Abstract | ||
---|---|---|
This paper proposes a design and implementation of an MPI-IO implementation of the Gfarm file system, called MPI-IO/Gfarm. The Gfarm file system is a global file system that federates the local storage of compute nodes among several clusters. It has a scale-out architecture designed to support distributed data-intensive computing. However Gfarm file system does not achieve scalable performance in the case of parallel writes to a single file, a typical file operation in MPI-IO. This paper proposes an optimization technique to improve the parallel write performance to a single file. In the evaluation, MPI-IO/Gfarm achieves scalable parallel I/O performance. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/CCGrid.2011.82 | Cluster, Cloud and Grid Computing |
Keywords | Field | DocType |
o performance,local storage,data-intensive computing,single file,scalable performance,typical file operation,global file system,optimized implementation,gfarm file system,parallel writes,mpi-io implementation,optimization,computer architecture,benchmark testing,distributed databases,message passing,parallel processing | File system,Global file system,Self-certifying File System,Computer science,Parallel computing,Distributed database,Parallel I/O,Operating system,Message passing,Benchmark (computing),Scalability | Conference |
ISBN | Citations | PageRank |
978-0-7695-4395-6 | 0 | 0.34 |
References | Authors | |
5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hiroki Kimura | 1 | 6 | 1.54 |
Osamu Tatebe | 2 | 309 | 42.94 |