Abstract
Probe-based nano storage is a new storage medium that has several desirable features such as nano-scale density, concurrent accessing, and low-power consumption. Thus, it is expected to be adopted in a wide range of domains such as medical devices and cloud servers. However, as the internal architecture of probe-based nano storage is different from hard disk drives, new management policies are necessary. In particular, probe-based nano storage has thousands of concurrent working heads, which should be managed efficiently for maximizing performances. In this article, we analyze three important considerations in managing probe-based nano storage devices and propose scheduling policies by taking into account them. The proposed policies aim to maximize the throughput of storage but also consider the variation of waiting time. Performance evaluation results show that the proposed policies perform better than existing policies with respect to the average waiting time and the variation of the waiting time.
References
- W. Koelmans, J. Engelen, and L. Abelmann, “Probe-based data storage,” Technical Report, https://arxiv.org/abs/1511.08755 (2015).
- B. Hong, S. Brandt, D. Long, E. Miller, K. Glocer, and Z. Peterson, “Zone-based Shortest Positioning Time First Scheduling for probe-based Storage Devices,” 11th IEEE/ACM MASCOTS Conf. (2003).
- H. Yu, D. Agrawal, and A. Abbadi, “Towards optimal I/O scheduling for probe-based storage,” 20th IEEE MSST Conf. (2003).
- J. Griffin, S. Schlosser, G. Ganger, and D. Nagle, “Modeling and performance of probe-based storage devices,” ACM SIGMETRICS Conf., 56-65 (2000).
- B. Worthington, G. Ganger, and Y. Patt, “Scheduling Policies for Modern Disk Drives,” ACM SIGMETRICS Conf., 241-251 (1994).
- S. Schlosser and G. Ganger, “probe-based storage devices and standard disk interfaces: A square peg in a round hole?” 3rd USENIX FAST Conf. (2004).
- J. Griffin, S. Schlosser, G. Ganger, and D. Nagle, “Operating system management of probe-based storage devices,” 4th USENIX Symp. Operating Systems Design and Implementation, 227-242 (2000).
- B. Hong, S. Brandt, D. Long, E. Miller, K. Glocer, and Z. Peterson, “Using probe-based Storage in Computer Systems – Device Modeling and Management,” ACM Transaction on Storage, 2, 2, 139-160 (2006).
- S. Lee, H. Bahn, and S. H. Noh, “Parallelism-aware Request Scheduling for probe-based Storage Devices,” 14th IEEE MASCOTS Conf. (2006).
- P. Denning, “Effects of scheduling on file memory operations,” AFIPS Spring Computer Conf., pp.9-21 (1967).
- S. Schlosser, J. Griffin, D. Nagle, and G. Ganger, “Designing computer systems with probe-based storage,” 9th Int’l Conf. Architectural Support for Programming Languages and Operating Systems (2000).
- P. Vettiger, M. Despont, U. Drechsler, U. Dürig, W. Häberle, M. Lutwyche, H. Rothuizen, R. Stutz, R. Widmer, and G. Binnig, “The Millipede – More than one thousand tips for future AFM data storage,” IBM Journal Research and Development, Vol.44, No.3, pp.323-340 (2000).
- R. Rangaswami, Z. Dimitrijevic, E. Chang, and K. Schauser, “probe-based disk buffer for streaming media servers,” Int’l Conf. Data Engineering (2003).
- H. Yu, D. Agrawal, and A. Abbadi, “Tabular placement of relational data on probe-based storage devices,” Int’l Conf. Very Large Databases (2003).
- H. Bahn, S. Lee, and S. H. Noh, “P/PA-SPTF: Parallelism-aware Request Scheduling Policies for probe-based Storage Devices,” ACM Transactions on Storage, Vol.5, No.1 (2009).