SCHEDULE: NOV 10-16, 2007

Using MPI File Caching to Improve Parallel Write Performance for Large-scale Scientific Applications

Session: System Performance

Event Type: Paper

Time: 10:30am - 11:00am

Session Chair: Bronis R. de Supinski

Author(s): Wei-keng Liao, Avery Ching, Kenin Coloma, Arifa Nisar, Alok Choudhary, Jacqueline Chen, Ramanan Sankaran, Scott Klasky

Location: A3 / A4

Abstract:
Typical large-scale scientific applications periodically write checkpoint files to save the computational state throughout execution. Existing parallel file systems improve such write-only I/O patterns through the use of client-side file caching and write-behind strategies. In distributed environments where files are rarely accessed by more than one client concurrently, file caching has achieved significant success; however, in parallel applications where multiple clients manipulate a shared file, cache coherence control can serialize I/O. We have designed a thread based caching layer for the MPI I/O library, which adds a portable caching system closer to user applications so more information about the application's I/O patterns is available for better coherence control. We demonstrate the impact of our caching solution on parallel write performance with a comprehensive evaluation that includes a set of widely used I/O benchmarks and production application I/O kernels.

This paper can be found in the ACM Digital Libaries
Click here for ACM

Chair/Author Details:

Bronis R. de Supinski (Chair)
LLNL/CASC

Wei-keng Liao
Northwestern University

Avery Ching
Northwestern University

Kenin Coloma
Northwestern University

Arifa Nisar
Northwestern University

Alok Choudhary
Northwestern University

Jacqueline Chen
Sandia National Laboratories

Ramanan Sankaran
Oak Ridge National Laboratory

Scott Klasky
Oak Ridge National Laboratory

Home | About | Contact Us | Registration