Hard disk driveFrom Wikipedia, the free encyclopedia"Hard drive" redirects here. For other uses, see Hard drive (disambiguation).Hard disk driveVideo of modern HDD operation (cover removed)Date invented 24 December 1954[note 1]Invented by IBM team led by Rey JohnsonA disassembled and labeled 1997 HDD. All major components were placed on a mirror, which created the symmetricalreflectionsOverview of how an HDD functions
A hard disk drive (HDD)[note 2]is a data storage device used for storing and retrieving digital information usingrapidly rotating discs (platters) coated with magnetic material. An HDD retains its data even when powered off.Data is read in a random-access manner, meaning individual blocks of data can be stored or retrieved in anyorder rather than sequentially. An HDD consists of one or more rigid ("hard") rapidly rotating discs (platters)withmagnetic heads arranged on a moving actuator arm to read and write data to the surfaces.Introduced by IBM in 1956,HDDs became the dominant secondary storage device for general purposecomputers by the early 1960s. Continuously improved, HDDs have maintained this position into the modern eraof servers and personal computers. More than 200 companies have produced HDD units, though most currentunits are manufactured by Seagate, Toshiba and Western Digital. Worldwide revenues for HDDs shipments areexpected to reach $33 billion in 2013, a decrease of about 12% from $37.8 billion in 2012.The primary characteristics of an HDD are its capacity and performance. Capacity is specified in unitprefixes corresponding to powers of 1000: a 1-terabyte (TB) drive has a capacity of 1,000 gigabytes (GB;where 1 gigabyte = 1 billion bytes). Typically, some of an HDDs capacity is unavailable to the user because itis used by the file system and the computer operating system, and possibly inbuilt redundancy for errorcorrection and recovery. Performance is specified by the time to move the heads to a file (Average AccessTime) plus the time it takes for the file to move under its head (average latency, a function of thephysical rotational speed in revolutions per minute) and the speed at which the file is transmitted (data rate).The two most common form factors for modern HDDs are 3.5-inch in desktop computers and 2.5-inch inlaptops. HDDs are connected to systems by standard interface cables such as SATA (Serial ATA), USB orSAS (Serial attached SCSI) cables.As of 2012, the primary competing technology for secondary storage is flash memory in the form of solid-statedrives (SSDs). HDDs are expected to remain the dominant medium for secondary storage due to predictedcontinuing advantages in recording capacity and price per unit of storage;but SSDs are replacing HDDswhere speed, power consumption and durability are more important considerations than price and capacity.Contents[hide]1 History2 Technologyo 2.1 Magnetic recordingo 2.2 Componentso 2.3 Error handlingo 2.4 Future development
3 Capacityo 3.1 Calculationo 3.2 Redundancyo 3.3 File system useo 3.4 Units4 Form factors5 Performance characteristicso 5.1 Time to access datao 5.2 Seek timeo 5.3 Latencyo 5.4 Data transfer rateo 5.5 Other considerations6 Access and interfaces7 Integrity and failure8 External removable drives9 Market segments10 Manufacturers and sales11 Icons12 See also13 Notes14 References15 Further reading16 External linksHistoryMain article: History of hard disk drivesHDDs were introduced in 1956 as data storage for an IBM real-time transaction processing computerandwere developed for use with general purpose mainframe and minicomputers. The first IBM drive, the 350RAMAC, was approximately the size of two refrigerators and stored 5 million 6-bit characters (the equivalent of3.75 million 8-bit bytes) on a stack of 50 discs.In 1961 IBM introduced the model 1311 disk drive, which was about the size of a washing machine and storedtwo million characters on a removable disk pack. Users could buy additional packs and interchange them asneeded, much like reels of magnetic tape. Later models of removable pack drives, from IBM and others,
became the norm in most computer installations and reached capacities of 300 megabytes by the early 1980s.Non-removable HDDs were called fixed disk drives.Some high performance HDDs were manufactured with one head per track, e.g., IBM 2305 so that no time waslost physically moving the heads to a track.Known as Fixed-Head or Head-Per-Track disk drives they werevery expensive and are no longer in production.In 1973, IBM introduced a new type of HDD codenamed "Winchester". Its primary distinguishing feature wasthat the disk heads were not withdrawn completely from the stack of disk platters when the drive was powereddown. Instead, the heads were allowed to "land" on a special area of the disk surface upon spin-down, "takingoff" again when the disk was later powered on. This greatly reduced the cost of the head actuator mechanism,but precluded removing just the disks from the drive as was done with the disk packs of the day. Instead, thefirst models of "Winchester technology" drives featured a removable disk module, which included both the diskpack and the head assembly, leaving the actuator motor in the drive upon removal. Later "Winchester" drivesabandoned the removable media concept and returned to non-removable platters.Like the first removable pack drive, the first "Winchester" drives used platters 14 inches (360 mm) in diameter.A few years later, designers were exploring the possibility that physically smaller platters might offeradvantages. Drives with non-removable eight-inch platters appeared, and then drives that used a 51⁄4 in(130 mm) form factor (a mounting width equivalent to that used by contemporary floppy disk drives). The latterwere primarily intended for the then-fledgling personal computer (PC) market.As the 1980s began, HDDs were a rare and very expensive additional feature on PCs; however by the late1980s, their cost had been reduced to the point where they were standard on all but the cheapest PC.Most HDDs in the early 1980s were sold to PC end users as an external, add-on subsystem. The subsystemwas not sold under the drive manufacturers name but under the subsystem manufacturers name suchas Corvus Systems and Tallgrass Technologies, or under the PC system manufacturers name such asthe Apple ProFile. The IBM PC/XT in 1983 included an internal 10MB HDD, and soon thereafter internal HDDsproliferated on personal computers.External HDDs remained popular for much longer on the Apple Macintosh. Every Mac made between 1986 and1998 has a SCSI port on the back, making external expansion easy; also, "toaster" Compact Macs did not haveeasily accessible HDD bays (or, in the case of the Mac Plus, any hard drive bay at all), so on those models,external SCSI disks were the only reasonable option.Driven by areal density doubling every two to four years since their invention (an observation knownas Kryders law, similar to Moores Law), HDDs have continuously improved their characteristics; a fewhighlights include:
Capacity per HDD increasing from 3.75 megabytesto 4 terabytes or more, more than a million timeslarger.Physical volume of HDD decreasing from 68 cubic feet (1.9 m3)(comparable to a large side-by-siderefrigerator), to less than 20 millilitres (0.70 imp fl oz; 0.68 US fl oz),a 100,000-to-1 decrease.Weight decreasing from 2,000 pounds (910 kg)to 48 grams (1.7 oz),a 20,000-to-1 decrease.Price decreasing from about US$15,000 per megabyteto less than $0.00006 per megabyte ($90/1.5terabyte), a greater than 250-million-to-1 decrease.Average Access Time decreasing from over 100 milliseconds to a few milliseconds, a greater than 40-to-1improvement.Market application expanding from mainframe computers of the late 1950s to most massstorage applications including computers and consumer applications such as storage of entertainmentcontent.TechnologyMagnetic cross section & frequency modulation encoded binary dataMagnetic recordingSee also: Magnetic storageAn HDD records data by magnetizing a thin film of ferromagnetic material[note 3]on a disk. Sequential changes inthe direction of magnetization represent binary data bits. The data is read from the disk by detecting thetransitions in magnetization. User data is encoded using an encoding scheme, such as run-lengthlimited encoding,which determines how the data is represented by the magnetic transitions.A typical HDD design consists of a spindle that holds flat circular disks, also called platters, which hold therecorded data. The platters are made from a non-magnetic material, usually aluminium alloy, glass, or ceramic,and are coated with a shallow layer of magnetic material typically 10–20 nm in depth, with an outer layer ofcarbon for protection.For reference, a standard piece of copy paper is 0.07–0.18 millimetre (70,000–180,000 nm).
Diagram labeling the major components of a computer HDDRecording of single magnetisations of bits on a 200MB HDD-platter (recording made visible using CMOS-MagView).Longitudinal recording (standard) & perpendicular recording diagramThe platters in contemporary HDDs are spun at speeds varying from 4,200 rpm in energy-efficient portabledevices, to 15,000 rpm for high performance servers.The first HDDs spun at 1,200 rpmand, for manyyears, 3,600 rpm was the norm.Today, the platters in most consumer HDDs spin in the range of 5,400 rpmto 7,200 rpm.Information is written to and read from a platter as it rotates past devices called read-and-write heads thatoperate very close (often tens of nanometers) over the magnetic surface. The read-and-write head is used todetect and modify the magnetization of the material immediately under it.
In modern drives there is one head for each magnetic platter surface on the spindle, mounted on a commonarm. An actuator arm (or access arm) moves the heads on an arc (roughly radially) across the platters as theyspin, allowing each head to access almost the entire surface of the platter as it spins. The arm is moved usinga voice coil actuator or in some older designs a stepper motor. Early hard disk drives wrote data at someconstant bits per second, resulting in all tracks having the same amount of data per track but modern drives(since the 1990s) use zone bit recording -- increasing the write speed from inner to outer zone and therebystoring more data per track in the outer zones.In modern drives, the small size of the magnetic regions creates the danger that their magnetic state might belost because of thermal effects. To counter this, the platters are coated with two parallel magnetic layers,separated by a 3-atom layer of the non-magnetic element ruthenium, and the two layers are magnetized inopposite orientation, thus reinforcing each other.Another technology used to overcome thermal effects toallow greater recording densities is perpendicular recording, first shipped in 2005,and as of 2007 thetechnology was used in many HDDs.ComponentsHDD with disks and motor hub removed exposing copper colored stator coils surrounding a bearing in the center of thespindle motor. Orange stripe along the side of the arm is thin printed-circuit cable, spindle bearing is in the center and theactuator is in the upper leftA typical HDD has two electric motors; a spindle motor that spins the disks and an actuator (motor) thatpositions the read/write head assembly across the spinning disks. The disk motor has an external rotorattached to the disks; the stator windings are fixed in place. Opposite the actuator at the end of the headsupport arm is the read-write head; thin printed-circuit cables connect the read-write heads to amplifierelectronics mounted at the pivot of the actuator. The head support arm is very light, but also stiff; in moderndrives, acceleration at the head reaches 550 g.
Head stack with an actuator coil on the left and read/write heads on the rightThe actuator is a permanent magnet and moving coil motor that swings the heads to the desired position. Ametal plate supports a squat neodymium-iron-boron (NIB) high-flux magnet. Beneath this plate is the movingcoil, often referred to as the voice coil by analogy to the coil in loudspeakers, which is attached to the actuatorhub, and beneath that is a second NIB magnet, mounted on the bottom plate of the motor (some drives onlyhave one magnet).The voice coil itself is shaped rather like an arrowhead, and made of doubly coated copper magnet wire. Theinner layer is insulation, and the outer is thermoplastic, which bonds the coil together after it is wound on aform, making it self-supporting. The portions of the coil along the two sides of the arrowhead (which point to theactuator bearing center) interact with the magnetic field, developing a tangential force that rotates the actuator.Current flowing radially outward along one side of the arrowhead and radially inward on the other producesthe tangential force. If the magnetic field were uniform, each side would generate opposing forces that wouldcancel each other out. Therefore the surface of the magnet is half N pole, half S pole, with the radial dividingline in the middle, causing the two sides of the coil to see opposite magnetic fields and produce forces that addinstead of canceling. Currents along the top and bottom of the coil produce radial forces that do not rotate thehead.The HDDs electronics control the movement of the actuator and the rotation of the disk, and perform reads andwrites on demand from the disk controller. Feedback of the drive electronics is accomplished by means ofspecial segments of the disk dedicated to servo feedback. These are either complete concentric circles (in thecase of dedicated servo technology), or segments interspersed with real data (in the case of embedded servotechnology). The servo feedback optimizes the signal to noise ratio of the GMR sensors by adjusting the voice-coil of the actuated arm. The spinning of the disk also uses a servo motor. Modern disk firmware is capable ofscheduling reads and writes efficiently on the platter surfaces and remapping sectors of the media which havefailed.Error handling
Modern drives make extensive use of error correction codes (ECCs), particularly Reed–Solomon errorcorrection. These techniques store extra bits, determined by mathematical formulas, for each block of data; theextra bits allow many errors to be corrected invisibly. The extra bits themselves take up space on the HDD, butallow higher recording densities to be employed without causing uncorrectable errors, resulting in much largerstorage capacity.In the newest drives of 2009, low-density parity-check codes (LDPC) were supplantingReed-Solomon; LDPC codes enable performance close to the Shannon Limit and thus provide the higheststorage density available.Typical HDDs attempt to "remap" the data in a physical sector that is failing to a spare physical sector—hopefully while the errors in the bad sector are still few enough that the ECC can recover the data without loss.The S.M.A.R.T-Self-Monitoring, Analysis and Reporting Technology system counts the total number of errors inthe entire HDD fixed by ECC and the total number of remappings, as the occurrence of many such errors maypredict HDD failure.Future developmentHDD areal densities have shown a long term compound annual growth rate not substantively differentfrom Moores Law, most recently in the range of 20-25% annually, with desktop 3.5" drives estimated to hit12 TB around 2016.New magnetic storage technologies are being developed to support higher areal densitygrowth and maintain the competitiveness of HDDs with potentially competitive products such as flash memory-based solid-state drives (SSDs). These new HDD technologies include:Heat-assisted magnetic recording (HAMR)Bit-patterned recording (BPR)Current Perpendicular to Plane giant magnetoresistance (CPP/GMR) headsShingled WriteWith these new technologies the relative position of HDDs and SSDs with regard to their cost and performanceis not projected to change through 2016.CapacityThe capacity of an HDD reported to an end user by the operating system is less than the amount stated by adrive or system manufacturer due to amongst other things, different units of measuring capacity, capacityconsumed by the file system and/or redundancy.CalculationBecause modern disk drives appear to their interface as a contiguous set of logical blocks their gross capacitycan be calculated by multiplying the number of blocks by the size of the block. This information is available
from the manufacturers specification and from the drive itself through use of special utilities invoking low levelcommands.The gross capacity of older HDDs can be calculated by multiplying for each zone of the drive the numberof cylinders by the number of heads by the number of sectors/zone by the number of bytes/sector (mostcommonly 512) and then summing the totals for all zones. Some modern SATA drives will also report cylinder-head-sector (C/H/S) values to the CPU but they are no longer actual physical parameters since the reportednumbers are constrained by historic operating-system interfaces.The old C/H/S scheme has been replaced by logical block addressing. In some cases, to try to "force-fit" theC/H/S scheme to large-capacity drives, the number of heads was given as 64, although no modern drive hasanywhere near 32 platters.RedundancyIn modern HDDs, spare capacity for defect management is not included in the published capacity; however inmany early HDDs a certain number of sectors were reserved for spares, thereby reducing capacity available toend users.In some systems, there may be hidden partitions used for system recovery that reduce the capacity available tothe end user.For RAID subsystems, data integrity and fault-tolerance requirements also reduce the realized capacity. Forexample, a RAID1 subsystem will be about half the total capacity as a result of data mirroring. RAID5subsystems with x drives, would lose 1/x of capacity to parity. RAID subsystems are multiple drives that appearto be one drive or more drives to the user, but provides a great deal of fault-tolerance. Most RAID vendors usesome form of checksums to improve data integrity at the block level. For many vendors, this involves usingHDDs with sectors of 520 bytes per sector to contain 512 bytes of user data and eight checksum bytes or usingseparate 512-byte sectors for the checksum data.File system useMain article: Disk formattingThe presentation of an HDD to its host is determined by its controller. This may differ substantially from thedrives native interface particularly in mainframes or servers.Modern HDDs, such as SASand SATAdrives, appear at their interfaces as a contiguous set of logicalblocks; typically 512 bytes long but the industry is in the process of changing to 4,096-byte logical blocks;see Advanced Format.The process of initializing these logical blocks on the physical disk platters is called low level formatting whichis usually performed at the factory and is not normally changed in the field.[note 4]
High level formatting then writes the file system structures into selected logical blocks to make the remaininglogical blocks available to the host OS and its applications.The operating system file system uses some ofthe disk space to organize files on the disk, recording their file names and the sequence of disk areas thatrepresent the file. Examples of data structures stored on disk to retrieve files include the file allocationtable (FAT) in the MS-DOS file system and inodes in many UNIX file systems, as well as other operatingsystem data structures. As a consequence not all the space on an HDD is available for user files. This filesystem overhead is usually less than 1% on drives larger than 100 MB.UnitsSee also: Binary prefixUnit prefixesAdvertised capacity by manufacturer(usingdecimal multiples)Expected capacity by consumers in classaction (using binary multiples)Reported capacityWindows (usingbinary multiples)Mac OS X 10.6+ (usingdecimal multiples)With prefix Bytes Bytes Diff.100 MB 100,000,000 104,857,600 4.86% 95.4 MB 100 MB100 GB 100,000,000,000 107,374,182,400 7.37% 93.1 GB, 95,367 MB 100 GB1 TB 1,000,000,000,000 1,099,511,627,776 9.95% 931 GB, 953,674 MB 1,000 GB, 1,000,000 MBThe total capacity of HDDs is given by manufacturers in megabytes(1 MB = 1,000,000bytes), gigabytes (1 GB = 1,000,000,000 bytes) orterabytes (1 TB = 1,000,000,000,000bytes).This numbering convention, where prefixes like mega- and giga- denote powers of 1,000,is also used for data transmission rates and DVD capacities. However, the convention is different from thatused by manufacturers ofmemory (RAM, ROM) and CDs, where prefixes like kilo- and mega- meanpowers of1,024.The practice of using prefixes assigned to powers of 1,000 within the HDD and computer industries dates backto the early days of computing.By the 1970s million, mega and M were consistently being used inthe powers of 1,000 sense to describe HDD capacity.Computers do not internally represent HDD or memory capacity in powers of 1,024; reporting it in this manneris just a convention.Microsoft Windows uses the powers of 1,024 convention when reporting HDD capacity,thus an HDD offered by its manufacturer as a 1 TB drive is reported by these OSes as a 931 GB HDD. MacOS X 10.6 ("Snow Leopard"), uses powers of 1,000when reporting HDD capacity.
In the case of "mega-", there is a nearly 5% difference between the powers of 1,000 definition and the powersof 1,024 definition. Furthermore, the difference is compounded by 2.4% with each incrementally larger prefix(gigabyte, terabyte, etc.). The discrepancy between the two conventions for measuring capacity was thesubject of several class action suits against HDD manufacturers. The plaintiffs argued that the use of decimalmeasurements effectively misled consumerswhile the defendants denied any wrongdoing or liability,asserting that their marketing and advertising complied in all respects with the law and that no class membersustained any damages or injuries.In December 1998, standards organizations addressed these dual definitions of the conventional prefixes bystandardizing on unique binary prefixes and prefix symbols to denote multiples of 1,024, such as"mebibyte (MiB)", which exclusively denotes 220or 1,048,576 bytes.This standard has seen little adoption bythe computer industry, and the conventionally prefixed forms of "byte" continue to denote slightly differentvalues depending on context.Form factorsPast and present HDD form factorsForm factor StatusLength[mm]Width[mm]Height [mm] Largest capacityPlatters(max)CapacityPer platter[GB]3.5" Current 146 101.6 19 or 25.4 4 TB(2011) 5 10002.5" Current 100 69.855,7,9.5,12.5, or152 TB(2012) 4 6941.8" Current 71 54 5 or 8 320 GB(2009) 2 220 8" Obsolete 362 241.3 117.55.25" FH Obsolete 203 146 130 47 GB(1998) 14 3.365.25" HH Obsolete 203 146 41.4 19.3 GB(1998) 44.83
1.3" Obsolete 43 40 GB(2007) 1 401" (CFII/ZIF/IDE-Flex)Obsolete 42 20 GB (2006) 1 200.85" Obsolete 32 24 5 8 GB(2004) 1 85¼" full height 110 MB HDD; 2½" (63.5 mm) 6,495 MB HDD2.5" SATA HDD from a Sony VAIO laptop
Six HDDs with 8", 5.25", 3.5", 2.5", 1.8", and 1" hard disks with a ruler to show the length of platters and read-write headsMainframe and minicomputer hard disks were of widely varying dimensions, typically in free standing cabinetsthe size of washing machines or designed to fit a 19" rack. In 1962, IBM introduced its model 1311 disk, whichused 14 inch (nominal size) platters. This became a standard size for mainframe and minicomputer drives formany years.Such large platters were never used with microprocessor-based systems.With increasing sales of microcomputers having built in floppy-disk drives (FDDs), HDDs that would fit to theFDD mountings became desirable. Thus HDD Form factors, initially followed those of 8-inch, 5.25-inch, and3.5-inch floppy disk drives. Because there were no smaller floppy disk drives, smaller HDD form factorsdeveloped from product offerings or industry standards.8 inch9.5 in × 4.624 in × 14.25 in (241.3 mm × 117.5 mm × 362 mm). In 1979,Shugart Associates SA1000was the first form factor compatible HDD, having the same dimensions and a compatible interface tothe 8" FDD.5.25 inch5.75 in × 3.25 in × 8 in (146.1 mm × 82.55 mm × 203 mm). This smaller form factor, first used in anHDD by Seagate in 1980,was the same size as full-height 51⁄4-inch-diameter (130 mm) FDD, 3.25-inches high. This is twice as high as "half height"; i.e., 1.63 in (41.4 mm). Most desktop models ofdrives for optical 120 mm disks (DVD, CD) use the half height 5¼" dimension, but it fell out of fashionfor HDDs. The Quantum Bigfoot HDD was the last to use it in the late 1990s, with "low-profile"(≈25 mm) and "ultra-low-profile" (≈20 mm) high versions.3.5 inch4 in × 1 in × 5.75 in (101.6 mm × 25.4 mm × 146 mm) = 376.77344 cm³. This smaller form factor issimilar to that used in an HDD by Rodime in 1983,which was the same size as the "half height" 3½"FDD, i.e., 1.63 inches high. Today, the 1-inch high ("slimline" or "low-profile") version of this form factoris the most popular form used in most desktops.2.5 inch
2.75 in × 0.275–0.59 in × 3.945 in (69.85 mm × 7–15 mm × 100 mm) = 48.895–104.775 cm3. Thissmaller form factor was introduced by PrairieTek in 1988;there is no corresponding FDD. It came tobe widely used for HDDs in mobile devices (laptops, music players, etc.) and for solid-statedrives (SSDs), by 2008 replacing some 3.5 inch enterprise-class drives.It is also used inthe PlayStation 3and Xbox 360video game consoles. Drives 9.5 mm high became anunofficial standard for all except the largest-capacity laptop drives (usually having two platters inside);12.5 mm-high drives, typically with three platters, are used for maximum capacity, but will not fit mostlaptop computers. Enterprise-class drives can have a height up to 15 mm.Seagate released a 7mmdrive aimed at entry level laptops and high end netbooks in December 2009.1.8 inch54 mm × 8 mm × 71 mm = 30.672 cm³. This form factor, originally introduced by Integral Peripherals in1993, evolved into the ATA-7 LIF with dimensions as stated. For a time it was increasingly used indigital audio players and subnotebooks, but its popularity decreased to the point where this form factoris increasingly rare and only a small percentage of the overall market.1 inch42.8 mm × 5 mm × 36.4 mm. This form factor was introduced in 1999 as IBMs Microdrive to fit insidea CF Type II slot. Samsung calls the same form factor "1.3 inch" drive in its product literature.0.85 inch24 mm × 5 mm × 32 mm. Toshiba announced this form factor in January 2004for use in mobilephones and similar applications, including SD/MMC slot compatible HDDs optimized for video storageon 4G handsets. Toshiba manufactured a 4 GB (MK4001MTD) and an 8 GB (MK8003MTD)versionand holds the Guinness World Record for the smallest HDD.As of 2012, 2.5-inch and 3.5-inch hard disks were the most popular sizes.By 2009 all manufacturers had discontinued the development of new productsfor the 1.3-inch, 1-inch and 0.85-inch form factors due to falling prices of flashmemory,which has no moving parts.While these sizes are customarily described by an approximately correct figurein inches, actual sizes have long been specified in millimeters.Performance characteristicsMain article: Hard disk drive performance characteristicsTime to access dataThe factors that limit the time to access the data on an HDD are mostly relatedto the mechanical nature of the rotating disks and moving heads. Seek time is
a measure of how long it takes the head assembly to travel to the track of thedisk that contains data. Rotational latency is incurred because the desired disksector may not be directly under the head when data transfer is requested.These two delays are on the order of milliseconds each. The bit rate or datatransfer rate (once the head is in the right position) creates delay which is afunction of the number of blocks transferred; typically relatively small, but canbe quite long with the transfer of large contiguous files. Delay may also occur ifthe drive disks are stopped to save energy.An HDDs Average Access Time is its average Seek time which technically isthe time to do all possible seeks divided by the number of all possible seeks,but in practice is determined by statistical methods or simply approximated asthe time of a seek over one-third of the number of tracks.Defragmentation is a procedure used to minimize delay in retrieving data bymoving related items to physically proximate areas on the disk.Somecomputer operating systems perform defragmentation automatically. Althoughautomatic defragmentation is intended to reduce access delays, performancewill be temporarily reduced while the procedure is in progress.Time to access data can be improved by increasing rotational speed (thusreducing latency) and/or by reducing the time spent seeking. Increasing arealdensity increases throughput by increasing data rate and by increasing theamount of data under a set of heads, thereby potentially reducing seek activityfor a given amount of data. Based on historic trends, analysts predict a futuregrowth in HDD areal density (and therefore capacity) of about 40% peryear.The time to access data has not kept up with throughput increases,which themselves have not kept up with growth in storage capacity.Seek timeAverage seek time ranges from 3 msfor high-end server drives, to 15 ms formobile drives, with the most common mobile drives at about 12 msand themost common desktop type typically being around 9 ms. The first HDD had anaverage seek time of about 600 ms;by the middle 1970s HDDs wereavailable with seek times of about 25 ms.Some early PC drives useda stepper motor to move the heads, and as a result had seek times as slow as80–120 ms, but this was quickly improved by voice coil type actuation in the
1980s, reducing seek times to around 20 ms. Seek time has continued toimprove slowly over time.Some desktop and laptop computer systems allow the user to make a tradeoffbetween seek performance and drive noise. Faster seek rates typically requiremore energy usage to quickly move the heads across the platter, causinglouder noises from the pivot bearing and greater device vibrations as the headsare rapidly accelerated during the start of the seek motion and decelerated atthe end of the seek motion. Quiet operation reduces movement speed andacceleration rates, but at a cost of reduced seek performance.LatencyLatency is the delay for the rotation of the disk to bring the required disksector under the read-write mechanism. It depends on rotational speed of adisk, measured in revolutions per minute(rpm). Average rotational latency isshown in the table below, based on the statistical relation that the averagelatency in milliseconds for such a drive is one-half the rotational period.Rotational speed[rpm]Average latency[ms]15,000 210,000 37,200 4.165,400 5.554,800 6.25Data transfer rateAs of 2010, a typical 7,200-rpm desktop HDD has a sustained "disk-to-buffer"data transfer rate up to 1,030 Mbits/sec.This rate depends on the tracklocation; the rate is higher for data on the outer tracks (where there are moredata sectors per rotation) and lower toward the inner tracks (where there are
fewer data sectors per rotation); and is generally somewhat higher for 10,000-rpm drives. A current widely used standard for the "buffer-to-computer"interface is 3.0 Gbit/s SATA, which can send about 300 megabyte/s (10-bitencoding) from the buffer to the computer, and thus is still comfortably aheadof todays disk-to-buffer transfer rates. Data transfer rate (read/write) can bemeasured by writing a large file to disk using special file generator tools, thenreading back the file. Transfer rate can be influenced by file systemfragmentation and the layout of the files.HDD data transfer rate depends upon the rotational speed of the platters andthe data recording density. Because heat and vibration limit rotational speed,advancing density becomes the main method to improve sequential transferrates. Higher speeds require more power absorbed by the electric engine,which hence warms up more. While areal density advances by increasing boththe number of tracks across the disk and the number of sectors per track, onlythe latter increases the data transfer rate for a given rpm. Since data transferrate performance only tracks one of the two components of areal density, itsperformance improves at a lower rate.Other considerationsOther performance considerations include power consumption, audible noise,and shock resistance.Access and interfacesInner view of a 1998 Seagate HDD which used Parallel ATA interfaceMain article: Hard disk drive interfaceHDDs are accessed over one of a number of bus types, including as of2011 parallel ATA (PATA, also called IDE or EIDE; described before theintroduction of SATA as ATA), Serial ATA (SATA), SCSI, Serial AttachedSCSI (SAS), and Fibre Channel. Bridge circuitry is sometimes used to connect
HDDs to buses with which they cannot communicate natively, suchas IEEE 1394, USB and SCSI.Modern HDDs present a consistent interface to the rest of the computer, nomatter what data encoding scheme is used internally. Typically a DSP in theelectronics inside the HDD takes the raw analog voltages from the read headand uses PRML and Reed–Solomon error correctionto decode the sectorboundaries and sector data, then sends that data out the standard interface.That DSP also watches the error rate detected by error detection andcorrection, and performs bad sector remapping, data collection for Self-Monitoring, Analysis, and Reporting Technology, and other internal tasks.Modern interfaces connect an HDD to a host bus interface adapter (todaytypically integrated into the "south bridge") with one data/control cable. Eachdrive also has an additional power cable, usually direct to the power supplyunit.Small Computer System Interface (SCSI), originally named SASI forShugart Associates System Interface, was standard on servers,workstations, Commodore Amiga, Atari ST and AppleMacintosh computers through the mid-1990s, by which time most modelshad been transitioned to IDE (and later, SATA) family disks. The rangelimitations of the data cable allows for external SCSI devices.Integrated Drive Electronics (IDE), later standardized under the name ATAttachment (ATA, with the alias P-ATA or PATA (Parallel ATA)retroactively added upon introduction of SATA) moved the HDD controllerfrom the interface card to the disk drive. This helped to standardize thehost/contoller interface, reduce the programming complexity in the hostdevice driver, and reduced system cost and complexity. The 40-pinIDE/ATA connection transfers 16 bits of data at a time on the data cable.The data cable was originally 40-conductor, but later higher speedrequirements for data transfer to and from the HDD led to an "ultra DMA"mode, known as UDMA. Progressively swifter versions of this standardultimately added the requirement for an 80-conductor variant of the samecable, where half of the conductors provides grounding necessary forenhanced high-speed signal quality by reducing cross talk.
EIDE was an unofficial update (by Western Digital) to the original IDEstandard, with the key improvement being the use of direct memoryaccess (DMA) to transfer data between the disk and the computer withoutthe involvement of the CPU, an improvement later adopted by the officialATA standards. By directly transferring data between memory and disk,DMA eliminates the need for the CPU to copy byte per byte, thereforeallowing it to process other tasks while the data transfer occurs.Fibre Channel (FC) is a successor to parallel SCSI interface on enterprisemarket. It is a serial protocol. In disk drives usually the Fibre ChannelArbitrated Loop (FC-AL) connection topology is used. FC has muchbroader usage than mere disk interfaces, and it is the cornerstoneof storage area networks (SANs). Recently other protocols for this field,like iSCSI and ATA over Ethernet have been developed as well.Confusingly, drives usually use copper twisted-pair cables for FibreChannel, not fibre optics. The latter are traditionally reserved for largerdevices, such as servers or disk array controllers.Serial Attached SCSI (SAS). The SAS is a new generation serialcommunication protocol for devices designed to allow for much higherspeed data transfers and is compatible with SATA. SAS uses amechanically identical data and power connector to standard 3.5-inchSATA1/SATA2 HDDs, and many server-oriented SAS RAID controllers arealso capable of addressing SATA HDDs. SAS uses serial communicationinstead of the parallel method found in traditional SCSI devices but stilluses SCSI commands.Serial ATA (SATA). The SATA data cable has one data pair for differentialtransmission of data to the device, and one pair for differential receivingfrom the device, just like EIA-422. That requires that data be transmittedserially. A similar differential signaling system is usedin RS485, LocalTalk, USB, FireWire, and differential SCSI.Integrity and failure
Close-up HDD head resting on disk platter; its mirror reflection is visible on the plattersurfaceMain articles: Hard disk drive failure and Data recoveryDue to the extremely close spacing between the heads and the disk surface,HDDs are vulnerable to being damaged by a head crash—a failure of the diskin which the head scrapes across the platter surface, often grinding away thethin magnetic film and causing data loss. Head crashes can be caused byelectronic failure, a sudden power failure, physical shock, contamination of thedrives internal enclosure, wear and tear, corrosion, or poorly manufacturedplatters and heads.The HDDs spindle system relies on air pressure inside the disk enclosure tosupport the heads at their proper flying height while the disk rotates. HDDsrequire a certain range of air pressures in order to operate properly. Theconnection to the external environment and pressure occurs through a smallhole in the enclosure (about 0.5 mm in breadth), usually with a filter on theinside (the breather filter).If the air pressure is too low, then there is notenough lift for the flying head, so the head gets too close to the disk, and thereis a risk of head crashes and data loss. Specially manufactured sealed andpressurized disks are needed for reliable high-altitude operation, above about3,000 m (9,800 ft).Modern disks include temperature sensors and adjusttheir operation to the operating environment. Breather holes can be seen on alldisk drives—they usually have a sticker next to them, warning the user not tocover the holes. The air inside the operating drive is constantly moving too,being swept in motion by friction with the spinning platters. This air passesthrough an internal recirculation (or "recirc") filter to remove any leftover
contaminants from manufacture, any particles or chemicals that may havesomehow entered the enclosure, and any particles or outgassing generatedinternally in normal operation. Very high humidity for extended periods cancorrode the heads and platters.For giant magnetoresistive (GMR) heads in particular, a minor head crash fromcontamination (that does not remove the magnetic surface of the disk) stillresults in the head temporarily overheating, due to friction with the disk surface,and can render the data unreadable for a short period until the headtemperature stabilizes (so called "thermal asperity", a problem which canpartially be dealt with by proper electronic filtering of the read signal).When a mechanical hard disk requires repairs, the easiest method is to replacethe circuit board using an identical hard disk, provided it is the circuit board thathas malfunctioned. In the case of read-write head faults, they can be replacedusing specialized tools in a dust-free environment. If the disk platters areundamaged, they can be transferred into an identical enclosure and the datacan be copied or cloned onto a new drive. In the event of disk-platter failures,disassembly and imaging of the disk platters may be required.For logicaldamage to file systems, a variety of tools, including fsck on UNIX-like systemsand CHKDSK on Windows, can be used for data recovery. Recovery fromlogical damage can require file carving.A 2011 summary of research into SSD and magnetic disk failure patternsby Toms Hardware summarized research findings as follows:1. MTBF does not indicate reliability; the annualized failure rate is higherand usually more relevant.2. Magnetic disks do not have a specific tendency to fail during earlyuse, and temperature only has a minor effect; instead, failure ratessteadily increase with age.3. SMART warns of mechanical issues but not other issues affectingreliability, and is therefore not a reliable indicator of condition.4. Failure rates of drives sold as "enterprise" and "consumer" are "verymuch similar", although customized for their different environments.5. In drive arrays, one drives failure significantly increases the short-term chance of a second drive failing.
External removable drivesToshiba 1 TB 2.5" external USB 2.0 HDD3.0 TB 3.5" Seagate FreeAgent GoFlex plug and play external USB 3.0-compatible drive (left), 750GB 3.5" Seagate Technology push-button externalUSB2.0 drive (right), and a 500 GB 2.5" generic brand plug and play external USB2.0 drive (front).External removable HDDstypically connect via USB. Plug and play drivefunctionality offers system compatibility, and features large storage options andportable design. External HDDs are available in 2.5" and 3.5" sizes, and as ofMarch 2012 their capacities generally range from 160GB to 2TB. Commonsizes are 160GB, 250GB, 320GB, 500GB, 640GB, 750GB, 1TB, and2TB.External HDDs are available as preassembled integrated products, or may beassembled by combining an external enclosure (with USB or other interface)with a separately purchased drive.Features such as biometric security or multiple interfaces are available at ahigher cost.External hard drives generally have a slower transfer rate than that of aninternally mounted hard drive connecting through SATA.
Market segmentsDesktop HDDs typically store between 60 GB and 4 TB and rotate at5,400 to 10,000 rpm, and have a media transfer rate of 0.5 Gbit/s or higher(1 GB = 109bytes; 1 Gbit/s = 109bit/s). As of September 2011, the highestcapacity consumer HDDs store 4 TB.Mobile HDDs or laptop HDDs, smaller than their desktop and enterprisecounterparts, tend to be slower and have lower capacity. Mobile HDDsspin at 4,200 rpm, 5,200 rpm, 5,400 rpm, or 7,200 rpm, with 5,400 rpmbeing typical. 7,200 rpm drives tend to be more expensive and havesmaller capacities, while 4,200 rpm models usually have very high storagecapacities. Because of smaller platter(s), mobile HDDs generally havelower capacity than their greater desktop counterparts.Enterprise HDDs are typically used with multiple-user computersrunning enterprise software. Examples are: transaction processingdatabases, internet infrastructure (email, webserver, e-commerce),scientific computing software, and nearline storage management software.Enterprise drives commonly operate continuously ("24/7") in demandingenvironments while delivering the highest possible performance withoutsacrificing reliability. Maximum capacity is not the primary goal, and as aresult the drives are often offered in capacities that are relatively low inrelation to their cost.The fastest enterprise HDDs spin at 10,000 or15,000 rpm, and can achieve sequential media transfer speeds above1.6 Gbit/sand a sustained transfer rate up to 1 Gbit/s.Drivesrunning at 10,000 or 15,000 rpm use smaller platters to mitigate increasedpower requirements (as they have less air drag) and therefore generallyhave lower capacity than the highest capacity desktop drives. EnterpriseHDDs are commonly connected through Serial Attached SCSI (SAS)or Fibre Channel (FC). Some support multiple ports, so they can beconnected to a redundant host bus adapter. They can be reformatted withsector sizes larger than 512 bytes (often 520, 524, 528 or 536 bytes). Theadditional storage can be used by hardware RAID cards or to store a DataIntegrity Field.Consumer electronics HDDs include drives embedded into digital videorecorders and automotive vehicles. The former are configured to provide a
guaranteed streaming capacity, even in the face of read and write errors,while the latter are built to resist larger amounts of shock.The exponential increases in disk space and data access speeds of HDDshave enabled consumer products that require large storage capacities, suchas digital video recorders and digital audio players.In addition, theavailability of vast amounts of cheap storage has made viable a variety of web-based services with extraordinary capacity requirements, such as free-of-charge web search, web archiving, and video sharing (Google, InternetArchive, YouTube, etc.).Manufacturers and salesDiagram of HDD manufacturer consolidationSee also: History of hard disk drives and List of defunct hard diskmanufacturersMore than 200 companies have manufactured HDDs over time. Butconsolidations have concentrated production into just three manufacturerstoday: Western Digital, Seagate, and Toshiba.Worldwide revenues for HDDs shipments are expected to reach $33 billion in2013, down about 12% from $37.8 billion in 2012. This corresponds to a 2013unit shipment forecast of 552 million compared to 577 million units in 2012 and624 million units in 2011. The estimated 2013 market shares are about 40-45%each for Seagate and Western Digital and 13-16% for Toshiba
IconsHDDs are traditionally symbolized as a stylized stack of platters or as acylinder and are found in diagrams, or on lights to indicate HDD access. Inmost modern operating systems, HDDs are represented by an illustration orphotograph of the drive enclosure.HDDs are commonly symbolized with a drive iconRAID diagram icon symbolizing the array of disks