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.
Publisher
Inventive Research Organization
Reference15 articles.
1. [1] W. Koelmans, J. Engelen, and L. Abelmann, “Probe-based data storage,” Technical Report, https://arxiv.org/abs/1511.08755 (2015).
2. [2] 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).
3. [3] H. Yu, D. Agrawal, and A. Abbadi, “Towards optimal I/O scheduling for probe-based storage,” 20th IEEE MSST Conf. (2003).
4. [4] J. Griffin, S. Schlosser, G. Ganger, and D. Nagle, “Modeling and performance of probe-based storage devices,” ACM SIGMETRICS Conf., 56-65 (2000).
5. [5] B. Worthington, G. Ganger, and Y. Patt, “Scheduling Policies for Modern Disk Drives,” ACM SIGMETRICS Conf., 241-251 (1994).
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献