Hive的分区和分桶

为了避免全表扫描，优化查询性能，我们可以使用分区和分桶表将数据细化，分桶表是分区表的进阶阶段，分桶表是使用表的字段进行进一步细分数据，分区则是指定外部的字段来分区

分区表

create table  `alibaba.orders` ( order_id bigint,
    user_id bigint,
    item_id bigint,
    times string,
    name string,
    address string,
    phone string,
    keyword int
)
PARTITIONED BY (dt STRING)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' 
STORED AS orc;

分桶表

create table  `alibaba.userInfo` ( order_id bigint,
    user_id bigint,
    address string,
    phone string
)
clustered by (user_id) sorted by (user_id desc) into 4 buckets
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' 
STORED AS orc;