Concentric hyperspaces and disk allocation for fast parallel range searching

Hakan Ferhatosmanoglu, Divyakant Agrawal, Amr El Abbadi

Research output: Chapter in Book/Report/Conference proceedingChapter

23 Citations (Scopus)

Abstract

Data partitioning and declustering have been extensively used in the past to parallelize I/O for range queries. Numerous declustering and disk allocation techniques have been proposed in the literature. However, most of these techniques were primarily designed for two-dimensional data and for balanced partitioning of the data space. As databases increasingly integrate multimedia information in the form of image, video, and audio data, it is necessary to extend the declustering techniques for multidimensional data. In this paper, we first establish that traditional declustering techniques do not scale for high-dimensional data. We then propose several new partitioning schemes based on concentric hyperspaces. We then develop disk allocation methods for each of the proposed schemes. We conclude with an evaluation of range queries based on these schemes and show that partitioning based on concentric hyperspaces has a significant advantage over balanced partitioning approach for parallel I/O.

Original languageEnglish
Title of host publicationProceedings - International Conference on Data Engineering
Place of PublicationLos Alamitos, CA, United States
PublisherInstitute of Electrical and Electronics Engineers Computer Society
Pages608-615
Number of pages8
Publication statusPublished - 1 Jan 1999
Externally publishedYes
EventProceedings of the 1999 15th International Conference on Data Engineering, ICDE-99 - Sydney, NSW, AUS
Duration: 23 Mar 199926 Mar 1999

Other

OtherProceedings of the 1999 15th International Conference on Data Engineering, ICDE-99
CitySydney, NSW, AUS
Period23/3/9926/3/99

ASJC Scopus subject areas

  • Software
  • Engineering(all)
  • Engineering (miscellaneous)

Cite this

Ferhatosmanoglu, H., Agrawal, D., & El Abbadi, A. (1999). Concentric hyperspaces and disk allocation for fast parallel range searching. In Proceedings - International Conference on Data Engineering (pp. 608-615). Los Alamitos, CA, United States: Institute of Electrical and Electronics Engineers Computer Society.

Concentric hyperspaces and disk allocation for fast parallel range searching. / Ferhatosmanoglu, Hakan; Agrawal, Divyakant; El Abbadi, Amr.

Proceedings - International Conference on Data Engineering. Los Alamitos, CA, United States : Institute of Electrical and Electronics Engineers Computer Society, 1999. p. 608-615.

Research output: Chapter in Book/Report/Conference proceedingChapter

Ferhatosmanoglu, H, Agrawal, D & El Abbadi, A 1999, Concentric hyperspaces and disk allocation for fast parallel range searching. in Proceedings - International Conference on Data Engineering. Institute of Electrical and Electronics Engineers Computer Society, Los Alamitos, CA, United States, pp. 608-615, Proceedings of the 1999 15th International Conference on Data Engineering, ICDE-99, Sydney, NSW, AUS, 23/3/99.
Ferhatosmanoglu H, Agrawal D, El Abbadi A. Concentric hyperspaces and disk allocation for fast parallel range searching. In Proceedings - International Conference on Data Engineering. Los Alamitos, CA, United States: Institute of Electrical and Electronics Engineers Computer Society. 1999. p. 608-615
Ferhatosmanoglu, Hakan ; Agrawal, Divyakant ; El Abbadi, Amr. / Concentric hyperspaces and disk allocation for fast parallel range searching. Proceedings - International Conference on Data Engineering. Los Alamitos, CA, United States : Institute of Electrical and Electronics Engineers Computer Society, 1999. pp. 608-615
@inbook{2c810bcb21a940679f4c7fa240b85bdb,
title = "Concentric hyperspaces and disk allocation for fast parallel range searching",
abstract = "Data partitioning and declustering have been extensively used in the past to parallelize I/O for range queries. Numerous declustering and disk allocation techniques have been proposed in the literature. However, most of these techniques were primarily designed for two-dimensional data and for balanced partitioning of the data space. As databases increasingly integrate multimedia information in the form of image, video, and audio data, it is necessary to extend the declustering techniques for multidimensional data. In this paper, we first establish that traditional declustering techniques do not scale for high-dimensional data. We then propose several new partitioning schemes based on concentric hyperspaces. We then develop disk allocation methods for each of the proposed schemes. We conclude with an evaluation of range queries based on these schemes and show that partitioning based on concentric hyperspaces has a significant advantage over balanced partitioning approach for parallel I/O.",
author = "Hakan Ferhatosmanoglu and Divyakant Agrawal and {El Abbadi}, Amr",
year = "1999",
month = "1",
day = "1",
language = "English",
pages = "608--615",
booktitle = "Proceedings - International Conference on Data Engineering",
publisher = "Institute of Electrical and Electronics Engineers Computer Society",

}

TY - CHAP

T1 - Concentric hyperspaces and disk allocation for fast parallel range searching

AU - Ferhatosmanoglu, Hakan

AU - Agrawal, Divyakant

AU - El Abbadi, Amr

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Data partitioning and declustering have been extensively used in the past to parallelize I/O for range queries. Numerous declustering and disk allocation techniques have been proposed in the literature. However, most of these techniques were primarily designed for two-dimensional data and for balanced partitioning of the data space. As databases increasingly integrate multimedia information in the form of image, video, and audio data, it is necessary to extend the declustering techniques for multidimensional data. In this paper, we first establish that traditional declustering techniques do not scale for high-dimensional data. We then propose several new partitioning schemes based on concentric hyperspaces. We then develop disk allocation methods for each of the proposed schemes. We conclude with an evaluation of range queries based on these schemes and show that partitioning based on concentric hyperspaces has a significant advantage over balanced partitioning approach for parallel I/O.

AB - Data partitioning and declustering have been extensively used in the past to parallelize I/O for range queries. Numerous declustering and disk allocation techniques have been proposed in the literature. However, most of these techniques were primarily designed for two-dimensional data and for balanced partitioning of the data space. As databases increasingly integrate multimedia information in the form of image, video, and audio data, it is necessary to extend the declustering techniques for multidimensional data. In this paper, we first establish that traditional declustering techniques do not scale for high-dimensional data. We then propose several new partitioning schemes based on concentric hyperspaces. We then develop disk allocation methods for each of the proposed schemes. We conclude with an evaluation of range queries based on these schemes and show that partitioning based on concentric hyperspaces has a significant advantage over balanced partitioning approach for parallel I/O.

UR - http://www.scopus.com/inward/record.url?scp=0032636022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032636022&partnerID=8YFLogxK

M3 - Chapter

SP - 608

EP - 615

BT - Proceedings - International Conference on Data Engineering

PB - Institute of Electrical and Electronics Engineers Computer Society

CY - Los Alamitos, CA, United States

ER -