Data Recovery Glossary
We have prepared this glossary for our customers to better understand the terms we use in data recovery and computer repair.
ATA - Acronym for AT Attachment. There are multiple levels of ATA standards including the base-level 16-bit IDE, ATA-2 (Enhanced IDE) and Ultra ATA.
ATAPI - ATA Packet Interface. Defines a set of commands supported through the ATA-2 interface for peripherals other than hard drives, such as CD-ROM, DVD-ROM, and tape drives.
Average seek time - The average time it takes for the read/write head to move to a specific location. To compute the average seek time, divide the time it takes to complete a large number of random seeks by the number of seeks performed.
Bad block - A block (usually the size of a sector) that cannot reliably hold data because of a media flaw or damaged format markings.
BIOS - This is the acronym for Basic Input/Output System. Your BIOS runs at startup, configures devices, and then boots the operating system. Because the BIOS is so integral to getting your computer started, it’s stored on a separate ROM chip, not your hard drive, to isolate it from crashes.
Bit - Abbreviation for binary digit. A binary digit may have one of two values - 1 or 0. This contrasts with a decimal digit, which may have a value from 0 to 9. A bit is one of the logic 1 or logic 0 binary settings that make up a byte of data.
Buffer - An area of RAM reserved for temporary storage of data that is waiting to be sent to a device.
Buffer Under Run - Occurs when the system cannot keep up a steady data stream to the CD recording software. The CD recorder itself has a buffer that is constantly filled with data in the event of a system slowdown or interruption. If the buffer is emptied before the system can recover, a buffer under-run occurs.
Byte
Cache - Specialized RAM used to optimize data transfers between system elements with different performance characteristics.
Clean Room - An environmentally controlled dust-free assembly or repair facility in which hard disk drives are assembled or can be opened for internal servicing.
CDR - An acronym for re-writable CD technology whose media can be written to and erased approximately 1,000 times before failure. Standard 74min CD-RW media can hold up to 500MB when formatted for fixed-length packet writing.
CRC - Acronym for Cyclic Redundancy Check. The CRC is used to verify data block integrity. In a typical scheme, 2 CRC bytes are added to each user data block. The 2 bytes are computed from the user data, by digital logical chips. The mathematical model is made up of polynomials with binary coefficients. When reading back data, the CRC bytes are read and compared to new CRC bytes computed from the read back block to detect a read error. The read back error check process is mathematically equivalent to dividing the read block, including its CRC, by a binomial. If the division remainder is zero, the data is error free.
Cylinder - The cylindrical surface formed by identical track numbers on vertically stacked discs. At any location of the head positioning arm, all tracks under all heads are the cylinder. The cylinder number is one of the three address components required to find a specific address. The other two are head number and sector number.
Dedicated Servo - A technology in which timing or positioning signals are located on a dedicated disk containing no user data. These signals provide the information the actuator needs to fine-tune the position of the read/write heads.
ECC - Acronym for Error Correction Code. The incorporation of extra parity bits in transmitted data in order to detect errors that can be corrected by the controller.
Embedded Servo - A method of using the space between sectors (intersector gaps) on each data surface of a disc drive to provide servo-positioning information. This method uses the same head to read both servo and data information, allowing all surfaces to be used for data storage.
File Allocation Table (FAT) - The operating systems use FAT to keep track of which clusters are allocated to which files and which are available for use.
Firmware
Flying Height - The distance between the read/write head and the disk surface, made up of a cushion of air that keeps the head from contacting the media.
Gigabyte (GB) - A unit of measure consisting of one billion bytes (one thousand megabytes).
HDA - Acronym for head disk assembly, typically a sealed unit.
Head - The tiny electromagnetic coil and metal pole used to create and read back the magnetic patterns on the disk. Also known as the read/write head.
Head Crash - Damage to a read/ write head and magnetic media, usually caused by sudden contact of the heads with the disk surface. Head crash also can be caused by dust and other contamination inside the HDA.
High Level Formatting - Formatting performed by the operating system’s format program (for example, the DOS FORMAT program). Among other things, the formatting program creates the root directory, file allocation tables, and other basic configurations.
Jumper - A tiny connector box that slips over two pins that protrude from a circuit board. The jumper can be moved to change electrical connectors. When in place, the jumper connects the pins electrically.
Kilobyte - A unit of measure consisting of 1,024 bytes.
Landing Zone - A non-data area on the disk’s inner cylinder where the heads can rest when the power is off.
Low Level Format - The first step in preparing a drive to store information after physical installation is complete. The process sets up the handshake between the drive and the controller.
Megabyte - A unit of measurement equal to 1 million bytes or 1,024 kilobytes or 1,048,576 bytes.
Megahertz (MHz) - A measurement of frequency in millions of cycles per second.
Mirroring - A popular term for RAID-1. A method of creating disc-fault tolerance by redundantly storing information on a pair of drives.
MTBF - Acronym for mean time between failures. It is the reliability rating indicating the expected failure rate of a product in power on hours.
Operating System - A program which acts as an interface between the user of a computer and the computer hardware. The purpose of the operating system is to provide an environment in which a user may run software applications. The goal of the operating system is to enable the user to conveniently use the computer’s resources such as the CPU, memory, storage devices and printers.
Partioning - Method for creating a logical file structure that the operating system can access. Method for dividing an area on the disc drive for use by more than one disc operating system, or for dividing large disc drives into areas which the file allocation table (FAT) can deal with when in use.
Platter - A disk made of metal (or other rigid material) that is mounted inside a fixed disk drive. Most drives use more than one platter mounted on a single spindle (shaft) to provide more data storage surfaces in a smaller area.
RAID - RAID (redundant array of independent discs) is a concept in storage subsystems that can deliver higher levels of protection against down-time and data loss than conventional disc drives. RAID refers to a drive architecture designed to safeguard critical data through redundancy. In theory, RAID arrays composed of conventional discs can function for hundreds or even thousands of years without losing data because of a disc failure. RAID also offers other benefits: it can improve input/output performance, make servicing simpler and quicker and allow users to fine-tune the drive system to match the needs of specific applications.
The RAID concept was first articulated by a group of Berkeley re-searchers in 1987. Their work defined five levels of RAID: five ways of distributing data across an array of discs so that the failure of a single disc does not cause data loss. Of the original designs, three have proven commercially attractive: Level 1, Level 3 and Level 5. Though not strictly RAID, an additional level, Level 0, is commonly included among RAID designs because of its similarity to the original designs. Level 0 distributes data across discs by striping-a technique for storing consecutive chunks of data on different discs. Striping improves I/O throughput but provides no more data protection than conventional drives. Level 1 achieves data redundancy through mirroring-keeping identical data on two separate discs. Mirroring offers excellent reliability and some improvement in I/O throughput but is relatively inefficient in its use of total disc capacity. Level 3 and Level 5 combine striping with parity codes to allow recovery of data if a disc fails. Level 3 and Level 5 both use disc capacity more efficiently than Level 1.
There is more to RAID than redundancy. RAID contributes to automatic load balancing, avoiding hot discs where 80 percent of the I/O requests target 20 percent of the disc capacity. The right choice of RAID level can speed up data transfers or handle more I/O requests per second. Level-3 drives process large amounts of data quickly by transferring data from all discs in parallel, shortening transfer times for applications such as image processing or CAD that read in large, sequential files. Level-5 arrays can handle large numbers of I/O requests concurrently, so they are a good match for applications that make many small requests: office automation, transaction processing and general-purpose multitasking.
RLL - Acronym for run length limited. A method used on some hard disks to encode data into magnetic pulses. RLL requires more processing, but stores almost 50 percent more data per disk than the older MFM (modified frequency modulation) method.
Sector - A sector is a section of track whose size is determined by formatting. When used as an address component, sector and location refer to the sequence number of the sector around the track. Typically, one sector stores one user record of data. Determining how many sectors per track to use is dependent on the system type, the controller capabilities, and the drive encoding method and interface.
Ultra ATA/100 - Ultra ATA/100 or Ultra DMA/100 is an extension of the current Ultra ATA/66 interface. This new high-speed interface has the capability of 100 Mbytes/sec transfer rate and maximized disk performance under the current PCI local bus environment.
Terabyte - A Terabyte = 1,099,511,627,776 bytes (or approximately one trillion bytes). A terabyte is equivalent to 1,000 gigabytes or 1,000,000 megabytes.
Winchester Disks - Former code name for an early IBM hard disk model. Sometimes still used to refer to hard drives in general.
