[MyBatis]五分钟向MySql数据库插入一千万条数据 批量插入 用时5分左右

本例代码下载：https://files.cnblogs.com/files/xiandedanteng/InsertMillionComparison20191012.rar

我的数据库环境是mysql Ver 14.14 Distrib 5.6.45, for Linux (x86_64) using EditLine wrapper

这个数据库是安装在T440p的虚拟机上的，操作系统为CentOs6.5.

插入一千万条数据，一次执行时间是4m57s，一次是5m。

数据表的定义是这样的：

CREATE TABLE `emp` (
  `Id` int(11) NOT NULL AUTO_INCREMENT,
  `name` varchar(255) DEFAULT NULL,
  `age` smallint(3) DEFAULT NULL,
  `cdate` timestamp NULL DEFAULT NULL COMMENT 'createtime',
  PRIMARY KEY (`Id`)
) ENGINE=InnoDB AUTO_INCREMENT=13548008 DEFAULT CHARSET=utf8;

这是一个以id为自增主键，包含了三种不同类型字段的简单表。

我使用MyBatis的Batch Insert功能给数据表插入数据，其SQL在Mapper中定义成这样：

<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE mapper PUBLIC "-//mybatis.org//DTD Mapper 3.0//EN" 
                    "http://mybatis.org/dtd/mybatis-3-mapper.dtd" >
<mapper namespace="com.hy.mapper.EmpMapper">
    <select id="selectById" resultType="com.hy.entity.Employee">
        select id,name,age,cdate as ctime  from emp where id=#{id}
    </select>
    
    <insert id="batchInsert">
        insert into emp(name,age,cdate)
        values
        <foreach collection="list" item="emp" separator=",">
            (#{emp.name},#{emp.age},#{emp.ctime,jdbcType=TIMESTAMP})
        </foreach>
    </insert>
</mapper>

与之对应的接口类是这样的：

package com.hy.mapper;

import java.util.List;

import com.hy.entity.Employee;

public interface EmpMapper {
    Employee selectById(long id);
    int batchInsert(List<Employee> emps);
}

实体类Employee如下：

package com.hy.entity;

import java.text.MessageFormat;

public class Employee {
    private long id;
    private String name;
    private int age;
    private String ctime;
    
    public Employee() {
        
    }
    
    public Employee(String name,int age,String ctime) {
        this.name=name;
        this.age=age;
        this.ctime=ctime;
    }
    
    public String toString() {
        Object[] arr={id,name,age,ctime};
        String retval=MessageFormat.format("Employee id={0},name={1},age={2},created_datetime={3}", arr);
        return retval;
    }
    
    public long getId() {
        return id;
    }
    public void setId(long id) {
        this.id = id;
    }
    public String getName() {
        return name;
    }
    public void setName(String name) {
        this.name = name;
    }
    public int getAge() {
        return age;
    }
    public void setAge(int age) {
        this.age = age;
    }
    public String getCtime() {
        return ctime;
    }
    public void setCtime(String ctime) {
        this.ctime = ctime;
    }
}

如果插入数据不多可以这样书写：

package com.hy.action;

import java.io.Reader;
import java.util.ArrayList;
import java.util.List;

import org.apache.ibatis.io.Resources;
import org.apache.ibatis.session.SqlSession;
import org.apache.ibatis.session.SqlSessionFactory;
import org.apache.ibatis.session.SqlSessionFactoryBuilder;
import org.apache.log4j.Logger;

import com.hy.entity.Employee;
import com.hy.mapper.EmpMapper;

public class BatchInsert01 {
private static Logger logger = Logger.getLogger(SelectById.class);
    
    public static void main(String[] args) throws Exception{
        Reader reader=Resources.getResourceAsReader("mybatis-config.xml");
        
        SqlSessionFactory ssf=new SqlSessionFactoryBuilder().build(reader);
        reader.close();
        
        SqlSession session=ssf.openSession();
        
        try {
            EmpMapper mapper=session.getMapper(EmpMapper.class);
            
            List<Employee> emps=new ArrayList<Employee>();
            emps.add(new Employee("Bill",22,"2018-12-25"));
            emps.add(new Employee("Cindy",22,"2018-12-25"));
            emps.add(new Employee("Douglas",22,"2018-12-25"));
            
            
            int changed=mapper.batchInsert(emps);
            System.out.println("changed="+changed);
            session.commit();
        }catch(Exception ex) {
            logger.error(ex);
            session.rollback();
        }finally {
            session.close();
        }
    }
}

如果插入数据多，就必须采用分批提交的方式，我采用的是插入一千个数据后提交一次，然后重复一万次的方式：

package com.hy.action;

import java.io.Reader;
import java.util.ArrayList;
import java.util.List;

import org.apache.ibatis.io.Resources;
import org.apache.ibatis.session.SqlSession;
import org.apache.ibatis.session.SqlSessionFactory;
import org.apache.ibatis.session.SqlSessionFactoryBuilder;
import org.apache.log4j.Logger;

import com.hy.entity.Employee;
import com.hy.mapper.EmpMapper;

public class BatchInsert1000 {
private static Logger logger = Logger.getLogger(SelectById.class);
    
    public static void main(String[] args) throws Exception{
        long startTime = System.currentTimeMillis();
        
        Reader reader=Resources.getResourceAsReader("mybatis-config.xml");
        
        SqlSessionFactory ssf=new SqlSessionFactoryBuilder().build(reader);
        reader.close();
        
        SqlSession session=ssf.openSession();
        
        try {
            EmpMapper mapper=session.getMapper(EmpMapper.class);
            String ctime="2017-11-01 00:00:01";
            
            for(int i=0;i<10000;i++) {
                List<Employee> emps=new ArrayList<Employee>();

                for(int j=0;j<1000;j++) {
                    Employee emp=new Employee("E"+i,20,ctime);
                    emps.add(emp);    
                }
                
                int changed=mapper.batchInsert(emps);
                session.commit();
                System.out.println("#"+i+" changed="+changed);
                
            }
        }catch(Exception ex) {
            session.rollback();
            logger.error(ex);
        }finally {
            session.close();
            
            long endTime = System.currentTimeMillis();
            logger.info("Time elapsed:" + toDhmsStyle((endTime - startTime)/1000) + ".");
        }
    }
    
    // format seconds to day hour minute seconds style
    // Example 5000s will be formatted to 1h23m20s
    public static String toDhmsStyle(long allSeconds) {
        String DateTimes = null;
        
        long days = allSeconds / (60 * 60 * 24);
        long hours = (allSeconds % (60 * 60 * 24)) / (60 * 60);
        long minutes = (allSeconds % (60 * 60)) / 60;
        long seconds = allSeconds % 60;
        
        if (days > 0) {
            DateTimes = days + "d" + hours + "h" + minutes + "m" + seconds + "s";
        } else if (hours > 0) {
            DateTimes = hours + "h" + minutes + "m" + seconds + "s";
        } else if (minutes > 0) {
            DateTimes = minutes + "m" + seconds + "s";
        } else {
            DateTimes = seconds + "s";
        }

        return DateTimes;
    }
}

最后查询数据库，结果如下：

当然插入过程中还有一些插曲，在后继篇章中我会说明。

--END-- 2019年10月12日16:52:14