From: Evaluating partitioning and bucketing strategies for Hive-based Big Data Warehousing systems
Data model | Attributes | SF | Tool | |||
---|---|---|---|---|---|---|
Time (s) | Increase along SF | |||||
Hive | Presto | Hive | Presto | |||
SS | None | 30 | 420 | 92 | ||
300 | 4874 | 733 | 11.60 | 7.97 | ||
SS-P | Od_Year + S_Region | 30 | 375 | 63 | ||
300 | 2849 | 399 | 7.60 | 6.33 | ||
SS-B | Orderdate + Custkey + Suppkey + Partkey | 30 | 420 | 121 | ||
300 | 5712 | 876 | 13.60 | 7.24 | ||
Suppkey | 30 | 404 | 120 | |||
300 | 1803 | 768 | 4.46 | 6.40 | ||
SS-PB | Od_Year + Orderkey | 30 | 378 | 100 | ||
300 | 5166 | 835 | 13.67 | 8.35 | ||
Od_Year + S_Region+ Suppkey | 30 | 362 | 81 | |||
300 | 933 | 650 | 2.58 | 8.02 | ||
S_Region + Suppkey | 30 | 349 | 77 | |||
300 | 982 | 452 | 2.81 | 5.87 | ||
DT | None | 30 | 349 | 63 | ||
300 | 1090 | 472 | 3.12 | 7.49 | ||
DT-P | Od_Year + S_Region | 30 | 292 | 43 | ||
300 | 602 | 299 | 2.06 | 6.95 |