ABSTRACT
Network attached storage devices improve I/O performance by separating control and data paths and eliminating host intervention during data transfer. Devices are attached to a high speed network for data transfer and to a slower network for control messages. Hierarchical mass storage systems use disks to cache the most recently used files and tapes (robotic and manually mounted) to store the bulk of the files in the file system. This paper shows how queuing network models can be used to assess the performance of hierarchical mass storage systems that use network attached storage devices. The analytic model validated through simulation was used to analyze many different scenarios.
- 1.R. Katz, "High-Performance Network and Channel Based Storage", Proceedings o} the IEEE, vol. 80, no. 8, pp. 1238-1261, August 1992.Google ScholarCross Ref
- 2.Convex Computer Corporation, Unitree-/-~ System Administration Guide, First Edition, Convex Press, Richardson, TX, 1993.Google Scholar
- 3.D. Teaff, D. Watson, and B. Coyne, "The Architecture of the High Performance Storage System", in Proc. o~ the Goddard Conf. on Mass Storage ~'t Technologies, College Park, MD, March 1995. Google ScholarDigital Library
- 4.O. Pentakalos, D. Menasc@, M. Haleru, and Y. Yesha, "An Approximate Performance Model of a Unitree Mass Storage System", ibid. Google ScholarDigital Library
- 5.S. Agrawal, Metamodeling: A Study o/ Approxima. tions in Queueing Models, The MIT Press, Cambridge, MA, 1985. Google ScholarDigital Library
- 6.C. Wood, "Client/Server Data Serving for High- Performance Computing", in 14th IEEE Sympo-. sium on Mass Storage Systems, Monterey, CA, September 1995, pp. 107-119. Google ScholarDigital Library
- 7.Maximum Strategy, inc., GEN-5 XL System. Guide/iPI-3 Manual Revision 1.00, January 1995.Google Scholar
- 8.D. Tolmie, "High-Performance Parallel Interface (HIPPI)", in High Performance Networks: Technology and Protocols, A. Tantawy, Ed., pp. 131- 156. Kluwer Academic Publishers, Boston, 1994.Google ScholarCross Ref
- 9.D. Menasc@, V. Almeida, and L. Dowdy, Capacity Planning and Performance Modeling: From Mainframes to Client-Server Systems, Prentice- Hall, Englewood Cliffs, NJ, 1994. Google ScholarDigital Library
- 10.K. Sevcik and i. Mitrani, "The Distribution of Queuing Network States at Input and Output Instants", JACM, vol. 28, no. 2, April 1981. Google ScholarDigital Library
- 11.H. Schwetman, "CSIM: A C-based, process oriented simulation language", in Proc. o} the 1991 Winter Simulation Conference, 1991, pp. 387-396. Google ScholarDigital Library
- 12.D. Menasc@, O. Pentakalos, and Y. Yesha, "An Analytic Model of Hierarchical Mass Storage Systems with Network-Attached ~torage Devices"~ Tech. Rep. TR-95-164, CESDIS, November 1995.Google Scholar
Index Terms
An analytic model of hierarchical mass storage systems with network-attached storage devices
Recommendations
An analytic model of hierarchical mass storage systems with network-attached storage devices
Network attached storage devices improve I/O performance by separating control and data paths and eliminating host intervention during data transfer. Devices are attached to a high speed network for data transfer and to a slower network for control ...
Deconstructing Network Attached Storage systems
Network Attached Storage (NAS) has been gaining general acceptance, because it can be managed easily and files shared among many clients, which run different operating systems. The advent of Gigabit Ethernet and high speed transport protocols further ...
Exploring the performance impact of stripe size on network attached storage systems
Network attached storage (NAS) integrates redundant array of independent disks (RAID) subsystem that consists of multiple disk drives to aggregate storage capacity, I/O performance and reliability based on data striping and distribution. Traditionally, ...
Comments