The parallel I/O architecture of the High Performance Storage System (HPSS)
- Lawrence Livermore National Lab., CA (United States)
- IBM Federal Systems Co., Houston, TX (United States)
Rapid improvements in computational science, processing capability, main memory sizes, data collection devices, multimedia capabilities and integration of enterprise data are producing very large datasets (10s-100s of gigabytes to terabytes). This rapid growth of data has resulted in a serious imbalance in I/O and storage system performance and functionality. One promising approach to restoring balanced I/O and storage system performance is use of parallel data transfer techniques for client access to storage, device-to-device transfers, and remote file transfers. This paper describes the parallel I/O architecture and mechanisms, Parallel Transport Protocol, parallel FIP, and parallel client Application Programming Interface (API) used by the High Performance Storage System (HPSS). Parallel storage integration issues with a local parallel file system are also discussed.
- Research Organization:
- Lawrence Livermore National Lab., CA (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States); National Aeronautics and Space Administration, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 81112
- Report Number(s):
- UCRL-JC--119772; CONF-950985--1; ON: DE95007126
- Country of Publication:
- United States
- Language:
- English
Similar Records
High Performance Storage System Scalability: Architecture, Implementation, and Experience
The architecture of the High Performance Storage System (HPSS)