[Hive_9] Hive 的排序

Posted 2021-02-02 share23

---

0. 说明

 

 

---

1. 前期准备

　　1.1 建表

create table user_order(id int, name string, age int, province string, city string)
row format delimited
fields terminated by ‘	‘;

 

　　1.2 设置 reduce 个数

set mapreduce.job.reduces=2;

 

 

2. 全排序（order by）

 　　一个 reduce，在真实使用中，需要加 limit 限制。

truncate table user_order;
insert into user_order select * from user_par order by id;

 

---

 

3. 部分排序（sort by ）

　　在每个 reduce 中分别排序

truncate table user_order;

insert into user_order select * from user_par sort by id;

 

---

 

 

4. hash分区（distribute by ）

 

truncate table user_order;

insert into user_order select * from user_par distribute by id;

 

---

 

cluster by = distribute by + sort by
truncate table user_order;
insert into user_order select * from user_par cluster by id;

 

 

 

 

 

---