Abstract
The high latencies for access to background memory like hard disks or flash memory can be reduced by caching or hidden by prefetching. We consider the problem of scheduling the resulting I/Os when the available fast cache memory is limited and when we have real-time constraints where for each requested data block we are given a time interval during which this block needs to be in main memory. We give a near linear time algorithm for this problem which produces a feasible schedule whenever one exists. Another algorithm additionally minimizes I/Os and still runs in polynomial-time. For the online variant of the problem, we give a competitive algorithm that uses lookahead and augmented disk speed. We show a tight relationship between the amount of lookahead and the speed required to get a competitive algorithm.
Similar content being viewed by others
Notes
Here we describe the final schedule of Lazy-LFD. The actual decision to evict such a page will be taken later in the algorithm because it works backwards from the end of the input.
Which are very common for hard disks, whereas for SSDs—at least when only reading—it should be possible to have highly deterministic disk access delays.
References
Albers, S. (1997). On the influence of lookahead in competitive paging algorithms. Algorithmica, 18, 283–305.
Albers, S., Garg, N., & Leonardi, S. (2000). Minimizing stall time in single and parallel disk systems. Journal of ACM, 47(6), 969–986.
Belady, L. A. (1966). A study of replacement algorithms for virtual storage computers. IBM Systems Journal, 5, 78–101.
Borodin, A., & El-Yaniv, R. (1998). Online computation and competitive analysis. Cambridge, MA: Cambridge University Press.
Borodin, A., Irani, S., Raghavan, P., & Schieber, B. (1995). Competitive paging with locality of reference. Journal of Computer Systems Sciences, 50, 244–258.
Cao, P., Felten, E. W., Karlin, A. R., & Li, K. (1995). A study of integrated prefetching and caching strategies. In SIGMETRICS (pp. 188–197).
Ertug, Ö., Kallahalla, M., & Varman, P. J. (2000) Real time parallel disk scheduling for VBR video servers. In Proceedings of Fifth International Conference on Computer Science and Informatics (CSI’00), Chennai, India.
Fiat, A., & Mendel M. (1997). Truly online paging with locality of reference. In Proceedings of the IEEE 38th Symposium on Foundations of Computer Science (FOCS) (pp. 326–335).
Hutchinson, D. A., Sanders, P., & Vitter, J. S. (2005). Duality between prefetching and queued writing. SIAM Journal on Computing, 34(6), 1443–1463.
Kallahalla, M., & Varman, P. J. (1999). Optimal read-once parallel disk scheduling. In 6th Workshop on Input/Output in Parallel and Distributed Systems (pp. 68–77).
Kallahalla, M., & Varman, P. J. (2001). Optimal prefetching and caching for parallel I/O systems. In 13th Symposium on Parallel Algorithms and Architectures (pp. 219–228).
Kimbrel, T., & Karlin, A. R. (2000). Near-optimal parallel prefetching and caching. SIAM Journal of Computing, 29(4), 1051–1082.
Krishnan, P., & Vitter, J. S. (1998). Optimal prediction for prefetching in the worst case. SIAM Journal of Computing, 27(6), 1617–1636.
Panagiotou, K., & Souza, A. (2006). On adequate performance measures for paging. In STOC ’06: Proceedings of the Thirty-eighth Annual ACM Symposium on Theory of Computing (pp. 487–496). New York: ACM Press.
Scott, J. V., & Krishnan, P. (1996). Optimal prefetching via data compression. Journal of ACM, 43(5), 771–793.
Acknowledgments
The authors would like to thank anonymous referees who pointed out some oversights in the proofs in a previous version of this paper. Research supported by German Research Foundation (DFG).
Author information
Authors and Affiliations
Corresponding author
Additional information
Work performed while the third author was at the Karlsruhe Institute of Technology, Germany.
Rights and permissions
About this article
Cite this article
Sanders, P., Singler, J. & van Stee, R. Real-time integrated prefetching and caching. J Sched 16, 47–58 (2013). https://doi.org/10.1007/s10951-012-0301-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10951-012-0301-1