Proceedings of Hot Interconnects 1999, August 18 - 20, 1999, Stanford University, Stanford, California, U.S.A.
David F. Nagle, Gregory R. Ganger, Jeff Butler, Garth Goodson, and Chris Sabol
Department of Electrical and Computer Engineering
Carnegie Mellon University
Pittsburgh, PA 15213
http://www.pdl.cmu.edu/NASD
Storage systems represent a vital market with storage densities growing at 60%/year, resulting in 35%-50% per year decreases in the cost per byte. Unfortunately, current distributed file system architectures severely limit scalable storage. In current distributed file systems, all storage bytes are copied through file server machines between peripheral buses (typically SCSI) and client LANs. In essence, these file server machines act as application-level inter-network routers, converting name-spaces (disk block versus file range) and protocol layers (SCSI versus RPC/UDP/IP). Storage devices, however, are already effective network data transfer engines. However, traditional client-server protocol stacks and operating system software layers often copy data several times in delivering it to applications, significantly reducing network-attached storage performance. This papers examines networking requirements for storage and the integration of user-level networking with network-attached storage (NAS). To provide context for the networking demands of NAS, we begin by describing alternative network-attached storage architectures and CMU's network-attached storage system. Next, we survey storage's networking requirements and describe how one user-level networking architecture, the VI Architecture (VIA), can be effectively mapped onto our network-attached storage prototype.
FULL PAPER: pdf / postscript