TY - JOUR
T1 - Scalable Implementations of MPI Atomicity for Concurrent Overlapping I/O
AU - Liao, Wei-keng
AU - Choudhary, Alok
AU - Coloma, Kenin
AU - Thiruvathukal, George K.
AU - Ward, Lee
AU - Russell, Eric
AU - Pundit, Neil
N1 - W. Liao et al., “Scalable Implementations of MPI Atomicity for Concurrent Overlapping I/O,” in International Conference on Parallel Processing, 2003.
PY - 2003/1/1
Y1 - 2003/1/1
N2 - For concurrent I/O operations, atomicity defines the results in the overlapping file regions simultaneously read/written by requesting processes. Atomicity has been well studied at the file system level, such as POSIX standard. In this paper, we investigate the problems arising from the implementation of MPI atomicity for concurrent overlapping write access and provide a few programming solutions. Since the MPI definition of atomicity differs from the POSIX one, an implementation that simply relies on the POSIX file systems does not guarantee correct MPI semantics. To have a correct implementation of atomic I/O in MPI, we examine the efficiency of three approaches: 1) file locking, 2) graph-coloring, and 3) process-rank ordering. Performance complexity for these methods are analyzed and their experimental results are presented for file systems including NFS, SGI’s XFS, and IBM’s GPFS.
AB - For concurrent I/O operations, atomicity defines the results in the overlapping file regions simultaneously read/written by requesting processes. Atomicity has been well studied at the file system level, such as POSIX standard. In this paper, we investigate the problems arising from the implementation of MPI atomicity for concurrent overlapping write access and provide a few programming solutions. Since the MPI definition of atomicity differs from the POSIX one, an implementation that simply relies on the POSIX file systems does not guarantee correct MPI semantics. To have a correct implementation of atomic I/O in MPI, we examine the efficiency of three approaches: 1) file locking, 2) graph-coloring, and 3) process-rank ordering. Performance complexity for these methods are analyzed and their experimental results are presented for file systems including NFS, SGI’s XFS, and IBM’s GPFS.
KW - I/O
KW - computer science
KW - data
UR - https://ecommons.luc.edu/cs_facpubs/12
U2 - 10.1109/ICPP.2003.1240586
DO - 10.1109/ICPP.2003.1240586
M3 - Article
JO - Computer Science: Faculty Publications and Other Works
JF - Computer Science: Faculty Publications and Other Works
ER -