Performance characterization and optimization of parallel I/O on the cray XT

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

80 Scopus citations

Abstract

This paper presents an extensive characterization, tuning, and optimization of parallel I/O on the Cray XT supercomputer, named Jaguar, at Oak Ridge National Laboratory. We have characterized the performance and scalability for different levels of storage hierarchy including a single Lustre object storage target, a single S2A storage couplet, and the entire system. Our analysis covers both data- and metadata-intensive I/O patterns. In particular, for small, non-contiguous data-intensive I/O on Jaguar, we have evaluated several parallel I/O techniques, such as data sieving and twophase collective I/O, and shed light on their effectiveness. Based on our characterization, we have demonstrated that it is possible, and often prudent, to improve the I/O performance of scientific benchmarks and applications by tuning and optimizing I/O. For example, we demonstrate that the I/O performance of the S3D combustion application can be improved at large scale by tuning the I/O system to avoid a bandwidth degradation of 49% with 8192 processes when compared to 4096 processes. We have also shown that the performance of Flash I/O can be improved by 34% by tuning the collective I/O parameters carefully.

Original languageEnglish
Title of host publicationIPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM
DOIs
StatePublished - 2008
EventIPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium - Miami, FL, United States
Duration: Apr 14 2008Apr 18 2008

Publication series

NameIPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM

Conference

ConferenceIPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium
Country/TerritoryUnited States
CityMiami, FL
Period04/14/0804/18/08

Fingerprint

Dive into the research topics of 'Performance characterization and optimization of parallel I/O on the cray XT'. Together they form a unique fingerprint.

Cite this