RAID Terminology


See disk group.


The process of using a high speed memory buffer to speed up a computer system’s overall read/write performance. The cache can be accessed at a higher speed than a disk subsystem. To improve read performance, the cache usually contains the most recently accessed data, as well as data from adjacent disk sectors. To improve write performance, the cache may temporarily store data in accordance with its write-back policies.

consistency check

An operation that verifies that all stripes in a virtual disk with a redundant RAID level are consistent and that automatically fixes any errors. For RAID 1 disk groups, this operation verifies correct mirrored data for each stripe.


A chip that controls the transfer of data between the microprocessor and memory or between the microprocessor and a peripheral device such as a physical disk. RAID controllers perform RAID functions such as striping and mirroring to provide data protection. MSM runs on the SAS Integrated RAID controller.

current write policy

A virtual disk property that indicates whether the virtual disk currently supports write back or write through caching mode.

default write policy

A virtual disk property indicating whether the default write policy is Write through or Write back.

See current write policy for a definition of these policies.

device driver

Software that allows the operating system to control a device such as a printer. Many devices do not work properly unless the correct driver is installed in the computer.

device ID

A controller or physical disk property indicating the manufacturer-assigned device ID.

device port count

A controller property indicating the number of ports on the controller.

disk cache policy

A virtual disk property indicating whether the virtual disk cache is enabled, disabled, or unchanged from its previous setting.

disk group

A logical grouping of disks attached to a RAID controller on which one or more virtual disks can be created, such that all virtual disks in the disk group use all of the physical disks in the disk group.

disk subsystem

A collection of disks and the hardware that controls them and connects them to one or more controllers. The hardware can include an intelligent controller, or the disks can attach directly to a system I/O bus controller.

fast initialization

A mode of initialization that quickly writes zeros to the first and last sectors of the virtual disk. This enables you to start writing data to the virtual disk immediately while the initialization is running in the background.

fault tolerance

The capability of the disk subsystem to undergo a single drive failure per disk group without compromising data integrity and processing capability. The SAS Integrated RAID controller provides fault tolerance through redundant in RAID 1 disk groups.

foreign configuration

A RAID configuration that already exists on a replacement set of physical disks that you install in a computer system. MSM enables you to import the existing configuration to the RAID controller, or you can clear the configuration so you can create a new one.


The process of writing a specific value to all data fields on a physical disk, to map out unreadable or bad sectors. Because most physical disks are formatted when manufactured, formatting is usually done only if a physical disk generates many media errors.


global hot spare

One or two disk drives per controller can be configured as global hot-spare disks, to protect data on the IM/IME volumes configured on the controller. If the firmware fails one of the mirrored disks, it automatically replaces the failed disk with a hot-spare disk and then re-synchronizes the mirrored data. The firmware is automatically notified when the failed disk has been replaced, and it then designates the failed disk as the new hot-spare.


In MSM (MegaRAID Storage Manager)-IR, a hole is a block of empty space in a disk group that can be used to define a virtual disk.

host interface

A controller property indicating the type of interface used by the computer host system: for example, PCIX.

host port count

A controller property indicating the number of host data ports currently in use.

host system

Any computer system on which the controller is installed. Mainframes, workstations, and stand-alone desktop systems can all be considered host systems.

hot spare

See global hot-spare.


The process of writing zeros to the data fields of a virtual disk and, in fault-tolerant RAID levels, generating the corresponding parity to put the virtual disk in a Ready state. Initialization erases all previous data on the physical disks. Disk groups will work without initializing, but they can fail a consistency check because the parity fields have not been generated.

IO policy

A virtual disk property indicating whether Cached IO or Direct IO is being used. In Cached IO mode, all reads are buffered in cache memory. In Direct IO mode, reads are not buffered in cache memory. Data is transferred to cache and the host concurrently. If the same data block is read again, it comes from cache memory. (The IO Policy applies to reads on a specific logical drive. It does not affect the Read-ahead cache.)


The process of moving virtual disks from one controller to another by disconnecting the physical disks from one controller and attaching them to another one. The firmware on the new controller will detect and retain the virtual disk information on the physical disks.


The process of providing complete data redundancy with two physical disks by maintaining an exact copy of one disk’s data on the second physical disk. If one physical disk fails, the contents of the other physical disk can be used to maintain the integrity of the system and to rebuild the failed physical disk.


A virtual disk property indicating the user-assigned name of the virtual disk.


A physical disk is offline when it is part of a virtual disk but its data is not accessible to the virtual disk.

physical disk

A nonvolatile, randomly addressable device for storing data. Physical disks are re-writable and are commonly referred to as disk drives.

physical drive state

A physical disk drive property indicating the status of the drive. A physical disk drive can be in one of the following states:

Unconfigured Good: A disk accessible to the RAID controller but not configured as a part of a virtual disk or as a hotspare.

Online: A physical disk can be accessed by the RAID controller and is part of the virtual disk.

Rebuild: A physical disk to which data is being written to restore full redundancy for a virtual disk.

Failed: A physical disk that was originally configured as Online but on which the firmware detects an unrecoverable error.

Unconfigured Bad: A physical disk on which the firmware detects an unrecoverable error; the physical disk was Unconfigured Good or the physical disk could not be initialized.

Missing: A physical disk that was Online, but which has been removed from its location.

Offline: A physical disk that is part of a virtual disk but which has invalid data.

None: A physical disk with the unsupported flag set. An Unconfigured Good or Offline physical disk that has completed the prepare for removal operation.

physical drive type

A physical disk drive property indicating the characteristics of the drive.

product info

A physical disk property indicating the vendor-assigned model number of the drive.

product name

A controller property indicating the manufacturing name of the controller.


A group of multiple, independent disk drives that provide high performance by increasing the number of disks used for saving and accessing data. A RAID disk group improves I/O performance and data availability. The group of disk drives appears to the host system as a single storage unit or as multiple logical disks. Data throughput improves because several physical disks can be accessed simultaneously. RAID configurations also improve data storage availability and fault tolerance.


RAID 0 uses data striping on two or more disk drives to provide high data throughput, especially for large files in an environment that requires no data redundancy.


RAID 1 uses data mirroring on a pair of disk drives so that data written to one physical disk is simultaneously written to the other physical disk. RAID 1 works well for small databases or other small applications that require complete data redundancy.


RAID 1E Integrated Mirroring Enhanced) uses data mirroring on three to ten disks. (Requires Integrated RAID firmware v1.20.00 or above.)

RAID level

A virtual disk property indicating the RAID level of the virtual disk.

read policy

A controller attribute indicating the current read policy mode. In Always read ahead mode, the controller reads sequentially ahead of requested data and stores the additional data in cache memory, anticipating that the data will be needed soon. This speeds up reads for sequential data, but there is little improvement when accessing random data. In No read ahead mode, read-ahead capability is disabled. In Adaptive read ahead mode, the controller begins using read-ahead read policy if the two most recent disk accesses occurred in sequential sectors. If the read requests are random, the controller reverts to No read ahead mode.


The regeneration of all data to a replacement disk in a redundant virtual disk after a physical disk failure. A disk rebuild normally occurs without interrupting normal operations on the affected virtual disk, though some degradation of performance of the disk subsystem can occur.

reclaim virtual disk

A method of undoing the configuration of a new virtual disk. If you highlight the virtual disk in the Configuration Wizard and click the Reclaim button, the individual disk drives are removed from the virtual disk configuration.


A property of a storage configuration that prevents data from being lost when one physical disk fails in the configuration.

redundant configuration

A virtual disk that has redundant data on physical disks in the disk group that can be used to rebuild a failed physical disk. The redundant data can be parity data striped across multiple physical disks in a disk group, or it can be a complete mirrored copy of the data stored on a second physical disk. A redundant configuration protects the data in case a physical disk fails in the configuration.

revision level

A physical disk property that indicates the revision level of the disk’s firmware.


Serial Attached SCSI. SAS is a serial, point-to-point, enterprise-level device interface that leverages the SCSI protocol set. The SAS interface provides improved performance, simplified cabling, smaller connectors, lower pin count, and lower power requirements when compared to parallel SCSI.

SCSI device type

A physical drive property indicating the type of the device, such as Disk Drive.

serial no.

A controller property indicating the manufacturer-assigned serial number.

stripe size

A virtual disk property indicating the data stripe size used in the virtual disk. See striping.


A technique used to write data across all physical disks in a virtual disk. Each stripe consists of consecutive virtual disk data addresses that are mapped in fixed-size units to each physical disk in the virtual disk using a sequential pattern. For example, if the virtual disk includes five physical disks, the stripe writes data to physical disks 1 through 5 without repeating any of the physical disks. The amount of space consumed by a stripe is the same on each physical disk. Striping by itself does not provide data redundancy.

subvendor ID

A controller property that lists additional vendor ID information about the controller.

vendor ID

A controller property indicating the vendor-assigned ID number of the controller.

vendor info

A physical disk drive property listing the name of the vendor of the drive.

virtual disk (VD)

A storage unit created by a RAID controller from one or more physical disks. Although a virtual disk may be created from several physical disks, it is seen by the operating system as a single disk. Depending on the RAID level used, the virtual disk may retain redundant data in case of a disk failure.

virtual disk state

A virtual disk property indicating the condition of the virtual disk. Examples include Optimal and Degraded.

write back caching

The controller sends a data transfer completion signal to the host when the controller cache has received all the data in a disk write transaction. Data is written to the disk subsystem in accordance with policies set up by the controller. These policies include the amount of dirty/clean cache lines, the number of cache lines available, and elapsed time from the last cache flush.

write through caching

The controller sends a data transfer completion signal to the host when the disk subsystem has received all the data in a transaction.

write policy

See Default Write Policy.