Disk System Architectures for High Performance Computing

Randy H. Katz, Garth A. Gibson and David A. Patterson

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-89-497
March 1989

http://www.eecs.berkeley.edu/Pubs/TechRpts/1989/CSD-89-497.pdf

Because of the mismatch between I/O and CPU speeds, high performance computers have long been forced to confront the fundamental I/O bottleneck. As processing power and memory size continue to grow rapidly for micro and mini computers, they too will become I/O limited. A number of hardware and software approaches, such as parallel read-out disks, expanded storage (e.g. solid state disks), and disk striping, have been used to increase I/O bandwidth and thus narrow the CPU-I/O performance gap. In addition, new developments driven by advances in small diameter (i.e., 5.25" and 3.5" disk drives, promise very high I/O bandwidth if large numbers of devices can be organized into arrays of disks. In this paper, we shall review the state of the art in disk devices and I/O controllers, and will describe new approaches for very high performance I/O based on redundant arrays of inexpensive disks (RAIDs).


BibTeX citation:

@techreport{Katz:CSD-89-497,
    Author = {Katz, Randy H. and Gibson, Garth A. and Patterson, David A.},
    Title = {Disk System Architectures for High Performance Computing},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1989},
    Month = {Mar},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1989/6166.html},
    Number = {UCB/CSD-89-497},
    Abstract = {Because of the mismatch between I/O and CPU speeds, high performance computers have long been forced to confront the fundamental I/O bottleneck. As processing power and memory size continue to grow rapidly for micro and mini computers, they too will become I/O limited. A number of hardware and software approaches, such as parallel read-out disks, expanded storage (e.g. solid state disks), and disk striping, have been used to increase I/O bandwidth and thus narrow the CPU-I/O performance gap. In addition, new developments driven by advances in small diameter (i.e., 5.25" and 3.5" disk drives, promise very high I/O bandwidth if large numbers of devices can be organized into arrays of disks. In this paper, we shall review the state of the art in disk devices and I/O controllers, and will describe new approaches for very high performance I/O based on redundant arrays of inexpensive disks (RAIDs).}
}

EndNote citation:

%0 Report
%A Katz, Randy H.
%A Gibson, Garth A.
%A Patterson, David A.
%T Disk System Architectures for High Performance Computing
%I EECS Department, University of California, Berkeley
%D 1989
%@ UCB/CSD-89-497
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1989/6166.html
%F Katz:CSD-89-497