Hive使用双重GroupBy解决数据倾斜问题

1.数据准备

create table wordcount(a string) row format delimited fields terminated by ‘,’;

load data local inpath ‘opt/2.txt’ into table wordcount;

hive (default)> select * from wordcount;
OK
wordcount.a
b
a
a
a
a
b
b
c
c
e
d

2.双重group by实现 解决数据倾斜

随机数：ceil(rand()*10)

select split(salt_a,‘‘)[1] alpah ,sum(count) from
(
select concat_ws(’’,cast(ceil(rand()*10) as string),a) salt_a,count(1) count from wordcount group by concat_ws(‘‘,cast(ceil(rand()*10) as string),a)
) b group by split(salt_a,’’)[1];

alpah _c1
a 4
b 3
c 2
d 1
e 1

解析:

2.1 第一层加盐group by

select concat_ws(‘‘,cast(ceil(rand()*10) as string),a) salt_a,count(1) count from wordcount group by concat_ws(’’,cast(ceil(rand()*10) as string),a)
sal