Optimizing Parallel Input/output Using Adaptive File System Policies

We have implemented this approach via several extensions to the Portable Parallel File System (PPFS) testbed. Sensor metrics that summarize dynamic access pattern information and file system performance effectively guide adaptive policy selection, affording significant performance improvements over less adaptive optimization strategies. Our results with both parallel access pattern benchmarks and parallel scientific applications demonstrate the efficacy of our approach.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Date dc:date

10000-01-01

Author dc:creator

• Elford, Christopher Lloyd

Contributors dc:contributor

• Daniel A. Reed

• Computer Science

Language dc:language

eng

Identifier

(MiAaPQ)AAI9904444

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/81916