BibTeX for papers by David Kotz; for complete/updated list see https://www.cs.dartmouth.edu/~kotz/research/papers.html @InProceedings{ap:enwrich, author = {Apratim Purakayastha and Carla Schlatter Ellis and David Kotz}, title = {{ENWRICH: A Compute-Processor Write Caching Scheme for Parallel File Systems}}, booktitle = {{Proceedings of the Workshop on Input/Output in Parallel and Distributed Systems (IOPADS)}}, year = 1996, month = {May}, pages = {55--68}, publisher = {ACM}, copyright = {ACM}, address = {Philadelphia}, DOI = {10.1145/236017.236034}, URL = {https://www.cs.dartmouth.edu/~kotz/research/ap-enwrich/index.html}, abstract = {Many parallel scientific applications need high-performance I/O. Unfortunately, end-to-end parallel-I/O performance has not been able to keep up with substantial improvements in parallel-I/O hardware because of poor parallel file-system software. Many radical changes, both at the interface level and the implementation level, have recently been proposed. One such proposed interface is \emph{collective I/O}, which allows parallel jobs to request transfer of large contiguous objects in a single request, thereby preserving useful semantic information that would otherwise be lost if the transfer were expressed as per-processor non-contiguous requests. Kotz has proposed \emph{disk-directed I/O} as an efficient implementation technique for collective-I/O operations, where the compute processors make a single collective data-transfer request, and the I/O processors thereafter take full control of the actual data transfer, exploiting their detailed knowledge of the disk-layout to attain substantially improved performance. \par Recent parallel file-system usage studies show that writes to write-only files are a dominant part of the workload. Therefore, optimizing writes could have a significant impact on overall performance. In this paper, we propose ENWRICH, a compute-processor write-caching scheme for write-only files in parallel file systems. ENWRICH combines low-overhead write caching at the compute processors with high performance disk-directed I/O at the I/O processors to achieve both low latency and high bandwidth. This combination facilitates the use of the powerful disk-directed I/O technique independent of any particular choice of interface. By collecting writes over many files and applications, ENWRICH lets the I/O processors optimize disk I/O over a large pool of requests. We evaluate our design via simulated implementation and show that ENWRICH achieves high performance for various configurations and workloads.}, }