Fully Automated RAID Level Selection Techniques for Disk Arrays
January 13, 2003 By John Vacca
Disk arrays have a myriad of configuration parameters which interact in counter-intuitive ways and can have significant impacts on cost, performance, and reliability. Even after values for these parameters have been chosen, there are an exponential number of ways to map data onto the disk array's logical units (LUs). Making correct choices is of vital importance as the need to respond more rapidly to changing needs increases, as the tolerance level for mistakes continues to decline, and as the increased use of storage area networks, or SANs (define)), continues to represent an ever-growing fraction of total system cost.
This article will explain why the automated design and configuration of SANs is the only viable solution to these issues. To that end, the article will present a brief general discussion and comparison of a range of automated techniques for choosing the Redundant Array of Independent (or Inexpensive) Disks, or RAID (define), levels to use in a disk array.
The simplest approaches presented in this article are modeled on existing, manual rules of thumb which involve "tagging" data with a RAID level before determining the configuration of the array it is assigned to. The best approach presented here simultaneously and automatically determines the RAID levels for the data, the array configuration, and the layout of data on that array. It can operate as an optimization process with the twin goals of minimizing array cost while ensuring that SAN workload performance requirements will be met.
Add www.enterprisestorageforum.com to your favorites Add www.enterprisestorageforum.com to your browser search box IE 7 | Firefox 2.0 | Firefox 1.5.xReceive news via our XML/RSS feed
Images
IE 7
Firefox 2.0
