T. Toyama, Y. Yamada, and K. Konishi (Japan)
desktop grid computing, PC grid, resource management, data-intensive applications, volume visualization, parallel visualization
Grid computing using idle desktop PCs is popular as a low-cost platform for high-throughput applications. How ever, they require high-cost data transfer systems from file servers to calculating nodes when very large amounts of data are handled. This high cost derives from inexpensive I/O of worker PCs and small inexpensive file systems of desktop grid computing. This work describes a desktop grid computing sys tem and proposes a resource management system for vol ume visualization. The resource management system pro posed in this work overcomes problems with high-cost data transfer and helps us to use desktop grid computing for data-intensive applications. The resource management system provides efficient scheduling while considering the data file location and consists of three technical parts: re source management, multiple data replication, and worker selection. The proposed system uses these techniques to make an intelligent reuse of data which has been previ ously copied. This paper evaluates the proposed system compared with a traditional system that does not consider data file location. The proposed resource management sys tem provides efficient scheduling and appears to achieve good performance for data-intensive applications.
Important Links:
Go Back
