This paper examines the performance of RAID the First, a prototype disk array built by the RAID group at U.C. Berkeley. A hierarchy of bottlenecks was discovered in the system that limit overall performance. The most serious is the memory system contention on the Sun4/280 host CPU, which limits array bandwidth to 2.3 MBytes/sec. The array performs more successfully on small random operations, achieving nearly 300 I/Os per second before the Sun4/280 becomes CPU-limited. Other bottlenecks in the system are the VME backplane, bandwidth on the disk controller, and overheads associated with the SCSI protocol. All are examined in detail.
The main conclusion of this report is that to achieve the potential bandwidth of arrays, more poserful CPUs alone will not suffice. Just as important are adequate host memory bandwidth and support for high bandwidth on disk controllers. Current disk controllers are more often designed to achieve large numbers of small random operations, rather than high bandwidth. Operating systems also need to change to support high bandwidth from disk arrays. In particular, they should transfer data in larger blocks, and should support asynchronous I/O to improve sequential write performance.