网址:GitHub - alibaba/canal: 阿里巴巴 MySQL binlog 增量订阅&消费组件
前期软件准备
上面的软件包(canal.deployer-1.1.5.tar.gz , canal.admin-1.1.5.tar.gz)
zookeep
mysql及开启binlog日志
[mysqld] lower_case_table_names=1 log-bin=mysql-bin # 开启 binlog binlog-format=ROW # 选择 ROW 模式 server_id=1 # 配置 MySQL replaction 需要定义,不要和 canal 的 slaveId 重复
一、数据库操作
-
在MySQL中需要创建一个用户,并授权
create user 'canal'@'%' identified by 'Canal123456#'; -- 授权 *.*表示所有库 grant SELECT, REPLICATION SLAVE, REPLICATION CLIENT on *.* to 'canal'@'%' identified by 'Canal123456#';
-
开启binlog日志
[mysqld] # 打开binlog log-bin=mysql-bin # 选择ROW(行)模式 binlog-format=ROW # 配置MySQL replaction需要定义,不要和canal的slaveId重复 server_id=1
-
重启mysql服务,验证
show binary logs;
show master status;
二、安装canal-admin
-
解压安装admin软件包
tar -zxvf canal.admin-1.1.5.tar.gz -C /soft/canal.admin-1.1.5
-
修改配置文件 config/application.yml
server: port: 8089 spring: jackson: date-format: yyyy-MM-dd HH:mm:ss time-zone: GMT+8 spring.datasource: address: 127.0.0.1 # canal.admin 数据库 修改成自己的 database: canal_manager username: canal # 修改成自己的 password: canal # 修改成自己的 driver-class-name: com.mysql.jdbc.Driver url: jdbc:mysql://${spring.datasource.address}/${spring.datasource.database}?useUnicode=true&characterEncoding=UTF-8&useSSL=false hikari: maximum-pool-size: 30 minimum-idle: 1 canal: adminUser: admin # canal.admin用户名 adminPasswd: 123456 # canal.admin密码
-
运行初始化文件 conf/canal_manager.sql
mysql> source /soft/canal.admin-1.1.5/conf/canal_manager.sql
-
启动canal.admin
cd /soft/canal.admin-1.1.5/bin
./startup.sh
-
打开网站 http://192.168.100.125:8089/,用户名:admin 密码:123456
三、安装canal
1.解压安装
tar -zxvf canal.deployer-1.1.5.tar.gz -C /soft/canal.deployer-1.1.5
# 备份配置文件
mv canal.properties canal.properties.bak
cp canal_local.properties canal.properties
2.修改配置文件 canal.properties
# register ip
canal.register.ip = 192.168.100.125
# 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_cluster
canal.admin.register.name = Canal-android-1
3.刷新浏览器可以看到了
4.编辑主配置文件
#################################################
######### 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
# admin auto register
#canal.admin.register.auto = true
#canal.admin.register.cluster =
#canal.admin.register.name =
canal.zkServers = 192.168.100.125:2181
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ
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
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 = tb_user
# 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 = manager
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.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
5.新建instance,使用默认模板
#################################################
## 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=39.xxx.xx.233:3306 # 改成自己的
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=canal_client # 改成自己的
canal.instance.dbPassword=Canal_client123# # 改成自己的
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlh
rWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==
# table regex
canal.instance.filter.regex=db_data.tb_user # 改成自己的
# 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/contac
t/ch
# mq config
canal.mq.topic=
# 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,.*\\..*
#################################################
6.修改主配置文件
四、客户端验证
clien.py
import time
from canal.client import Client
from canal.protocol import EntryProtocol_pb2
from canal.protocol import CanalProtocol_pb2
client = Client()
client.connect(host='192.168.100.125', port=11111) # 修改成自己的
client.check_valid(username=b'', password=b'')
client.subscribe(client_id=b'1001', destination=b'tb_user', filter=b'.*\\..*')
while True:
message = client.get(100)
entries = message['entries']
for entry in entries:
entry_type = entry.entryType
if entry_type in [EntryProtocol_pb2.EntryType.TRANSACTIONBEGIN, EntryProtocol_pb2.EntryType.TRANSACTIONEND]:
continue
row_change = EntryProtocol_pb2.RowChange()
row_change.MergeFromString(entry.storeValue)
event_type = row_change.eventType
header = entry.header
database = header.schemaName
table = header.tableName
event_type = header.eventType
for row in row_change.rowDatas:
format_data = dict()
if event_type == EntryProtocol_pb2.EventType.DELETE:
for column in row.beforeColumns:
format_data = {
column.name: column.value
}
elif event_type == EntryProtocol_pb2.EventType.INSERT:
for column in row.afterColumns:
format_data = {
column.name: column.value
}
else:
format_data['before'] = format_data['after'] = dict()
for column in row.beforeColumns:
format_data['before'][column.name] = column.value
for column in row.afterColumns:
format_data['after'][column.name] = column.value
data = dict(
db=database,
table=table,
event_type=event_type,
data=format_data,
)
print(data)
time.sleep(1)
client.disconnect()
Canal启动报错踩坑记录
服务启动报错,数据无法同步
java.io.IOException: Received error packet: errno = 1236, sqlstate = HY000 errmsg = Could not find first log file name in binary log index file
解决方案:
单机:先把服务停止,然后删除canal/conf/下对应实例的meta.dat文件;重启canal即可恢复 zk集群模式:进入canal对应的zookeeper集群下,删除节点/otter/canal/destinations/xxxxx/1001/cursor ;重启canal即可恢复
注:1.1.6版本的canal自己编译二进制包,官网包有bug