mysql百萬數據實踐-分區

今天實踐下mysql百萬級數據分區的影響，首先是產生百萬級別的數據量

//建立帶分區的數據表
CREATE TABLE `part_person` (
  `id` bigint(20) unsigned NOT NULL,
  `username` varchar(100) NOT NULL,
  `born` date NOT NULL DEFAULT '1970-01-01',
  `sex` tinyint(1) unsigned NOT NULL,
  PRIMARY KEY (`id`,`born`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8
PARTITION BY RANGE (year(born))
(PARTITION p0 VALUES LESS THAN (1980) ENGINE = MyISAM,
 PARTITION p1 VALUES LESS THAN (1990) ENGINE = MyISAM,
 PARTITION p2 VALUES LESS THAN (2000) ENGINE = MyISAM,
 PARTITION p3 VALUES LESS THAN (2010) ENGINE = MyISAM,
 PARTITION p4 VALUES LESS THAN (2020) ENGINE = MyISAM,
 PARTITION p5 VALUES LESS THAN MAXVALUE ENGINE = MyISAM);

//建立不帶分區的數據表
CREATE TABLE `no_part_person` (
  `id` bigint(20) unsigned NOT NULL,
  `username` varchar(100) NOT NULL,
  `born` date NOT NULL DEFAULT '1970-01-01',
  `sex` tinyint(1) unsigned NOT NULL,
  PRIMARY KEY (`id`,`born`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8;

//填充數據，建立procedure向數據表插入數據
CREATE PROCEDURE `part_generate`(IN num INT)  
BEGIN     
    DECLARE char_str varchar(100) DEFAULT 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789';
    DECLARE username VARCHAR(25) DEFAULT '';    
    DECLARE id int UNSIGNED;  
    DECLARE len int;  
    set id=1;  
    DELETE from person;  
    WHILE id <= num DO  
        set len = FLOOR(1 + RAND()*25);  
        set username = '';  
        WHILE len > 0 DO  
            SET username = CONCAT(username,substring(char_str,FLOOR(1 + RAND()*62),1));  
            SET len = len - 1;  
        END WHILE;   
        INSERT into part_person VALUES (id,username, ADDDATE('1970-01-01',INTERVAL RAND()*365*60 DAY), FLOOR(RAND()*2));  
        set id = id + 1;  
    END WHILE;  
END

//執行procedure插入600萬數據
call part_generate(6000000)

//向未分區表插入數據 
insert into no_part_person select * from part_person;

如今有了數據，對比一下有沒有分區對查詢的影響

查詢不是按照該列分區的數據時分區反而更慢一些，查詢born數據時不跨區時分區效果提高顯著，當數據跨區時提高效果沒那麼顯著，但也有提高。