫(kù)鏈接時(shí)起始的binlog文件
canal.instance.master.journal.name=
#mysql主庫(kù)鏈接時(shí)起始的binlog偏移量
canal.instance.master.position=
#mysql主庫(kù)鏈接時(shí)起始的binlog的時(shí)間戳
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
#v1.0.25版本新增,是否開啟table meta的時(shí)間序列版本記錄功能
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 連接數(shù)據(jù)庫(kù)使用的賬號(hào)密碼
canal.instance.dbUsername=canal
canal.instance.dbPassword=canal
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSw
lWKUCAwEAAQ==
# table regex 訂閱庫(kù)表正則（白名單表）
#mysql 數(shù)據(jù)解析關(guān)注的表，Perl正則表達(dá)式.
多個(gè)正則之間以逗號(hào)(,)分隔，轉(zhuǎn)義符需要雙斜杠(\\)
常見例子：
1. 所有表：.* or .*\\..*
2. canal schema下所有表： canal\\..*
3. canal下的以canal打頭的表：canal\\.canal.*
4. canal schema下的一張表：canal.test1
5. 多個(gè)規(guī)則組合使用：canal\\..*,mysql.test1,mysql.test2 (逗號(hào)分隔)
注意：此過(guò)濾條件只針對(duì)row模式的數(shù)據(jù)有效(ps. mixed/statement因?yàn)椴唤馕鰏ql，所以無(wú)法準(zhǔn)確提取tableName進(jìn)行過(guò)濾)
canal.instance.filter.regex=.*\\..*
# table black regex 配置正則（黑名單表）
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=example
# 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,.*\\..*
#################################################
啟動(dòng)
image.png
查看日志
##tail -200f /usr/local/canal/logs/example/example.log
2020-12-21 02:47:51.308 [pool-2-thread-1] INFO c.a.otter.canal.instance.spring.CanalInstanceWithSpring - start CannalInstance for 1-example
2020-12-21 02:47:51.314 [pool-2-thread-1] WARN c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table filter : ^.*\..*$
2020-12-21 02:47:51.315 [pool-2-thread-1] WARN c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table black filter :
2020-12-21 02:47:51.327 [pool-2-thread-1] INFO c.a.otter.canal.instance.core.AbstractCanalInstance - subscribe filter change to .*\..*
2020-12-21 02:47:51.327 [pool-2-thread-1] WARN c.a.o.canal.parse.inbound.mysql.dbsync.LogEventConvert - --> init table filter : ^.*\..*$
2020-12-21 02:47:51.327 [pool-2-thread-1] INFO c.a.otter.canal.instance.core.AbstractCanalInstance - start successful....
2020-12-21 02:47:51.485 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - ---> begin to find start position, it will be long time for reset or first position
2020-12-21 02:47:51.529 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - prepare to find start position just last position
{"identity":{"slaveId":-1,"sourceAddress":{"address":"docker_server","port":3306}},"postion":{"gtid":"","included":false,"journalName":"mysql-bin.000001","position":9846,"serverId":1,"timestamp":1608468374000}}
2020-12-21 02:47:51.981 [destination = example , address = /192.168.1.115:3306 , EventParser] WARN c.a.o.c.p.inbound.mysql.rds.RdsBinlogEventParserProxy - ---> find start position successfully, EntryPosition[included=false,journalName=mysql-bin.000001,position=9846,serverId=1,gtid=,timestamp=1608468374000] cost : 479ms , the next step is binlog dump
創(chuàng)建canal-client服務(wù)
pom.xml引入
<dependency>
<groupId>com.alibaba.otter</groupId>
<artifactId>canal.client</artifactId>
<version>1.1.4</version>
</dependency>
官網(wǎng)測(cè)試代碼
public class ClientTest {
//canal server地址
private static String SERVER_ADDRESS="192.168.1.114";
//服務(wù)端口
private static int PORT = 11111;
private static String DESTINATION="example";
private static String USERNAME="";
private static String PASSWORD="";
public static void main(String[] args) {
CanalConnector canalConnector = CanalConnectors.newSingleConnector(new InetSocketAddress(SERVER_ADDRESS,PORT),DESTINATION,USERNAME,PASSWORD);
int emptyCount = 0;
long batchId = 0l;
try{
canalConnector.connect();
//訂閱如果這里配置將覆蓋服務(wù)端
canalConnector.subscribe(".*\\..*");
canalConnector.rollback();
int totalEmptyCount = 1200;
while (emptyCount < totalEmptyCount) {
Message message = canalConnector.getWithoutAck(100); // 獲取指定數(shù)量的數(shù)據(jù)
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);
printEntity(message.getEntries());
// int i = 1/0;
}
canalConnector.ack(batchId); // 提交確認(rèn)
// connector.rollback(batchId); // 處理失敗, 回滾數(shù)據(jù)
}
System.out.println("empty too many times, exit");
}catch (Exception e){
e.printStackTrace();
if(batchId>0){
canalConnector.rollback(batchId); // 處理失敗, 回滾數(shù)據(jù)
}
}finally {
canalConnector.disconnect();
}
}
public static void printEntity(List<CanalEntry.Entry> list){
for(CanalEntry.Entry entry : list){
if(entry.getEntryType() != CanalEntry.EntryType.ROWDATA){
continue;
}
try{
CanalEntry.RowChange rowChange = CanalEntry.RowChange.parseFrom(entry.getStoreValue());
System.out.println("sql--->"+rowChange.getSql());
CanalEntry.EventType eventType = rowChange.getEventType();
System.out.println(String.format("================> binlog[%s:%s] , name[%s,%s] , eventType : %s",
entry.getHeader().getLogfileName(), entry.getHeader().getLogfileOffset(),
entry.getHeader().getSchemaName(), entry.getHeader().getTableName(),
eventType));
for (CanalEntry.RowData rowData : rowChange.getRowDatasList()){
if (eventType == CanalEntry.EventType.DELETE) {
printColumn(rowData.getBeforeColumnsList());
} else if (eventType == CanalEntry.EventType.INSERT) {
printColumn(rowData.getAfterColumnsList());
} else {
System.out.println("-------> before");
printColumn(rowData.getBeforeColumnsList());
System.out.println("-------> after");
printColumn(rowData.getAfterColumnsList());
}
}
}catch (Exception e){
e.printStackTrace();
}
}
}
private static void printColumn(List<CanalEntry.Column> columns) {
for (CanalEntry.Column column : columns) {
System.out.println(column.getName() + " : " + column.getValue() + " update=" + column.getUpdated());
}
}
