摘要: 针对机群系统中存在的大量空闲活跃结点所造成的严重能耗浪费,提出空闲结点的cache 式动态功耗管理模型,即利用结点多级休眠机制,将空闲结点划分为不同休眠等级的结点集合,每级休眠状态对应一级结点储备cache,力求获得近似活跃状态的系统响应速率,以及近似最深休眠状态的能耗节省。基于cache式功耗管理模型,综合能耗与响应速率两个因素,设计了空闲结点在不同休眠状态之间的动态升降级算法、基于储备池的资源结点分配与回收算法以及储备额阈值自适应算法,以在保证系统响应速率的同时降低系统能耗。实验表明,提出的空闲结点cache式功耗管理技术在作业相对延迟仅增加0.99%的代价下,系统空闲结点功耗降低69.51%,优化效果显著。
[1] Feng Wu-chun.Making a case for efficient supercomputing [J].ACM Queue,2003,1(7):54-64 [2] Top 500.Top500List .http://www.top500.org,2012 [3] U.S.Environmental Protection Agency.Report to congress on server and data center energy efficiency .http://www.energy star.gov/ia/partners/prod_development/downloads/EPA_Datacenter_Report_Congress _Final1.pdf,2007 [4] Krioukov A,Mohan P,Alspaugh S,et al.NapSAC:Design and implementation of a power-proportional web cluster [J].ACM SIGCOMM Computer Communication Review,2011,41(1):102-108 [5] Mustafa R M,Nishkam R,Srihari C,et al.Power management for heterogeneous clusters:an experimental study[C]∥Procee-dings of the 2nd International Green Computing Conference (IGCC’11).Orlando,Florida,2011:1-8 [6] Liu Yong-peng,Zhu Hong.A survey of the research on power management techniques for high performance systems [J].Software Practice and Experience,2010,40(1):943-964 [7] Chase J,Aderson D,Thakar P,et al.Managing energy and server resources in hosting centers[C]∥Proceedings of the 18th ACM Symposium on Operating Systems Principles (SOSP’01).Banff,Canada,2001:103-116 [8] Hong Liang-jie,Davison B D.Empirical study of topic modeling in Twitter[C]∥Proceedings of the First Workshop on Social Media Analytics.Washington DC,USA,2010:80-88 [9] Rosen-Zvi M,Griffiths T,Steyvers M,et al.The author-topic model for authors and documents[C]∥Proceedings of the 20th conference on Uncertainty in artificial intelligence.AUAI Press Arlington,Virginia,United States,2004:487-494 [10] Steyvers M,Smyth P,Rosen-Zvi M,et al.Probabilistic author-topic models for information discovery[C]∥Proceedings of the Tenth ACM SIGKDD International Confe-rence on Knowledge Discovery and Data Mining.Seattle,WA,USA,2004:306-315 [11] Ramage D,Dumais S,Liebling D.Characterizing micorblogs with topic models[C]∥Proceedings of the 4th International Confe-rence on Weblogs and Social Media.Washington DC,U S A,2010 [12] Daud A,Li Juan-zi,Zhou Li-zhu,et al.Exploiting temporal authors interests via temporal-author-topic modeling[C]∥Proceedings of 5th International Conference on Advanced Data Mi-ning and Applications.Verlag Berlin,Heidelberg,2009:435-443 [13] Liu Yan,Niculescu-Mizil A,Gryc W.Topic-link LDA:jointmodels of topic and author community[C]∥Proceedings of the 26th Annual International Conference on Machine Learning.Montreal,QC,Canada,2009:665-672 [14] Wang Xue-rui,McCallum A.Topics over time:a non-markovcontinuous-time model of topical trends[C]∥Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Philadelphia,USA,2006:424-433 [15] McCallum A,Corrada-Emmanuel A,Wang Xue-rui.Topic androle discovery in social networks[C]∥Proceedings of 19th International Joint Conference on Artificial Intelligence,Morgan Kaufmann Publishers Inc.San Francisco,CA,USA:786-791 [16] Mei Qiao-zhu,Liu Chao,Su Hang,et al.A probabilistic ap-proach to spatiotemporal theme pattern mining on weblogs[C]∥Proceedings of the 15th International Conference on Word Wide Web.Edinburgh,Scotland,UK,2006:533-542 [17] Su Yi-zhou,Han Jia-wei,Gao Jing,et al.iTopicModel:Information Network-Integrated Topic Modeling[C]∥Proceeding of the 9th IEEE International Conference on Data Mining.Miami,USA,2009:487-497 [18] Mei Qiao-zhu,Cai Deng,Zhang Duo,et al.Topic modeling with network regularization[C]∥Proceeding of the 17th InternationalWorld Wide Web Conference.Beijing,China,2008:101-111 |
No related articles found! |
|