Institutional Repository
| dynamic modeling of elastic caching platforms for cache strategy reconfiguration | |
| Zhang Wenbo; Huang Xiang; Chen Ningjiang; Qin Xiulei; Zhong Hua | |
| 2012 | |
| Source | Journal of Computational Information Systems
 |
| ISSN | 1553-9105 |
| Volume | 8Issue:22Pages:9299-9314 |
| English Abstract | Elastic caching platforms (ECPs) support various cache strategies that can largely affect the system performance, where cache strategy reconfiguration plays an important role. While traditional try-and-do approaches are not capable of making such costly decisions, performance models have some native advantages to do so. However, building performance models for ECPs is challenging, since some arguments, such as their cluster sizes, are variable according to workloads. In this paper, we propose a dynamic modeling approach for cache strategy reconfiguration of ECPs. In our study, an ECP is firstly decoupled into several aspect models that can be dynamically instantiated with their current arguments. These models, together with the application model, can be woven into different LQN (Layer Queue Network) models of the entire ECP-based system for each specific cache strategy. Then reconfiguration decisions can be made based on the predict results of these LQN models. Our experimental results have shown the effectiveness of the approach. Copyright © 2012 Binary Information Press.; Elastic caching platforms (ECPs) support various cache strategies that can largely affect the system performance, where cache strategy reconfiguration plays an important role. While traditional try-and-do approaches are not capable of making such costly decisions, performance models have some native advantages to do so. However, building performance models for ECPs is challenging, since some arguments, such as their cluster sizes, are variable according to workloads. In this paper, we propose a dynamic modeling approach for cache strategy reconfiguration of ECPs. In our study, an ECP is firstly decoupled into several aspect models that can be dynamically instantiated with their current arguments. These models, together with the application model, can be woven into different LQN (Layer Queue Network) models of the entire ECP-based system for each specific cache strategy. Then reconfiguration decisions can be made based on the predict results of these LQN models. Our experimental results have shown the effectiveness of the approach. Copyright © 2012 Binary Information Press. |
| Indexed Type | EI |
| Keyword | Computer Applications Information Systems Models |
| Department | (1) Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences Beijing 100190 China; (2) College of Computer Electronic and Information Guangxi University Nanning 530004 China |
| Language | 英语 |
| Content Type | 期刊论文 |
| URI | http://ir.iscas.ac.cn/handle/311060/15419 |
| Collection | 中国科学院软件研究所 |
| Recommended Citation GB/T 7714 | Zhang Wenbo,Huang Xiang,Chen Ningjiang,et al. dynamic modeling of elastic caching platforms for cache strategy reconfiguration[J]. Journal of Computational Information Systems,2012,8(22):9299-9314. |
| APA | Zhang Wenbo,Huang Xiang,Chen Ningjiang,Qin Xiulei,&Zhong Hua.(2012).dynamic modeling of elastic caching platforms for cache strategy reconfiguration.Journal of Computational Information Systems,8(22),9299-9314. |
| MLA | Zhang Wenbo,et al."dynamic modeling of elastic caching platforms for cache strategy reconfiguration".Journal of Computational Information Systems 8.22(2012):9299-9314. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment