Processor-embedded distributed smart disks for I/O-intensive workloads: Architectures, performance models and evaluation

Steve C. Chiu*, Wei Keng Liao, Alok N. Choudhary, Mahmut T. Kandemir

*Corresponding author for this work

Research output: Contribution to journalComment/debatepeer-review

3 Scopus citations

Abstract

Processor-embedded disks, or smart disks, with their network interface controller, can in effect be viewed as processing elements with on-disk memory and secondary storage. The data sizes and access patterns of today's large I/O-intensive workloads require architectures whose processing power scales with increased storage capacity. To address this concern, we propose and evaluate disk-based distributed smart storage architectures. Based on analytically derived performance models, our evaluation with representative workloads show that offloading processing and performing point-to-point data communication improve performance over centralized architectures. Our results also demonstrate that distributed smart disk systems exhibit desirable scalability and can efficiently handle I/O-intensive workloads, such as commercial decision support database (TPC-H) queries, association rules mining, data clustering, and two-dimensional fast Fourier transform, among others.

Original languageEnglish (US)
Pages (from-to)532-551
Number of pages20
JournalJournal of Parallel and Distributed Computing
Volume65
Issue number4
DOIs
StatePublished - Apr 2005

Keywords

  • Association rules mining
  • Data clustering
  • Embedded systems
  • I/O architecture
  • InfiniBand
  • Parallel I/O
  • Smart disk

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Processor-embedded distributed smart disks for I/O-intensive workloads: Architectures, performance models and evaluation'. Together they form a unique fingerprint.

Cite this