FORESEE: An Effective and Efficient Framework for Estimating the Execution Times of IO Traces on the SSD

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

Research output: Contribution to journalArticlepeer-review

Abstract

We propose a framework named FORESEE that estimates accurately the execution time of a query IO trace on an SSD without its actual execution. It estimates the execution time of a query IO trace by using the execution times of the IO traces in the DB similar to the query IO trace. This estimation is based on the observation that if two IO traces are similar each other in their IO behavior, their execution times tend to be similar when they are executed on the same SSD. To this end, we propose (1) goodness function that efficiently evaluates the quality of feature sets that are used to measure the similarity of IO traces, (2) DB structure and searching method for efficiently searching for similar IO traces to a query IO trace, and (3) aggregation method that aggregates the execution times of similar IO traces to a query IO trace for accurately estimating the execution time of the query IO trace. The results of extensive experiments with real-world application IO traces show that FORESEE estimates the execution time accurately.

Original languageEnglish
JournalIEEE Transactions on Computers
DOIs
Publication statusAccepted/In press - 2020

Keywords

  • Channel estimation
  • Correlation
  • Databases
  • Estimation
  • Execution time estimation
  • IO traces
  • Performance evaluation
  • Time measurement
  • Windows
  • solid-state drives

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'FORESEE: An Effective and Efficient Framework for Estimating the Execution Times of IO Traces on the SSD'. Together they form a unique fingerprint.

Cite this