文章目录
1. 简述数据库调优
- 索引失效、没有充分利用到索引–索引建立
- 关联查询太多JOIN(设计缺陷或不得已的需求)—-SQL优化
- 服务器调优及各个参数设置(缓冲、线程数等)–调整my.cnf
- 数据过多–分库分表
虽然SQL查询优化的技术有很多,I但是大方向上完全可以分成物理查询优化
和逻辑查询优化
两大块。
- 物理查询优化是通过
索引
和表连接
方式等技术来进行优化,这里重点需要掌握索引的使用。 - 逻辑查询优化就是通过SQL
等价变换
提升查询效率,直白一点就是说,换一种查询写法执行效率可能更高。
2. 索引失效案例
2.1 数据的准备
#1. 数据准备
CREATE DATABASE atguigudb2;
USE atguigudb2;
#建表
CREATE TABLE `class` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`className` VARCHAR(30) DEFAULT NULL,
`address` VARCHAR(40) DEFAULT NULL,
`monitor` INT NULL ,
PRIMARY KEY (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
CREATE TABLE `student` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`stuno` INT NOT NULL ,
`name` VARCHAR(20) DEFAULT NULL,
`age` INT(3) DEFAULT NULL,
`classId` INT(11) DEFAULT NULL,
PRIMARY KEY (`id`)
#CONSTRAINT `fk_class_id` FOREIGN KEY (`classId`) REFERENCES `t_class` (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
SET GLOBAL log_bin_trust_function_creators=1;
#随机产生字符串
DELIMITER //
CREATE FUNCTION rand_string(n INT) RETURNS VARCHAR(255)
BEGIN
DECLARE chars_str VARCHAR(100) DEFAULT 'abcdefghijklmnopqrstuvwxyzABCDEFJHIJKLMNOPQRSTUVWXYZ';
DECLARE return_str VARCHAR(255) DEFAULT '';
DECLARE i INT DEFAULT 0;
WHILE i < n DO
SET return_str =CONCAT(return_str,SUBSTRING(chars_str,FLOOR(1+RAND()*52),1));
SET i = i + 1;
END WHILE;
RETURN return_str;
END //
DELIMITER ;
#用于随机产生多少到多少的编号
DELIMITER //
CREATE FUNCTION rand_num (from_num INT ,to_num INT) RETURNS INT(11)
BEGIN
DECLARE i INT DEFAULT 0;
SET i = FLOOR(from_num +RAND()*(to_num - from_num+1)) ;
RETURN i;
END //
DELIMITER ;
#创建往stu表中插入数据的存储过程
DELIMITER //
CREATE PROCEDURE insert_stu( START INT , max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0; #设置手动提交事务
REPEAT #循环
SET i = i + 1; #赋值
INSERT INTO student (stuno, NAME ,age ,classId ) VALUES ((START+i),rand_string(6),rand_num(1,50),rand_num(1,1000));
UNTIL i = max_num
END REPEAT;
COMMIT; #提交事务
END //
DELIMITER ;
#执行存储过程,往class表添加随机数据
DELIMITER //
CREATE PROCEDURE `insert_class`( max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0;
REPEAT
SET i = i + 1;
INSERT INTO class ( classname,address,monitor ) VALUES (rand_string(8),rand_string(10),rand_num(1,100000));
UNTIL i = max_num
END REPEAT;
COMMIT;
END //
DELIMITER ;
#执行存储过程,往class表添加1万条数据
CALL insert_class(10000);
#执行存储过程,往stu表添加50万条数据
CALL insert_stu(100000,500000);
SELECT COUNT(*) FROM class;
SELECT COUNT(*) FROM student;
DELIMITER //
CREATE PROCEDURE `proc_drop_index`(dbname VARCHAR(200),tablename VARCHAR(200))
BEGIN
DECLARE done INT DEFAULT 0;
DECLARE ct INT DEFAULT 0;
DECLARE _index VARCHAR(200) DEFAULT '';
DECLARE _cur CURSOR FOR SELECT index_name FROM information_schema.STATISTICS WHERE table_schema=dbname AND table_name=tablename AND seq_in_index=1 AND index_name <>'PRIMARY' ;
#每个游标必须使用不同的declare continue handler for not found set done=1来控制游标的结束
DECLARE CONTINUE HANDLER FOR NOT FOUND SET done=2 ;
#若没有数据返回,程序继续,并将变量done设为2
OPEN _cur;
FETCH _cur INTO _index;
WHILE _index<>'' DO
SET @str = CONCAT("drop index " , _index , " on " , tablename );
PREPARE sql_str FROM @str ;
EXECUTE sql_str;
DEALLOCATE PREPARE sql_str;
SET _index='';
FETCH _cur INTO _index;
END WHILE;
CLOSE _cur;
END //
DELIMITER ;
2.2 索引的作用
MySQL中提高性能的一个最有效的方式是对数据表设计合理的索引。索引提供了高效访问数据的方法,并且加快查询的速度,因此索引对查询的速度有着至关重要的影响。
- 使用索引可以
快速地定位表
中的某条记录,从而提高数据库查询的速度,提高数据库的性能。 - 如果查询时没有使用索引,查询语句就会
扫描表中的所有记录
。在数据量大的情况下,这样查询的速度会很慢。
大多数情况下都(默认)采用B+树
来构建索引。只是空间列类型的索引使用R-树
,并且MEMORY表还支持hash索引
。
用不用索引,最终都是优化器说了算。优化器是基于什么的优化器?基于cost开销
(CostBaseOptimizer),它不是基于规则
(Rule-BasedOptimizer),也不是基于语义
。怎么样开销小就怎么来。另外,SQL语句是否使用索引,跟数据库版本、数据量、数据选择度
都有关系。
2.3 全值匹配我最爱
#1)全值匹配我最爱
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
CREATE INDEX idx_age ON student(age);
CREATE INDEX idx_age_classid ON student(age,classId);
CREATE INDEX idx_age_classid_name ON student(age,classId,NAME);
2.4 最佳左前缀法则
#2)最佳左前缀法则
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.age=30 AND student.name = 'abcd' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.classid=1 AND student.name = 'abcd';
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE classid=4 AND student.age=30 AND student.name = 'abcd';
DROP INDEX idx_age ON student;
DROP INDEX idx_age_classid ON student;
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abcd';
2.5 主键插入顺序
对于一个使用InnoDB存储引擎
的表来说,在我们没有显式的创建索引时,表中的数据实际上都是存储在聚簇索引的叶子节点的。而记录又是存储在数据页中的,数据页和记录又是按照记录主键值从小到大
的顺序进行排序,所以如果我们插入的记录的主键值是依次增大的话,那我们每插满一个数据页就换到下一个数据页继续插,而如果我们插入的主键值忽大忽小的话,效率很低,最好能让插入的记录主键依次递增
。
2.6 计算、函数、类型转换(自动或手动)导致索引失效
#4)计算、函数、类型转换(自动或手动)导致索引失效
#此语句比下一条要好!(能够使用上索引)
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name LIKE 'abc%';
#先遍历运行函数,后比较,不能用上索引
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE LEFT(student.name,3) = 'abc';
CREATE INDEX idx_name ON student(NAME);
#
CREATE INDEX idx_sno ON student(stuno);
#先遍历计算,后比较,不能使用索引
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno+1 = 900001;
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno = 900000;
#先遍历进行类型转换,后比较,不能使用索引
EXPLAIN SELECT id, stuno, NAME FROM student WHERE SUBSTRING(NAME, 1,3)='abc';
2.7 范围条件右边的列索引失效
#6)范围条件右边的列索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age_classId_name ON student(age,classId,NAME);
#name没用上,因为classId是范围查询,后面的索引就用不上了
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.classId>20 AND student.name = 'abc' ;
#跟上面执行一样,优化器会调整顺序
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abc' AND student.classId>20;
#将范围查询写在最后就可以了
CREATE INDEX idx_age_name_cid ON student(age,NAME,classId);
应用开发中范围查询,例如:金额查询,日期查询往往都是范围查询。应将查询条件放置where语句最后。(创建的联合索引中,务必把范围涉及到的字段写在最后)
2.8 不等于(!= 或者<>)索引失效
#7)不等于(!= 或者<>)索引失效
CREATE INDEX idx_name ON student(NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name <> 'abc' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name != 'abc' ;
2.9 is null可以使用索引,is not null无法使用索引
#8)is null可以使用索引,is not null无法使用索引
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NULL;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NOT NULL;
结论:最好在设计数据表的时候就将字段设置为NOTNULL约束,比如你可以将INT类型的字段,默认值设置为0。将字符类型的默认值设置为空字符串()。
拓展:同理,在查询中使用not like也无法使用索引,导致全表扫描。
2.10 like以通配符%开头索引失效
#9)like以通配符%开头索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE 'ab%';
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE '%ab%';
2.11 OR 前后存在非索引的列,索引失效
在WHERE子句中,如果在OR前的条件列进行了索引,而在OR后的条件列没有进行索引,那么索引会失效。也就是说,OR前后的两个条件中的列都是索引时
,查询中才使用索引。
因为OR的含义就是两个只要满足一个即可,因此只有一个条件列进行了索引是没有意义的,只要有条件列没有进行索引,就会进行全表扫描,因此索引的条件列也会失效。
查询语句使用OR关键字的情况:
#10)OR 前后存在非索引的列,索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age ON student(age);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 10 OR classid = 100;
CREATE INDEX idx_cid ON student(classid);
2.12 数据库和表的字符集统一使用utf8mb4
统一使用utf8mb4(5.5.3版本以上支持)兼容性更好,统一字符集可以避免由于字符集转换产生的乱码。不同的字符集进行比较前需要进行转换会造成索引失效
。
2.13 代码演示
# 06-索引优化与查询优化
#1. 数据准备
CREATE DATABASE atguigudb2;
USE atguigudb2;
#建表
CREATE TABLE `class` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`className` VARCHAR(30) DEFAULT NULL,
`address` VARCHAR(40) DEFAULT NULL,
`monitor` INT NULL ,
PRIMARY KEY (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
CREATE TABLE `student` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`stuno` INT NOT NULL ,
`name` VARCHAR(20) DEFAULT NULL,
`age` INT(3) DEFAULT NULL,
`classId` INT(11) DEFAULT NULL,
PRIMARY KEY (`id`)
#CONSTRAINT `fk_class_id` FOREIGN KEY (`classId`) REFERENCES `t_class` (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
SET GLOBAL log_bin_trust_function_creators=1;
#随机产生字符串
DELIMITER //
CREATE FUNCTION rand_string(n INT) RETURNS VARCHAR(255)
BEGIN
DECLARE chars_str VARCHAR(100) DEFAULT 'abcdefghijklmnopqrstuvwxyzABCDEFJHIJKLMNOPQRSTUVWXYZ';
DECLARE return_str VARCHAR(255) DEFAULT '';
DECLARE i INT DEFAULT 0;
WHILE i < n DO
SET return_str =CONCAT(return_str,SUBSTRING(chars_str,FLOOR(1+RAND()*52),1));
SET i = i + 1;
END WHILE;
RETURN return_str;
END //
DELIMITER ;
#用于随机产生多少到多少的编号
DELIMITER //
CREATE FUNCTION rand_num (from_num INT ,to_num INT) RETURNS INT(11)
BEGIN
DECLARE i INT DEFAULT 0;
SET i = FLOOR(from_num +RAND()*(to_num - from_num+1)) ;
RETURN i;
END //
DELIMITER ;
#创建往stu表中插入数据的存储过程
DELIMITER //
CREATE PROCEDURE insert_stu( START INT , max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0; #设置手动提交事务
REPEAT #循环
SET i = i + 1; #赋值
INSERT INTO student (stuno, NAME ,age ,classId ) VALUES ((START+i),rand_string(6),rand_num(1,50),rand_num(1,1000));
UNTIL i = max_num
END REPEAT;
COMMIT; #提交事务
END //
DELIMITER ;
#执行存储过程,往class表添加随机数据
DELIMITER //
CREATE PROCEDURE `insert_class`( max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0;
REPEAT
SET i = i + 1;
INSERT INTO class ( classname,address,monitor ) VALUES (rand_string(8),rand_string(10),rand_num(1,100000));
UNTIL i = max_num
END REPEAT;
COMMIT;
END //
DELIMITER ;
#执行存储过程,往class表添加1万条数据
CALL insert_class(10000);
#执行存储过程,往stu表添加50万条数据
CALL insert_stu(100000,500000);
SELECT COUNT(*) FROM class;
SELECT COUNT(*) FROM student;
DELIMITER //
CREATE PROCEDURE `proc_drop_index`(dbname VARCHAR(200),tablename VARCHAR(200))
BEGIN
DECLARE done INT DEFAULT 0;
DECLARE ct INT DEFAULT 0;
DECLARE _index VARCHAR(200) DEFAULT '';
DECLARE _cur CURSOR FOR SELECT index_name FROM information_schema.STATISTICS WHERE table_schema=dbname AND table_name=tablename AND seq_in_index=1 AND index_name <>'PRIMARY' ;
#每个游标必须使用不同的declare continue handler for not found set done=1来控制游标的结束
DECLARE CONTINUE HANDLER FOR NOT FOUND SET done=2 ;
#若没有数据返回,程序继续,并将变量done设为2
OPEN _cur;
FETCH _cur INTO _index;
WHILE _index<>'' DO
SET @str = CONCAT("drop index " , _index , " on " , tablename );
PREPARE sql_str FROM @str ;
EXECUTE sql_str;
DEALLOCATE PREPARE sql_str;
SET _index='';
FETCH _cur INTO _index;
END WHILE;
CLOSE _cur;
END //
DELIMITER ;
#2. 索引失效案例
#1)全值匹配我最爱
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
CREATE INDEX idx_age ON student(age);
CREATE INDEX idx_age_classid ON student(age,classId);
CREATE INDEX idx_age_classid_name ON student(age,classId,NAME);
#2)最佳左前缀法则
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.age=30 AND student.name = 'abcd' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.classid=1 AND student.name = 'abcd';
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE classid=4 AND student.age=30 AND student.name = 'abcd';
DROP INDEX idx_age ON student;
DROP INDEX idx_age_classid ON student;
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abcd';
#3)主键插入顺序
#4)计算、函数、类型转换(自动或手动)导致索引失效
#此语句比下一条要好!(能够使用上索引)
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name LIKE 'abc%';
#先遍历运行函数,后比较,不能用上索引
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE LEFT(student.name,3) = 'abc';
CREATE INDEX idx_name ON student(NAME);
#
CREATE INDEX idx_sno ON student(stuno);
#先遍历计算,后比较,不能使用索引
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno+1 = 900001;
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno = 900000;
#先遍历进行类型转换,后比较,不能使用索引
EXPLAIN SELECT id, stuno, NAME FROM student WHERE SUBSTRING(NAME, 1,3)='abc';
#5)类型转换导致索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME = 123;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME = '123';
#6)范围条件右边的列索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age_classId_name ON student(age,classId,NAME);
#name没用上,因为classId是范围查询,后面的索引就用不上了
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.classId>20 AND student.name = 'abc' ;
#跟上面执行一样,优化器会调整顺序
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abc' AND student.classId>20;
#将确定的等值name先创建就可以使用到name了
CREATE INDEX idx_age_name_cid ON student(age,NAME,classId);
#7)不等于(!= 或者<>)索引失效
CREATE INDEX idx_name ON student(NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name <> 'abc' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name != 'abc' ;
#8)is null可以使用索引,is not null无法使用索引
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NULL;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NOT NULL;
#9)like以通配符%开头索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE 'ab%';
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE '%ab%';
#10)OR 前后存在非索引的列,索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age ON student(age);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 10 OR classid = 100;
CREATE INDEX idx_cid ON student(classid);
# 11)数据库和表的字符集统一使用utf8mb4
2.14 总结
- 对于单列索引,尽量选择针对当前query过滤性更好的索引
- 在选择组合索引的时候,当前query中过滤性最好的字段在索引字段顺序中,位置越靠前越好。
- 在选择组合索引的时候,尽量选择能够包含当前query中的where子句中更多字段的索引。
- 在选择组合索引的时候,如果某个字段可能出现范围查询时,尽量把这个字段放在索引次序的最后面。
总之,书写SQL语句时,尽量避免造成索引失效的情况。
3. 关联查询优化
#3. 关联查询优化
# 情况1:左外连接
#分类
CREATE TABLE IF NOT EXISTS `type` (
`id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
`card` INT(10) UNSIGNED NOT NULL,
PRIMARY KEY (`id`)
);
#图书
CREATE TABLE IF NOT EXISTS `book` (
`bookid` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
`card` INT(10) UNSIGNED NOT NULL,
PRIMARY KEY (`bookid`)
);
#向分类表中添加20条记录
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
#向图书表中添加20条记录
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
#添加索引
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
CREATE INDEX X ON `type`(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
DROP INDEX Y ON book;
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
# 情况2:内连接
DROP INDEX X ON `type`;
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#添加索引
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
CREATE INDEX X ON `type`(card);
#结论:对于内连接来说,查询优化器可以决定谁作为驱动表,谁作为被驱动表出现的
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#删除索引
DROP INDEX Y ON book;
#结论:对于内连接来讲,如果表的连接条件中只能有一个字段有索引,则有索引的字段所在的表会被作为被驱动表出现。
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#向type表中添加数据(20条数据)
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
#结论:对于内连接来说,在两个表的连接条件都存在索引的情况下,会选择小表作为驱动表。“小表驱动大表”
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
4. JOIN的底层原理
join方式连接多个表,本质就是各个表之间数据的循环匹配。MySQL5.5版本之前,MySQL只支持一种表间关联方式,就是嵌套循环(Nested LoopJoin)。如果关联表的数据量很大,则join关联的执行时间会非常长。在MySQL5.5以后的版本中,MySQL通过引入BNLJ算法来优化嵌套执行。
4.1 驱动表和被驱动表
驱动表就是主表,被驱动表就是从表、非驱动表。
对于内连接来说
:
select * from A join B on...
对于外连接来说
:
select * from A left join B on...
select * from B right A on...
优化器会根据你查询语句做优化,决定先查哪张表。先查询的那张表就是驱动表,反之就是被驱动表。通过explain关键字可以查看。
4.2 Simple Nested-Loop Join(简单嵌套循环连接)
从表A中取出一条数据1,遍历表B,将匹配到的数据放到result…以此类推,驱动表A中的每一条记录与被驱动表B的记录进行判断:
可以看到这种方式效率是非常低的,以上述表A数据100条,表B数据1000条计算,则A*B=10万次。开销统计如下:
4.3 Index Nested-Loop Join(索引嵌套循环连接)
Index Nested-Loop Join其优化的思路主要是为了减少内层表数据的匹配次数
,所以要求被驱动表上必须有索引才行。通过外层表匹配条件直接与内层表索引进行匹配,避免和内层表的每条记录去进行比较,这样极大的减少了对内层表的匹配次数。
驱动表中的每条记录通过被驱动表的索引进行访问,因为索引查询的成本是比较固定的,故mysql优化器都倾向于使用记录数少的表作为驱动表(外表)。
4.4 Block Nested-Loop Join(块嵌套循环连接)
如果存在索引,那么会使用index的方式进行join,,如果join的列没有索引,被驱动表要扫描的次数太多了。每次访问被驱动表,其表中的记录都会被加载到内存中,“然后再从驱动表中取一条与其匹配,匹配结束后清除内存,然后再从驱动表中加载一条记录,然后把被驱动表的记录在加载到内存匹配,这样周而复始,大大增加了Io的次数。为了减少被驱动表的IO次数,就出现了Block Nested-Loop Join的方式。
不再是逐条获取驱动表的数据,而是一块一块的获取,引入了join buffer缓冲区,将驱动表join相关的部分数据列(大小受join buffer的限制)缓存到join buffer中,然后全表扫描被驱动表,被驱动表的每一条记录一次性和joinbuffer中的所有驱动表记录进行匹配(内存中操作),将简单嵌套循环中的多次比较合并成一次,降低了被驱动表的访问频率。
4.5JOIN小结
- 整体效率比较:INLJ>BNLJ>SNLL
- 永远用小结果集驱动大结果集(其本质就是减少外层循环的数据数量)(小的度量单位指的是表行数*每行大小)
select t1.b,t2.* from t1 straight_join t2 on (t1.b=t2.b) where t2.id<=100;#推荐
select t1.b,t2.* from t2 straight_join t1 on (t1.b=t2.b) where t2.id<=100;#不推荐
- 为被驱动表匹配的条件增加索引(减少内层表的循环匹配次数)
- 增大join buffer size的大小(一次缓存的数据越多,那么内层包的扫表次数就越少)
- 减少驱动表不必要的字段查询(字段越少,join buffer所缓存的数据就越多)
4.6 Hash join
5. 子查询优化
MySQL从4.1版本开始支持子查询,使用子查询可以进行SELECT语句的嵌套查询,即一个SELECT查询的结果作为另一个SELECT语句的条件。子查询可以一次性完成很多逻辑上需要多个步骤才能完成的SQL操作
。
子查询是MySQL的一项重要的功能,可以帮助我们通过一个SQL语句实现比较复杂的查询。但是,子查询的执行效率不高。原因:
- 执行子查询时,MySQL需要为内层查询语句的查询结果
建立一个临时表
,然后外层查询语句从临时表中查询记录。查询完毕后,再撤销这些临时表
。这样会消耗过多的CPU和IO资源,产生大量的慢查询。 - 子查询的结果集存储的临时表,不论是内存临时表还是磁盘临时表都
不会存在索引
,所以查询性能会受到一定的影响。 - 对于返回结果集比较大的子查询,其对查询性能的影响也就越大。
在MySQL中,可以使用连接(JOIN)查询来替代子查询
。连接查询不需要建立临时表
,其速度比子查询要快
,如果查询中使用索引的话,性能就会更好。
#4. 子查询的优化
#创建班级表中班长的索引
CREATE INDEX idx_monitor ON class(monitor);
#查询班长的信息
EXPLAIN SELECT * FROM student stu1
WHERE stu1.`stuno` IN (
SELECT monitor
FROM class c
WHERE monitor IS NOT NULL
);
#改造成多表查询
EXPLAIN SELECT stu1.* FROM student stu1 JOIN class c
ON stu1.`stuno` = c.`monitor`
WHERE c.`monitor` IS NOT NULL;
#查询不为班长的学生信息
EXPLAIN SELECT SQL_NO_CACHE a.*
FROM student a
WHERE a.stuno NOT IN (
SELECT monitor FROM class b
WHERE monitor IS NOT NULL)
#改造成多表查询
EXPLAIN SELECT SQL_NO_CACHE a.*
FROM student a LEFT OUTER JOIN class b
ON a.stuno =b.monitor
WHERE b.monitor IS NULL;
结论:尽量不要使用NOT IN或者NOT EXISTS,用LEFT JOIN XXX ON XX WHERE XX IS NULL替代
6. 排序优化
6.1 优化建议
问题:在WHERE条件字段上加索引,但是为什么在ORDERBY字段上还要加索引呢?
回答:
在MySQL中,支持两种排序方式,分别是FileSort
和Index
排序。
- Index排序中,索引可以保证数据的有序性,不需要再进行排序,
效率更高
。 - FileSort排序则一般在
内存中进行排序
,占用CPU较多
。如果待排结果较大,会产生临时文件I/O到磁盘进行排序的情况,效率较低。
6.2 案例分析
优化:
- SQL中,可以在WHERE子句和ORDER BY子句中使用索引,目的是在WHERE子句中
避免全表扫描
,在ORDER BY子句避免使用FileSort排序
。当然,某些情况下全表扫描,或者FileSort排序不一定比索引慢。但总的来说,我们还是要避免,以提高查询效率。 - 尽量使用Index完成ORDER BY排序。如果WHERE和ORDER BY后面是相同的列就使用单索引列;如果不同就使用联合索引。
- 无法使用Index时,需要对FileSort方式进行调优。
#5. 排序优化
#删除student和class表中的非主键索引
CALL proc_drop_index('atguigudb2','student');
CALL proc_drop_index('atguigudb2','class');
SHOW INDEX FROM student;
SHOW INDEX FROM class;
#过程一:
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid;
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid LIMIT 10;
#过程二:order by时不limit,索引失效
#创建索引
CREATE INDEX idx_age_classid_name ON student (age,classid,NAME);
#不限制,索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid;
#EXPLAIN SELECT SQL_NO_CACHE age,classid,name,id FROM student ORDER BY age,classid;
#增加limit过滤条件,使用上索引了。
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid LIMIT 10;
#过程三:order by时顺序错误,索引失效
#创建索引age,classid,stuno
CREATE INDEX idx_age_classid_stuno ON student (age,classid,stuno);
#以下哪些索引失效?
EXPLAIN SELECT * FROM student ORDER BY classid LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY classid,NAME LIMIT 10; #未用上索引
EXPLAIN SELECT * FROM student ORDER BY age,classid,stuno LIMIT 10; #用上索引
EXPLAIN SELECT * FROM student ORDER BY age,classid LIMIT 10;#用上索引
EXPLAIN SELECT * FROM student ORDER BY age LIMIT 10;#用上索引
#过程四:order by时规则不一致, 索引失效 (顺序错,不索引;方向反,不索引)
EXPLAIN SELECT * FROM student ORDER BY age DESC, classid ASC LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY classid DESC, NAME DESC LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY age ASC,classid DESC LIMIT 10; #未用上索引
EXPLAIN SELECT * FROM student ORDER BY age DESC, classid DESC LIMIT 10;#用上索引,倒着看索引
#过程五:无过滤,不索引
EXPLAIN SELECT * FROM student WHERE age=45 ORDER BY classid;#where用上索引
EXPLAIN SELECT * FROM student WHERE age=45 ORDER BY classid,NAME; #where用上索引
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age;#未用上索引
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age LIMIT 10;#用上索引
CREATE INDEX idx_cid ON student(classid);
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age;
6.3 filesort算法:双路排序和单路排序
6.3.1 双路排序(慢)
MySQL4.1之前是使用双路排序
,字面意思就是两次扫描磁盘,最终得到数据,读取行指针和order by列,对他们进行排序,然后扫描已经排序好的列表,按照列表中的值重新从列表中读取对应的数据输出- 从磁盘取排序字段,在buffer进行排序,再从磁盘取其他字段。
取一批数据,要对磁盘进行两次扫描,众所周知,l0是很耗时的,所以在mysql4.1之后,出现了第二种改进的算
法,就是单路排序。
6.3.2 单路排序(快)
从磁盘读取查询需要的所有列
,按照order by列在buffer对它们进行排序,然后扫描排序后的列表进行输出,它的效率更快一些,避免了第二次读取数据。并且把随机Io变成了顺序Io,但是它会使用更多的空间,因为它把每一行都保存在内存中了。
6.3.3 结论及引申出的问题
- 由于单路是后出的,总体而言好过双路
- 但是用单路有问题
- 在sort_buffer中,单路比多路要多占用很多空间,因为单路是把所有字段都取出,所以有可能取出的数据的
- 总大小超出了sort_buffer的容量,导致每次只能取sort_buffer容量大小的数据,进行排序(创建tmp文件,多路合并),排完再取sort_buffer容量大小,再排………从而多次I/o。
- 单路本来想省一次/O操作,反而导致了大量的I/0操作,反而得不偿失。
6.3.4 优化策略
- 尝试提高sort_buffer_size
不管用哪种算法,提高这个参数都会提高效率,要根据系统的能力去提高,因为这个参数是针对每个进程(connection)的1M-8M之间调整。MySQL5.7,InnoDB存储引擎默认值是1048576字节,1MB。
SHOW VARIABLES LIKE '%sort_buffer_size%';
- 尝试提高max_length for_sort_data
提高这个参数,会增加用改进算法的概率。
SHOW VARIABLES LIKE '%max_length_for_sort_data%';#默认1024字节
但是如果设的太高,数据总容量超出sort_buffer_size的概率就增大,明显症状是高的磁盘I/o活动和低的处理器使用率。如果需要返回的列的总长度大于max_length_for_sort_data,使用双路算法,否则使用单路算法。1024-8192字节之间调整
- Order by 时select*是一个大忌。最好只Query需要的字段。
- 当Query的字段大小总和小于
max_length_for_sort_data
,而且排序字段不是TEXT|BLOB类型时,会用改进后的算法–单路排序,否则用老算法–多路排序。 - 两种算法的数据都有可能超出sort_buffer_size的容量,超出之后,会创建tmp文件进行合并排序,导致多次I/O,但是用单路排序算法的风险会更大一些,所以要提高
sort_buffer_size
。
7. GROUP BY优化
- group by使用索引的原则几乎跟order by一致,group by即使没有过滤条件用到索引,也可以直接使用索引。
- group by先排序再分组,遵照索引建的最佳左前缀法则
- 当无法使用索引列,增大
max_length_for_sort_data
和sort_buffer_size
参数的设置 - where效率高于having,能写在where限定的条件就不要写在having中了
- 减少使用order by,和业务沟通能不排序就不排序,或将排序放到程序端去做。order by、group by、distinct这些语句较为耗费CPU,数据库的CPU资源是极其宝贵的。
- 包含了order by、group by、distinct这些查询的语句,where条件过滤出来的结果集请保持在1000行以内,否则SQL会很慢。
8. 优化分页查询(limit)
一般分页查询时,通过创建覆盖索引能够比较好地提高性能。一个常见又非常头疼的问题就是limit 2000000,10,此时需要MySQL排序前2000010记录,仅仅返回2000000-2000010的记录,其他记录丢弃,查询排序的代价非常大。
EXPLAIN SELECT * FROM student LIMIT 2000000,10;
优化思路一
在索引上完成排序分页操作,最后根据主键关联回原表查询所需要的其他列内容。
EXPLAIN SELECT * FROM student t, (SELECT id FROM student ORDER BY id LIMIT 2000000,10) a WHERE t.id = a.id;
优化思路二
该方案适用于主键自增的表,可以把Limit查询转换成某个位置的查询。
EXPLAIN SELECT * FROM student WHERE id > 2000000 LIMIT 10;
9.覆盖索引的使用
9.1 什么是覆盖索引
理解方式一:索引是高效找到行的一个方法,但是一般数据库也能使用索引找到一个列的数据,因此它不必读取整个行。毕竟索引叶子节点存储了它们索引的数据;当能通过读取索引就可以得到想要的数据,那就不需要读取行了。一个索引包含了满足查询结果的数据就叫做覆盖索引
。
理解方式二:非聚簇复合索引的一种形式,它包括在查询里的SELECT、JOIN和WHERE子句用到的所有列(即建索引的字段正好是覆盖查询条件中所涉及的字段)。
简单说就是,
索引列+主键包含SELECT到FROM之间查询的列
。
9.2 代码演示
#6. 覆盖索引
#删除之前的索引
#举例1:
DROP INDEX idx_age_stuno ON student;
CREATE INDEX idx_age_name ON student (age,NAME);
EXPLAIN SELECT * FROM student WHERE age <> 20;#索引失效
EXPLAIN SELECT age,NAME FROM student WHERE age <> 20;#索引有效,为覆盖索引
#举例2:
EXPLAIN SELECT * FROM student WHERE NAME LIKE '%abc';#索引失效
EXPLAIN SELECT id,age FROM student WHERE NAME LIKE '%abc';#索引有效,为覆盖索引
9.3 覆盖索引的利弊
9.3.1 好处
- 避免Innodb表进行索引的二次查询(回表)
Innodb是以聚集索引的顺序来存储的,对于Innodb来说,二级索引在叶子节点中所保存的是行的主键信息,如果是用二级索引查询数据,在查找到相应的键值后,需通过主键进行二次查询才能获取我们真实所需要的数据。
在覆盖索引中,二级索引的键值中可以获取所要的数据,避免了对主键的二次查询,减少了I0操作
,提升了查询效率。
- 可以把随机IO变成顺序IO加快查询效率
由于覆盖索引是按键值的顺序存储的,对于I0密集型的范围查找来说,对比随机从磁盘读取每一行的数据I0要少的多,因此利用覆盖索引在访问时也可以把磁盘的
随机读取的IO
转变成索引查找的顺序IO
。
由于覆盖索引可以减少树的搜索次数,显著提升查询性能,所以使用覆盖索引是一个常用的性能优化手段。
9.3.2 坏处
索引字段的维护
总是有代价的。因此,在建立冗余索引来支持覆盖索引时就需要权衡考虑了。这是业务DBA,或者称为业务数据架构师的工作。
10. 索引下推
10.1 概念
Index Condition Pushdown(ICP)是MySQL5.6中新特性,是一种在存储擎层使用索引过滤数据的优化方式。
从二级索引中查找数据,如果二级索引中已经有了要筛选的列,但是又不能使用索引,会先从该二级索引筛选完以后再回表
。
- 好处:ICP可以减少存储引擎必须访问基表的次数和MySQL服务器必须访问存储引擎的次数。
- 但是, ICP的加速效果取决于在存储引擎内通过ICP筛选掉的数据的比例。
10.2 代码演示
#7. 索引条件下推(ICP)
#举例1:
USE atguigudb1;
EXPLAIN SELECT * FROM s1 WHERE key1 > 'z' AND key1 LIKE '%a';
#举例2:
CREATE TABLE `people` (
`id` INT NOT NULL AUTO_INCREMENT,
`zipcode` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`firstname` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`lastname` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`address` VARCHAR(50) COLLATE utf8_bin DEFAULT NULL,
PRIMARY KEY (`id`),
KEY `zip_last_first` (`zipcode`,`lastname`,`firstname`)
) ENGINE=INNODB AUTO_INCREMENT=5 DEFAULT CHARSET=utf8mb3 COLLATE=utf8_bin;
INSERT INTO `people` VALUES
('1', '000001', '三', '张', '北京市'),
('2', '000002', '四', '李', '南京市'),
('3', '000003', '五', '王', '上海市'),
('4', '000001', '六', '赵', '天津市');
EXPLAIN SELECT * FROM people
WHERE zipcode='000001'
AND lastname LIKE '%张%'
AND address LIKE '%北京市%';
EXPLAIN SELECT * FROM people
WHERE zipcode='000001'
AND lastname LIKE '张%'
AND firstname LIKE '三%';
10.3 打开/关闭ICP
默认情况索引条件下推是开启的
#关闭索引下推
SET optimizer_switch = 'index_condition_pushdown=off';
#打开索引下推
SET optimizer_switch = 'index_condition_pushdown=on';
10.4 ICP的使用条件
- 如果表访问的类型为range、 ref、 eq_ref和ref_or_null可以使用ICP
- ICP可以用于
InnoDB
和MyISAM
表,包括分区表InnoDB和MyISAM表 - 对于InnoDB表,ICP
仅用于二级索引
。IICP的目标是减少全行读取次数,从而减少I/O操作。 - 当SQL使用覆盖索引时,不支持ICP。因为这种情况下使用ICP不会减少I/O。
- 相关子查询的条件不能使用ICP
11. 其它查询优化策略
11.1 EXISTS和IN的区分
#大表A驱动小表cc时用in
SELECT * FROM A WHERE cc IN (SELECT CC FROM B);
#小表A驱动大表cc时用EXISTS ,因为执行时每次是从A中取一条数据到SELECT cc FROM B WHERE B.cc = a.cc中执行,A小一点更合适
SELECT * FROM A WHERE EXISTS (SELECT cc FROM B WHERE B.cc = a.cc)
11.2 COUNT(*)与COUNT(具体字段)效率
11.3 关于SELECT(*)
在表查询中,建议明确字段,不要使用*作为查询的字段列表,推荐使用SELECT<字段列表>查询。原因:
①MySQL在解析的过程中,会通过查询数据字典
将"*"按序转换成所有列名,这会大大的耗费资源和时间。
②无法使用覆盖索引
11.4 LIMIT1对优化的影响
针对的是会扫描全表
的SQL语句,如果你可以确定结果集只有一条,那么加上LIMIT1
的时候,当找到一条结果的时候就不会继续扫描了,这样会加快查询速度。
如果数据表已经对字段建立了唯一索引
,那么可以通过索引进行查询,不会全表扫描的话,就不需要加上LIMIT1
了。
11.5 多使用COMMIT
只要有可能,在程序中尽量多使用COMMIT,这样程序的性能得到提高,需求也会因为COMMIT所释放的资源而减少。
COMMIT所释放的资源:
- 回滚段上用于恢复数据的信息
- 被程序语句获得的锁
- redo/ undo log buffer 中的空间
- 管理上述3种资源中的内部花费
12. 综合案例演示
# 06-索引优化与查询优化
#1. 数据准备
CREATE DATABASE atguigudb2;
USE atguigudb2;
#建表
CREATE TABLE `class` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`className` VARCHAR(30) DEFAULT NULL,
`address` VARCHAR(40) DEFAULT NULL,
`monitor` INT NULL ,
PRIMARY KEY (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
CREATE TABLE `student` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`stuno` INT NOT NULL ,
`name` VARCHAR(20) DEFAULT NULL,
`age` INT(3) DEFAULT NULL,
`classId` INT(11) DEFAULT NULL,
PRIMARY KEY (`id`)
#CONSTRAINT `fk_class_id` FOREIGN KEY (`classId`) REFERENCES `t_class` (`id`)
) ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;
SET GLOBAL log_bin_trust_function_creators=1;
#随机产生字符串
DELIMITER //
CREATE FUNCTION rand_string(n INT) RETURNS VARCHAR(255)
BEGIN
DECLARE chars_str VARCHAR(100) DEFAULT 'abcdefghijklmnopqrstuvwxyzABCDEFJHIJKLMNOPQRSTUVWXYZ';
DECLARE return_str VARCHAR(255) DEFAULT '';
DECLARE i INT DEFAULT 0;
WHILE i < n DO
SET return_str =CONCAT(return_str,SUBSTRING(chars_str,FLOOR(1+RAND()*52),1));
SET i = i + 1;
END WHILE;
RETURN return_str;
END //
DELIMITER ;
#用于随机产生多少到多少的编号
DELIMITER //
CREATE FUNCTION rand_num (from_num INT ,to_num INT) RETURNS INT(11)
BEGIN
DECLARE i INT DEFAULT 0;
SET i = FLOOR(from_num +RAND()*(to_num - from_num+1)) ;
RETURN i;
END //
DELIMITER ;
#创建往stu表中插入数据的存储过程
DELIMITER //
CREATE PROCEDURE insert_stu( START INT , max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0; #设置手动提交事务
REPEAT #循环
SET i = i + 1; #赋值
INSERT INTO student (stuno, NAME ,age ,classId ) VALUES ((START+i),rand_string(6),rand_num(1,50),rand_num(1,1000));
UNTIL i = max_num
END REPEAT;
COMMIT; #提交事务
END //
DELIMITER ;
#执行存储过程,往class表添加随机数据
DELIMITER //
CREATE PROCEDURE `insert_class`( max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0;
REPEAT
SET i = i + 1;
INSERT INTO class ( classname,address,monitor ) VALUES (rand_string(8),rand_string(10),rand_num(1,100000));
UNTIL i = max_num
END REPEAT;
COMMIT;
END //
DELIMITER ;
#执行存储过程,往class表添加1万条数据
CALL insert_class(10000);
#执行存储过程,往stu表添加50万条数据
CALL insert_stu(100000,500000);
SELECT COUNT(*) FROM class;
SELECT COUNT(*) FROM student;
DELIMITER //
CREATE PROCEDURE `proc_drop_index`(dbname VARCHAR(200),tablename VARCHAR(200))
BEGIN
DECLARE done INT DEFAULT 0;
DECLARE ct INT DEFAULT 0;
DECLARE _index VARCHAR(200) DEFAULT '';
DECLARE _cur CURSOR FOR SELECT index_name FROM information_schema.STATISTICS WHERE table_schema=dbname AND table_name=tablename AND seq_in_index=1 AND index_name <>'PRIMARY' ;
#每个游标必须使用不同的declare continue handler for not found set done=1来控制游标的结束
DECLARE CONTINUE HANDLER FOR NOT FOUND SET done=2 ;
#若没有数据返回,程序继续,并将变量done设为2
OPEN _cur;
FETCH _cur INTO _index;
WHILE _index<>'' DO
SET @str = CONCAT("drop index " , _index , " on " , tablename );
PREPARE sql_str FROM @str ;
EXECUTE sql_str;
DEALLOCATE PREPARE sql_str;
SET _index='';
FETCH _cur INTO _index;
END WHILE;
CLOSE _cur;
END //
DELIMITER ;
#2. 索引失效案例
#1)全值匹配我最爱
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
SELECT SQL_NO_CACHE * FROM student WHERE age=30 AND classId=4 AND NAME = 'abcd';
CREATE INDEX idx_age ON student(age);
CREATE INDEX idx_age_classid ON student(age,classId);
CREATE INDEX idx_age_classid_name ON student(age,classId,NAME);
#2)最佳左前缀法则
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.age=30 AND student.name = 'abcd' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.classid=1 AND student.name = 'abcd';
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE classid=4 AND student.age=30 AND student.name = 'abcd';
DROP INDEX idx_age ON student;
DROP INDEX idx_age_classid ON student;
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abcd';
#3)主键插入顺序
#4)计算、函数、类型转换(自动或手动)导致索引失效
#此语句比下一条要好!(能够使用上索引)
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name LIKE 'abc%';
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE LEFT(student.name,3) = 'abc';
CREATE INDEX idx_name ON student(NAME);
#
CREATE INDEX idx_sno ON student(stuno);
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno+1 = 900001;
EXPLAIN SELECT SQL_NO_CACHE id, stuno, NAME FROM student WHERE stuno = 900000;
EXPLAIN SELECT id, stuno, NAME FROM student WHERE SUBSTRING(NAME, 1,3)='abc';
#5)类型转换导致索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME = 123;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME = '123';
#6)范围条件右边的列索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age_classId_name ON student(age,classId,NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.classId>20 AND student.name = 'abc' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student
WHERE student.age=30 AND student.name = 'abc' AND student.classId>20;
CREATE INDEX idx_age_name_cid ON student(age,NAME,classId);
#7)不等于(!= 或者<>)索引失效
CREATE INDEX idx_name ON student(NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name <> 'abc' ;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE student.name != 'abc' ;
#8)is null可以使用索引,is not null无法使用索引
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NULL;
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age IS NOT NULL;
#9)like以通配符%开头索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE 'ab%';
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE NAME LIKE '%ab%';
#10)OR 前后存在非索引的列,索引失效
SHOW INDEX FROM student;
CALL proc_drop_index('atguigudb2','student');
CREATE INDEX idx_age ON student(age);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 10 OR classid = 100;
CREATE INDEX idx_cid ON student(classid);
# 11)数据库和表的字符集统一使用utf8mb4
#3. 关联查询优化
# 情况1:左外连接
#分类
CREATE TABLE IF NOT EXISTS `type` (
`id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
`card` INT(10) UNSIGNED NOT NULL,
PRIMARY KEY (`id`)
);
#图书
CREATE TABLE IF NOT EXISTS `book` (
`bookid` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT,
`card` INT(10) UNSIGNED NOT NULL,
PRIMARY KEY (`bookid`)
);
#向分类表中添加20条记录
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO TYPE(card) VALUES(FLOOR(1 + (RAND() * 20)));
#向图书表中添加20条记录
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO book(card) VALUES(FLOOR(1 + (RAND() * 20)));
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
#添加索引
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
CREATE INDEX X ON `type`(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
DROP INDEX Y ON book;
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` LEFT JOIN book ON type.card = book.card;
# 情况2:内连接
DROP INDEX X ON `type`;
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#添加索引
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
CREATE INDEX X ON `type`(card);
#结论:对于内连接来说,查询优化器可以决定谁作为驱动表,谁作为被驱动表出现的
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#删除索引
DROP INDEX Y ON book;
#结论:对于内连接来讲,如果表的连接条件中只能有一个字段有索引,则有索引的字段所在的表会被作为被驱动表出现。
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
CREATE INDEX Y ON book(card);
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#向type表中添加数据(20条数据)
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
INSERT INTO `type`(card) VALUES(FLOOR(1 + (RAND() * 20)));
#结论:对于内连接来说,在两个表的连接条件都存在索引的情况下,会选择小表作为驱动表。“小表驱动大表”
EXPLAIN SELECT SQL_NO_CACHE * FROM `type` INNER JOIN book ON type.card = book.card;
#JOIN的底层原理
CREATE TABLE a(f1 INT, f2 INT, INDEX(f1))ENGINE=INNODB;
CREATE TABLE b(f1 INT, f2 INT)ENGINE=INNODB;
INSERT INTO a VALUES(1,1),(2,2),(3,3),(4,4),(5,5),(6,6);
INSERT INTO b VALUES(3,3),(4,4),(5,5),(6,6),(7,7),(8,8);
#测试1
EXPLAIN SELECT * FROM a LEFT JOIN b ON(a.f1=b.f1) WHERE (a.f2=b.f2);
#测试2
EXPLAIN SELECT * FROM a LEFT JOIN b ON(a.f1=b.f1) AND (a.f2=b.f2);
#测试3
EXPLAIN SELECT * FROM a JOIN b ON(a.f1=b.f1) WHERE (a.f2=b.f2);
SHOW VARIABLES LIKE '%optimizer_switch%';
SHOW VARIABLES LIKE '%join_buffer%';
#4. 子查询的优化
#创建班级表中班长的索引
CREATE INDEX idx_monitor ON class(monitor);
#查询班长的信息
EXPLAIN SELECT * FROM student stu1
WHERE stu1.`stuno` IN (
SELECT monitor
FROM class c
WHERE monitor IS NOT NULL
);
#改造成多表查询
EXPLAIN SELECT stu1.* FROM student stu1 JOIN class c
ON stu1.`stuno` = c.`monitor`
WHERE c.`monitor` IS NOT NULL;
#查询不为班长的学生信息
EXPLAIN SELECT SQL_NO_CACHE a.*
FROM student a
WHERE a.stuno NOT IN (
SELECT monitor FROM class b
WHERE monitor IS NOT NULL)
#改造成多表查询
EXPLAIN SELECT SQL_NO_CACHE a.*
FROM student a LEFT OUTER JOIN class b
ON a.stuno =b.monitor
WHERE b.monitor IS NULL;
#5. 排序优化
#删除student和class表中的非主键索引
CALL proc_drop_index('atguigudb2','student');
CALL proc_drop_index('atguigudb2','class');
SHOW INDEX FROM student;
SHOW INDEX FROM class;
#过程一:
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid;
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid LIMIT 10;
#过程二:order by时不limit,索引失效
#创建索引
CREATE INDEX idx_age_classid_name ON student (age,classid,NAME);
#不限制,索引失效
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid;
#EXPLAIN SELECT SQL_NO_CACHE age,classid,name,id FROM student ORDER BY age,classid;
#增加limit过滤条件,使用上索引了。
EXPLAIN SELECT SQL_NO_CACHE * FROM student ORDER BY age,classid LIMIT 10;
#过程三:order by时顺序错误,索引失效
#创建索引age,classid,stuno
CREATE INDEX idx_age_classid_stuno ON student (age,classid,stuno);
#以下哪些索引失效?
EXPLAIN SELECT * FROM student ORDER BY classid LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY classid,NAME LIMIT 10; #未用上索引
EXPLAIN SELECT * FROM student ORDER BY age,classid,stuno LIMIT 10; #用上索引
EXPLAIN SELECT * FROM student ORDER BY age,classid LIMIT 10;#用上索引
EXPLAIN SELECT * FROM student ORDER BY age LIMIT 10;#用上索引
#过程四:order by时规则不一致, 索引失效 (顺序错,不索引;方向反,不索引)
EXPLAIN SELECT * FROM student ORDER BY age DESC, classid ASC LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY classid DESC, NAME DESC LIMIT 10;#未用上索引
EXPLAIN SELECT * FROM student ORDER BY age ASC,classid DESC LIMIT 10; #未用上索引
EXPLAIN SELECT * FROM student ORDER BY age DESC, classid DESC LIMIT 10;#用上索引,倒着看索引
#过程五:无过滤,不索引
EXPLAIN SELECT * FROM student WHERE age=45 ORDER BY classid;#where用上索引
EXPLAIN SELECT * FROM student WHERE age=45 ORDER BY classid,NAME; #where用上索引
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age;#未用上索引
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age LIMIT 10;#用上索引
CREATE INDEX idx_cid ON student(classid);
EXPLAIN SELECT * FROM student WHERE classid=45 ORDER BY age;
#实战:测试filesort和index排序
CALL proc_drop_index('atguigudb2','student');
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 30 AND stuno <101000 ORDER BY NAME ;
#方案一: 为了去掉filesort我们可以把索引建成
CREATE INDEX idx_age_name ON student(age,NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 30 AND stuno <101000 ORDER BY NAME ;
#方案二:
CREATE INDEX idx_age_stuno_name ON student(age,stuno,NAME);
EXPLAIN SELECT SQL_NO_CACHE * FROM student WHERE age = 30 AND stuno <101000 ORDER BY NAME ;
DROP INDEX idx_age_stuno_name ON student;
CREATE INDEX idx_age_stuno ON student(age,stuno);
#6. 覆盖索引
#删除之前的索引
#举例1:
DROP INDEX idx_age_stuno ON student;
CREATE INDEX idx_age_name ON student (age,NAME);
EXPLAIN SELECT * FROM student WHERE age <> 20;
EXPLAIN SELECT age,NAME FROM student WHERE age <> 20;
#举例2:
EXPLAIN SELECT * FROM student WHERE NAME LIKE '%abc';
EXPLAIN SELECT id,age FROM student WHERE NAME LIKE '%abc';
###
SELECT CRC32('hello')
FROM DUAL;
#7. 索引条件下推(ICP)
#举例1:
USE atguigudb1;
EXPLAIN SELECT * FROM s1 WHERE key1 > 'z' AND key1 LIKE '%a';
#举例2:
CREATE TABLE `people` (
`id` INT NOT NULL AUTO_INCREMENT,
`zipcode` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`firstname` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`lastname` VARCHAR(20) COLLATE utf8_bin DEFAULT NULL,
`address` VARCHAR(50) COLLATE utf8_bin DEFAULT NULL,
PRIMARY KEY (`id`),
KEY `zip_last_first` (`zipcode`,`lastname`,`firstname`)
) ENGINE=INNODB AUTO_INCREMENT=5 DEFAULT CHARSET=utf8mb3 COLLATE=utf8_bin;
INSERT INTO `people` VALUES
('1', '000001', '三', '张', '北京市'),
('2', '000002', '四', '李', '南京市'),
('3', '000003', '五', '王', '上海市'),
('4', '000001', '六', '赵', '天津市');
EXPLAIN SELECT * FROM people
WHERE zipcode='000001'
AND lastname LIKE '%张%'
AND address LIKE '%北京市%';
EXPLAIN SELECT * FROM people
WHERE zipcode='000001'
AND lastname LIKE '张%'
AND firstname LIKE '三%';
SET optimizer_switch = 'index_condition_pushdown=on';
#创建存储过程,向people表中添加1000000条数据,测试ICP开启和关闭状态下的性能
DELIMITER //
CREATE PROCEDURE insert_people( max_num INT )
BEGIN
DECLARE i INT DEFAULT 0;
SET autocommit = 0;
REPEAT
SET i = i + 1;
INSERT INTO people ( zipcode,firstname,lastname,address ) VALUES ('000001', '六', '赵', '天津市');
UNTIL i = max_num
END REPEAT;
COMMIT;
END //
DELIMITER ;
CALL insert_people(1000000);
####
SELECT UUID() FROM DUAL;
SET @uuid = UUID();
SELECT @uuid,uuid_to_bin(@uuid),uuid_to_bin(@uuid,TRUE);