Article

Distributed and Parallel Databases

, Volume 2, Issue 3, pp 243-260

Performance and design evaluation of the RAID-II storage server

  • Peter M. ChenAffiliated withDepartment of Electrical Engineering and Computer Science, University of Michigan
  • , Edward K. LeeAffiliated withDigital Equipment Corporation Systems Research Center
  • , Ann L. DrapeauAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , Ken LutzAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , Ethan L. MillerAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , Srinivasan SeshanAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , Ken ShirriffAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , David A. PattersonAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley
  • , Randy H. KatzAffiliated withComputer Science Division, Department of Electrical Engineering and Computer Science, University of California at Berkeley

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

RAID-II is a high-bandwidth, network-attached storage server designed and implemented at the University of California at Berkeley. In this paper, we measure the performance of RAID-II and evaluate various architectural decisions made during the design process. We first measure the end-to-end performance of the system to be approximately 20 MB/s for both disk array reads and writes. We then perform a bottleneck analysis by examining the performance of each individual subsystem and conclude that the disk subsystem limits performance. By adding a custom interconnect board with a high-speed memory and bus system and parity engine, we are able to achieve a performance speedup of 8 to 15 over a comparative system using only off-the-shelf hardware.

Keywords

RAID HIPPI disk array crossbar mass storage system I/O input/output