Random I/O scheduling in online tertiary storage systems

Hillyer, Bruce K.; Silberschatz, Abraham

doi:10.1145/233269.233332

Cited by 29 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The augmented hierarchy we explore in this study is reminiscent of prior efforts that explored integration of DRAM, disk, and tape into an online storage hierarchy [Chervenak 1994;Hillyer and Silberschatz 1996]. The study of Chervenak [1994] specifically pointed out the unsuitability of such an augmented online storage hierarchy (with tapes at the tertiary level) for the class of streaming media applications.…”

Section: Related Workmentioning

confidence: 99%

Building MEMS-based storage systems for streaming media

et al. 2007

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Building MEMS-based storage systems for streaming media

et al. 2007

View full text Add to dashboard Cite

show abstract

“…This supports the approach we used in Promote-IT where we read all the data requested from an RSM before the RSM is unloaded. Hillyer et al [13,12,11] compare different scheduling algorithms for retrieving data from a magnetic tape without real-time requirements.…”

Section: Related Workmentioning

confidence: 99%

A Flexible Real-Time Hierarchical Multimedia Archive

Lijding

Jansen

Mullender

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We present a hierarchical multimedia archive that can serve complex multimedia requests from tertiary storage. Requests can consist of multiple request units of streamed and non-streamed data. The request units can have arbitrary synchronization patterns. Our scheduler Promote-IT promotes data from tertiary to secondary storage with real-time guarantees. Promote-IT uses an on-line heuristic algorithm to compute feasible schedules and a separate ASAP dispatcher to increase the efficiency of the resource usage. The heuristic algorithm runs in polynomial time. Schedules are optimized to give short response times to incoming requests. Three major problems complicate this scheduling problem. First, the fragments of requested real-time data and their synchronization are unpredictable. Second, the medium switching times in tertiary storage are high, and the number of drives and robots is low compared to the number of removable media. Third, the shared resources in the tertiary storage system create resource contention problems.

show abstract

“…On the market, there are a large number of different tape formats that are distinguished according to the following criteria: 1) tape track orientation, 2) tape width (e.g., 19mm, 8mm, 4mm, 1/2" and 1/4"), and 3) cartridge size [11,6]. The current tape technologies primarily use one of the two tape track orientations: helical-scan, or serpentine [11,6]. With helical-scan recording, the data is recorded in diagonal stripes using a rotating drum (that contains the read/write heads) and a slow moving motor (that runs the tape over the drum).…”

Section: Overviewmentioning

confidence: 99%

Data placement techniques for serpentine tapes

Dashti

Shahabi

Proceedings of the 33rd Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Due to the information explosion we are witnessing, a growing number of applications store, maintain, and retrieve large volumes of data, where the data is required to be available online or near-online. These data repositories are implemented using hierarchical storage structures (HSS). One of the components of HSS is tertiary storage, which provides a cost-effective storage for the vast amount of data manipulated by these applications. However, it is crucial that the 3-4 orders of magnitude difference in access time between the tertiary storage and the secondary storage be bridged to allow online or near-online access to the tertiary resident data. This wide access-gap is mainly due to: the sequential nature of the most popular tertiary technologies (i.e., tapes) and the low number of drives per media in tertiary storage juke boxes. In this paper, we propose a novel data placement technique specifically designed for the serpentine tape technology, namely: Wrap ARound data Placement (WARP). We focus on tape technology because they provide the most cost-effective storage for very large databases, and more specifically on serpentine tapes because they are increasingly the technology of choice for mid-range and high-end systems. WARP may reduce the access time by 1 order of magnitude, depending on the tape device specifications and object sizes. An important feature of WARP is that it optimizes access-time independently of the retrieval order. This is achieved by exploiting the serpentine tape technology characteristics as opposed to the application characteristics. We have implemented this technique on an IBM 3590 tape drive and have observed up to 5 times improvement in access-time as compared to other data placement techniques. Moreover, with WARP, the variance between the best, the worst, and the average access-times is very small, allowing for a priori prediction NIH grant 1P20MH52194-01A1 (USCBP), and NSF grants EEC-9529152 (IMSC ERC) and MRI-9724567. of the access-time behavior by time sensitive applications.

show abstract

Random I/O scheduling in online tertiary storage systems

Cited by 29 publications

References 16 publications

Building MEMS-based storage systems for streaming media

Building MEMS-based storage systems for streaming media

A Flexible Real-Time Hierarchical Multimedia Archive

Data placement techniques for serpentine tapes

Contact Info

Product

Resources

About