IBM ATA 133 User manual

IBM ATA 133 RAID Controller User's
Guide
MAN-524
2/6/03

IBM ATA 133 RAID Controller User’s Guide
ii
© Copyright 2003 International Business Machines Corporation
All rights reserved.
This publication contains proprietary information that is protected by copyright. No part of this publication can be reproduced,
transcribed, stored in a retrieval system, translated into any language or computer language, or transmitted in any form whatsoever
without the prior written consent of the publisher, LSI Logic Corporation. LSI Logic Corporation acknowledges the following
trademarks:
Intel is a registered trademark of Intel Corporation.
MS-DOS, Windows, and Microsoft are registered trademarks of Microsoft Corporation. Microsoft Windows is a trademark of
Microsoft Corporation.
MegaRAID is a registered trademark of LSI Logic Corporation.
IBM, AT, VGA, PS/2, and OS/2 are registered trademarks and XT and CGA are trademarks of International Business Machines
Corporation.
Revision History
2/6/03 Initial release.
Part Number
DB15-000283-00

Preface iii
Table of Contents
1Overview ...................................................1
IBM ATA 133 RAID Controller Items ............................ 1
Features ............................................................................ 1
Documentation ................................................................. 2
2Introduction to RAID ...............................3
RAID Benefits.................................................................. 3
In This Chapter................................................................. 3
RAID Overview ............................................................... 4
Disk Striping .................................................................... 4
Disk Mirroring ................................................................. 5
Disk Spanning .................................................................. 6
RAID Terminology .......................................................... 6
Physical Drive .................................................................. 7
Physical Drive States........................................................ 7
Array ................................................................................ 7
Array States...................................................................... 7
Logical Drive ................................................................... 7
Fault Tolerance................................................................. 7
Disk Rebuild..................................................................... 8
Hot Spares ........................................................................ 8
Check Consistency ........................................................... 8
Configuration Strategies................................................... 8
Selecting a RAID Level.................................................... 9
Assigning RAID Levels.................................................... 9
3RAID Levels ...........................................11
RAID 0........................................................................... 11
RAID 1........................................................................... 12
RAID 10......................................................................... 13
4Hardware Installation...........................15
Installation Steps ............................................................ 15
Step 1 Unpack ................................................................ 16
Step 2 Power Down........................................................ 16
Step 3 Set Jumpers ......................................................... 16
Step 4 Install IBM ATA 133 RAID Controller .............. 17
Step 5 Connect IDE Cables............................................ 18
Step 6 Power Up............................................................. 20
Step 7 Configure the System BIOS ................................ 20
Step 8 Install the Operating System Driver .................... 20
Step 9 Run MegaRAID Configuration Console ............. 20
5 Operating System Installation..............21
Installing Windows 2000 Drivers................................... 21
Updating the Windows 2000 Driver............................... 21
Confirming the Windows 2000 Driver Installation ........ 22
Installing DOS................................................................ 22

IBM ATA 133 RAID Controller User’s Guide
iv
Table of Contents, Continued
6 BIOS Configuration Utility....................23
Starting the BIOS Configuration Utility......................... 23
Configuring Arrays and Logical Drives ......................... 23
Designating Drives as Hot Spares .................................. 24
Selecting the Configuration Method............................... 24
Drive Roaming ............................................................... 32
Initializing Logical Drives.............................................. 32
Deleting Logical Drives ................................................. 33
Formatting Physical Drives ............................................ 34
Rebuilding Failed Hard Drives....................................... 35
Using Online Volume Extension.................................... 36
Running a Consistency Check........................................ 36
Exiting the BIOS Configuration Utility.......................... 37
7Troubleshooting....................................39
Drive Connection Tips ................................................... 39
Problems and Suggested Solutions................................. 40
AGetting Help and Technical Assistance.41
Before You Call ............................................................. 41
Using the Documentation ............................................... 41
Getting Help and Information from the World Wide Web.42
Software Service and Support ........................................ 42
Hardware Service and Support....................................... 42
BWarranty Information............................43
Warranty Information..................................................... 43
Warranty Period ............................................................. 43
Problem Determination .................................................. 43
Warranty Service and Support ....................................... 44
International Warranty Service....................................... 45
Purchasing Additional Services...................................... 45
Index ..................................................................47

Preface v
Preface
The IBM PCI Bus Master ATA 133 RAID Disk Array Controller provides a cost-
effective way to achieve higher transfer rates and reliability. IBM’s IDE controller
supports two IDE channels and up to four drives. It supports the following drive modes:
PIO 0-4, DMA 0-2, and Ultra DMA 0-6. The RAID levels supported are RAID 0, 1, and
10. The highest data transfer rate in UDMA mode 4 is 66 MBs, in UDMA mode 5 is 100
MBs, and in UDMA mode 6 is 133 MBs. This manual describes the IBM ATA 133
RAID controller.
Package Contents You should have received the following:
• An IBM ATA 133 RAID controller card
• Two standard length 40-pin connector ATA-100/133 cables with two drive
connectors
• Two extended length 40-pin connector ATA-100/133 cables with one drive
connector
• The IBM ATA 133 RAID Controller Quick Hardware Setup Guide (hard copy)
• A Driver and Documentation CD with utility programs, device drivers for various
operating systems, and the following documentation:
• The IBM ATA 133 RAID Controller User's Guide (on CD)
• A software license agreement
FCC Regulatory Statement
This device complies with Part 15 of the FCC Rules. Operation is subject to the following two conditions:
(1) this device may not cause harmful interference, and (2) this device must accept any interference
received, including interference that may cause undesired operation.
Warning: Changes or modifications to this unit not expressly approved by the party responsible for
compliance could void the user's authority to operate the equipment.
Note: This equipment has been tested and found to comply with the limits for a Class B digital device,
pursuant to Part 15 of the FCC Rules. These limits are designed to provide reasonable protection against
harmful interference in a residential installation. This equipment generates, uses and can radiate radio
frequency energy and, if not installed and used in accordance with the instructions, may cause harmful
interference to radio communications. However, there is no guarantee that interference will not occur in a
specific installation. If this equipment does cause harmful interference to radio or television reception,
which can be determined by turning the equipment off and on, try to correct the interference by one or more
of the following measures:
1) Reorient or relocate the receiving antenna.
2) Increase the separation between the equipment and the receiver.
3) Connect the equipment into an outlet on a circuit different from that to which the receiver is
connected.
4) Consult the dealer or an experienced radio/TV technician for help.
Shielded interface cables must be used with this product to ensure compliance with the Class B FCC
limits.
LSI IDE PCI RAID Disk Array Controller
Model Number: Series 524

IBM ATA 133 RAID Controller User’s Guide
vi

Chapter 1 Overview 1
1 Overview
The IBM ATA 133 RAID controller is a short PCI adapter card that provides two IDE
channels with ATA 133 capability. IBM ATA 133 provides a simple and cost-effective
way to improve the performance and reliability of your storage subsystems. The RAID
controller offers high transfer rates, and fault-tolerant data redundancy during high
performance applications by using low-cost Ultra ATA drives in desktops, workstations,
or low-end servers.
You can connect from one to four drives to this card using ATA 100/133 cables (Ultra
ATA drives need special 80-pin IDE cables) and configure these drives using a simple
setup menu embedded in the controller BIOS. The card supports the following drive
modes: programmable input/output (PIO) 0-4, direct memory address (DMA) 0-2, and
Ultra DMA 0-6.
In addition, the card supports RAID levels 0, 1, and 10. You can use striping (RAID 0) to
improve performance or mirroring (RAID 1) to improve data security. RAID 10 provides
both RAID 1 (disk mirroring) and RAID 0 (data striping). This manual describes RAID
features, RAID levels, hardware installation, operating system installation, and technical
assistance.
IBM ATA 133 RAID Controller Items
The following items are included with the IBM ATA 133 RAID Controller:
• Two standard length 40-pin connector ATA-100/133 cables with two drive
connectors
• Two extended length 40-pin connector ATA-100/133 cables with one drive
connector
• A Driver and Documentation CD with utility programs, device drivers for various
operating systems, and the following documentation:
• IBM ATA 133 RAID Controller User’s Guide
• Software license agreement
Features
IDE Channels The controller supports two IDE channels.
IDE Connectors The controller has two 40-pin internal connectors.
Controller The controller provides a single chip solution for a PCI-to-IDE/ATA controller. It
receives PCI commands and data which it processes and sends to the IDE/ATA bus.
Cont’d

IBM ATA 133 RAID Controller User's Guide
2
Features, Continued
Manageability/Disk Console The manageability/disk console features include:
• configuration information display
• online mirror rebuilding
• online consistency checks
• error logging and notification
• control panel, property sheet, and Microsoft Configuration Console (MCC) plug-in
• desktop management interface (DMI) agent
• simple network management protocol (SNMP) agent
• support for power management features
BIOS Features The BIOS features include:
• RAID support before operating system loads
• automatic detection and configuration
• drive roaming capability
• ability to handle configuration changes
• support for Interrupt 13, and Enhanced Disk Drive Specification
• support for PIO modes 0-4, DMA modes 0-2, and Ultra DMA modes 0-6 (0-6 for
ATA/100 and ATA/133).
• support for RAID levels 0, 1, and 10
• multiple drive rebuilding
• special handling of error log, spare drive, and rebuilding
• support for BIOS boot specification (BBS)
• co-existence with SCSI, CD, and ARMD devices
Driver features The driver features include:
• automatic negotiation of the highest mode of data transfer
• handling of both RAID and non-RAID drives
• special interface for configuration information, configuration changes, and
manageability
• optimized disk access
• support for RAID levels 0, 1, and 10
• error logging in event log and on disks
• support for online mirror rebuilding
• support for consistency check for mirrored disks
• support for Stand-by and Hibernation in Windows 2000
• support for PIO modes 0-4, DMA modes 0-2, and Ultra DMA modes 0-6
Documentation
The technical documentation set for the IBM ATA 133 RAID controller includes the IBM
ATA 133 RAID Controller Quick Hardware Setup Guide (hard copy), and IBM ATA 133
RAID Controller User's Guide (on CD).

Chapter 2 Introduction to RAID 3
2 Introduction to RAID
RAID (Redundant Array of Independent Disks) is an array (group) of multiple
independent hard drives that provide high performance and fault tolerance. A RAID disk
subsystem improves I/O (input/output) performance and reliability. The RAID array
appears to the host computer as a single storage unit or as multiple logical units. I/O is
expedited because several disks can be accessed simultaneously.
RAID systems improve data storage reliability and fault tolerance compared to single-
drive computers. Data loss resulting from a hard drive failure can be prevented by
reconstructing missing data from the remaining hard drives.
RAID Benefits
RAID has gained popularity because it improves I/O performance, and increases storage
subsystem reliability. RAID provides data security through fault tolerance and redundant
data storage.
Improved I/O Although hard drive capabilities have improved drastically, actual performance has
improved only three to four times in the last decade. Computing performance has
improved over 50 times during the same time period. RAID allows you to access several
disks simultaneously.
Increased Reliability The electromechanical components of a disk subsystem operate more slowly, require
more power, and generate more noise and vibration than electronic devices. These factors
reduce the reliability of data stored on disks. RAID systems improve data storage
reliability and fault tolerance compared to single-drive computers. The additional drives
make it possible to prevent data loss from a hard drive failure. You can reconstruct
missing data from the remaining data.
In This Chapter
Table 2-1 lists the topics discussed in this chapter.
Table 2-1. Topics in This Chapter
Major Topic Subtopic
RAID Overview
Disk Striping
Disk Mirroring
Disk Spanning
RAID Terminology
Physical Drive
Physical Drive States
Array
Array States
Fault Tolerance
Logical Drive
Disk Rebuild
Hot Spares
Consistency Check
Configuration Strategies
Selecting a RAID Level
Assigning RAID Levels

IBM ATA 133 RAID Controller User's Guide
4
RAID Overview
RAID is a collection of specifications that describe a system for ensuring the reliability
and stability of data stored on large disk subsystems. A RAID system can be implemented
in a number of different versions (or RAID levels). The standard RAID levels are 0, 1, 3,
and 5. This controller supports RAID levels 0, 1, and 10 (spanned RAID 1 arrays).
Disk Striping
Disk striping writes data across multiple hard drives instead of just one hard drive. Disk
striping involves partitioning each drive storage space into stripes that can vary in size.
These stripes are interleaved in a repeated sequential manner. The combined storage
space is composed of stripes from each drive. IBM IDE supports stripe sizes of 32 KB to
4 MB.
For example, in a four-disk system using only disk striping (as in RAID level 0), segment
1 is written to disk 1, segment 2 is written to disk 2, and so on. Disk striping enhances
performance because multiple drives are accessed simultaneously; but does not provide
data redundancy.
Figure 2-1. Disk Striping
Segment 1
Segment 3
Segment 5
Segment 7
Segment 2
Segment 4
Segment 6
Segment 8
Data Flow
Stripe Width Stripe width is the number of disks involved in an array where striping is implemented.
For example, a four-disk array with disk striping has a stripe width of four.
Stripe Size The stripe size is the length of the interleaved data segments that are written across
multiple drives.

Chapter 2 Introduction to RAID 5
Disk Mirroring
With mirroring (used in RAID 1), data written to one hard drive is simultaneously written
to another hard drive. If one hard drive fails, the contents of the other hard drive can be
used to run the system and reconstruct the failed drive. The primary advantage of disk
mirroring is that it provides 100% data redundancy. Since the contents of the hard drive
are completely written to a second drive, it does not matter if one of the drives fails. Both
drives contain the same data at all times. Either drive can act as the operational drive.
Disk mirroring provides 100% redundancy, but is expensive because each drive in the
system must be duplicated.
Figure 2-2. Disk Mirroring
Segment 1
Segment 2
Segment 3
Segment 4
Seg me nt 1 Du plicate
Seg me nt 2 Du plicate
Seg me nt 3 Du plicate
Seg me nt 4 Du plicate
Data Flow

IBM ATA 133 RAID Controller User's Guide
6
Disk Spanning
Disk spanning allows multiple hard drives to function like one big drive. Spanning
overcomes lack of disk space and simplifies storage management by combining existing
resources or adding relatively inexpensive resources.
Spanning alone does not provide reliability or performance enhancements. Spanned
logical drives must have the same stripe size and must be contiguous. In the following
graphic, a pair of RAID 1 arrays are turned into a RAID 10 array.
Figure 2-3. Disk Spanning
Segment 1
Segment 3
Segment 7
Segment 1 Duplicate
Segment 3 Duplicate
Segment 7 Duplicate
Segment 2
Segment 4
Segment 8
Seg me nt 2 Du plicate
Seg me nt 4 Du plicate
Seg me nt 8 Du plicate
S eg me nt 5 Se gm en t 5 Dup li ca te S egm e nt 6 Seg me nt 6 D u pli cate
Data Flow
RAID 1 RAID 1 RAID 10
RAID 0
RAID Terminology
The following sections explains terms associated with RAID, including:
• physical drive
• physical drive state
• array
• array state
• logical drive
• rebuild
• hot spare
• consistency check
• fault tolerance

Chapter 2 Introduction to RAID 7
Physical Drive
The physical drive is the IDE hard drive that is connected by cable to the IBM IDE card.
The hard drive contains platters that are coated with material that allows them to record
data magnetically. Another important feature is the read/write head, which hovers over the
surface of the platter. You can store and access data much more quickly on a hard drive
than on a floppy disk.
Physical Drive States
Table 2-2 describes the possible conditions of the physical drives.
Table 2-2. Physical Drive States
State Description
Online The drive is functioning normally and is a part of a
configured array.
Spare The drive is powered up and ready for use as a spare in case
an online drive fails.
Failed A fault has occurred in the drive, placing it out of service.
Rebuilding The drive is being rebuilt with data from a failed drive.
Ready The drive is available for configuration and is not yet part of
an array.
Array
A RAID array is a collection of physical drives governed by the RAID management
software. A RAID array appears to the host computer as one or more logical drives.
Array States
Table 2-3. Array States
State Description
Online The drive operating conditions are good. All configured drives are
online.
Degraded The drive operating condition is not optimal. One or more of the
configured drives has failed.
Failed The array has failed.
Offline The array is not available for IBM IDE.
Logical Drive
A logical drive is a partition in a physical array of disks that is made up of contiguous
data segments on the physical disks. A logical drive can consist of an entire physical array
or part of an array.
Fault Tolerance
Fault tolerance is achieved through the use of mirroring (RAID 1). Mirroring provides
100% redundancy. See Disk Mirroring on page 5 for more information.

IBM ATA 133 RAID Controller User's Guide
8
Disk Rebuild
You rebuild a hard drive by recreating the data that had been stored on the drive before
the drive failed. Rebuilding can be done only in arrays with data redundancy, such as
RAID level 1.
IBM IDE automatically and transparently rebuilds failed drives with user-definable
rebuild rates. If a hot spare is available, the rebuild starts automatically when a drive fails.
Rebuilding can start automatically at boot up if the mirror drive is degraded and a spare is
available.
Note:If a hot spare is not available, the failed hard drive mustbe replaced with a new hard
drive so that the data on the failed drive can be rebuilt. The replacement hard drive
capacity must be greater than or equal to the failed drive it replaces.
Hot Spares
A hot spare is an extra, unused hard drive that is part of the RAID subsystem. It is usually
in standby mode, ready for service if a drive fails. Hot spares permit you to replace failed
array drives without system shutdown or user intervention.
IBM IDE implements automatic and transparent rebuilds using hot spare drives,
providing a high degree of fault tolerance and zero downtime. The IBM IDE BIOS
configurator allows you to specify physical drives as hot spares. When a hot spare is
needed, IBM IDE automatically selects the spare and includes it in the configuration.
Note that spare drives are applicable only in arrays with redundancy, such as RAID 1
arrays.
Check Consistency
In RAID, check consistency verifies the correctness of redundant data in an array and
helps to find disk errors. For example, in a system with a mirrored drive, checking
consistency means making sure that both the member-drives of the mirror contains the
same data.
Configuration Strategies
The most important factors in RAID array configuration are drive availability (fault
tolerance), and drive performance.
Maximizing Drive Availability You can maximize the drive availability by increasing fault tolerance. Use
RAID 1 or mirror configuration to attain this objective.
Maximizing Drive Performance You can optimize drive performance by using striping. Select RAID 0 or
striping to configure an array for optimal performance.
Performance and Availability You can achieve both drive performance and availability. Select RAID 10
for this configuration. You will need four drives to configure RAID 10.

Chapter 2 Introduction to RAID 9
Selecting a RAID Level
To ensure the best performance, you should select the optimal RAID level when you
create a system drive. The optimal RAID level for your disk array depends on the
following factors:
• Number of drives in the disk array
• Capacity of the drives in the array
• Need for data redundancy
• Disk performance requirements
Table 2-4 describes the factors you need to consider when selecting a RAID level.
Table 2-4. Factors to Consider When Selecting a RAID Level
Level Description and Use Pros Cons Number
of Drives
Fault
Tolerant
0 Data divided in blocks
and distributed
sequentially (pure
striping). Use for non-
critical data that
requires high
performance.
High data
throughput for
large files.
No fault
tolerance. All
data lost if any
drive fails.
One to
Four
No
1 Data duplicated on
another disk
(mirroring). Use for
read-intensive fault-
tolerant systems.
100 percent
data
redundancy.
Doubles disk
space required.
Reduced
performance
during rebuilds.
Two Yes
10 Data divided in blocks
and distributed
sequentially and each
block is duplicated to
another disk.
100 percent
data
redundancy and
High data
throughput.
Four drives
required.
Four Yes
Assigning RAID Levels
Only one RAID level can be assigned to each array. Table 2-5 lists the drives required per
RAID level.
Table 2-5. Drives Required Per RAID Level
RAID
Level
Minimum Number of
Physical Drives
Maximum Number of Physical
Drives
0 One Four
1 Two Two
10 Four Four

IBM ATA 133 RAID Controller User's Guide
10

Chapter 3 RAID Levels 11
3 RAID Levels
There are six official RAID levels (RAID 0 through RAID 5). IBM IDE supports RAID
levels 0, 1, and 10.
Table 3-1. Physical Drive States
RAID Level Type Turn to
0 Standard page 11
1 Standard page 12
10 Standard page 13
RAID 0
RAID 0 provides disk striping across all configured drives in the RAID subsystem. RAID
0 does not provide any data redundancy, but does offer the best performance of any RAID
level. RAID 0 breaks up data into smaller blocks and then writes a block to each drive in
the array. The size of each block is determined by the stripe size parameter, set during the
creation of the RAID set. RAID 0 offers high bandwidth.
By breaking up a large file into smaller blocks, IBM IDE can use multiple IDE channels
and drives to read or write the file faster. RAID 0 involves no parity calculations to
complicate the write operation. This makes RAID 0 ideal for applications that require
high bandwidth but do not require fault tolerance.
Uses In any environment that does not require fault tolerance.
Strong Points Provides increased data throughput for large files. No capacity loss penalty for parity.
Weak Points Does not provide fault tolerance. All data lost if any drive fails.
Drives One to four
Figure 3-1. RAID 0 Array
Segment 1
Segment 3
Segment 5
Segment 7
Segment 2
Segment 4
Segment 6
Segment 8
Data Flow

IBM ATA 133 RAID Controller User's Guide
12
RAID 1
RAID 1 duplicates all data from one drive to a second drive. RAID 1 provides complete
data redundancy, but at the cost of doubling the required data storage capacity.
Uses Use RAID 1 for small databases or any other environment that requires fault tolerance but small
capacity.
Strong Points RAID 1 provides complete data redundancy. RAID 1 is ideal for any application that requires
fault tolerance and minimal capacity.
Weak Points RAID 1 requires twice as many hard drives. Performance is impaired during drive rebuilds.
Drives Two
Figure 3-2. RAID 1 Array
Segment 1
Segment 2
Segment 3
Segment 4
Seg me nt 1 Du plicate
Seg me nt 2 Du plicate
Seg me nt 3 Du plicate
Seg me nt 4 Du plicate
Data Flow

Chapter 3 RAID Levels 13
RAID 10
RAID 10 provides both RAID 0 (data striping) and RAID 1 (disk mirroring). It requires
two sets of RAID 1 drives (total of four drives). In RAID 10, data is striped across the
two arrays and duplicated from one drive to the second drive in each RAID 1 array.
Uses Use RAID 10 for small databases or any other environment that requires fault tolerance and high
data throughput, especially for large files.
Strong Points RAID 10 provides complete data redundancy. RAID 10 is ideal for any application that requires
fault tolerance and increased data throughput.
Weak Points RAID 10 requires a minimum of four hard drives. Performance is impaired during drive
rebuilds.
Drives Four
Figure 3-3. RAID 10 Array
Segment 1
Segment 3
Segment 7
Segment 1 Duplicate
Segment 3 Duplicate
Segment 7 Duplicate
Segment 2
Segment 4
Segment 8
Seg me nt 2 Du plicate
Seg me nt 4 Du plicate
Seg me nt 8 Du plicate
S eg me nt 5 Se gm en t 5 Dup li ca te S egm e nt 6 Seg me nt 6 D u plicate
Data Flow
RAID 1 RAID 1 RAID 10
RAID 0

IBM ATA 133 RAID Controller User's Guide
14