Nedeljko Vasić
Dejan Kostic
ABSTRACT
Power consumption has become a critical issue in large scale clusters. Existing solutions for addressing the servers' energy consumption suggest "shrinking" the set of active machines, at least until the more power-proportional hardware devices become available. This paper demonstrates that leveraging the sleeping state, however, may lead to unacceptably poor performance and low data availability if the distributed services are not aware of the power management's actions. Therefore, we present an architecture for cluster services in which the deployed services overcome this problem by actively participating in any action taken by the power management. We propose, implement, and evaluate modifications for the Hadoop Distributed File System and the MapReduce clone that make them capable of operating efficiently under limited power budgets.
- Hadoop distributed file system.Google Scholar
- Luiz André Barroso and Urs Hölzle. The case for energy-proportional computing. Computer, 2007. Google ScholarDigital Library
- Ricardo Bianchini and Ram Rajamony. Power and energy management for server systems. Computer, 2004. Google ScholarDigital Library
- Jeffrey S. Chase, Darrell C. Anderson, Prachi N. Thakar, Amin M. Vahdat, and Ronald P. Doyle. Managing energy and server resources in hosting centers. SIGOPS, 2001. Google ScholarDigital Library
- Fred Douglis, P. Krishnan, and Brian N. Bershad. Adaptive disk spin-down policies for mobile computers. In MLICS, 1995. Google ScholarDigital Library
- Mootaz Elnozahy, Michael Kistler, and Ramakrishnan Rajamony. Energy conservation policies for web servers. In USITS, 2003. Google ScholarDigital Library
- U.S. EPA. Report to congress on server and data center energy efficiency. Technical report, 2007.Google Scholar
- Wu-chun Feng. Making a case for efficient supercomputing. Queue, 2003. Google ScholarDigital Library
- Krisztián Flautner, Steve Reinhardt, and Trevor Mudge. Automatic performance setting for dynamic voltage scaling. Wirel. Netw., 2002. Google ScholarDigital Library
- Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung. The google file system. SIGOPS, 2003. Google ScholarDigital Library
- Sudhanva Gurumurthi, Anand Sivasubramaniam, Mahmut Kandemir, and Hubertus Franke. Drpm: dynamic speed control for power management in server class disks. SIGARCH, 2003. Google ScholarDigital Library
- Taliver Heath, Ana Paula Centeno, Pradeep George, Luiz Ramos, Yogesh Jaluria, and Ricardo Bianchini. Mercury and freon: temperature emulation and management for server systems. In ASPLOS, 2006. Google ScholarDigital Library
- Kyong Hoon Kim, Rajkumar Buyya, and Jong Kim. Power aware scheduling of bag-of-tasks applications with deadline constraints on dvs-enabled clusters. In CCGRID, 2007.Google ScholarDigital Library
- Alvin R. Lebeck, Xiaobo Fan, Heng Zeng, and Carla Ellis. Power aware page allocation. SIGOPS, 2000. Google ScholarDigital Library
- Eduardo Pinheiro, Ricardo Bianchini, Enrique V. Carrera, and Taliver Heath. Dynamic cluster reconfiguration for power and performance. Compilers and operating systems for low power, pages 75--93, 2003. Google ScholarDigital Library
- Ramya Raghavendra, Parthasarathy Ranganathan, Vanish Talwar, Zhikui Wang, and Xiaoyun Zhu. No "power" struggles: coordinated multi-level power management for the data center. SIGARCH, 2008. Google ScholarDigital Library
- Arun Rangasamy, Rahul Nagpal, and Y.N. Srikant. Compiler-directed frequency and voltage scaling for a multiple clock domain microarchitecture. In CF, 2008. Google ScholarDigital Library
- Alexey Rudenko, Peter Reiher, Gerald J. Popek, and Geoffrey H. Kuenning. Saving portable computer battery power through remote process execution. SIGMOBILE, 1998. Google ScholarDigital Library
- Yasushi Saito, Svend Frolund, Alistair Veitch, Arif Merchant, and Susan Spence. Fab: building distributed enterprise disk arrays from commodity components. SIGOPS, 2004. Google ScholarDigital Library
- Mark Weiser, Brent Welch, Alan Demers, and Scott Shenker. Scheduling for reduced cpu energy. In OSDI, 1994. Google ScholarDigital Library
- Hung-chih Yang, Ali Dasdan, Ruey-Lung Hsiao, and D. Stott Parker. Map-reduce-merge: simplified relational data processing on large clusters. In SIGMOD, 2007. Google ScholarDigital Library
- Matei Zaharia, Andy Konwinski, Anthony D. Joseph, Randy H. Katz, and Ion Stoica. Improving mapreduce performance in heterogeneous environments. In OSDI, 2008. Google ScholarDigital Library
Index Terms
- Making cluster applications energy-aware
Recommendations
Engineering energy-aware web services toward dynamically-green computing
ICSOC'11: Proceedings of the 2011 international conference on Service-Oriented ComputingWith the emergence of commodity computing environments (i.e. clouds), information technology (IT) infrastructure providers are creating data centers in distributed geographical regions. Since geographic regions have different costs and demands on their ...
A dynamic Energy-aware fault tolerant routing protocol for wireless sensor networks
In recent decades, cluster-based schemes have emerged as viable solutions for energy conservation problem in wireless sensor networks (WSN). However, most of the existing solutions incur imbalanced energy consumption and high network overheads. In ...
Energy-aware parallel task scheduling in a cluster
Reducing energy consumption for high end computing can bring various benefits such as reducing operating costs, increasing system reliability, and environmental respect. This paper aims to develop scheduling heuristics and to present application ...
Comments