Hard disk drive

thumb|Hitachi 500GB 3.5" drive, 2011, opened to show the disk platters and read/write arm

A hard disk drive (HDD), hard disk, hard drive, or fixed disk is an electro-mechanical computer data storage device that stores and retrieves digital data using magnetic storage with one or more rigid rapidly rotating platters coated with magnetic material. The platters are paired with magnetic heads, usually arranged on a moving actuator arm, which read and write data to the platter surfaces. Data is accessed in a random-access manner, meaning that individual blocks of data can be stored and retrieved in any order. HDDs are a type of non-volatile storage, retaining stored data when powered off. Modern HDDs are typically in the form of a small rectangular box, possibly in a disk enclosure for portability. Modern disks do not have removable media, in contrast to the disk drives common in the 1960s and 1970s.

IBM introduced the first disk drive, the 350 for the 305 RAMAC, in 1956,), sales revenues and unit shipments are declining, because solid-state drives (SSDs) have higher data-transfer rates, higher areal storage density, somewhat better reliability, and much lower latency and access times.

The revenues for SSDs, most of which use NAND flash memory, slightly exceeded those for HDDs in 2018. Flash storage products had more than twice the revenue of hard disk drives . Though SSDs have four to nine times higher cost per bit, they are replacing HDDs in applications where speed, power consumption, small size, high capacity and durability are important.

| invent-name = IBM team led by Rey Johnson

{| class="wikitable floatright" style="max-width: 35em;"

|+ Improvement of HDD characteristics over time

! Parameter !! Started with (1957) !! Improved to!! Improvement

| Capacity (formatted) || 3.75 megabytes

|| 9.6-million-to-one

| Physical volume || || 56,000-to-one

| Weight || in 2022)

|| US$14.4 per terabyte by end of 2022

|| 6.8-billion-to-one

| Data density || 2,000 bits per square inch || 1.4 terabits per square inch in 2023 || 700-million-to-one

| Average lifespan || c. 2000 hrs MTBF || c. 2,500,000 hrs (~285 years) MTBF || 1250-to-one

1950s–1960s

The first production IBM hard disk drive, the 350 disk storage, shipped in 1957 as a component of the IBM 305 RAMAC system. It was approximately the size of two large refrigerators and stored five million six-bit characters (3.75 megabytes) on a stack of 52 disks (100 surfaces used). The 350 had a single arm with two read/write heads, one facing up and the other down, that moved both horizontally between a pair of adjacent platters and vertically from one pair of platters to a second set. Variants of the IBM 350 were the IBM 355, IBM 7300 and IBM 1405.

In 1961, IBM announced, and in 1962 shipped, the IBM 1301 disk storage unit, which superseded the IBM 350 and similar drives. The 1301 consisted of one (for Model 1) or two (for model 2) modules, each containing 25 platters, each platter about thick and in diameter. While the earlier IBM disk drives used only two read/write heads per arm, the 1301 used an array of 48 heads (comb), each array moving horizontally as a single unit, one head per surface used. Cylinder-mode read/write operations were supported, and the heads flew about 250 micro-inches (about 6 μm) above the platter surface. Motion of the head array depended upon a binary adder system of hydraulic actuators which assured repeatable positioning. The 1301 cabinet was about the size of three large refrigerators placed side by side, storing the equivalent of about 21 million eight-bit bytes per module. Access time was about a quarter of a second.

Also in 1962, IBM introduced the model 1311 disk drive, which was about the size of a washing machine and stored two million characters on a removable disk pack. Users could buy additional packs and interchange them as needed, 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.

In 1963, IBM introduced the 1302, with twice the track capacity and twice as many tracks per cylinder as the 1301. The 1302 had one (for Model 1) or two (for Model 2) modules, each containing a separate comb for the first 250 tracks and the last 250 tracks.

Some high-performance HDDs were manufactured with one head per track, e.g., the Burroughs B-475 in 1964 and the IBM 2305 in 1970, so that no time was lost physically moving the heads to a track and the only latency was the time for the desired block of data to rotate into position under the head. Known as fixed-head or disk drives, they were very expensive and are no longer in production.

1970s

In 1973, IBM introduced a new type of HDD code-named "Winchester". Its primary distinguishing feature was that the disk heads were not withdrawn completely from the stack of disk platters when the drive was powered down. Instead, the heads were allowed to "land" on a special area of the disk surface upon spin-down, "taking off" 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, the first models of "Winchester technology" drives featured a removable disk module, which included both the disk pack and the head assembly, leaving the actuator motor in the drive upon removal. Later "Winchester" drives abandoned the removable media concept and returned to non-removable platters.

In 1974, IBM introduced the swinging arm actuator, made feasible because the Winchester recording heads function well when skewed to the recorded tracks. The simple design of the IBM GV (Gulliver) drive, invented at IBM's UK Hursley Labs, became IBM's most licensed electro-mechanical invention of all time, the actuator and filtration system being adopted in the 1980s eventually for all HDDs, and still universal over 50 years and 10 billion arms later.

Like the first removable pack drive, the first "Winchester" drives used platters in diameter. In 1978, IBM introduced a swing arm drive, the IBM 0680 (Piccolo), with eight-inch platters, exploring the possibility that smaller platters might offer advantages. Other eight-inch drives followed, then drives, sized to replace the contemporary floppy disk drives. The latter were primarily intended for the then fledgling personal computer (PC) market.

1980s–1990s

Over time, as recording densities were greatly increased, further reductions in disk diameter to 3.5" and 2.5" were found to be optimum. Powerful rare-earth magnet materials became affordable during this period and were complementary to the swing arm actuator design to make possible the compact form factors of modern HDDs.

By 1986, 10 MB was the most commonly used hard disk size, and most new corporate computers had hard drives. Most in the industry expected that 20 MB would soon become the new standard size. By the late 1980s, their cost had been reduced to the point where they were standard on all but the cheapest computers.

Most HDDs in the early 1980s were sold to PC end users as an external, add-on subsystem. The subsystem was not sold under the drive manufacturer's name but under the subsystem manufacturer's name such as Corvus Systems and Tallgrass Technologies, or under the PC system manufacturer's name such as the Apple ProFile.

The IBM PC XT in 1983 included an internal 10 MB HDD; by 1985 internal HDDs outsold external drives for personal computers. When IBM began selling the XT without a hard disk, hard disk manufacturers that had only sold to OEM customers began selling to resellers, which bundled XTs with the non-IBM hard disks. Hardcards became popular upgrades for existing computers.

External HDDs remained popular for much longer on the Apple Macintosh. Many Macintosh computers made between 1986 and 1998 featured a SCSI port on the back, making external expansion simple. Older compact Macintosh computers did not have user-accessible hard drive bays (indeed, the Macintosh 128K, Macintosh 512K, and Macintosh Plus did not feature a hard drive bay at all), so on those models, external SCSI disks were the only reasonable option for expanding upon any internal storage.

21st century

HDD improvements have been driven by increasing areal density, listed in the table above. Applications expanded through the 2000s, from the mainframe computers of the late 1950s to most mass storage applications including computers and consumer applications such as storage of entertainment content.

In the 2000s and 2010s, NAND began supplanting HDDs in applications requiring portability or high performance. In 2018, the largest hard drive had a capacity of 15 TB, while the largest capacity SSD had a capacity of 100 TB. but , the expected pace of improvement was pared back to 50 TB by 2026. Smaller form factors (1.8 inches and below) were discontinued around 2010.

The cost of solid-state storage (NAND), represented by Moore's law, is improving faster than HDDs. NAND has a higher price elasticity of demand than HDDs, and this drives market growth. During the late 2000s and 2010s, the product life cycle of HDDs entered a mature phase, and slowing sales may indicate the onset of the declining phase. During the 2020s, NAND adoption rate has significantly accelerated, in no small part due to the rising use of the technology in consumer electronics, while its performance has been improving faster than HDD performance.

The 2011 Thailand floods damaged the manufacturing plants and impacted hard disk drive cost adversely between 2011 and 2013.

In 2019, Western Digital closed its last Malaysian HDD factory due to decreasing demand, to focus on SSD production. All three remaining HDD manufacturers have had decreasing demand for their HDDs since 2014.

Technology

Magnetic recording

A modern HDD records data by magnetizing a thin film of ferromagnetic material on both sides of a disk. Sequential changes in the direction of magnetization represent binary data bits. The data is read from the disk by detecting the transitions in magnetization. User data is encoded using an encoding scheme, such as run-length limited encoding, which determines how the data is represented by the magnetic transitions.

A typical HDD design consists of a ' that holds flat circular disks, called platters, which hold the recorded data. The platters are made from a non-magnetic material, usually aluminum alloy, glass, or ceramic. They are coated with a shallow layer of magnetic material typically 10–20 nm in depth, with an outer layer of carbon for protection. , the platters in most consumer-grade HDDs spin at 5,400 or 7,200 rpm.

Information is written to and read from a platter as it rotates past devices called read-and-write heads that are positioned to operate very close to the magnetic surface, with their flying height often in the range of tens of nanometers. The read-and-write head is used to detect and modify the magnetization of the material passing immediately under it.

In modern drives, there is one head for each magnetic platter surface on the spindle, mounted on a common arm. An actuator arm (or access arm) moves the heads on an arc (roughly radially) across the platters as they spin, allowing each head to access almost the entire surface of the platter as it spins. The arm is moved using a voice coil actuator or, in some older designs, a stepper motor. Early hard disk drives wrote data at some constant 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 thereby storing 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 be lost because of thermal effects⁠ ⁠— thermally induced magnetic instability which is commonly known as the "superparamagnetic limit". To counter this, the platters are coated with two parallel magnetic layers, separated by a three-atom layer of the non-magnetic element ruthenium, and the two layers are magnetized in opposite orientation, thus reinforcing each other.

In 2004, a higher-density recording media was introduced, consisting of coupled soft and hard magnetic layers. So-called exchange spring media magnetic storage technology, also known as exchange coupled composite media, allows good writability due to the write-assist nature of the soft layer. However, the thermal stability is determined only by the hardest layer and not influenced by the soft layer.

magneticMedia.svg|Magnetic cross section & frequency modulation encoded binary data

HDD_Startup_and_Shutdown.webm|HDD with front cover removed to show its operation

Aufnahme einzelner Magnetisierungen gespeicherter Bits auf einem Festplatten-Platter..jpg|Recording of single magnetisations of bits on a 200 MB HDD-platter (recording made visible using CMOS-MagView) The spinning of the disks uses fluid-bearing spindle motors. Modern disk firmware is capable of scheduling reads and writes efficiently on the platter surfaces and remapping sectors of the media that have failed.

File:Hard drive.svg|Diagram labeling the major components of a computer HDD

File:Hard disk dismantled.jpg|An HDD with disks and motor hub removed, exposing copper-colored stator coils surrounding a bearing in the center of the spindle motor. The orange stripe along the side of the arm is a thin printed-circuit cable, the spindle bearing is in the center and the actuator is in the upper left.

File:Circuit board of a Samsung hard disk MP0402H.jpg|Printed circuit board of a 2.5-inch Samsung hard disk MP0402H.

File:Kopftraeger WD2500JS-00MHB0.jpg|Head stack with an actuator coil on the left and read/write heads on the right

File:HDD read-write head.jpg|Close-up of a single read–write head, showing the side facing the platter

File:Hard drive underside (better angle and lighting).jpg|The circuit board of a Western Digital hard drive attached to its chassis

File:Hard drive arm 2.jpg|The read/write arm

</gallery>

Error rates and handling

Modern drives make extensive use of error correction codes (ECCs), particularly Reed–Solomon error correction. These techniques store extra bits, determined by mathematical formulas, for each block of data; the extra bits allow many errors to be corrected invisibly. The extra bits themselves take up space on the HDD, but allow higher recording densities to be employed without causing uncorrectable errors, resulting in much larger storage capacity. For example, a typical 1 TB hard disk with 512-byte sectors provides additional capacity of about 93 GB for the ECC data.

In the newest drives, ,

Typical hard disk drives attempt to "remap" the data in a physical sector that is failing to a spare physical sector provided by the drive's "spare sector pool" (also called "reserve pool"), while relying on the ECC to recover stored data while the number of errors in a bad sector is still low enough. The S.M.A.R.T (Self-Monitoring, Analysis and Reporting Technology) feature counts the total number of errors in the entire HDD fixed by ECC (although not on all hard drives as the related S.M.A.R.T attributes "Hardware ECC Recovered" and "Soft ECC Correction" are not consistently supported), and the total number of performed sector remappings, as the occurrence of many such errors may predict an HDD failure.

The "No-ID Format", developed by IBM in the mid-1990s, contains information about which sectors are bad and where remapped sectors have been located.

Only a tiny fraction of the detected errors end up as not correctable. Examples of specified uncorrected bit read error rates include:

2013 specifications for enterprise SAS disk drives state the error rate to be one uncorrected bit read error in every 1016 bits read,
2018 specifications for consumer SATA hard drives state the error rate to be one uncorrected bit read error in every 1014 bits.

Within a given manufacturers model the uncorrected bit error rate is typically the same regardless of capacity of the drive.

Development

thumb|Leading-edge hard disk drive [[Density (computer storage)|areal densities from 1956 through 2009 compared to Moore's law. By 2016, progress had slowed significantly below the extrapolated density trend.]]

The rate of areal density advancement was similar to Moore's law (doubling every two years) through 2010: 60% per year during 1988–1996, 100% during 1996–2003 and 30% during 2003–2010. Speaking in 1997, Gordon Moore called the increase "flabbergasting", while observing later that growth cannot continue forever. Price improvement decelerated to −12% per year during 2010–2017, as the growth of areal density slowed. The rate of advancement for areal density slowed to 10% per year during 2010–2016, and there was difficulty in migrating from perpendicular recording to newer technologies.

As bit cell size decreases, more data can be put onto a single drive platter. In 2013, a production desktop 3 TB HDD (with four platters) would have had an areal density of about 500 Gbit/in2 which would have amounted to a bit cell comprising about 18 magnetic grains (11 by 1.6 grains). Since the mid-2000s, areal density progress has been challenged by a superparamagnetic trilemma involving grain size, grain magnetic strength and ability of the head to write. In order to maintain acceptable signal-to-noise, smaller grains are required; smaller grains may self-reverse (electrothermal instability) unless their magnetic strength is increased, but known write head materials are unable to generate a strong enough magnetic field sufficient to write the medium in the increasingly smaller space taken by grains.

Magnetic storage technologies are being developed to address this trilemma, and compete with flash memory–based solid-state drives (SSDs). In 2013, Seagate introduced shingled magnetic recording (SMR), intended as something of a "stopgap" technology between PMR and Seagate's intended successor heat-assisted magnetic recording (HAMR). SMR utilizes overlapping tracks for increased data density, at the cost of design complexity and lower data access speeds (particularly write speeds and random access 4k speeds).

By contrast, HGST (now part of Western Digital) focused on developing ways to seal helium-filled drives instead of the usual filtered air. Since turbulence and friction are reduced, higher areal densities can be achieved due to using a smaller track width, and the energy dissipated due to friction is lower as well, resulting in a lower power draw. Furthermore, more platters can be fit into the same enclosure space, although helium gas is notoriously difficult to prevent escaping. Thus, helium drives are completely sealed and do not have a breather port, unlike their air-filled counterparts.

Other recording technologies are either under research or have been commercially implemented to increase areal density, including Seagate's heat-assisted magnetic recording (HAMR). HAMR requires a different architecture with redesigned media and read/write heads, new lasers, and new near-field optical transducers. HAMR shipped commercially in early 2024 after technical issues delayed its introduction by more than a decade, from earlier projections as early as 2009. HAMR's planned successor, bit-patterned recording (BPR), Western Digital's microwave-assisted magnetic recording (MAMR), also referred to as energy-assisted magnetic recording (EAMR), was sampled in 2020, with the first EAMR drive, the Ultrastar HC550, shipping in late 2020. Two-dimensional magnetic recording (TDMR) and "current perpendicular to plane" giant magnetoresistance (CPP/GMR) heads have appeared in research papers.

Some drives have adopted dual independent actuator arms to increase read/write speeds and compete with SSDs.

A 3D-actuated vacuum drive (3DHD) concept and 3D magnetic recording have been proposed.

Depending upon assumptions on feasibility and timing of these technologies, Seagate forecasts that areal density will grow 20% per year during 2020–2034.

The capacity of a hard disk drive, as reported by an operating system to the end user, is smaller than the amount stated by the manufacturer for several reasons, e.g. the operating system using some space, use of some space for data redundancy, space use for file system structures. Confusion of decimal prefixes and binary prefixes can also lead to errors.

Calculation

Modern hard disk drives appear to their host controller as a contiguous set of logical blocks, and the gross drive capacity is calculated by multiplying the number of blocks by the block size. This information is available from the manufacturer's product specification, and from the drive itself through use of operating system functions that invoke low-level drive commands. When using the C/H/S method to describe modern large drives, the number of heads is often set to 64, although a typical modern hard disk drive has between one and four platters. In modern HDDs, spare capacity for defect management is not included in the published capacity; however, in many early HDDs, a certain number of sectors were reserved as spares, thereby reducing the capacity available to the operating system. Furthermore, many HDDs store their firmware in a reserved service zone, which is typically not accessible by the user, and is not included in the capacity calculation.

For RAID subsystems, data integrity and fault-tolerance requirements also reduce the realized capacity. For example, a RAID 1 array has about half the total capacity as a result of data mirroring, while a RAID 5 array with drives loses of capacity (which equals to the capacity of a single drive) due to storing parity information. RAID subsystems are multiple drives that appear to be one drive or more drives to the user, but provide fault tolerance. Most RAID vendors use checksums to improve data integrity at the block level. Some vendors design systems using HDDs with sectors of 520 bytes to contain 512 bytes of user data and eight checksum bytes, or by using separate 512-byte sectors for the checksum data.

Formatting

Data is stored on a hard drive in a series of logical blocks. Each block is delimited by markers identifying its start and end, error detecting and correcting information, and space between blocks to allow for minor timing variations. These blocks often contained 512 bytes of usable data, but other sizes have been used. As drive density increased, an initiative known as Advanced Format extended the block size to 4096 bytes of usable data, with a resulting significant reduction in the amount of disk space used for block headers, error-checking data, and spacing.

The process of initializing these logical blocks on the physical disk platters is called low-level formatting, which is usually performed at the factory and is not normally changed in the field. High-level formatting writes data structures used by the operating system to organize data files on the disk. This includes writing partition and file system structures into selected logical blocks. For example, some of the disk space will be used to hold a directory of disk file names and a list of logical blocks associated with a particular file.

Examples of partition mapping scheme include master boot record (MBR) and GUID Partition Table (GPT). Examples of data structures stored on disk to retrieve files include the File Allocation Table (FAT) in the MS-DOS file system and inodes in many UNIX file systems, as well as other operating system data structures (also known as metadata). As a consequence, not all the space on an HDD is available for user files, but this system overhead is usually small compared with user data.

Units

{| class="wikitable floatcenter" style="width: 60%; margin-left: 1.5em;"

|+ Decimal and binary unit prefixes interpretation

The difference between the decimal and binary prefix interpretation caused some consumer confusion and led to class action suits against HDD manufacturers. The plaintiffs argued that the use of decimal prefixes effectively misled consumers, while the defendants denied any wrongdoing or liability, asserting that their marketing and advertising complied in all respects with the law and that no class member sustained any damages or injuries.

Form factors

thumb|right|8-, 5.25-, 3.5-, 2.5-, 1.8- and 1-inch HDDs, together with a ruler to show the size of platters and read-write heads

thumb|A newer 2.5-inch (63.5 mm) 6,495 MB HDD compared to an older 5.25-inch full-height 110 MB HDD

alt=Portable hard drives in enclosures|thumb|Portable hard drives in enclosures

IBM's first hard disk drive, the IBM 350, used a stack of fifty 24-inch platters, stored 3.75 MB of data (approximately the size of one modern digital picture), and was of a size comparable to two large refrigerators. In 1962, IBM introduced its model 1311 disk, which used six 14-inch (nominal size) platters in a removable pack and was roughly the size of a washing machine. This became a standard platter size for many years, used also by other manufacturers. only the latter increases the data transfer rate for a given rpm. Since data transfer rate performance tracks only one of the two components of areal density, its performance improves at a lower rate.

Other considerations

Other performance considerations include quality-adjusted price, power consumption, audible noise, and both operating and non-operating shock resistance.

Access and interfaces

thumb|right|Inner view of a 1998 [[Seagate Technology|Seagate HDD that used the Parallel ATA interface]]

thumb|right|2.5-inch SATA drive on top of 3.5-inch SATA drive, showing close-up of (7-pin) data and (15-pin) power connectors

Current hard drives connect to a computer over one of several bus types, including parallel ATA, Serial ATA, SCSI, Serial Attached SCSI (SAS), and Fibre Channel. Some drives, especially external portable drives, use IEEE 1394, or USB. All of these interfaces are digital; electronics on the drive process the analog signals from the read/write heads. Current drives present a consistent interface to the rest of the computer, independent of the data encoding scheme used internally, and independent of the physical number of disks and heads within the drive.

Typically, a DSP in the electronics inside the drive takes the raw analog voltages from the read head and uses PRML and Reed–Solomon error correction For logical damage to file systems, a variety of tools, including fsck on UNIX-like systems and CHKDSK on Windows, can be used for data recovery. Recovery from logical damage can require file carving.

A common expectation is that hard disk drives designed and marketed for server use will fail less frequently than consumer-grade drives usually used in desktop computers. However, two independent studies by Carnegie Mellon University and Google found that the "grade" of a drive does not relate to the drive's failure rate.

A 2011 summary of research, into SSD and magnetic disk failure patterns by Tom's Hardware summarized research findings as follows:

Mean time between failures (MTBF) does not indicate reliability; the annualized failure rate (AFR) is higher and usually more relevant.
HDDs do not tend to fail during early use, and temperature has only a minor effect; instead, failure rates steadily increase with age.
S.M.A.R.T. warns of mechanical issues but not other issues affecting reliability, and is therefore not a reliable indicator of condition.
Failure rates of drives sold as "enterprise" and "consumer" are "very much similar", although these drive types are customized for their different operating environments.
In drive arrays, one drive's failure significantly increases the short-term risk of a second drive failing.

, Backblaze, a storage provider, reported an annualized failure rate of two percent per year for a storage farm with 110,000 off-the-shelf HDDs with the reliability varying widely between models and manufacturers. An independent 2026 peer-reviewed analysis of the Backblaze data found that manufacturer differences remained after adjusting for drive age, capacity, form factor, and temperature. Backblaze subsequently reported in 2021 that the failure rate for HDDs and SSD of equivalent age was similar.

To minimize cost and overcome failures of individual HDDs, storage systems providers rely on redundant HDD arrays. HDDs that fail are replaced on an ongoing basis. with plans to release 50 TB drives later in 2025. 36 TB HDDs were released in 2025.. , the typical speed of a hard drive in an average desktop computer is 7,200 rpm, whereas low-cost desktop computers may use 5,900 rpm or 5,400 rpm drives. For some time in the 2000s and early 2010s some desktop users and data centers also used 10,000 rpm drives such as Western Digital Raptor but such drives have become much rarer (since the WD VelociRaptor was discontinued) and are not commonly used now, having been replaced by NAND flash-based SSDs.

Mobile (laptop) HDDs

: Smaller than their desktop and enterprise counterparts, they tend to be slower and have lower capacity, because typically has one internal platter and were 2.5" or 1.8" physical size instead of more common for desktops 3.5" form-factor. Mobile HDDs spin at 4,200 rpm, 5,200 rpm, 5,400 rpm, or 7,200 rpm, with 5,400 rpm being the most common; 7,200 rpm drives tend to be more expensive and have smaller capacities, while 4,200 rpm models usually were in older laptops and portables but are now outdated. Because of smaller platter(s), mobile HDDs generally have lower capacity than their desktop counterparts.

Consumer electronics HDDs

These drives typically spin at 5400 rpm and include:

Video hard drives, sometimes called "surveillance hard drives", are embedded into digital video recorders and provide a guaranteed streaming capacity, even in the face of read and write errors.
Drives embedded into automotive vehicles; they are typically built to resist larger amounts of shock and operate over a larger temperature range.

External and portable HDDs

: Current external hard disk drives typically connect via USB-C; earlier models use USB-B (sometimes with using of a pair of ports for better bandwidth) or (rarely) eSATA connection. Variants using USB 2.0 interface generally have slower data transfer rates when compared to internally mounted hard drives connected through SATA. Plug and play drive functionality offers system compatibility and features large storage options and portable design. , available capacities for external hard disk drives ranged from 500 GB to 10 TB. External hard disk drives are usually available as assembled integrated products, but may be also assembled by combining an external enclosure (with USB or other interface) with a separately purchased drive. They are available in 2.5-inch and 3.5-inch sizes; 2.5-inch variants are typically called portable external drives, while 3.5-inch variants are referred to as desktop external drives. "Portable" drives are packaged in smaller and lighter enclosures than the "desktop" drives; additionally, "portable" drives use power provided by the USB connection, while "desktop" drives require external power bricks. Features such as encryption, Wi-Fi connectivity, biometric security or multiple interfaces (for example, FireWire) are available at a higher cost.

File:WD External Hard Drives IMG 7899.jpg|Two 2.5" external USB hard drives

File:ST3400820AS.jpg|Seagate Hard Drive with a controller board to convert SATA to USB, FireWire, and eSATA

</gallery>

Enterprise and business segment

; Server and workstation HDDs

: thumb|[[hot-swapping|Hot-swappable HDD enclosure]]

: Typically used with multiple-user computers running enterprise software. Examples are: transaction processing databases, internet infrastructure (email, webserver, e-commerce), scientific computing software, and nearline storage management software. Enterprise drives commonly operate continuously ("24/7") in demanding environments while delivering the highest possible performance without sacrificing reliability. Maximum capacity is not the primary goal, and as a result the drives are often offered in capacities that are relatively low in relation to their cost.

;Surveillance hard drives;

: Video recording HDDs used in network video recorders.

The Federal Reserve Board has published a quality-adjusted price index for large-scale enterprise storage systems including three or more enterprise HDDs and associated controllers, racks and cables. Prices for these large-scale storage systems decreased at the rate of 30% per year during 2004–2009 and 22% per year during 2009–2014. Seagate at 43% of units had the largest market share.

<!--

Bad number:

HDD revenue in 2022 is estimated at $222 million.

-->

Competition from SSDs

thumb|HDD and SSD

HDDs are being superseded by solid-state drives (SSDs) in markets where the higher speed (up to 7 gigabytes per second for M.2 (NGFF) NVMe drives and 2.5 gigabytes per second for PCIe expansion card drives)), ruggedness, and lower power of SSDs are more important than price, since the bit cost of SSDs is four to nine times higher than HDDs. , HDDs are reported to have a failure rate of 2–9% per year, while SSDs have fewer failures: 1–3% per year.

SSDs are available in larger capacities (up to 100 TB) than the largest HDD, as well as higher storage densities (100 TB and 30 TB SSDs are housed in 2.5 inch HDD cases with the same height as a 3.5-inch HDD), although such large SSDs are very expensive.

A laboratory demonstration of a 1.33 Tb 3D NAND chip with 96 layers (NAND commonly used in solid-state drives (SSDs)) had 5.5 Tbit/in2 ), while the maximum areal density for HDDs is 1.5 Tbit/in2. The areal density of flash memory is doubling every two years, similar to Moore's law (40% per year) and faster than the 10–20% per year for HDDs. In 2025, the maximum capacity was 36 terabytes for a HDD, and 100 terabytes for an SSD. HDDs were used in 70% of the desktop and notebook computers produced in 2016, and SSDs were used in 30%. In 2025 HDDs are not found in laptops, if not very rarely, and most desktops come with an SSD only, though some still are configured with an SSD and HDD, or rarely with an HDD only.

The market for silicon-based flash memory (NAND) chips, used in SSDs and other applications, is growing faster than for HDDs. Worldwide NAND revenue grew 16% per year from $22 billion to $57 billion during 2011–2017, while production grew 45% per year from 19 exabytes to 175 exabytes.

Notes

References

</references>

External links

Hard Disk Drives Encyclopedia
Video showing an opened HD working
Average seek time of a computer disk (archived)
Timeline: 50 Years of Hard Drives. .
HDD from inside: Tracks and Zones. How hard it can be?
Hard disk hacking firmware modifications, in eight parts, going as far as booting a Linux kernel on an ordinary HDD controller board
Hiding Data in Hard Drive's Service Areas (PDF), February 14, 2013, by Ariel Berkman (archived)
Rotary Acceleration Feed Forward (RAFF) Information Sheet (PDF), Western Digital, January 2013
PowerChoice Technology for Hard Disk Drive Power Savings and Flexibility (PDF), Seagate Technology, March 2010
Shingled Magnetic Recording (SMR), HGST, Inc., 2015
The Road to Helium, HGST, Inc., 2015
Research paper about perspective usage of magnetic photoconductors in magneto-optical data storage.