Abstract
In 1989, the RAID (Redundant Arrays of Inexpensive Disks) group at U. C. Berkeley built a prototype disk array called RAID-I. The bandwidth achieved by RAID-I was severely limited by the memory system bandwidth of the disk array’s host workstation. As a result, most of the bandwidth available from the disks could not be delivered to clients of the RAID-I file server. We designed our second prototype, RAID-II, to deliver more of the disk array bandwidth to file server clients. A custom-built crossbar memory system called the XBUS board connects the disks directly to the high-speed network, allowing data for large requests to bypass the server workstation. A single workstation can control several XBUS boards for increased bandwidth. RAID-II runs the Log-Structured File System (LFS) software to optimize performance for bandwidth-intensive applications. The RAID-II hardware with a single XBUS controller board delivers 20 megabytes/second of raw I/O between 24 disks and the high-speed network for large, random read operations and up to 31 megabytes/second for sequential read operations. This is an order of magnitude better than our first prototype, but lower than our performance goal of 40 megabytes/second because of lower-than-expected performance of the commercial disk controller boards and our disk system interfaces. A preliminary implementation of LFS software on RAID-II configured with 24 disks delivers 13.4 megabytes/second on large read requests.
Original language | English (US) |
---|---|
Title of host publication | High Performance Mass Storage and Parallel I/O |
Subtitle of host publication | Technologies and Applications |
Publisher | Wiley-IEEE Press |
Pages | 408-419 |
Number of pages | 12 |
ISBN (Electronic) | 9780470544839 |
ISBN (Print) | 0471208094, 9780471208099 |
DOIs | |
State | Published - Jan 1 2001 |
Keywords
- Arrays
- Bandwidth
- File servers
- Hardware
- Prototypes
- Servers
- Workstations
ASJC Scopus subject areas
- General Computer Science