pNFS, POSIX, and MPI-IO: A Tale of Three Semantics
Advanced research collaborations push the bounds of modern technology, but continue to be constrained by rigid computing and storage infrastructures. Many large compute clusters are tightly coupled with a single file system, requiring large data sets to be moved multiple times across a computational grid. MPI-IO is emerging as the standard mechanism for file I/O within HPC applications. While pNFS demonstrates high-performance I/O for bulk data transfers, its performance and scalability with MPI-IO is unproven. To attain success, the consistency semantics and interfaces of pNFS, POSIX, and MPI-IO must all be reconciled and efficiently translated. This paper investigates and discusses the challenges of using pNFS to support the consistency semantics of HPC applications.