Abstract | ||
---|---|---|
•We create a multivariate regression model that can leverage query semantics to accurately predict the execution time of jobs and queries.•We design a two-level scheduling framework that can schedule analytics queries at two levels: the intra-query level for better job parallelism and the inter-query level for fast and fair query completion.•Using an extensive set of queries and mixed workloads, we have evaluated TLS and demonstrated its benefits in improving system throughput and query fairness. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.parco.2019.01.006 | Parallel Computing |
Keywords | Field | DocType |
MapReduce,Multivariate modeling,Query scheduling | Query throughput,Computer science,Scheduling (computing),Concurrency,Theoretical computer science,Two-level scheduling,Directed acyclic graph,Queueing theory,Throughput,Speedup | Journal |
Volume | ISSN | Citations |
85 | 0167-8191 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhuo Liu | 1 | 118 | 16.03 |
Amit Kumar Nath | 2 | 0 | 0.68 |
Xiaoning Ding | 3 | 1111 | 65.19 |
Huansong Fu | 4 | 2 | 1.39 |
Md. Muhib Khan | 5 | 0 | 0.34 |
Weikuan Yu | 6 | 1042 | 77.40 |