Abstract
Energy management for cluster architectures has become an important design issue. In this paper, we propose a dynamic reconfiguration algorithm, named DRA-SD, to reduce the energy consumption of a real-time shared disk (SD) cluster. DRA-SD consolidates cluster load on a subset of nodes if the quality of service (QoS) is met. Remaining nodes are deactivated so that they can stay at a low-power state. When the load increases again, DRA-SD dynamically activates additional nodes. Unlike previous algorithms proposed for web server clusters, DRA-SD exploits the inherent characteristics of SD cluster to reduce the internode interference and to improve the processing capacity of a given cluster configuration. This enables DRA-SD to meet the QoS constraint while consuming minimal energy. Experiment results show that DRA-SD can save energy significantly under a wide variety of transaction workloads and node characteristics.
Similar content being viewed by others
References
Barroso LA, U H (2007) The case for energy-proportional computing. Computer 41:33–37
Bianchini R, Rajamony R (2003) Power and energy management for server systems. Computer 37:68–74
Box GEP, Jenkis GM, Reinsel GC (2008) Time series analysis. Wiley, New York
Cho H, Yoo K (2010) Buffer management in a real-time shared disks cluster. J Supercomput 53:313–328
Horvath T, Skadron K (2008) Multi-mode energy management for multi-tier server clusters. In: Proc 17th int conf parallel architectures and compilation tech (PACT), pp 270–279
IBM (2011) DB2 10 for z/OS—data sharing: planning and administration. IBM SC19-2973-03
Imada T, Sato M, Hotta Y, Kimura H (2008) Power management of distributed web servers by controlling server power state and traffic prediction for QoS. In: Proc 22nd IEEE int symp parallel and distrib processing (IPDPS), pp 1–8
Korn F, Muthukrishnan S, Wu Y (2006) Modeling skew in data streams. In: Proc 2006 ACM SIGMOD int conf management of data (SIGMOD), pp 181–192
Krioukov A, Mohan P, Alspaugh S, Keys L, Culler D, Katz R (2011) NapSAC: design and implementation of a power-proportional web cluster. ACM SIGCOMM Comput Commun Rev 41:102–108
Lang W, Patel JM (2010) Energy management for MapReduce clusters. In: Proc 2010 very large data bases conf (VLDB), pp 129–139
Lang W, Patel JM, Naughton JF (2009) On energy management, load balancing and replication. ACM SIGMOD Rec 38(4):35–42
Lee S, Ohn K, Cho H (2005) Feasibility and performance study of a shared disks cluster for real-time processing. Lect Notes Comput Sci 3397:518–527
Leverich J, Kozyrakis C (2010) On the energy (in)efficiency of hadoop clusters. Oper Syst Rev 44(1):61–65
Liu Y, Zhu H (2010) A survey of the research on power management techniques for high-performance systems. Softw Pract Exp 40:943–964
Lundhild B, Michalewicz M (2010) Oracle real application clusters (ORAC) 11g release 2. An Oracle White Paper
Meisner D, Gold BT, Wenisch TF (2009) PowerNap: eliminating server idle power. In: Proc architectural support for programming languages and operating syst, pp 205–216
Mesquite Software, Inc (2009) User’s guide of CSIM20 simulation engine
Mohan C, Narang I (1991) Recovery and coherency control protocols for fast intersystem page transfer and fine-granularity locking in a shared disks transaction environment. In: Proc 1991 very large data bases conf (VLDB), pp 193–207
Ohn K, Cho H (2006) Dynamic affinity cluster allocation in a shared disks cluster. J Supercomput 37:47–69
Pinheiro E, Bianchini R, Carrera E, Heath T (2001) Load balancing and unbalancing for power and performance in cluster-based systems. In: Proc workshop on compilers and operating syst for low power (COLP)
Poess M, Nambiar RO (2008) Energy cost, the key challenge of today’s data centers: a power consumption analysis of TPC-C results. In: Proc 2008 very large data bases conf (VLDB), pp 1229–1240
Poess M, Nambiar RO (2010) Tuning servers, storage and database for energy efficient data warehouses. In: Proc 2010 IEEE int conf data eng (ICDE), pp 1006–1017
Rajamani K, Lefurgy C (2003) On evaluating request-distribution schemes for saving energy in server clusters. In: Proc 2003 IEEE int symp performance analysis of syst and software (ISPASS), pp 111–122
Ramamritham K, Son S, Dipippo L (2004) Real-time databases and data services. Real-Time Syst 28:179–215
Rusu C, Ferreira A, Scordino C, Watson A, Melhem R, Mosse D (2006) Energy-efficient real-time heterogeneous server clusters. In: Proc IEEE real time tech and app symp (RTAS), pp 418–428
Santana C, Leite JCB, Mosse D (2011) Power management by load forecasting in web server clusters. Clust Comput 14(4):471–481
TPC Benchmark C Full Disclosure Report (2009) Sun SPARC enterprise T5440 servers using Oracle database 11g
TPC Benchmark C Full Disclosure Report (2010) Oracle’s SPARC SuperCluster with T3-4 servers using Oracle database 11g
TPC-C—top ten performance results—clustered version 5 results (2012). http://www.tpc.org/tpcc/results/tpcc_perf_results.asp?resulttype=cluster. Transaction Processing Performance Council
Yu P, Dan A (1994) Performance analysis of affinity clustering on transaction processing coupling architecture. IEEE Trans Knowl Data Eng 6(5):764–786
Zhu Q, Zhou Y (2005) Power-aware storage cache management. IEEE Trans Comput 54(5):587–602
Acknowledgements
The author would like to thank the anonymous reviewers for their helpful comments. This research was supported by the Yeungnam University research grants in 2011.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cho, H. Energy management for a real-time shared disk cluster. J Supercomput 62, 1338–1361 (2012). https://doi.org/10.1007/s11227-012-0794-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-012-0794-6