mysql 存储过程批量删除重复数据
表结构:
LOAD DATA INFILE '/usr/local/phone_imsi_12' replace INTO TABLE tbl_imsi2number_new FIELDS TERMINATED BY '\t' ENCLOSED BY '' (number,imsi);
先用SQL语句来进行去重操作:
delete from tbl_imsi2number_new where imsi in (select imsi from (select imsi from tbl_imsi2number_new group by imsi having count(imsi) > 1) a) and number not in (select * from (select min(number) from tbl_imsi2number_new group by imsi having count(imsi) > 1 ) b);
因为数据量太大(共计3亿多数据),所以:
将开发那边拿过来的数据load data infile到大表里,不进行任何去重操作,没有任何约束。然后将这些数据分成几十个小文件,再load进几十个小表中,用这几十个小表去对比大表去重。得到去重后的小表。去重以后的小表,根据字段进行hash算出后两位数字(mod(conv(right(md5(imsi),2),16,10),100))进行批量插入。
存储过程如下(去重):
DELIMITER //
/*tblname 动态控制表名*/
CREATE PROCEDURE create_imsi(IN tblname varchar(200))
begin
declare age int default 1;
declare done int(1) default 0;
declare v_imsi varchar(200);
/*定义游标*/
declare cur_l cursor for select imsi from sqlstr;
/*定义异常*/
DECLARE CONTINUE HANDLER FOR SQLSTATE '02000' set done=1;
drop view if exists sqlstr;
/*定义视图*/
set @tbl = CONCAT("create view sqlstr as select a.imsi from tbl_new a,(select imsi from phone_",tblname," group by imsi having count(imsi) > 1) b where a.imsi = b.imsi group by imsi");
/*执行视图语句*/
PREPARE stmt FROM @tbl;
EXECUTE stmt;
DEALLOCATE PREPARE stmt;
OPEN cur_l;
FETCH cur_l INTO v_imsi;
while (done <> 1)
do
/*对比大表数据,删除小表中的重复数据*/
set @del = CONCAT("delete from phone_",tblname," where imsi=",v_imsi);
PREPARE stmt1 FROM @del;
EXECUTE stmt1;
DEALLOCATE PREPARE stmt1;
FETCH cur_l INTO v_imsi;
end while;
close cur_l;
end//
DELIMITER ;
2、根据hash算法插入新表:
DELIMITER //
CREATE PROCEDURE insert_imsi(IN tblname varchar(20))
begin
declare age int default 1;
declare done int(1) default 0;
declare done1 int(1) default 0;
declare v_imsi varchar(200);
declare v_e varchar(2000);
declare v_number varchar(3000);
declare v_ctype varchar(2000);
declare cur_l cursor for select split from sqlstr;
DECLARE CONTINUE HANDLER FOR SQLSTATE '02000' set done=1;
DECLARE CONTINUE HANDLER FOR 1146 set done1=3;
DECLARE CONTINUE HANDLER FOR SQLSTATE '23000' set done1=1;
DECLARE CONTINUE HANDLER FOR SQLSTATE '42000' set done1=2;
DECLARE CONTINUE HANDLER FOR SQLSTATE 'HY000' set done1=3;
drop view if exists sqlstx;
drop view if exists sqlstr;
set @sqlstx = CONCAT("create view sqlstr as SELECT imsi,number,ctype,mod(conv(right(md5(imsi),2),16,10),100) split from imsi_phone_",tblname);
PREPARE stmt1 FROM @sqlstx;
EXECUTE stmt1;
DEALLOCATE PREPARE stmt1;
OPEN cur_l;
WHILE done <> 1
DO
FETCH cur_l INTO v_e;
set @ins = concat("insert into imsi_",v_e,"(imsi,number,ctype) select imsi,number,ctype from sqlstr where split = '",v_e,"'");
PREPARE stmt3 FROM @ins;
EXECUTE stmt3;
END WHILE;
close cur_l;
end//
DELIMITER ;
报错:1、ERROR 1243 (HY000) at line 1: Unknown prepared statement handler (stmt3) given to EXECUTE
2、ERROR 1054 (42S22) at line 1: Unknown column '000cdc41b2a02518' in 'where clause'
由于set @dat = concat("insert into imsi_",v_e,"(imsi,number,ctype) select imsi,number,ctype from imsi_phone_",tblname," where imsi=‘’",v_imsi,“‘’”);没有在(=)那里加单引号,因为字段里有字母。
参数优化:
由于建表使用innodb引擎,所以此优化是针对innodb引擎的:
1、innodb_flush_log_at_trx_commit参数设置为1,减少刷新。
2、set sql_log_bin=0 暂时不产生二进制日志
3、sync_binlog 设置为0,减少刷新
4、innodb_buffer_pool_size 尽可能设置最大
5、set foreign_key_checks=0 去除外键检查
6、减少不必要的索引,有重复数据的话,主键是必须要的
7、innodb_change_buffer_max_size 上限为50,这里我设置为40,因为load是插入数据,所以设置插入缓冲
8、binlog_cache_size 如果必须要开启二进制日志,设置此参数尽可能大,因为sync_binlog设置为0,所以缓冲应该大
9、innodb_flush_method 刷新模式,设置为O_DIRECT
10、innodb_io_capacity 刷新脏页,根据你的硬盘设置,SAS设置800--900
11、innodb_log_buffer_size与innodb_sort_buffer_size 尽可能设置最大
12、unique_checks 设置为不检查:set unique_checks=0;
13、alter table tablename disable keys;设置表忽略索引,如果有。
14、设置自动提交为0,减少日志刷新:SET autocommit=0;
15、设置innodb_autoinc_lock_mode=2
16、设置主键,聚簇索引,按照主键顺序插入会更快