同时,即便是设置了填充因子为100%,Innodb也会主动留下page页面1/16的空间作为预留使用(An innodb_fill_factor setting of 100 leaves 1/16 of the space in clustered index pages free for future index growth)防止update带来的行溢出。
#执行SQL语句 mysql> select id, age ,phone from user where name like 'lyn12%'; +--------+-----+-------------+ | id | age | phone | +--------+-----+-------------+ | 124 | 3 | 15240540354 | | 1231 | 30 | 15240540354 | | 12301 | 60 | 15240540354 | ............................. | 129998 | 37 | 15240540354 | | 129999 | 38 | 15240540354 | | 130000 | 39 | 15240540354 | +--------+-----+-------------+ 11111 rows in set (0.03 sec)
mysql> explain select id, age ,phone from user where name like 'lyn12%'; +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ | id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra | +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ | 1 | SIMPLE | user | range | idx_name | idx_name | 82 | NULL | 22226 | Using index condition | +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ 1 row in set (0.00 sec)
mysql> select id, age ,phone from user where name like 'lyn12%'; Empty set (0.05 sec)
mysql> explain select id, age ,phone from user where name like 'lyn12%'; +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ | id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra | +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ | 1 | SIMPLE | user | range | idx_name | idx_name | 82 | NULL | 22226 | Using index condition | +----+-------------+-------+-------+---------------+----------+---------+------+-------+-----------------------+ 1 row in set (0.00 sec)
#创建用户数据库并授权 create database mt_user charset utf8mb4; grant USAGE, SELECT, INSERT, UPDATE ON mt_user.* to 'w_user'@'%' identified by 't$W*g@gaHTGi123456'; flush privileges;
`id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键id', `is_deleted` tinyint(4) NOT NULL DEFAULT '0' COMMENT '是否逻辑删除:0:未删除,1:已删除', `create_time` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间', `update_time` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '修改时间'
#有了删除标记,业务接口的delete操作就可以转换为update update user set is_deleted = 1 where user_id = 1213;
#查询的时候需要带上is_deleted过滤 select id, age ,phone from user where is_deleted = 0 and name like 'lyn12%';
数据归档方式
通用数据归档方法
#1. 创建归档表,一般在原表名后面添加_bak。 CREATE TABLE `ota_order_bak` ( `id` bigint(11) NOT NULL AUTO_INCREMENT COMMENT '主键', `order_id` varchar(255) DEFAULT NULL COMMENT '订单id', `ota_id` varchar(255) DEFAULT NULL COMMENT 'ota', `check_in_date` varchar(255) DEFAULT NULL COMMENT '入住日期', `check_out_date` varchar(255) DEFAULT NULL COMMENT '离店日期', `hotel_id` varchar(255) DEFAULT NULL COMMENT '酒店ID', `guest_name` varchar(255) DEFAULT NULL COMMENT '顾客', `purcharse_time` timestamp NULL DEFAULT NULL COMMENT '购买时间', `create_time` datetime DEFAULT NULL, `update_time` datetime DEFAULT NULL, `create_user` varchar(255) DEFAULT NULL, `update_user` varchar(255) DEFAULT NULL, `status` int(4) DEFAULT '1' COMMENT '状态 :1 正常 , 0 删除', `hotel_name` varchar(255) DEFAULT NULL, `price` decimal(10,0) DEFAULT NULL, `remark` longtext, PRIMARY KEY (`id`), KEY `IDX_order_id` (`order_id`) USING BTREE, KEY `hotel_name` (`hotel_name`) USING BTREE, KEY `ota_id` (`ota_id`) USING BTREE, KEY `IDX_purcharse_time` (`purcharse_time`) USING BTREE, KEY `IDX_create_time` (`create_time`) USING BTREE ) ENGINE=InnoDB DEFAULT CHARSET=utf8 PARTITION BY RANGE (to_days(create_time)) ( PARTITION p201808 VALUES LESS THAN (to_days('2018-09-01')), PARTITION p201809 VALUES LESS THAN (to_days('2018-10-01')), PARTITION p201810 VALUES LESS THAN (to_days('2018-11-01')), PARTITION p201811 VALUES LESS THAN (to_days('2018-12-01')), PARTITION p201812 VALUES LESS THAN (to_days('2019-01-01')), PARTITION p201901 VALUES LESS THAN (to_days('2019-02-01')), PARTITION p201902 VALUES LESS THAN (to_days('2019-03-01')), PARTITION p201903 VALUES LESS THAN (to_days('2019-04-01')), PARTITION p201904 VALUES LESS THAN (to_days('2019-05-01')), PARTITION p201905 VALUES LESS THAN (to_days('2019-06-01')), PARTITION p201906 VALUES LESS THAN (to_days('2019-07-01')), PARTITION p201907 VALUES LESS THAN (to_days('2019-08-01')), PARTITION p201908 VALUES LESS THAN (to_days('2019-09-01')), PARTITION p201909 VALUES LESS THAN (to_days('2019-10-01')), PARTITION p201910 VALUES LESS THAN (to_days('2019-11-01')), PARTITION p201911 VALUES LESS THAN (to_days('2019-12-01')), PARTITION p201912 VALUES LESS THAN (to_days('2020-01-01')));
#2. 插入原表中无效的数据(需要跟开发同学确认数据保留范围) create table tbl_p201808 as select * from ota_order where create_time between '2018-08-01 00:00:00' and '2018-08-31 23:59:59';
#3. 跟归档表分区做分区交换 alter table ota_order_bak exchange partition p201808 with table tbl_p201808;
#4. 删除原表中已经规范的数据 delete from ota_order where create_time between '2018-08-01 00:00:00' and '2018-08-31 23:59:59' limit 3000;
优化后的归档方式
#1. 创建中间表 CREATE TABLE `ota_order_2020` (........) ENGINE=InnoDB DEFAULT CHARSET=utf8 PARTITION BY RANGE (to_days(create_time)) ( PARTITION p201808 VALUES LESS THAN (to_days('2018-09-01')), PARTITION p201809 VALUES LESS THAN (to_days('2018-10-01')), PARTITION p201810 VALUES LESS THAN (to_days('2018-11-01')), PARTITION p201811 VALUES LESS THAN (to_days('2018-12-01')), PARTITION p201812 VALUES LESS THAN (to_days('2019-01-01')), PARTITION p201901 VALUES LESS THAN (to_days('2019-02-01')), PARTITION p201902 VALUES LESS THAN (to_days('2019-03-01')), PARTITION p201903 VALUES LESS THAN (to_days('2019-04-01')), PARTITION p201904 VALUES LESS THAN (to_days('2019-05-01')), PARTITION p201905 VALUES LESS THAN (to_days('2019-06-01')), PARTITION p201906 VALUES LESS THAN (to_days('2019-07-01')), PARTITION p201907 VALUES LESS THAN (to_days('2019-08-01')), PARTITION p201908 VALUES LESS THAN (to_days('2019-09-01')), PARTITION p201909 VALUES LESS THAN (to_days('2019-10-01')), PARTITION p201910 VALUES LESS THAN (to_days('2019-11-01')), PARTITION p201911 VALUES LESS THAN (to_days('2019-12-01')), PARTITION p201912 VALUES LESS THAN (to_days('2020-01-01')));
#2. 插入原表中有效的数据,如果数据量在100W左右可以在业务低峰期直接插入,如果比较大,建议采用dataX来做,可以控制频率和大小,之前我这边用Go封装了dataX可以实现自动生成json文件,自定义大小去执行。 insert into ota_order_2020 select * from ota_order where create_time between '2020-08-01 00:00:00' and '2020-08-31 23:59:59';
#3. 表重命名 alter table ota_order rename to ota_order_bak; alter table ota_order_2020 rename to ota_order; #4. 插入差异数据 insert into ota_order select * from ota_order_bak a where not exists (select 1 from ota_order b where a.id = b.id); #5. ota_order_bak改造成分区表,如果表比较大不建议直接改造,可以先创建好分区表,通过dataX把导入进去即可。
#6. 后续的归档方法 #创建中间普遍表 create table ota_order_mid like ota_order; #交换原表无效数据分区到普通表 alter table ota_order exchange partition p201808 with table ota_order_mid; ##交换普通表数据到归档表的相应分区 alter table ota_order_bak exchange partition p201808 with table ota_order_mid;