RT Journal Article
JF Cluster Computing and the Grid, IEEE International Symposium on
YR 2006
VO 00
SP 35
TI Scalable Approaches for Supporting MPI-IO Atomicity
A1 Avery Ching,
A1 Peter M. Aarestad,
A1 Alok N. Choudhary,
A1 George K. Thiruvathukal,
K1 null
AB Scalable atomic and parallel access to noncontiguous regions of a file is essential to exploit high performance I/O as required by large-scale applications. Parallel I/O frameworks such as MPI I/O conceptually allow I/O to be defined on regions of a file using derived datatypes. Access to regions of a file can be automatically computed on a perprocessor basis using the datatype, resulting in a list of (offset, length) pairs. We describe three approaches for implementing lock serving (whole file, region locking, and byterange locking) and compare the various approaches using three noncontiguous I/O benchmarks. We present the details of the lock server architecture and describe the implementation of a fully-functional prototype that makes use of a lightweight message passing library and red/black trees.
PB IEEE Computer Society, [URL:http://www.computer.org]
LA English
DO 10.1109/CCGRID.2006.88
LK http://doi.ieeecomputersociety.org/10.1109/CCGRID.2006.88