Optimizing Parallel Input/output Using Adaptive File System Policies

187 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1998.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.U of I OnlyRestricted to the U of I community idenfinitely during batch ingest of legacy ETD