Hive中如何有效率地執行增量資料更新？

insert overwrite target_data [partition() if applicable]
SELECT
  case when i.PK is not null then i.PK   else t.PK   end as PK,
  case when i.PK is not null then i.COL1 else t.COL1 end as COL1,
  ...
  case when i.PK is not null then i.COL_n else t.COL_n end as COL_n
FROM
    target_data t --restrict partitions if applicable
    FULL JOIN increment_data i on (t.PK=i.PK);

INSERT INTO target_data (pk, col1, col2, ...)
SELECT pk, col1, col2, ...
FROM increment_data
WHERE pk NOT IN (SELECT pk FROM target_data)
UNION ALL
SELECT pk, col1, col2, ...
FROM target_data;