Improving collective I/O performance by pipelining request aggregation and file access

Saba Sehrish, Seung Woo Son, Wei Keng Liao, Alok Choudhary, Karen Schuchardt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

In this paper, we propose a multi-buffer pipelining approach to improve collective I/O performance by overlapping the dominant request aggregation phases with the I/O phase in the two-phase I/O implementation. Our pipelining method first divides the collective buffer into a group of small size buffers for an individual collective I/O call and then pipelines the asynchronous communication to exchange the I/O requests with the I/O requests sent to the file system. Our performance evaluation of a representative I/O benchmark and a production application shows 20% improvement in the I/O time, given theoretical upper bound of 50% when both phases completely overlap.

Original languageEnglish (US)
Title of host publicationProceedings of the 20th European MPI Users' Group Meeting, EuroMPI 2013
PublisherAssociation for Computing Machinery
Pages37-42
Number of pages6
ISBN (Print)9788461651337
DOIs
StatePublished - 2013
Event20th European MPI Users' Group Meeting, EuroMPI 2013 - Madrid, Spain
Duration: Sep 15 2013Sep 18 2013

Publication series

NameACM International Conference Proceeding Series

Other

Other20th European MPI Users' Group Meeting, EuroMPI 2013
Country/TerritorySpain
CityMadrid
Period9/15/139/18/13

Keywords

  • Collective I/O
  • Parallel I/O
  • Two-phase I/O performance

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Improving collective I/O performance by pipelining request aggregation and file access'. Together they form a unique fingerprint.

Cite this