索引与慢查询优化

#1. 准备表
create table s1(
id int,
name varchar(20),
gender char(6),
email varchar(50)
);

#2. 创建存储过程，实现批量插入记录
delimiter $$ #声明存储过程的结束符号为$$
create procedure auto_insert1()
BEGIN
    declare i int default 1;
    while(i<3000000)do
        insert into s1 values(i,‘jason‘,‘male‘,concat(‘jason‘,i,‘@oldboy‘));
        set i=i+1;
    end while;
END$$ #$$结束
delimiter ; #重新声明 分号为结束符号

#3. 查看存储过程
show create procedure auto_insert1\G 

#4. 调用存储过程
call auto_insert1();
```

``` mysql 
# 表没有任何索引的情况下
select * from s1 where id=30000;
# 避免打印带来的时间损耗
select count(id) from s1 where id = 30000;
select count(id) from s1 where id = 1;

# 给id做一个主键
alter table s1 add primary key(id);  # 速度很慢

select count(id) from s1 where id = 1;  # 速度相较于未建索引之前两者差着数量级
select count(id) from s1 where name = ‘jason‘  # 速度仍然很慢


"""
范围问题
"""
# 并不是加了索引，以后查询的时候按照这个字段速度就一定快   
select count(id) from s1 where id > 1;  # 速度相较于id = 1慢了很多
select count(id) from s1 where id >1 and id < 3;
select count(id) from s1 where id > 1 and id < 10000;
select count(id) from s1 where id != 3;

alter table s1 drop primary key;  # 删除主键 单独再来研究name字段
select count(id) from s1 where name = ‘jason‘;  # 又慢了

create index idx_name on s1(name);  # 给s1表的name字段创建索引
select count(id) from s1 where name = ‘jason‘  # 仍然很慢！！！
"""
再来看b+树的原理，数据需要区分度比较高，而我们这张表全是jason，根本无法区分
那这个树其实就建成了“一根棍子”
"""
select count(id) from s1 where name = ‘xxx‘;  
# 这个会很快，我就是一根棍，第一个不匹配直接不需要再往下走了
select count(id) from s1 where name like ‘xxx‘;
select count(id) from s1 where name like ‘xxx%‘;
select count(id) from s1 where name like ‘%xxx‘;  # 慢 最左匹配特性

# 区分度低的字段不能建索引
drop index idx_name on s1;

# 给id字段建普通的索引
create index idx_id on s1(id);
select count(id) from s1 where id = 3;  # 快了
select count(id) from s1 where id*12 = 3;  # 慢了  索引的字段一定不要参与计算

drop index idx_id on s1;
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id = 3 and email = ‘xxx‘;
# 针对上面这种连续多个and的操作，mysql会从左到右先找区分度比较高的索引字段，先将整体范围降下来再去比较其他条件
create index idx_name on s1(name);
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id = 3 and email = ‘xxx‘;  # 并没有加速

drop index idx_name on s1;
# 给name，gender这种区分度不高的字段加上索引并不难加快查询速度

create index idx_id on s1(id);
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id = 3 and email = ‘xxx‘;  # 快了  先通过id已经讲数据快速锁定成了一条了
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id > 3 and email = ‘xxx‘;  # 慢了  基于id查出来的数据仍然很多，然后还要去比较其他字段

drop index idx_id on s1

create index idx_email on s1(email);
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id > 3 and email = ‘xxx‘;  # 快 通过email字段一剑封喉 
```

#### 联合索引

```mysql
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id > 3 and email = ‘xxx‘;  
# 如果上述四个字段区分度都很高，那给谁建都能加速查询
# 给email加然而不用email字段
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id > 3; 
# 给name加然而不用name字段
select count(id) from s1 where gender = ‘male‘ and id > 3; 
# 给gender加然而不用gender字段
select count(id) from s1 where id > 3; 

# 带来的问题是所有的字段都建了索引然而都没有用到，还需要花费四次建立的时间
create index idx_all on s1(email,name,gender,id);  # 最左匹配原则，区分度高的往左放
select count(id) from s1 where name=‘jason‘ and gender = ‘male‘ and id > 3 and email = ‘xxx‘;  # 速度变快
```

总结:上面这些操作，你感兴趣可以敲一敲，不感兴趣你就可以不用敲了，权当看个乐呵。理论掌握了就行了

慢查询日志

设定一个时间检测所有超出改时间的sql语句，然后针对性的进行优化！