hive几种排序

order by：全局排序

select * from emp order by sal;

sort by：对于每个reduce进行排序

set mapreduce.job.reduces=3;

insert overwrite local directory ‘/opt/datas/emp_sort’

row format delimited fields terminated by ‘\t’ select * from emp sort by sal;

distribute by :底层就是mapreduce 的分区，一般与sort by连用

insert overwrite local directory ‘/opt/datas/emp_dis’

row format delimited fields terminated by ‘\t’

select * from emp distribute by deptno sort by sal;

cluster by:等价于distribute by 与sort by的字段相同时

insert overwrite local directory ‘/opt/datas/emp_cls’

row format delimited fields terminated by ‘\t’

select * from emp cluster by sal;