Sharding-JDBC之水平分表

- 一、简介
- 1.1、垂直分表
- 1.2、水平分表
- 二、maven依赖
- 三、数据库
- - 3.1、创建数据库
  - 3.2、创建表
- 四、配置（二选一）
- - 4.1、properties配置
  - 4.2、yml配置
- 五、实现
- - 5.1、实体
  - 5.2、持久层
  - 5.3、服务层
  - 5.4、测试类
  - - 5.4.1、保存数据
    - 5.4.2、查询数据

一、简介

1.1、垂直分表

垂直分片又称为纵向拆分。最简单的就是单库把一个表拆成多个关联的表，通常是一个表中存储的信息类型比较多，比如一二十个字段，但是经常用到的可能又比较少，频繁操作就影响性能，所以就把大表拆分成多个小表，比如 tb_course 拆分成 tb_course 和 tb_course_detail 。这个主要是数据库设计的相关知识，也和我们这里说的 Sharding-JDBC 关系不是那么大，我就不多进行讲解，所以后面也不会讲垂直分表这种了，主要是我们要讲的水平分表。

1.2、水平分表

水平分片又称为横向拆分。最简单的就是单库水平分表，也就是一个库中有两个一模一样的表，只是名称不一样比如： tb_order_1 和 tb_order_2 ，如下图所示。

在这里插入图片描述

二、maven依赖

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.6.0</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.alian</groupId>
    <artifactId>sharding-jdbc</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>sharding-jdbc</name>
    <description>sharding-jdbc</description>

    <properties>
        <java.version>1.8</java.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-data-jpa</artifactId>
        </dependency>

        <dependency>
            <groupId>org.apache.shardingsphere</groupId>
            <artifactId>sharding-jdbc-spring-boot-starter</artifactId>
            <version>4.1.1</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>druid</artifactId>
            <version>1.2.15</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>8.0.26</version>
            <scope>runtime</scope>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.20</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
            </plugin>
        </plugins>
    </build>

</project>

有些小伙伴的 druid 可能用的是 druid-spring-boot-starter

<dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>druid-spring-boot-starter</artifactId>
    <version>1.2.6</version>
</dependency>

然后出现可能使用不了的各种问题，这个时候你只需要在主类上添加 @SpringBootApplication(exclude = {DruidDataSourceAutoConfigure.class}) 即可

package com.alian.shardingjdbc;

import com.alibaba.druid.spring.boot.autoconfigure.DruidDataSourceAutoConfigure;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication(exclude = {DruidDataSourceAutoConfigure.class})
@SpringBootApplication
public class ShardingJdbcApplication {

    public static void main(String[] args) {
        SpringApplication.run(ShardingJdbcApplication.class, args);
    }

}

三、数据库

3.1、创建数据库

sharding_0

CREATE DATABASE `sharding_0` DEFAULT CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci;

3.2、创建表

tb_order_1

CREATE TABLE `tb_order_1` (
  `order_id` bigint(20) NOT NULL COMMENT '主键',
  `user_id` int unsigned NOT NULL DEFAULT '0' COMMENT '用户id',
  `price` int unsigned NOT NULL DEFAULT '0' COMMENT '价格（单位：分）',
  `order_status` tinyint unsigned NOT NULL DEFAULT '1' COMMENT '订单状态(1:待付款,2:已付款,3:已取消)',
  `order_time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
  `title` varchar(100)  NOT NULL DEFAULT '' COMMENT '订单标题',
  PRIMARY KEY (`order_id`),
  KEY `idx_user_id` (`user_id`),
  KEY `idx_order_time` (`order_time`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='订单表';

tb_order_2

CREATE TABLE `tb_order_2` (
  `order_id` bigint(20) NOT NULL COMMENT '主键',
  `user_id` int unsigned NOT NULL DEFAULT '0' COMMENT '用户id',
  `price` int unsigned NOT NULL DEFAULT '0' COMMENT '价格（单位：分）',
  `order_status` tinyint unsigned NOT NULL DEFAULT '1' COMMENT '订单状态(1:待付款,2:已付款,3:已取消)',
  `order_time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
  `title` varchar(100)  NOT NULL DEFAULT '' COMMENT '订单标题',
  PRIMARY KEY (`order_id`),
  KEY `idx_user_id` (`user_id`),
  KEY `idx_order_time` (`order_time`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='订单表';

四、配置（二选一）

4.1、properties配置

application.properties

server.port=8899
server.servlet.context-path=/sharding-jdbc

# 允许一个实体映射多个表
#spring.main.allow-bean-definition-overriding=true
# 数据源名称，多数据源以逗号分隔
spring.shardingsphere.datasource.names=ds1
# 数据库连接池类名称
spring.shardingsphere.datasource.ds1.type=com.alibaba.druid.pool.DruidDataSource
# 数据库驱动类名
spring.shardingsphere.datasource.ds1.driver-class-name=com.mysql.cj.jdbc.Driver
# 数据库url连接
spring.shardingsphere.datasource.ds1.url=jdbc:mysql://192.168.19.129:3306/sharding_0?serverTimezone=GMT%2B8&characterEncoding=utf8&useUnicode=true&useSSL=false&zeroDateTimeBehavior=CONVERT_TO_NULL&autoReconnect=true&allowMultiQueries=true&failOverReadOnly=false&connectTimeout=6000&maxReconnects=5
# 数据库用户名
spring.shardingsphere.datasource.ds1.username=alian
# 数据库密码
spring.shardingsphere.datasource.ds1.password=123456

# 指定tb_order表的数据分布情况，配置数据节点，使用Groovy的表达式,逻辑表tb_order对应的节点是：ds1.tb_order_1, ds1.tb_order_2
spring.shardingsphere.sharding.tables.tb_order.actual-data-nodes=ds1.tb_order_$->{1..2}

# 采用行表达式分片策略：InlineShardingStrategy
# 指定tb_order表的分片策略中的分片键
spring.shardingsphere.sharding.tables.tb_order.table-strategy.inline.sharding-column=order_id
# 指定tb_order表的分片策略中的分片算法表达式,使用Groovy的表达式
spring.shardingsphere.sharding.tables.tb_order.table-strategy.inline.algorithm-expression=tb_order_$->{ order_id % 2 == 0 ? 2 : 1 }

# 指定tb_order表的主键为order_id
spring.shardingsphere.sharding.tables.tb_order.key-generator.column=order_id
# 指定tb_order表的主键生成策略为SNOWFLAKE
spring.shardingsphere.sharding.tables.tb_order.key-generator.type=SNOWFLAKE
# 指定雪花算法的worker.id
spring.shardingsphere.sharding.tables.tb_order.key-generator.props.worker.id=100
# 指定雪花算法的max.tolerate.time.difference.milliseconds
spring.shardingsphere.sharding.tables.tb_order.key-generator.props.max.tolerate.time.difference.milliseconds=20

# 打开sql输出日志
spring.shardingsphere.props.sql.show=true

4.2、yml配置

application.yml

server:
  port: 8899
  servlet:
    context-path: /sharding-jdbc

spring:
  main:
    # 允许定义相同的bean对象去覆盖原有的
    allow-bean-definition-overriding: true
  shardingsphere:
    props:
      sql:
       # 打开sql输出日志
       show: true
    datasource:
      # 数据源名称，多数据源以逗号分隔
      names: ds1
      ds1:
        # 数据库连接池类名称
        type: com.alibaba.druid.pool.DruidDataSource
        # 数据库驱动类名
        driver-class-name: com.mysql.cj.jdbc.Driver
        # 数据库url连接
        url: jdbc:mysql://192.168.19.129:3306/sharding_0?serverTimezone=GMT%2B8&characterEncoding=utf8&useUnicode=true&useSSL=false&zeroDateTimeBehavior=CONVERT_TO_NULL&autoReconnect=true&allowMultiQueries=true&failOverReadOnly=false&connectTimeout=6000&maxReconnects=5
        # 数据库用户名
        username: alian
        # 数据库密码
        password: 123456
    sharding:
      # 未配置分片规则的表将通过默认数据源定位
      default-data-source-name: ds1
      tables:
        tb_order:
          # 由数据源名 + 表名组成，以小数点分隔。多个表以逗号分隔，支持inline表达式
          actual-data-nodes: ds1.tb_order_$->{1..2}
          # 分表策略
          table-strategy:
            # 行表达式分片策略
            inline:
              # 分片键
              sharding-column: order_id
              # 算法表达式
              algorithm-expression: tb_order_$->{order_id%2==0?2:1}
          # key生成器
          key-generator:
            # 自增列名称，缺省表示不使用自增主键生成器
            column: order_id
            # 自增列值生成器类型，缺省表示使用默认自增列值生成器（SNOWFLAKE/UUID）
            type: SNOWFLAKE
            # SnowflakeShardingKeyGenerator
            props:
              # SNOWFLAKE算法的worker.id
              worker:
                id: 100
              # SNOWFLAKE算法的max.tolerate.time.difference.milliseconds
              max:
                tolerate:
                  time:
                    difference:
                      milliseconds: 20

actual-data-nodes ：使用Groovy的表达式 ds1.tb_order_$->{1…2}，表示逻辑表tb_order对应的物理表是：ds1.tb_order_1和 ds1.tb_order_2
key-generator :key生成器，需要指定字段和类型，如果是SNOWFLAKE，最好也配置下props中的两个属性： worker.id 与 max.tolerate.time.difference.milliseconds 属性（主要还是yml中配置）
table-strategy 表的分片策略，这里只是一个简单的奇数偶数，采用的是 行表达式分片策略 ，需要指定分片键和分片算法表达式（算法支持Groovy的表达式）

五、实现

5.1、实体

Order.java

@Data
@Entity
@Table(name = "tb_order")
public class Order implements Serializable {

    @Id
    @GeneratedValue(strategy = GenerationType.IDENTITY)
    @Column(name = "order_id")
    private Long orderId;

    @Column(name = "user_id")
    private Integer userId;

    @Column(name = "price")
    private Integer price;

    @Column(name = "order_status")
    private Integer orderStatus;

    @Column(name = "title")
    private String title;

    @Column(name = "order_time")
    private LocalDateTime orderTime;

}

5.2、持久层

OrderRepository.java

public interface OrderRepository extends PagingAndSortingRepository<Order, Long> {

    /**
     * 根据订单id查询订单
     * @param orderId
     * @return
     */
    Order findOrderByOrderId(Long orderId);
}

5.3、服务层

OrderService.java

@Slf4j
@Service
public class OrderService {

    @Autowired
    private OrderRepository orderRepository;

    public void saveOrder(Order order) {
        orderRepository.save(order);
    }

    public Order queryOrder(Long orderId) {
        return orderRepository.findOrderByOrderId(orderId);
    }
}

5.4、测试类

OrderTests.java

@Slf4j
@RunWith(SpringJUnit4ClassRunner.class)
@SpringBootTest
public class OrderTests {

    @Autowired
    private OrderService orderService;

    @Test
    public void saveOrder() {
        for (int i = 0; i < 10; i++) {
            Order order = new Order();
            order.setUserId(1000);
            // 随机生成50到100的金额
            int price = (int) Math.round(Math.random() * (10000 - 5000) + 5000);
            order.setPrice(price);
            order.setOrderStatus(2);
            order.setOrderTime(LocalDateTime.now());
            order.setTitle("");
            orderService.saveOrder(order);
        }
    }

    @Test
    public void queryOrder() {
        Long orderId = 845308485917736960L;
        Order order = orderService.queryOrder(orderId);
        log.info("查询的结果：{}", order);
    }
}

5.4.1、保存数据

结果如下：

14:34:08 180 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 181 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_2 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:07.717, 7601, , 1000, 845308485917736960]
14:34:08 231 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 231 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_1 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.23, 7175, , 1000, 845308486400081921]
14:34:08 255 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 256 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_2 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.254, 5318, , 1000, 845308486504939520]
14:34:08 277 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 278 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_1 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.276, 5490, , 1000, 845308486597214209]
14:34:08 299 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 300 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_2 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.298, 7559, , 1000, 845308486689488896]
14:34:08 321 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 321 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_1 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.32, 9422, , 1000, 845308486777569281]
14:34:08 342 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 343 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_2 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.341, 7935, , 1000, 845308486869843968]
14:34:08 362 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 363 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_1 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.361, 8939, , 1000, 845308486953730049]
14:34:08 383 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 383 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_2 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.382, 7499, , 1000, 845308487041810432]
14:34:08 408 INFO [main]:Logic SQL: insert into tb_order (order_status, order_time, price, title, user_id) values (?, ?, ?, ?, ?)
14:34:08 408 INFO [main]:Actual SQL: ds1 ::: insert into tb_order_1 (order_status, order_time, price, title, user_id, order_id) values (?, ?, ?, ?, ?, ?) ::: [2, 2023-03-22 14:34:08.407, 9598, , 1000, 845308487146668033]

效果图：

在这里插入图片描述

5.4.2、查询数据

从上面的结果我们可以看到order_id为 845308485917736960 的记录在 tb_order_2 表，我们查询时实际的查询也是去这个表中查的，请看下面的 Actual SQL

15:03:09 579 INFO [main]:Logic SQL: select order0_.order_id as order_id1_0_, order0_.order_status as order_st2_0_, order0_.order_time as order_ti3_0_, order0_.price as price4_0_, order0_.title as title5_0_, order0_.user_id as user_id6_0_ from tb_order order0_ where order0_.order_id=?
15:03:09 580 INFO [main]:Actual SQL: ds1 ::: select order0_.order_id as order_id1_0_, order0_.order_status as order_st2_0_, order0_.order_time as order_ti3_0_, order0_.price as price4_0_, order0_.title as title5_0_, order0_.user_id as user_id6_0_ from tb_order_2 order0_ where order0_.order_id=? ::: [845308485917736960]
15:03:09 621 INFO [main]:查询的结果：Order(orderId=845308485917736960, userId=1000, price=7601, orderStatus=2, title=, orderTime=2023-03-22T14:34:08)