Block2Vec: A Deep Learning Strategy on Mining Block Correlations in Storage Systems

Dong Dai, Forrest Sheng Bao, Jiang Zhou, Yong Chen

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

2 Scopus citations

Abstract

Block correlations represent the semantic patterns in storage systems. These correlations can be exploited for data caching, pre-fetching, layout optimization, I/O scheduling, etc. In this paper, we introduce Block2Vec, a deep learning based strategy to mine the block correlations in storage systems. The core idea of Block2Vec is twofold. First, it proposes a new way to abstract blocks, which are considered as multi-dimensional vectors instead of traditional block Ids. In this way, we are able to capture similarity between blocks through the distances of their vectors. Second, based on vector representation of blocks, it further trains a deep neural network to learn the best vector assignment for each block. We leverage the recently advanced word embedding technique in natural language processing to efficiently train the neural network. To demonstrate the effectiveness of Block2Vec, we design a demonstrative block prediction algorithm based on mined correlations. Empirical comparison based on the simulation of real system traces shows that Block2Vec is capable of mining block-level correlations efficiently and accurately. This research and trial show that the deep learning strategy is a promising direction in optimizing storage system performance.

Original languageEnglish
Title of host publicationProceedings - 45th International Conference on Parallel Processing Workshops, ICPPW 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages230-239
Number of pages10
ISBN (Electronic)9781509028252
DOIs
StatePublished - Sep 23 2016
Event45th International Conference on Parallel Processing Workshops, ICPPW 2016 - Philadelphia, United States
Duration: Aug 16 2016Aug 19 2016

Publication series

NameProceedings of the International Conference on Parallel Processing Workshops
Volume2016-September
ISSN (Print)1530-2016

Conference

Conference45th International Conference on Parallel Processing Workshops, ICPPW 2016
CountryUnited States
CityPhiladelphia
Period08/16/1608/19/16

Keywords

  • IO
  • block correlation
  • deep learning
  • embedding

Fingerprint Dive into the research topics of 'Block2Vec: A Deep Learning Strategy on Mining Block Correlations in Storage Systems'. Together they form a unique fingerprint.

Cite this