Mysql使用索引的正确方法及索引原理详解

#方法一：创建表时
 　　CREATE TABLE 表名 (
 字段名1 数据类型 [完整性约束条件…],
 字段名2 数据类型 [完整性约束条件…],
 [UNIQUE | FULLTEXT | SPATIAL ] INDEX | KEY
 [索引名] (字段名[(长度)] [ASC |DESC]) 
 );


#方法二：CREATE在已存在的表上创建索引
 CREATE [UNIQUE | FULLTEXT | SPATIAL ] INDEX 索引名 
 ON 表名 (字段名[(长度)] [ASC |DESC]) ;


#方法三：ALTER TABLE在已存在的表上创建索引
 ALTER TABLE 表名 ADD [UNIQUE | FULLTEXT | SPATIAL ] INDEX
 索引名 (字段名[(长度)] [ASC |DESC]) ;
 
#删除索引：DROP INDEX 索引名 ON 表名字;

#方式一
create table t1(
 id int,
 name char,
 age int,
 sex enum('male','female'),
 unique key uni_id(id),
 index ix_name(name) #index没有key
);


#方式二
create index ix_age on t1(age);

#方式三
alter table t1 add index ix_sex(sex);

#查看
mysql> show create table t1;
| t1 | CREATE TABLE `t1` (
 `id` int(11) DEFAULT NULL,
 `name` char(1) DEFAULT NULL,
 `age` int(11) DEFAULT NULL,
 `sex` enum('male','female') DEFAULT NULL,
 UNIQUE KEY `uni_id` (`id`),
 KEY `ix_name` (`name`),
 KEY `ix_age` (`age`),
 KEY `ix_sex` (`sex`)
) ENGINE=InnoDB DEFAULT CHARSET=latin1

#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,'duoduo','male',concat('duoduo',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();

#等到时间长短，看机器性能

#无索引：mysql根本就不知道到底是否存在id等于333333333的记录，只能把数据表从头到尾扫描一遍，此时有多少个磁盘块就需要进行多少IO操作，所以查询速度很慢
mysql> select * from s1 where id=333333333;
Empty set (0.33 sec)

#先把表中的索引都删除，让我们专心研究区分度的问题
mysql> desc s1;
+--------+-------------+------+-----+---------+-------+
| Field | Type | Null | Key | Default | Extra |
+--------+-------------+------+-----+---------+-------+
| id | int(11) | YES | MUL | NULL | |
| name | varchar(20) | YES | | NULL | |
| gender | char(5) | YES | | NULL | |
| email | varchar(50) | YES | MUL | NULL | |
+--------+-------------+------+-----+---------+-------+
rows in set (0.00 sec)

mysql> drop index a on s1;
Query OK, 0 rows affected (0.20 sec)
Records: 0 Duplicates: 0 Warnings: 0

mysql> drop index d on s1;
Query OK, 0 rows affected (0.18 sec)
Records: 0 Duplicates: 0 Warnings: 0

mysql> desc s1;
+--------+-------------+------+-----+---------+-------+
| Field | Type | Null | Key | Default | Extra |
+--------+-------------+------+-----+---------+-------+
| id | int(11) | YES | | NULL | |
| name | varchar(20) | YES | | NULL | |
| gender | char(5) | YES | | NULL | |
| email | varchar(50) | YES | | NULL | |
+--------+-------------+------+-----+---------+-------+
rows in set (0.00 sec)

- 使用函数
 select * from tb1 where reverse(email) = 'duoduo';
 
- 类型不一致
 如果列是字符串类型，传入条件是必须用引号引起来，不然...
 select * from tb1 where email = 999;
 
#排序条件为索引，则select字段必须也是索引字段，否则无法命中
- order by
 select name from s1 order by email desc;
 当根据索引排序时候，select查询的字段如果不是索引，则速度仍然很慢
 select email from s1 order by email desc;
 特别的：如果对主键排序，则还是速度很快：
 select * from tb1 order by nid desc;
 
- 组合索引最左前缀
 如果组合索引为：(name,email)
 name and email -- 命中索引
 name -- 命中索引
 email -- 未命中索引


- count(1)或count(列)代替count(*)在mysql中没有差别了

- create index xxxx on tb(title(19)) #text类型，必须制定长度

mysql> create table t(
 -> a int,
 -> b int,
 -> primary key(a),
 -> key idx_a_b(a,b)
 -> );
Query OK, 0 rows affected (0.11 sec)

#===========准备表==============
create table buy_log(
 userid int unsigned not null,
 buy_date date
);

insert into buy_log values
(1,'2009-01-01'),
(2,'2009-01-01'),
(3,'2009-01-01'),
(1,'2009-02-01'),
(3,'2009-02-01'),
(1,'2009-03-01'),
(1,'2009-04-01');

alter table buy_log add key(userid);
alter table buy_log add key(userid,buy_date);

#===========验证==============
mysql> show create table buy_log;
| buy_log | CREATE TABLE `buy_log` (
 `userid` int(10) unsigned NOT NULL,
 `buy_date` date DEFAULT NULL,
 KEY `userid` (`userid`),
 KEY `userid_2` (`userid`,`buy_date`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 |

#可以看到possible_keys在这里有两个索引可以用，分别是单个索引userid与联合索引userid_2,但是优化器最终选择了使用的key是userid因为该索引的叶子节点包含单个键值，所以理论上一个页能存放的记录应该更多
mysql> explain select * from buy_log where userid=2;
+----+-------------+---------+------+-----------------+--------+---------+-------+------+-------+
| id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra |
+----+-------------+---------+------+-----------------+--------+---------+-------+------+-------+
| 1 | SIMPLE | buy_log | ref | userid,userid_2 | userid | 4 | const | 1 | |
+----+-------------+---------+------+-----------------+--------+---------+-------+------+-------+
row in set (0.00 sec)

#接着假定要取出userid为1的最近3次的购买记录，用的就是联合索引userid_2了，因为在这个索引中，在userid=1的情况下，buy_date都已经排序好了
mysql> explain select * from buy_log where userid=1 order by buy_date desc limit 3;
+----+-------------+---------+------+-----------------+----------+---------+-------+------+--------------------------+
| id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra |
+----+-------------+---------+------+-----------------+----------+---------+-------+------+--------------------------+
| 1 | SIMPLE | buy_log | ref | userid,userid_2 | userid_2 | 4 | const | 4 | Using where; Using index |
+----+-------------+---------+------+-----------------+----------+---------+-------+------+--------------------------+
row in set (0.00 sec)

#ps：如果extra的排序显示是Using filesort，则意味着在查出数据后需要二次排序


#对于联合索引（a,b）,下述语句可以直接使用该索引，无需二次排序
select ... from table where a=xxx order by b;

#然后对于联合索引(a,b,c)来首，下列语句同样可以直接通过索引得到结果
select ... from table where a=xxx order by b;
select ... from table where a=xxx and b=xxx order by c;

#但是对于联合索引(a,b,c)，下列语句不能通过索引直接得到结果，还需要自己执行一次filesort操作，因为索引（a，c)并未排序
select ... from table where a=xxx order by c;

select age from s1 where id=123 and name = 'duoduo'; #id字段有索引，但是name字段没有索引,该sql命中了索引，但未覆盖，需要去聚集索引中再查找详细信息。
最牛逼的情况是，索引字段覆盖了所有，那全程通过索引来加速查询以及获取结果就ok了
mysql> desc s1;
+--------+-------------+------+-----+---------+-------+
| Field | Type | Null | Key | Default | Extra |
+--------+-------------+------+-----+---------+-------+
| id | int(11) | NO | | NULL | |
| name | varchar(20) | YES | | NULL | |
| gender | char(6) | YES | | NULL | |
| email | varchar(50) | YES | | NULL | |
+--------+-------------+------+-----+---------+-------+
rows in set (0.21 sec)

mysql> explain select name from s1 where id=1000; #没有任何索引
+----+-------------+-------+------------+------+---------------+------+---------+------+---------+----------+-------------+
| id | select_type | table | partitions | type | possible_keys | key | key_len | ref | rows | filtered | Extra |
+----+-------------+-------+------------+------+---------------+------+---------+------+---------+----------+-------------+
| 1 | SIMPLE | s1 | NULL | ALL | NULL | NULL | NULL | NULL | 2688336 | 10.00 | Using where |
+----+-------------+-------+------------+------+---------------+------+---------+------+---------+----------+-------------+
row in set, 1 warning (0.00 sec)

mysql> create index idx_id on s1(id); #创建索引
Query OK, 0 rows affected (4.16 sec)
Records: 0 Duplicates: 0 Warnings: 0

mysql> explain select name from s1 where id=1000; #命中辅助索引，但是未覆盖索引，还需要从聚集索引中查找name
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------+
| id | select_type | table | partitions | type | possible_keys | key | key_len | ref | rows | filtered | Extra |
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------+
| 1 | SIMPLE | s1 | NULL | ref | idx_id | idx_id | 4 | const | 1 | 100.00 | NULL |
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------+
row in set, 1 warning (0.08 sec)

mysql> explain select id from s1 where id=1000; #在辅助索引中就找到了全部信息，Using index代表覆盖索引
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------------+
| id | select_type | table | partitions | type | possible_keys | key | key_len | ref | rows | filtered | Extra |
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------------+
| 1 | SIMPLE | s1 | NULL | ref | idx_id | idx_id | 4 | const | 1 | 100.00 | Using index |
+----+-------------+-------+------------+------+---------------+--------+---------+-------+------+----------+-------------+
row in set, 1 warning (0.03 sec)

mysql> explain select count(*) from buy_log;
+----+-------------+---------+-------+---------------+--------+---------+------+------+-------------+
| id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra |
+----+-------------+---------+-------+---------------+--------+---------+------+------+-------------+
| 1 | SIMPLE | buy_log | index | NULL | userid | 4 | NULL | 7 | Using index |
+----+-------------+---------+-------+---------------+--------+---------+------+------+-------------+
row in set (0.00 sec)

#联合索引userid_2（userid,buy_date）,一般情况，我们按照buy_date是无法使用该索引的，但特殊情况下：查询语句是统计操作，且是覆盖索引，则按照buy_date当做查询条件时，也可以使用该联合索引
mysql> explain select count(*) from buy_log where buy_date >= '2011-01-01' and buy_date < '2011-02-01';
+----+-------------+---------+-------+---------------+----------+---------+------+------+--------------------------+
| id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra |
+----+-------------+---------+-------+---------------+----------+---------+------+------+--------------------------+
| 1 | SIMPLE | buy_log | index | NULL | userid_2 | 8 | NULL | 7 | Using where; Using index |
+----+-------------+---------+-------+---------------+----------+---------+------+------+--------------------------+
row in set (0.00 sec)

# vim /etc/my.cnf
[mysqld]
log-bin[=dir\[filename]]
# service mysqld restart

//仅当前会话
SET SQL_LOG_BIN=0;
SET SQL_LOG_BIN=1;

# mysqlbinlog mysql.000002
按时间：
# mysqlbinlog mysql.000002 --start-datetime="2012-12-05 10:02:56"
# mysqlbinlog mysql.000002 --stop-datetime="2012-12-05 11:02:54"
# mysqlbinlog mysql.000002 --start-datetime="2012-12-05 10:02:56" --stop-datetime="2012-12-05 11:02:54" 

# mysqlbinlog mysql.000002 --start-position=260
# mysqlbinlog mysql.000002 --stop-position=260
# mysqlbinlog mysql.000002 --start-position=260 --stop-position=930

# mysql -uroot -p123 -e 'reset master' 

# vim /etc/my.cnf
[mysqld]
log[=dir\[filename]]
# service mysqld restart

# vim /etc/my.cnf
[mysqld]
log-slow-queries[=dir\[filename]]
long_query_time=n
# service mysqld restart

slow-query-log=1
slow-query-log-file=slow.log
long_query_time=3

BENCHMARK(count,expr)
SELECT BENCHMARK(50000000,2*3);