Abstract
The performance of streaming media servers has been limited by the dual requirements of high disk throughput (to service more clients simultaneously) and low memory use (to decrease system cost). To achieve high disk throughput, disk drives must be accessed with large IOs to amortize disk access overhead. Large IOs imply an increased requirement of expensive DRAM, and, consequently, greater overall system cost. MEMS-based storage, an emerging storage technology, is predicted to offer a price-performance point between those of DRAM and disk drives. In this study, we propose storage architectures that use the relatively inexpensive MEMS-based storage devices as an intermediate layer (between DRAM and disk drives) for temporarily staging large disk IOs at a significantly lower cost. We present data layout mechanisms and synchronized IO scheduling algorithms for the real-time storage and retrieval of streaming data within such an augmented storage system. Analytical evaluation suggests that MEMS-augmented storage hierarchies can reduce the cost and improve the throughput of streaming servers significantly.
- Anderson, D., Dykes, J., and Riedel, E. 2003. More than an interface---SCSI vs. ATA. Proceedings of the 2nd USENIX Conference on File and Storage Technologies. 245--257. Google Scholar
Digital Library
- Carley, L. R., Ganger, G. R., and Nagle, D. 2000. MEMS-based integrated-circuit mass-storage systems. Comm. ACM 43, 11 (Nov), 73--80. Google Scholar
Digital Library
- Chang, E. and Garcia-Molina, H. 1997. Effective memory use in a media server. Proceedings of the 23rd VLDB Conference. 496--505. Google Scholar
Digital Library
- Chervenak, A. L. 1994. Tertiary storage: An evaluation of new applications. Tech. rep. No. UCB/CSD-94-847. University of California, Berkeley. Google Scholar
Digital Library
- Chervenak, A. L. and Patterson, D. A. 1995. Choosing the best storage system for video service. Proceedings of ACM Multimedia. 109--118. Google Scholar
Digital Library
- Daigle, S. J. and Strosnider, J. K. 1994. Disk scheduling for multimedia data streams. Proceedings of the IS&T/SPIE Conference.Google Scholar
- Denehy, T. E., Arpaci-Dusseau, A. C., and Arpaci-Dusseau, R. H. 2002. Bridging the information gap in storage protocol stacks. Proceedings of the USENIX Annual Technical Conference. 177--190. Google Scholar
Digital Library
- Dimitrijevic, Z. and Rangaswami, R. 2003. Quality of service support for real-time storage systems. Proceedings of International IPSI Conference.Google Scholar
- Dimitrijevic, Z., Rangaswami, R., and Chang, E. 2003. Design and implementation of semi-preemptible IO. Proceedings of Usenix File and Storage Technologies Conference. Google Scholar
Digital Library
- Grochowski, E. and Halem, R. D. 2003. Technological impact of magnetic hard disk drives on storage systems. IBM Sys. J. 42, 2 (April) 338--346. Google Scholar
Digital Library
- Hillyer, B. K. and Silberschatz, A. 1996. Random I/O scheduling in online tertiary storage systems. Proceedings of the 1996 ACM SIGMOD. 195--204. Google Scholar
Digital Library
- Hong, B., Brandt, S. A., Long, D. D. E., Miller, E., and Lin, Y. 2006. Using MEMS-based storage in computer systems: Device modeling and measurement. ACM Trans. Storage 2, 2 (May) 139--160. Google Scholar
Digital Library
- Hong, B., Wang, F., Brandt, S. A., Long, D. D. E., and Schwarz, T. J. E. 2006. Using MEMS-based storage in computer systems: MEMS storage architectures. ACM Trans. Storage 2, 1 (Feb) 1--21. Google Scholar
Digital Library
- Hsu, W. and Smith, A. J. 2004. The performance impact of I/O optimizations and disk improvements. IBM J. Resear. Develop. 48, 2 (March) 255--289. Google Scholar
Digital Library
- Liu, B., Rangaswami, R., and Dimitrijevic, Z. 2006. Stream combination: Adaptive IO scheduling for streaming servers. ACM SigBED Rev. 3, 1 (Jan). Google Scholar
Digital Library
- Makaroff, D., Neufeld, G., and Hutchinson, N. 1997. An evaluation of VBR disk admission algorithms for continuous media file. Proceedings of the 5th ACM Multimedia Conference. 143--154. Google Scholar
Digital Library
- Maxtor Corporation. 2002. Atlas 10KIII-U320 product datasheet.Google Scholar
- Molano, A., Juvva, K., and Rajkumar, R. 1997. Guaranteeing timing constraints for disk accesses in RT-mach. Proceedings of the Real-Time Systems Symposium. Google Scholar
Digital Library
- Nanochip Inc. 2006. Nanochip secures $10 million in series C funding led By Intel capital. Nanochip Media Release (http://www.nanochip.com/pr/pr20060418.htm.Google Scholar
- Rambus Inc. 2006. RDRAM. http://www.rambus.com/.Google Scholar
- Rangan, P. V., Vin, H. M., and Ramanathan, S. 1992. Designing and on-demand multimedia service. IEEE Comm. Mag. 30, 7 (July) 56--65.Google Scholar
Digital Library
- Rangaswami, R., Dimitrijevic, Z., Chang, E., and Schauser, K. E. 2003. MEMS-based disk buffer for streaming media servers. Proceedings of IEEE International Conference on Data Engineering. 619--630.Google Scholar
- Santos, J. R., Muntz, R. R., and Ribeiro-Neto, B. A. 2000. Comparing random data allocation and data striping in multimedia servers. Proceedings of the International Conference on Measurement and Modeling of Computer Systems. 44--55. Google Scholar
Digital Library
- Schindler, J., Schlosser, S. W., Shao, M., Ailamaki, A., and Ganger, G. R. 2004. Atropos: A disk array volume manager for orchestrated use of disks. Proceedings of the USENIX Conference on File and Storage Technologies. Google Scholar
Digital Library
- Schlosser, S. W. and Ganger, G. R. 2004. Mems-based storage devices and standard disk interfaces: A square peg in a round hole? Proceedings of the USENIX Conference on File and Storage Technologies. Google Scholar
Digital Library
- Schlosser, S. W., Griffin, J. L., Nagle, D., and Ganger, G. R. 2000. Designing computer systems with MEMS-based storage. Proceedings of Architectural Support for Programming Languages and Operating Systems. 1--12. Google Scholar
Digital Library
- Shahabi, C., Ghandeharizadeh, S., and Chaudhuri, S. 2002. On scheduling atomic and composite multimedia objects. IEEE Trans. Knowl. and Data Engin. 14, 2, 447--455. Google Scholar
Digital Library
- Thompson, D. A. and Best, J. S. 2000. The future of magnetic data storage technology. IBM J. Resear. Develop. 44, 3 (May). Google Scholar
Digital Library
- To, T.-P. J. and Hamidzadeh, B. 1999. Dynamic real-time scheduling strategies for interactive continuous media servers. ACM/Springer Multimedia Sys. 7, 2, 91--106. Google Scholar
Digital Library
- Uysal, M., Merchant, A., and Alverez, G. A. 2003. Using MEMS-based storage in disk arrays. Proceedings of Usenix Conference on File and Storage Technologies. 89--101. Google Scholar
Digital Library
- Vettiger, P., Despont, M., Drechsler, U., Durig, U., Haberle, W., Lutwyche, M. I., Rothuizen, H. E., Stutz, R., Widmer, R., and Binning, G. K. 2000. The “Millipede”---More than one thousand tips for future AFM data storage. IBM J. Resear. Develop. 44, 3, 323--340. Google Scholar
Digital Library
- Wolf, J. L., Yu, P. S., and Shachnai, H. 1995. DASD Dancing: A disk load balancing optimization scheme for video-on-demand computer systems. Proceedings of the ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems. 157--166. Google Scholar
Digital Library
- Yu, H., Agrawal, D., and Abbadi, A. E. 2003. Tabular placement of relational data on MEMS-based storage devices. Proceedings of the International Conference on Very Large Data Bases. Google Scholar
Digital Library
- Yu, H., Agrawal, D., and Abbadi, A. E. 2004. Declustering two-dimensional datasets over MEMS-based storage. Proceedings of the International Conference on Extending DataBase Technology.Google Scholar
Index Terms
Building MEMS-based storage systems for streaming media
Recommendations
Using MEMS-based storage in computer systems---MEMS storage architectures
As an emerging nonvolatile secondary storage technology, MEMS-based storage exhibits several desirable properties including high performance, high storage volumic density, low power consumption, low entry cost, and small form factor. However, MEMS-based ...
On the parallelism of I/O scheduling algorithms in MEMS-based large storage systems
MEMS-based storage is being developed as a new storage media that has several salient characteristics such as high-parallelism, high density, and low-power consumption. Because physical structures of MEMS-based storage is different from those of hard ...
Comparison of I/O scheduling algorithms for high parallelism MEMS-based storage devices
SEPADS'09: Proceedings of the 8th WSEAS International Conference on Software engineering, parallel and distributed systemsMEMS-based storage is one of the leading candidates as tomorrow's storage medium due to its salient characteristics such as high-parallelism, high density, and low-power consumption. Because physical structures of MEMS-based storage is different from ...






Comments