Evaluating partitioning and bucketing strategies for Hive-based Big Data Warehousing systems

Journal of Big Data

Table 6 SSB execution times (in seconds): bucketing by “Suppkey”

	SF = 30		SF = 100		SF = 300		SF = 30		SF = 100		SF = 300
	HIVE						PRESTO
	SS	SS-B	SS	SS-B	SS	SS-B	SS	SS-B	SS	SS-B	SS	SS-B
Q1.1	25	22	31	29	44	46	5	6	13	16	36	36
Q1.2	24	23	29	29	42	44	5	7	13	16	34	36
Q1.3	24	23	29	30	43	45	4	7	13	14	35	34
Q2.1	32	31	47	53	531	110	8	11	19	25	59	62
Q2.2	31	29	46	66	531	611	7	9	18	22	51	56
Q2.3	30	29	44	49	531	101	7	9	17	22	49	53
Q3.1	35	33	59	68	651	137	8	11	29	35	81	83
Q3.2	30	28	45	52	677	92	6	8	17	23	51	53
Q3.3	33	33	219	45	665	80	5	7	15	17	43	44
Q3.4	34	30	222	44	675	78	6	6	15	19	43	43
Q4.1	38	39	86	88	226	237	13	17	43	51	119	127
Q4.2	49	49	70	65	141	119	9	11	26	32	69	75
Q4.3	34	35	54	57	116	103	8	10	23	28	63	67
Total	420	404	982	676	4874	1803	92	120	262	321	733	768
Diff.		− 4%		− 31%		− 63%		30%		22%		5%

Italic values indicate the fastest processing time by query, workload, tool and data model