Advances, Systems and Applications
From: Improving the performance of Hadoop Hive by sharing scan and computation tasks
Query names | Correlation | Execution time (sec.) Hive/SharedHive (reduction %) | ||
---|---|---|---|---|
 |  | 1GB | 100GB | 1TB |
11,12 (set 1) | none | 231/215 (6.9%) | 676/666 (1.5%) | 5,410/5,386 (0.4%) |
17,22 (set 2) | none | 272/262 (3.7%) | 1,382/1.323 (4,3%) | 11,078/11,060 (0.2%) |
1,17 (set 3) | partial | 192/185 (3.6%) | 1,330/1,134 (14.7%) | 12,300/11,386 (7.4%) |
1,18 (set 4) | partial | 252/248 (1.6%) | 1,540/1,396 (9.4%) | 17,499/16,324 (6.7%) |
6,17 (set 5) | partial | 163/160 (1.8%) | 1,169/1,042 (10.9%) | 10,430/8,636 (17.2%) |
1,6 (set 6) | full | 103/90 (12.6%) | 601/436 (27.5%) | 5,057/3,936 (22.2%) |
14,19 (set 7) | full | 138/83 (39.9%) | 1,004/789 (21.9%) | 8,989/7,178 (20.1%) |
1,14,18 (set 10) | mixed | 317/299 (5.7%) | 1,870/1,689 (9.7%) | 20,425/18,590 (9.0%) |
1,3,11,14,17,19 (set 11) | mixed | 620/524 (15.5%) | 3,232/2,830 (12.4%) | 30,069/26,024 (13.5%) |