A framework for estimating execution times of IO traces on SSDs

Yoonsuk Kang, Yong Yeon Jo, Jaehyuk Cha, Wan D. Bae, Sang Wook Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the NAND .ash memory technology of solid-state drives (SSDs), the usage of SSDs is expanded to various devices. Due to the cost and time limitations of measuring the actual execution time of each application on SSDs, it is di?cult for users to determine the best SSD for their most commonly used applications. In this paper, we propose a framework of estimating the execution time of an application IO trace (i.e., a query IO trace) on a target SSD without its real execution. Our framework is based on the observation that if two IO traces are similar in their IO behavior, their execution times tend to be similar when executed on the same SSD. The performance of the framework is evaluated through extensive experiments on real applications. The results show that our framework is accurate in estimating the execution time of an IO trace on SSDs.

Original languageEnglish
Title of host publicationCIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages2123-2126
Number of pages4
ISBN (Electronic)9781450349185
DOIs
StatePublished - 2017 Nov 6
Event26th ACM International Conference on Information and Knowledge Management, CIKM 2017 - Singapore, Singapore
Duration: 2017 Nov 62017 Nov 10

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings
VolumePart F131841

Other

Other26th ACM International Conference on Information and Knowledge Management, CIKM 2017
Country/TerritorySingapore
CitySingapore
Period17/11/617/11/10

Keywords

  • Application IO trace
  • Execution time estimation
  • Solid-state drive (SSD)

Fingerprint

Dive into the research topics of 'A framework for estimating execution times of IO traces on SSDs'. Together they form a unique fingerprint.

Cite this