Performance of a disk array protype
SIGMETRICS '91 Proceedings of the 1991 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Caching and database scaling in distributed shared-nothing information retrieval systems
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Efficient data layout, scheduling and playout control in MARS
Multimedia Systems - Special issue on the fifth workshop on network and operating system support for digital audio and video 1995 (NOSSDAV)
Query processing and inverted indices in shared: nothing text document information retrieval systems
The VLDB Journal — The International Journal on Very Large Data Bases - Parallelism in database systems
Hi-index | 0.00 |
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 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.