Abstract
Increasing data replication improves the reliability and availability of the large-scale storage systems. However, multiple replication required much more storage capacity and disk I/O frequency that cause of increasing the power consumption of the storage systems. To address this issue, we propose two data placement policies, Disk Group Aggregation and Cache Striping. These data placement policies employ different data mapping between buffers (memory) and disk drives to control buffer overflow timing of each replica to reduce the disk access frequency. In addition, we also propose two buffer flush algorithms, WithAllSpins and SpinupEE. WithAllSpins flushes buffered data to currently rotating disks, whereas SpinupEE forces disks to spin up based on the estimated energy efficiency, and writes buffered data to the disk to make the buffer space fresh. We evaluated the effectiveness of our proposals using a simulation program and demonstrated that they can reduce power consumption, even if the data are replicated multiply.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amur, H., et al.: Robust and flexible power-proportional storage. In: Proceedings of the 1st ACM Symposium on Cloud Computing, SoCC 2010 (2010)
Colarelli, D., Grunwald, D.: Massive arrays of idle disks for storage archives. In: Proceedings of the ACM/IEEE Conference on Supercomputing, pp. 1–11 (2002)
Ghemawat, S., Gobioff, H., Leung, S.T.: The Google file system. SIGOPS Oper. Syst. Rev. 37(5), 29–43 (2003)
Le, H.H., Hikida, S., Yokota, H.: Accordion: an efficient gear-shifting for a power-proportional distributed data-placement method. IEICE Trans. Inform. Syst. 1013–1026 (2015)
Hitachi Global Storage Technologies: Hard disk drive specification, hitachi deskstar 7k2000. http://www.hgst.com/tech/techlib.nsf/products/Ultrastar_7K4000
Hsiao, H.I., DeWitt, D.J.: Chained declustering: a new availability strategy for multiprocessor database machines. In: Proceedings of the 6th ICDE, pp. 456–465 (1990)
Kim, J., Rotem, D.: Energy proportionality for disk storage using replication. In: Proceedings of the 14th EDBT (2011)
Lakshman, A., Malik, P.: Cassandra: a decentralized structured storage system. SIGOPS Oper. Syst. Rev. 44(2), 35–40 (2010)
Lang, W., Patel, J.M., Naughton, J.F.: On energy management, load balancing and replication. SIGMOD Rec. 38(4), 35–42 (2010)
Hikida, S., Le, H.H., Yokota, H.: A power saving storage method that considers individual disk rotation. In: Lee, S., Peng, Z., Zhou, X., Moon, Y.-S., Unland, R., Yoo, J. (eds.) DASFAA 2012. LNCS, vol. 7239, pp. 138–149. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29035-0_10
Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The Hadoop distributed file system. In: 2010 IEEE 26th MSST, pp. 1–10, May 2010
Storage system simulator. https://github.com/reddikih/spsim2
Thereska, E., Donnelly, A., Narayanan, D.: Sierra: practical power-proportionality for data center storage. In: Proceedings of the 6th Conference on Computer Systems. ACM (2011)
Yin, S., Li, X., et al.: REED: a reliable energy-efficient raid. In: 2015 44th International Conference on Parallel Processing, pp. 649–658, September 2015
Yin, S., Xiao, Z., et al.: RESS: a reliable energy-efficient storage system. In: IEEE 22nd International Conference on Parallel and Distributed Systems, pp. 1193–1198, December 2016
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hikida, S., Le, H.H., Yokota, H. (2019). Energy Efficient Data Placement and Buffer Management for Multiple Replication. In: Hartmann, S., Küng, J., Chakravarthy, S., Anderst-Kotsis, G., Tjoa, A., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2019. Lecture Notes in Computer Science(), vol 11707. Springer, Cham. https://doi.org/10.1007/978-3-030-27618-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-27618-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27617-1
Online ISBN: 978-3-030-27618-8
eBook Packages: Computer ScienceComputer Science (R0)