A comparative analysis of disk scheduling policies

Teorey, Toby J.; Pinkerton, Tad B.

doi:10.1145/361268.361278

Cited by 169 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reordering buffer can be used to rearrange the incoming sequence of accesses in such a way that latencies are reduced. This problem is known as disk scheduling (see, e. g., [17]). …”

Section: Introductionmentioning

confidence: 99%

Reordering buffers for general metric spaces

Englert

Räcke

Westermann

2007

Proceedings of the Thirty-Ninth Annual ACM Symposium on Theory of Computing

View full text Add to dashboard Cite

In the reordering buffer problem, we are given an input sequence of requests for service each of which corresponds to a point in a metric space. The cost of serving the requests heavily depends on the processing order. When serving a request the cost is equal to the distance, in the metric space, between this request and the previously served request. A reordering buffer with storage capacity k can be used to reorder the input sequence in a restricted fashion so as to construct an output sequence with lower service cost. This simple and universal framework is useful for many applications in computer science and economics, e. g., disk scheduling, rendering in computer graphics, or painting shops in car plants.In this paper, we design online algorithms for the reordering buffer problem where the goal is to minimize the total cost. Our main result is a strategy with a polylogarithmic competitive ratio for general metric spaces. Previous work on the reordering buffer problem only considered very restricted metric spaces. We obtain our result by first developing a * An earlier version of this work appeared in Proceedings of the 39th Annual ACM Symposium MATTHIAS ENGLERT, HARALD RÄCKE, AND MATTHIAS WESTERMANN deterministic algorithm for weighted trees whose competitive ratio depends on k and the hop-diameter of the tree. Then we show how to improve this competitive ratio to O(log 2 k) for metric spaces that correspond to hierarchically well-separated trees. Combining this result with the results on the probabilistic approximation of arbitrary metrics by tree metrics due to Fakcharoenphol, Rao, and Talwar, we obtain a randomized strategy for general metric spaces that achieves a competitive ratio of O(log 2 k · log n) in expectation against an oblivious adversary. Here n denotes the number of distinct points in the metric space. Note that the length of the input sequence can be much larger than n.

show abstract

“…A reordering buffer can be used to rearrange the incoming sequence of accesses in such a way that latencies are reduced. This problem is known as disk scheduling (see, e. g., [17]). …”

Section: Introductionmentioning

confidence: 99%

Reordering buffers for general metric spaces

Englert

Räcke

Westermann

2007

Proceedings of the Thirty-Ninth Annual ACM Symposium on Theory of Computing

View full text Add to dashboard Cite

show abstract

“…The shortest seek time first (SSTF) scheduler is a greedy scheduler that first serves the requests on the nearest track to minimize seek time [4,5]. There are several drawbacks to using SSTF: i) it does not take into account the rotational delay, which may be (at least) equally important to the seek time in modern disk drives; ii) since the middle disk tracks are more likely to be chosen by the SSTF algorithm, the pending requests located close to the inner and outermost disk tracks may potentially starve, leading to unfairness among tracks; iii) the disk's internal details may not be available to the host OS, which may then only approximate SSTF, for example by a nearest block first (NBF) algorithm [1].…”

Section: Shortest Seek Time First Schedulermentioning

confidence: 99%

“…However, request 5 arrives just before the service completion of request 3, which occurs at time t 1 . The algorithm SCAT F v2B (2,2) is then run at time t 1 , with request 5 taken into account to find the shortest cumulative access time two-hop sequence, which turns out to be (5,1). Once the service of request 5 completes, request 6 has just arrived.…”

Section: Scatfv1a Scatfv1b Scatfv2a Scatfv2bmentioning

confidence: 99%

Disk scheduling with shortest cumulative access time first algorithms

Akar¹,

Tunç²,

Gaertner³

et al. 2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:A new class of scheduling algorithms is proposed for disk drive scheduling. As opposed to choosing the request with the shortest access time in conventional shortest access time first (SATF) algorithms, we choose an ordered sequence of pending I/O requests at the scheduling instant with the shortest cumulative access time. Additionally, we introduce flexibility for forthcoming requests to alter the chosen sequence. Simulation results are provided to validate the effectiveness of the proposed disk scheduler. Throughput gains of 3% and above are shown to be attainable, although this occurs at the expense of increased computational complexity.

show abstract

“…A number of logical sequences are possible, (15,16) e.g. SCAN, shortest-seek-time-first, but studies have shown that this processing method only produces an advantage at comparatively high rates of transactions.…”

Section: Processing Mode Of Master Filementioning

confidence: 99%

Design of transaction-oriented systems employing a transaction monitor

Davenport¹

1974

Proceedings of the 1974 Annual Conference on - ACM 74

View full text Add to dashboard Cite

A comparative analysis of disk scheduling policies

Cited by 169 publications

References 5 publications

Reordering buffers for general metric spaces

Reordering buffers for general metric spaces

Disk scheduling with shortest cumulative access time first algorithms

Design of transaction-oriented systems employing a transaction monitor

Contact Info

Product

Resources

About