Performance of the IBM general parallel file system
- 7 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We measure the performance and scalability of IBM's General Parallel File System (GPFS) under a variety of conditions. The measurements are based on benchmark programs that allow us to vary block sizes, access patterns, etc., and to measure aggregate throughput rates. We use the data to give performance recommendations for application development and as a guide to the improvement of parallel file systemsKeywords
This publication has 11 references indexed in Scilit:
- PIOUS: a scalable parallel I/O system for distributed computing environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Scotch parallel storage systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- TFLOPS PFS: Architecture and Design of a Highly Efficient Parallel File SystemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- RAMA: An easy-to-use, high-performance parallel file systemParallel Computing, 1997
- The Galley parallel file systemParallel Computing, 1997
- Multidimensional array I/O in Panda 1.0The Journal of Supercomputing, 1996
- I/O requirements of scientific applications: an evolutionary viewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- PPFSPublished by Association for Computing Machinery (ACM) ,1995
- The SP2 High-Performance SwitchIBM Systems Journal, 1995
- POWER2: Next generation of the RISC System/6000 familyIBM Journal of Research and Development, 1994