1. 建立多个表,每个表导入不同的数据
create table test_1 (id int);
create table test_2 (id int);
create table test_3 (id int);
............
2. 创建分区表
create table test(id int) partitioned by (name sting);
alter table test add partition (name = '1')
alter table test add partition (name = '2')
切忌分区过多, namenode 压力太大
3. 分区数目太多可以考虑分桶
create table test(id int, name string) partitioned by (age int) clustered by (id) into 96 buckets;