Click Here!
home account info subscribe login search My ITKnowledge FAQ/help site map contact us


 
Brief Full
 Advanced
      Search
 Search Tips
To access the contents, click the chapter and section titles.

Oracle Performance Tuning and Optimization
(Publisher: Macmillan Computer Publishing)
Author(s): Edward Whalen
ISBN: 067230886x
Publication Date: 04/01/96

Bookmark It

Search this book:
 
Previous Table of Contents Next


Chapter 15
Disk Arrays

A disk array is collection of disk drives that are configured and act as one larger disk drive. Both hardware and software disk arrays are available today. Hardware disk arrays consist of a disk array controller and a set of disk drives (typically SCSI). Software disk arrays are made up of a software layer that lies between the file system and the device driver layers.

Disk arrays usually support disk striping, disk mirroring, disk parity, and so on. Hardware disk arrays also support other features such as hot swappable disks. Depending on the manufacturer and model, the disk array controller can support several different types of RAID fault tolerance.

Disk arrays offer many benefits to the system administrator and the end users:

  Ease of management. A disk array can offer tens of gigabytes of disk space that appear to the administrator as one large disk. This arrangement simplifies some of the management tasks involved with managing large numbers of disks.
  I/O balancing. Because a disk array is made up of many individual disks with striped data, random I/Os are automatically distributed among the disks.
  Fault tolerance. Disk arrays provide a wide range of RAID options with a wide variety of performance and economic choices.

This chapter examines the operation of disk arrays. You will see how a disk array works and what features are available. You will look at the different fault tolerant modes and examine the different RAID levels available in today’s disk array controllers.

The end of the chapter looks at how you can take advantage of disk arrays from a performance standpoint. How do you best configure your database to use disk arrays? How are disk arrays different from standard disk subsystems?

As this chapter looks more into the workings of the disk array, you will understand why disk arrays are so popular today. This chapter helps you determine whether your system can benefit from a disk array or whether you can improve your system by reconfiguring an existing disk array.

How Does a Disk Array Work?

A disk array is a set of disk drives that make up a larger logical disk, sometimes called a logical volume. The logical volume is made up of identical-sized pieces of the individual drives, called stripes. The data is said to be striped across the logical volume because the logical drive has pieces of all the individual drives striped within it (see Figure 15.1). If you look at the logical volume, the physical drives seem to make stripes.


Figure 15.1  Disk stripes on a logical volume.

The stripes are all the same size and in sequence (that is, in the order of the disk and the position on each individual disk). The size of the stripe varies based on the manufacturer and model of the disk array controller. The stripe size also varies in a software array. The size of the stripe is called the striping factor and is given in number of blocks. A typical striping factor is 32. Given a 512 bytes-per-block size, a striping factor of 32 makes the disk stripe 16K in size.

As far as the user and the RDBMS is concerned, there is only one large disk drive. It is up to the OS and the hardware to manage the individual disks within the array.

Software Array

In a software array, all the disk-array processing is done by the system CPU. Each time a disk request is issued, the OS must perform all the processes needed to maintain the array. If fault tolerance is used, significant overhead can be involved.

The extra processing involved in maintaining a software disk array can be a performance problem if you are running your machine near the capacity of the CPUs. If you have a significant amount of idle CPU cycles, the overhead associated with a software array will not be noticeable.

Hardware Array

In a hardware disk array, all the processing associated with maintaining the array is done on the disk controller itself. The disk controller has its own CPU, which is responsible for performing the necessary processing. Even when you employ fault tolerance, the CPUs on the system are not affected; all the fault tolerance processing is done on the controller itself.

The controller also includes a small amount of memory to use in this processing. Most hardware disk array controllers have enough CPU power to keep up with any I/O rate requested of it. The only bottlenecks occur when the I/O rates of the physical disk drives that make up the array are exceeded and jobs start queuing up.

Sophisticated disk array controllers also offer advanced features such as hot swappable disk drives, automatic rebuild options, and advanced fault detection and correction. Fault correction is available only if you run in a fault-tolerant mode.

Hot-Swappable Disk Drives

Many vendors support hot-swappable disk drives with their disk array products. This type of drive allows failed disk drives to be removed and replaced without having to shut down or power off the system. Most disk array controllers can automatically rebuild a disk drive that has replaced a failed drive. This feature works in conjunction with advanced fault detection features that continually test and report failed or “soon to fail” disk drives.

A disk array such as the Compaq SMART disk array can detect faults and signal a remote monitoring station. The faulty disk drive is indicated by a red light on the drive itself. If this array is running in a fault-tolerant mode, an operator can simply remove the faulty disk drive and replace it with a spare. The spare drive is automatically rebuilt using information stored on the remaining disk drives without operator intervention. The rebuild is done while the drives are still online and fulfilling user requests. Only a small degradation in performance is experienced while the disk drive is being rebuilt. You can even configure an optional online spare drive that instantly and automatically replaces a faulty drive. The online spare drive replaces a faulty drive the moment the fault is detected.


Previous Table of Contents Next


Products |  Contact Us |  About Us |  Privacy  |  Ad Info  |  Home

Use of this site is subject to certain Terms & Conditions, Copyright © 1996-2000 EarthWeb Inc.
All rights reserved. Reproduction whole or in part in any form or medium without express written permission of EarthWeb is prohibited.