Seatunnel Docker image镜像制作

crabdave123

已于 2024-03-01 10:54:12 修改

阅读量1.8k

点赞数 16

文章标签： docker 容器运维

于 2023-12-28 15:17:15 首次发布

本文链接：https://blog.csdn.net/alksjdfp32r/article/details/135270117

版权

Seatunnel Docker image镜像制作

- #下载 seatunnel
```
- export version="2.3.3"
- wget "https://archive.apache.org/dist/seatunnel/${version}/apache-seatunnel-${version}-bin.tar.gz"
- tar -xzvf "apache-seatunnel-${version}-bin.tar.gz"
```
- #解压
  - tar -xzvf apache-seatunnel-${SEATUNNEL_VERSION}-bin.tar.gz
- #配置connector, config/plugin_config 根据需要配置，Demo只需要以下两个即可
  - --seatunnel-connectors--
  - connector-fake
  - connector-console
  - --end--
- #执行插件安装
  - sh bin/install-plugin.sh 2.3.3
  - #执行后，会自动下载maven包到 ~/.m2/wrapper/dists/apache-maven-3.8.4-bin/目录中
  - #连接到 Central Repository:，下载传统比较慢
  - #需要一下镜像，全用本地的setting.xml
    - #:~/.m2/wrapper/dists/apache-maven-3.8.4-bin/52ccbt68d252mdldqsfsn03jlf/apache-maven-3.8.4/conf#
  - #再重新执行 sh bin/install-plugin.sh 2.3.3 使用国内镜像，例如：阿里云，此时就很快了
  - #bin/install-plugin.sh 会将对就的jar包复制到 connectors/seatunnel和lib目录下
- #修改apache-seatunnel-${version}-bin目录下的配置文件
  - #编写plugin_config文件
    - vi config/plugin_config
      - --seatunnel-connectors--
      - connector-fake
      - connector-console
      - --end--
  - #编写批处理配置文件
    - vi config/v2.batch.config.template


env {
  execution.parallelism = 1
  job.mode = "BATCH"
}

source {
  FakeSource {
    result_table_name = "fake"
    row.num = 16
    schema = {
      fields {
        name = "string"
        age = "int"
      }
    }
  }
}

transform {
  FieldMapper {
    source_table_name = "fake"
    result_table_name = "fake1"
    field_mapper = {
      age = age
      name = new_name
    }
  }
}

sink {
  Console {
    source_table_name = "fake1"
  }
}

- #下载openjdk:8镜像
  - docker pull openjdk:8
- #创建Dockerfile
  - vi dockerfile-seatunnel-2.3.3
  - #内容当前目录下的seatunnel包、lib目录、connectors目录复制到镜像中
    - FROM openjdk:8
    - ENV SEATUNNEL_VERSION="2.3.3"
    - COPY ./apache-seatunnel-${SEATUNNEL_VERSION}-bin.tar.gz /opt/apache-seatunnel-${SEATUNNEL_VERSION}-bin.tar.gz
    - WORKDIR /opt
    - RUN tar -xzvf apache-seatunnel-${SEATUNNEL_VERSION}-bin.tar.gz
    - RUN mv apache-seatunnel-${SEATUNNEL_VERSION} seatunnel
    - RUN rm -f /opt/apache-seatunnel-${SEATUNNEL_VERSION}-bin.tar.gz
    - WORKDIR /opt/seatunnel
    - ENTRYPOINT ["sh","-c"," bin/seatunnel.sh --config $config -e local"]
- #build镜像
  - docker build -t seatunnel:2.3.3 -f dockerfile-seatunnel-2.3.3 .
- #使用镜像后台运行
  - docker run -d -p 9000:9000 --restart=unless-stopped --name seatunnel -d --hostname seatunnel-node1 --network my-net -e config="/data/seatunnel.batch.conf" -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/v2.batch.config.template:/data/seatunnel.batch.conf -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/plugin_config:/opt/seatunnel/plugin_config -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/lib:/opt/seatunnel/lib -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/plugins:/opt/seatunnel/plugins -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/connectors/seatunnel:/opt/seatunnel/connectors/seatunnel -v /etc/localtime:/etc/localtime seatunnel:2.3.3
- #使用镜像临时测试
  - docker run --name seatunnel --hostname seatunnel-node1 --network my-net -e config="/data/seatunnel.batch.conf" -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/v2.batch.config.template:/data/seatunnel.batch.conf -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/plugin_config:/opt/seatunnel/plugin_config -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/lib:/opt/seatunnel/lib -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/plugins:/opt/seatunnel/plugins -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/connectors/seatunnel:/opt/seatunnel/connectors/seatunnel -v /etc/localtime:/etc/localtime seatunnel:2.3.3
- #使用JDBC模式，同步两个库的数据
  - 修改plugin_config

- - - --seatunnel-connectors--
    - connector-fake
    - connector-console
    - connector-jdbc
    - --end--
  - 安装插件，安装过程中会自动把相应的jar包复制到对应的目录中
    - sh bin/install-plugin.sh 2.3.3
  - 修改v2.streaming.conf.template配置


# Defining the runtime environment
env {
  # You can set flink configuration here
  execution.parallelism = 1
  job.mode = "BATCH"
}
source{
  Jdbc {
    url = "jdbc:mysql://mysql:3306/test"
    driver = "com.mysql.cj.jdbc.Driver"
    connection_check_timeout_sec = 100
    user = "root"
    password = "123456"
    query = "select * from help_keyword_1 limit 2"
  }
}

transform {
    # If you would like to get more information about how to configure seatunnel and see full list of transform plugins,
    # please go to https://seatunnel.apache.org/docs/transform-v2/sql
}

sink {
#    Console {}
  jdbc {
    url = "jdbc:mysql://mysql:3306/test2"
    driver = "com.mysql.cj.jdbc.Driver"
    user = "root"
    password = "123456"
    query = "insert into help_keyword_1(help_keyword_1_id,name) values(?,?)"
  }
}

#配置MYSQL-CDC通过binlog实时数据同步

- MYSQL开启binlog
  - mysql的binlog开启方式,查看方式.三种binlog模式介绍.以及使用binlog恢复数据.删除binlog_mysql binlog 日志怎么打开-CSDN博客
- 开始CDC同步
  - 使用Apache SeaTunnel进行数据库同步（MySQL to MySQL）_seatunnel mysql-CSDN博客
  - Apache SeaTunnel 同步MySQL 数据到 Apache Kafka （SeaTunnel Engine）_seatunnel 从tcp到kafka-CSDN博客使用CDC同步到KAFKA
- 修改配置文件，与batch不同，是conf不是config
- vi v2.streaming.conf.template
- 内容如下

env {
      # You can set SeaTunnel environment configuration here
      execution.parallelism = 1
      job.mode = "STREAMING"
      # 10秒检查一次，可以适当加大这个值
      checkpoint.interval = 10000
      #execution.checkpoint.interval = 10000
      #execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint"
    }

    # 配置数据源
    source {
      MySQL-CDC {
        # 数据库账号
        username = "root"
        password = "123456"
        # 源表，格式：数据库名.表名
        table-names = ["test.help_keyword_1"]
        base-url = "jdbc:mysql://mysql:3306/test"
      }
    }

    # 配置目标库
    sink {

      jdbc {
        url = "jdbc:mysql://mysql:3306/test2"
        driver = "com.mysql.cj.jdbc.Driver"
        user = "root"
        password = "123456"
        
        generate_sink_sql = true
        # 目标数据库名
        database = "test2"
        # 目标表名
        table = "help_keyword_1"
        # 主键名称
        primary_keys = ["help_keyword_1_id"]
      }

    }

- 临时启动容器
  - docker run --name seatunnel --hostname seatunnel-node1 --network my-net -e config="/data/seatunnel.streaming.conf" -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/v2.streaming.conf.template:/data/seatunnel.streaming.conf -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/config/plugin_config:/opt/seatunnel/plugin_config -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/lib:/opt/seatunnel/lib -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/plugins:/opt/seatunnel/plugins -v /mnt/sda1/seatunnel/apache-seatunnel-2.3.3/connectors/seatunnel:/opt/seatunnel/connectors/seatunnel -v /etc/localtime:/etc/localtime seatunnel:2.3.3