ハイブラテラルビュー爆発内部メカニズム

Question

私は、単一のテーブル（サイズ約12GB）上で単一のクエリで複数回（約9回）ラテラルビューを使用しました。これにより、膨大な量のマップサイドデータ（100Pb +）が生成されました。私はそれが12GBからこの量のデータをどのように生成したのか理解できませんでした。

誰かが横方向の爆発が（内部的に）どのように機能するか説明できますか？事前に

おかげ

Answer 1

デモ

create table mytable (a1 array<int>,a2 array<int>,a3 array<int>); 
insert into mytable select array(1,2),array(3,4,5),array(6,7,8,9); 

---

select * 

from mytable 
     lateral view explode (a1) e1 as a1_val 
     lateral view explode (a2) e2 as a2_val 
     lateral view explode (a3) e3 as a3_val 
;   

---

+-------+---------+-----------+--------+--------+--------+ 
| a1 | a2 | a3  | a1_val | a2_val | a3_val | 
+-------+---------+-----------+--------+--------+--------+ 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  3 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  3 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  3 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  3 |  9 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  4 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  4 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  4 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  4 |  9 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  5 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  5 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  5 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  1 |  5 |  9 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  3 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  3 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  3 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  3 |  9 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  4 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  4 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  4 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  4 |  9 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  5 |  6 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  5 |  7 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  5 |  8 | 
| [1,2] | [3,4,5] | [6,7,8,9] |  2 |  5 |  9 | 
+-------+---------+-----------+--------+--------+--------+