- 期刊
- OpenAccess
PAReS: A Proactive and Adaptive Redundant System for MapReduce
並列摘要
Recently, MapReduce has been a key and popular technology for tackling data-intensive applications. But its two master servers in current MapReduce implementations have a single-failure problem, which may interrupt MapReduce operations and filesystem services. In this paper, we propose a hybrid takeover scheme, called the Proactive and Adaptive Redundant System (PAReS for short), which employs three service-quality improvement mechanisms, including a proactive synchronization and replication method, a mutual monitoring algorithm, and an adaptive warm-up mechanism, to mitigate the above problems. The extensive experiments show that PAReS enhances service quality at acceptable energy consumption level and synchronization cost as compared with four stateof- the-art schemes.
延伸閱讀
- 紀玟君（2014）。Parallel QBL-PSO Using MapReduce〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU.2014.10785
- Said, M. B., Kacem, Y. H., Kerboeuf, M., Amor, N. B., & Abid, M. (2014). Design Patterns for Self-Adaptive RTE Systems Specification. International Journal of Reconfigurable Computing, (2014), 84-104. https://doi.org/10.1155/2014/536362
- Kim, S. G., Han, H., Jung, H., Eom, H., & Yeom, H. Y. (2011). Improving MapReduce Performance by Exploiting Input Redundancy. Journal of Information Science and Engineering, 27(3), 1137-1152. https://doi.org/10.6688/JISE.2011.27.3.21
- Kim, S. G., Han, H., Jung, H. S., Eom, H. S., & Yeom, H. Y. (2011). Improving MapReduce Performance by Exploiting Input Redundancy. Journal of Information Science and Engineering, 27(2), 789-804. https://doi.org/10.6688/JISE.2011.27.2.24
- Park, J. H., Jeong, H. Y., Jeong, Y. S., & Choi, M. (2014). REST-MapReduce: An Integrated Interface but Differentiated Service. Journal of Applied Mathematics, 2014(), 847-856-075. https://doi.org/10.1155/2014/170723