Hard disk

From Wikipedia, the free encyclopedia

The inside of a hard disk displaying the read/write head traveling over the platters.

A hard disk drive (HDD, or also hard drive or the now-obsolete usage hard file) is a non-volatile data storage device that stores data on a magnetic surface layered onto hard disk platters.

Mechanics and magnetics

Top and bottom views of a Western Digital WD400 3.5" hard disk

The inside of a hard disk drive with the platter (disk) removed. To the left is the read-write arm. In the middle the electromagnets of the platter's motor can be seen.

A hard disk uses rotating platters (disks) to store data. Each platter has a smooth magnetic surface on which digital data is stored. Information is written to the disk by applying a magnetic field from a read-write head that flies very close over the magnetic surface. The magnetic medium (film) on the disk surface changes its magnetization in microscopic spots (bits) due to the head's write field. The information can be read back by a magnetoresistive (MR) read sensor which is part of the same head structure on the trailing end of the flying slider. The read sensor detects the magnetic flux emanating from the bit transitions passing underneath it through a small change of the MR sensor's electric resistance.

A typical hard disk drive design consists of a spindle on which the platters spin at a constant RPM. Moving along and between the platters on a common arm are read-write heads, with one head for each platter surface. The actuator 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.

The associated electronics control the movement of the actuator and the rotation of the disk, and perform reads and writes on demand from the disk controller. Modern drive firmware is capable of scheduling reads and writes efficiently on the disk surfaces and remapping sectors of the disk which have failed.

Also, most major hard drive and motherboard vendors now support self-monitoring, analysis, and reporting technology (S.M.A.R.T.), by which impending failures can be predicted, allowing the user to be alerted to prevent data loss.

The mostly sealed enclosure protects the drive internals from dust, condensation, and other sources of contamination. The hard disk's read-write heads fly on an air bearing which is a cushion of air only nanometers above the disk surface. The disk surface and the drive's internal environment must therefore be kept immaculate to prevent damage from fingerprints, hair, dust, smoke particles, etc., given the submicroscopic gap between the heads and disk.

The system relies on air pressure inside the drive to support the heads at their proper flying height while the disk is in motion. A hard disk drive requires a certain range of air pressures in order to operate properly. The connection to the external environment and pressure occur through a small orifice in the enclosure, usually featuring also a carbon filter on the inside (the breather filter, see below). If the air pressure is too low, there will not be enough lift for the flying head, the head will not be at the proper height, and there is a risk of head crashes and data loss. Specially manufactured sealed and pressurized drives are needed for reliable high-altitude operation, above about 10,000 feet. This does not apply to pressurized enclosures, like an airplane pressurized cabin. Modern drives include temperature sensors and adjust their operation to the operating environment.

Close-up of a hard disk head suspended above the disk platter together with its mirror image in the smooth surface of the magnetic platter.

Very high humidity for extended periods can cause accelerated wear of the drive's heads and disks by corrosion. If the drive uses "Contact Start/Stop" (CSS) technology to park its heads on the disk when not operating, increased humidity can also lead to increased stiction (the tendency for the heads to stick to the disk surface). This can cause physical damage to the disk and spindle motor and can also lead to head crash. Breather holes can be seen on all drives — they usually have a warning sticker next to them, informing the user not to cover the holes. The air inside the operating drive is constantly moving too, being swept in motion by friction with the spinning disk platters. This air passes through an internal filter to remove any leftover contaminants from manufacture, any particles or chemicals that may have somehow entered the drive, and any particles or outgassing generated internally in normal operation.

Due to the extremely close spacing between the heads and the disk surface, any contamination of the read-write heads or disk platters can lead to a head crash — a failure of the disk in which the head scrapes across the platter surface, often grinding away the thin magnetic film. For Giant Magnetoresistive (GMR) heads in particular, a minor head crash from contamination (that does not remove the magnetic surface of the disk) will still result in the head temporarily overheating, due to friction with the disk surface, and can render the data unreadable for a short period until the head temperature stabilizes (so called "thermal asperity," a problem which can partially be dealt with proper electronic filtering of the read signal). Head crashes can be caused by electronic failure, a sudden power failure, physical shock, wear and tear, corrosion, or poorly manufactured disks and heads. In most desktop and server drives, when powering down, the heads are moved to a landing zone, an area of the disk usually near its inner diameter (ID), where no data is stored. This area is called the CSS (Contact Start/Stop) zone. However, especially in old models, sudden power interruptions or a power supply failure can sometimes result in the drive shutting down with the heads in the data zone, which increases the risk of data loss. In fact, it used to be procedure to "park" the hard drive before shutting down your computer. Newer drives are designed such that either a spring (at first) and then rotational inertia in the platters is used to safely park the heads in the case of unexpected power loss.

Around 1995 IBM pioneered a technology where the landing zone is made by a precision laser process (Laser Zone Texture = LZT) producing an array of smooth nanometer-scale "bumps" in the ID landing zone, thus vastly improving stiction and wear performance. This technology is still widely in use today (2006). A few years after LZT, initially for mobile applications (i.e. laptop etc.), and later also for the other HDD types, IBM introduced "head unloading" technology, where the heads are lifted off the platters onto plastic "ramps" near the outer disk edge, thus eliminating the risk of stiction altogether and greatly improving non-operating shock performance. All HDD manufacturers use these two technologies to this day. Both have a list of advantages and drawbacks in terms of loss of storage space, relative difficulty of mechanical tolerance control, cost of implementation, etc.

Microphotograph of a hard disk head. The size of the front face (which is the "trailing face" of the slider) is about 0.3 mm × 1.0 mm. The (not visible) bottom face of the slider is about 1.0 mm × 1.25 mm (so called "nano" size) and faces the disk. One functional part of the head is the round, orange structure in the middle - the lithographically defined copper coil of the write transducer. Also note the electric connections by wires bonded to gold-plated pads.

IBM created a technology for their Thinkpad line of laptop computers called the Active Protection System. When a sudden, sharp movement is detected by the built-in motion sensor in the Thinkpad, internal hard disk heads automatically unload themselves into the parking zone to reduce the risk of any potential data loss or scratches made. Apple later also utilized this technology in their Powerbook (and MacBook) line, known as the Sudden Motion Sensor.

Spring tension from the head mounting constantly pushes the heads towards the disk. While the disk is spinning, the heads are supported by an air bearing and experience no physical contact or wear. In CSS drives the sliders carrying the head sensors (often also just called heads) are designed to reliably survive a number of landings and takeoffs from the disk surface, though wear and tear on these microscopic components eventually takes its toll. Most manufacturers design the sliders to survive 50,000 contact cycles before the chance of damage on startup rises above 50%. However, the decay rate is not linear—when a drive is younger and has fewer start-stop cycles, it has a better chance of surviving the next startup than an older, higher-mileage drive (as the head literally drags along the drive's surface until the air bearing is established). For example, the Maxtor DiamondMax series of desktop hard drives are rated to 50,000 start-stop cycles. This means that no failures attributed to the head-disk interface were seen before at least 50,000 start-stop cycles during testing.

Using rigid platters and sealing the unit allows much tighter tolerances than in a floppy disk. Consequently, hard disks can store much more data than floppy disk and access and transmit it faster. In 2006, a typical workstation hard disk might store between 80 GB and 500 GB of data, rotate at 7,200 to 10,000 rpm, and have a sequential media transfer rate of over 50 MB/s. The fastest workstation and server hard drives spin at 15,000 rpm, and can achieve sequential media transfer speeds up to and beyond 80 MB/s. Notebook hard drives, which are physically smaller than their desktop counterparts, tend to be slower and have less capacity. Most spin at only 4,200 rpm or 5,400 rpm, whereas the newest top models spin at 7,200 rpm.

An IBM hard disk, circa 2002, with the metal cover removed. The platters are highly reflective.

The platters are made from a non-magnetic material, usually glass or aluminum, and coated on both sides with a thin layer of magnetic material. Older drives used iron(III) oxide, but current drives use a thin film of a cobalt-based alloy, applied by sputtering.

The magnetic surface in the hard drive is divided into small sub-micrometre-sized magnetic regions, each of which is used to represent a single binary unit of information. Each of these magnetic regions is further subdivided into a few hundred magnetic grains. Each grain is considered to be a single magnetic domain. Each grain will thus be a magnetic dipole which points in a certain direction, creating a magnetic field around it. All of the grains in a magnetic region are expected to point in the same direction, so that the magnetic region as a whole also has a magnetic dipole moment and an associated magnetic field. ^[1]

The magnetic surface and how it operates. In this case the binary data encoded using frequency modulation.

The data is encoded through the change in magnetization at a region boundary, rather than the direction of magnetization of a region. If the magnetization reverses between two magnetic domains, this signifies one state, while no change in magnetization signifies the other state. For various reasons, the actual binary data is encoded using consecutive sequences of these two possible states, rather than the states themselves. Most hard drives use a form of Run Length Limited coding, for example. At a boundary where the magnetization reverses, magnetic field lines will be dense and perpendicular to the medium. The read head is designed to detect these changes.

In older hard drives, the read head was usually a small inductor, often filled with a paramagnetic material in order to enhance the signal. As it passes over a boundary with a magnetization reversal, the read head experiences magnetic flux, which is converted by the inductor into an electric current. Modern hard drives usually have a read head that makes use of the Giant Magnetoresistive effect, which causes the resistance of certain materials to change in response to a strong magnetic field. As this type of read head passes over a boundary with a magnetization reversal, the strong magnetic field will cause its resistance to change in a detectable way. ^[2]

Comparison of the transition width caused by Neel Spikes in continuous media and granular media, at a boundary between two magnetic regions of opposite magnetization

One reason magnetic grains are used as opposed to a continuous magnetic medium is that they reduce the space needed for a magnetic region. In continuous magnetic materials, formations called Neel spikes tend to appear. These are spikes of opposite magnetization, and form for the same reason that bar magnets will tend to align themselves in opposite directions. These cause problems because the spikes cancel each other's magnetic field out, so that at region boundaries, the transition from one magnetization to the other will happen over the length of the Neel spikes. This is called the transition width. Grains help solve this problem because each grain is a single magnetic domain. This means that the magnetic domains cannot grow or shrink to form spikes, and therefore the transition width will be on the order of the diameter of the grains. Thus, much of the development in hard drives has been in reduction of grain size. ^[1]

Access and interfaces

Hard disks are generally accessed over one of a number of bus types, including ATA (IDE, EIDE), Serial ATA, SCSI, SAS, IEEE 1394, USB, and Fibre Channel.

Back in the days of the ST-506 interface, the data encoding scheme was also important. The first ST-506 disks used Modified Frequency Modulation (MFM) encoding (which is still used on the common "1.44 MB" (1.4 MiB) 3.5-inch floppy), and transferred data at a rate of 5 megabits per second. Later on, controllers using 2,7 RLL (or just "RLL") encoding increased the transfer rate by half, to 7.5 megabits per second; it also increased drive capacity by half.

Many ST-506 interface drives were only certified by the manufacturer to run at the lower MFM data rate, while other models (usually more expensive versions of the same basic drive) were certified to run at the higher RLL data rate. In some cases, the drive was overengineered just enough to allow the MFM-certified model to run at the faster data rate; however, this was often unreliable and was not recommended. (An RLL-certified drive could run on a MFM controller, but with 1/3 less data capacity and speed.)

Enhanced Small Disk Interface (ESDI) also supported multiple data rates (ESDI drives always used 2,7 RLL, but at 10, 15 or 20 megabits per second), but this was usually negotiated automatically by the drive and controller; most of the time, however, 15 or 20 megabit ESDI drives weren't downward compatible (i.e. a 15 or 20 megabit drive wouldn't run on a 10 megabit controller). ESDI drives typically also had jumpers to set the number of sectors per track and (in some cases) sector size.

SCSI originally had just one speed, 5 MHz (for a maximum data rate of 5 megabytes per second), but later this was increased dramatically. The SCSI bus speed had no bearing on the drive's internal speed because of buffering between the SCSI bus and the drive's internal data bus; however, many early drives had very small buffers, and thus had to be reformatted to a different interleave (just like ST-506 drives) when used on slow computers, such as early IBM PC compatibles and Apple Macintoshes.

ATA drives have typically had no problems with interleave or data rate, due to their controller design, but many early models were incompatible with each other and couldn't run in a master/slave setup (two drives on the same cable). This was mostly remedied by the mid-1990s, when ATA's specification was standardised and the details began to be cleaned up, but still causes problems occasionally (especially with CD-ROM and DVD-ROM drives, and when mixing Ultra DMA and non-UDMA devices).

Serial ATA does away with master/slave setups entirely, placing each drive on its own channel (with its own set of I/O ports) instead.

FireWire/IEEE 1394 and USB(1.0/2.0) hard disks are external units containing generally ATA or SCSI drives with ports on the back allowing very simple and effective expansion and mobility. Most FireWire/IEEE 1394 models are able to daisy-chain in order to continue adding peripherals without requiring additional ports on the computer itself.

Other characteristics

• Capacity (measured in gigabytes)
• Physical size (inches)
  • Almost all hard disks today are of either the 3.5" or 2.5" varieties, used in desktops and laptops, respectively. 2.5" drives are usually slower and have less capacity but use less power and are more tolerant of movement. An increasingly common size is the 1.8" drives used in portable MP3 players and subnotebooks, which have very low power consumption and are highly shock-resistant. Additionally, there is the 1" form factor designed to fit the dimensions of CF Type II, which is usually used as storage for portable devices such as mp3 players and digital cameras. 1" was a de facto form factor lead by IBM's Microdrive, but is now generically called 1" due to other manufacturers producing similar products. There is also a 0.85" form factor produced by Toshiba for use in mobile phones and similar applications. The size designations can be slightly confusing, for example a 3.5" disk drive has a case that is 4" wide. Furthermore, server-class hard disks also come in both 3.5" and 2.5" form factors.
• Reliability: Mean Time Between Failures (MTBF)
  • SATA 1.0 drives support speeds up to 10,000 rpm and mean time between failure (MTBF) levels up to 1 million hours under an eight-hour, low-duty cycle. Fibre Channel (FC) drives support up to 15,000 rpm and an MTBF of 1.4 million hours under a 24-hour duty cycle.
• Number of I/O operations per second
  • Modern disks can perform around 50 random or 100 sequential OPS
• Power consumption (especially important in battery-powered laptops)
• audible noise (in dBA, although many still report it in bels, not decibels)
• G-shock rating (surprisingly high in modern drives)
• Transfer Rate
  • Inner Zone: from 44.2 MB/s to 74.5 MB/s
  • Outer Zone: from 74.0 MB/s to 111.4 MB/s
• Random access time: from 5 ms to 15 ms

Addressing modes

There are two ways to specify the location of a block of data on the drive.

One is by the Linear Block Address LBA , which makes it really easy to calculate how to move '300 blocks along' - just add 300. The other is "CHS" meaning, Cylinder, Head, Sector.

The exact addressing mode employed in any layer of the system is generally unimportant, suffice it to say the following operating systems use LBA at the file system level - unix ( Unix or by any other trademark or name.. eg Solaris, SunOS, SCO, FreeBSD, or SYSV or any other unix) Microsoft Dos (all) Microsoft Windows (all)

(To contrast, the Operating system that I can say used CHS addressing is Apple II's DOS and ProDOS .. but that was for a floppy disk OS. )

However, in the IBM PC, the BIOS used the CHS addressing system.

Operating Systems also are only designed and tested with available sized hard drives, and the huge increase in size of hard drives means that the operating sytems ability to handle large drives is also tested.

There have been particular limitations in various PC compatible systems in that they have not been able "see" all of large hard drives ( large means larger than was avaiable when the computer bios and operating system was programmed )

IBM PC hard drive addressing methods

CHS (cylinder, head, sector) describes the disk space in terms of its physical dimensions, data-wise; this is the traditional way of accessing a disk on IBM PC compatible hardware, and while it works well for floppies (for which it was originally designed) and small hard disks, it caused problems when disks started to exceed the design limits of the PCs CHS bios.

Note: Microsoft designed its partition table to store both CHS and LBA addresses, and to use LBA addresses only. By that way, Microsoft does not impose limitations of the CHS addressing system in anyway.

When drives larger than 504 MiB began to appear in the mid-1990s, many system BIOSes had problems communicating with them, requiring LBA BIOS upgrades or special driver software to work correctly. This CHS limit for the IBM PC family was the 1024 cylinders, 16 heads and 63 sectors limit. On a drive with 512-byte sectors, this comes to 504 MiB (528 megabytes). This limit occurs when requiring the bios CHS address be the same as used by the IDE interface . The combination of the 16 head limit of the IDE interface, and the 1024 cylinder and 63 sector limit of the BIOS meant that the geometry was limited to 1024 cylinders, 16 heads and 63 sectors, which for 512 bytes per sector means 504 megabytes..

The solution was to modify - either directly, or by loading compatibility software such as "ontrack disk manager" - the bios to allow the "hard drive geometry" (in terms of CHS) to be translated, so the bios reports that the drive had one CHS arrangement to the operating system (the OS CHS) , and takes commands from the operating system based on the OS CHS, but issues commands to the drive bases on another CHS arrangement. And thus it must translate between the two different geometries.

The simplest way to do this translation was to make the OS CHS specification was to increase the number of heads in the OS CHS and reduce the number of cylinders, with the aim of reducing the number of cylinders to less than 1024. This works up to 8 gigabytes, because the bios limit of 256 heads was run into at that point.

To get past the 8 gigabyte limit, the BIOS was extended, and thus the operating system had to be aware of the bios extensions. That limits DOS (except as part of windows 98 )to the first 8 gigabytes of the hard drive. The bios extension allows the operating system or program to issue hard drive commands in terms of a 28 bit LBA address,and the standard misnamed as LBA32.

IBM PC's then started to have two choices for translation - Large or LBA.

Even after the introduction of LBA, similar limitations reappeared several times over the following years: at 2.1, 4.2, 8.4, 32, and 128 GiB.

The 2.1, 4.2 and 32 GiB limits are bios bugs that affected SOME IBM PC and clone computers. The BIOS writers failed to handle the appearance of larger drives than they tested with, and motherboard manufacturers refused to pay for the development and release of upgraded bios to solve the problem. Fitting a drive larger than the limit resulted in a PC that refuses to boot, unless the drive includes special jumpers to make it appear as a smaller capacity. (For the 32 gigabyte limit, many IDE drives have a a command that tells them to return to operating as a large drive even though the jumper is set to limit it to 32 gigabytes. Suitiable software would be installed on the computer to be started before the Operating system, where it can rectify the OS (temporarily - until the next reboot) and then tell the drive to operate as a large drive again and so the 32 gigabyte limit could be solved.

The 8.4 and 128 GiB limits are generally soft limits: the PC simply ignores the extra capacity and reports a drive of the maximum size it is able to communicate with. It is possible that specific bios versions also locked up at these limits, but that is far less common.

The 128GiB is the limit of the original IDE specification interface. The solution is to use ATA's LBA48, which is a new addressing mode for new commands, that allows sending a 48 bit LBA address to the hard drive or other device.

Because SCSI interfaces have always used LBA addressing,and the OS's required a CHS geomoetry , and OS's would make CHS addressed calls to bios, the SCSI interface's bios would have to nominate a CHS address and translate CHS addresses to LBA addresses.Since LBA32 aware OS's, this has become a thing of the past.

See also: hard disk drive partitioning, master boot record, file system, drive letter assignment, boot sector.

Note: it is a myth that ATA drives power up in "CHS mode". There is no such "CHS mode". or "LBA mode". These are addressing modes, not "modes of operation". If you write an address to the ATA drive, it is marked as either an LBA address or a CHS address. If the bios or operating system is programmed to issue LBA addresses, it can issue them at will, and intermingle any commands using LBA addresses with commands using CHS addresses quite easily. At the IDE interface level, and on the IDE cable, the CHS address can address 120 Gigabytes, and so can the LBA address. The 8 gigiabyte limit is only a result of the old BIOS calls being limitted.

Manufacturers

Hitachi 2.5 inch laptop hard drive

Most of the world's hard disks are now manufactured by just a handful of large firms: Seagate, Maxtor (acquired by Seagate in 2006), Western Digital, Samsung, and Hitachi, the former drive manufacturing division of IBM. Fujitsu continues to make mobile- and server-class drives but exited the desktop-class market in 2001. Toshiba is a major manufacturer of 2.5-inch and 1.8-inch notebook drives.

Firms that have come and gone

Dozens of former hard drive manufacturers have gone out of business, merged, or closed their hard drive divisions; as capacities and demand for products increased, profits became hard to find, and there were shakeouts in the late 1980s and late 1990s. The first notable casualty of the business in the PC era was Computer Memories Inc. or CMI; after the 1985 incident with the faulty 20 MB AT drives^[3], CMI's reputation never recovered, and they exited the hard drive business in 1987. Another notable failure was MiniScribe, who went bankrupt in 1990 after it was found that they had "cooked the books" and inflated sales numbers for several years. Many other smaller companies (like Kalok, Microscience, LaPine, Areal, Priam and PrairieTek) also did not survive the shakeout, and had disappeared by 1993; Micropolis was able to hold on until 1997, and JTS, a relative latecomer to the scene, lasted only a few years and was gone by 1999, after attempting to manufacture hard drives in India using a 2nd hand factory. Rodime was also an important manufacturer during the 1980s, but stopped making drives in the early 1990s amid the shakeout and now concentrates on technology licensing; they hold a number of patents related to 3.5-inch form factor hard drives.

There have also been a number of notable mergers in the hard disk industry:

• Tandon sold its disk manufacturing division to Western Digital (which was then a controller maker and ASIC house) in 1988; by the early 1990s Western Digital disks were among the top sellers.
• In 1995, Conner Peripherals announced a merger with Seagate (which had earlier bought Imprimis from CDC), which was completed in early 1996.
• JTS infamously merged with Atari in 1996, giving it the capital it needed to bring its drive range into production - and then to achieve complete failure in any market JTS or Atari were in.

• In 2003, following the controversy over the mass failures of its Deskstar 75GXP (colloquially known as "deathstar") range, hard disk pioneer IBM sold the majority of its disk division to Hitachi, who renamed it Hitachi Global Storage Technologies (HGST).
• Quantum bought DEC's storage division in 1994, and later (2000) sold the hard disk division to Maxtor to concentrate on tape drives.
• In March 2006 US DoJ approval was given for Maxtor to be acquired by Seagate - for USD1.9 billion. (http://www.antitrustlawblog.com/article-entry-eases-merger-approval-of-hardware-and-software-firms.html)

Capacity measurements

Hard drive manufacturers typically specify drive capacity using 'SI prefixes', that is, the SI definition of the prefixes "giga" and "mega." This is largely for historical reasons, since disk drive storage capacities exceeded millions of bytes ^[4] long before there were standard 'binary prefixes' (even before there were the SI prefixes, 1960). The IEC only standardized 'binary prefixes' in 1999. As it turned out, many practitioners early on in the computer and semiconductor industries adopted the term kilobyte to describe 2¹⁰ (1024) bytes because 1024 is "close enough" to the metric prefix kilo, which is defined as 10³ or 1000. Sometimes this non-SI conforming usage include a qualifier such as '"1 kB = 1,024 Bytes"' but this qualifier was frequently omitted, particularly in marketing literature. This trend became habit and continued to be applied to the prefixes "mega," "giga," "tera," and even "Peta (prefix)."

Operating systems and their utilities, particularly visual operating systems such as Microsoft's various Windows operating systems frequently report capacity using binary prefixes which results in a discrepancy between the drive manufacturer's stated capacity and the system's reported capacity. Obviously the difference becomes much more noticeable in reported capacities in the multiple gigabyte range, and users will often notice that the volume capacity reported by their OS is significantly less than that advertised by the hard drive manufacturer. For example, Microsoft's Windows 2000 reports drive capacity both in decimal to 12 or more significant digits and with binary prefixes to 3 significant digits. Thus a disk drive specified by a drive manufacturer as a '30 GB' drive has its capacity reported by Windows 2000 both as '30,065,098,568 bytes' and '28.0 GB'. The drive manufacturer has used the SI definition of "giga," 10⁹ and can be considered as an approximation of a gibibyte. Since utilities provided by the operating system probably define a gigabyte as 2³⁰, or 1073741824, bytes, the reported capacity of the drive will be closer to 28.0 GB, a difference of well over 7%. For this very reason, many utilities that report capacity have begun to use the aforementioned IEC standard binary prefixes (e.g. KiB, MiB, GiB) since their definitions are unambiguous.

Many people mistakenly attribute the discrepancy in reported and specified capacities to reserved space used for file system and partition accounting information. However, for large (several GiB) filesystems, this data rarely occupies more than a few MiB, and therefore cannot possibly account for the apparent "loss" of tens of GBs.

Hard disk usage

From the original use of a hard drive in a single computer, techniques for guarding against hard disk failure were developed such as the redundant array of independent disks (RAID). Hard disks are also found in network attached storage (NAS) devices, but for large volumes of data are most efficiently used in a storage area network (SAN). Applications for hard disk drives expanded to include video recorders, audio players, digital organizers, and digital cameras. In 2005 the first cellular telephones to include hard disk drives were introduced by Samsung and Nokia.

History

Old IBM Hard Disk Drive.

The first hard disk drive was the IBM 350 Disk File, invented by Reynold Johnson and introduced in 1955 with the IBM 305 computer. This drive had fifty 24 inch platters, with a total capacity of five million characters. A single head was used for access to all the platters, making the average access time very slow.

The IBM 1301 Disk Storage Unit Control System Meganical International System, announced in 1961, introduced the usage of a separate head for each data surface.

The first disk drive to use removable media was the IBM 1311 drive, which used the IBM 1316 disk pack to store two million characters.

In 1973, IBM introduced the 3340 "Winchester" disk system, the first to use a sealed head/disk assembly (HDA). Almost all modern disk drives now use this technology, and the term "Winchester" became a common description for all hard disks, though generally falling out of use during the 1990s. Project head designer/lead designer Kenneth Haughton named it after the Winchester 30-30 rifle after the developers called it the "30-30" because of its two 30 MB spindles^[5].

For many years, hard disks were large, cumbersome devices, more suited to use in the protected environment of a data center or large office than in a harsh industrial environment (due to their delicacy), or small office or home (due to their size and power consumption). Before the early 1980s, most hard disks had 8-inch (20 cm) or 14-inch (35 cm) platters, required an equipment rack or a large amount of floor space (especially the large removable-media drives, which were often referred to as "washing machines"), and in many cases needed high-amperage or even three-phase power hookups due to the large motors they used. Because of this, hard disks were not commonly used with microcomputers until after 1980, when Seagate Technology introduced the ST-506, the first 5.25-inch hard drive, with a capacity of 5 megabytes. In fact, in its factory configuration the original IBM PC (IBM 5150) was not equipped with a hard drive.

5.25" MFM 110 MB hard drive, (2.5" IDE 6495 MB hard drive, cent & penny for comparison)

Most microcomputer hard disk drives in the early 1980s were not sold under their manufacturer's names, but by OEMs as part of larger peripherals (such as the Corvus Disk System and the Apple ProFile). The IBM PC/XT had an internal hard disk, however, and this started a trend toward buying "bare" drives (often by mail order) and installing them directly into a system. Hard disk makers started marketing to end users as well as OEMs, and by the mid-1990s, hard disks had become available on retail store shelves.

While internal drives became the system of choice on PCs, external hard drives remained popular for much longer on the Apple Macintosh and other platforms. Every Mac made between 1986 and 1998 has a SCSI port on the back, making external expansion easy; also, "toaster" Macs did not have easily accessible hard drive 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. External SCSI drives were also popular with older microcomputers such as the Apple II series, and were also used extensively in Servers, a usage which is still popular today. The appearance in the late 1990s of high-speed external interfaces such as USB and FireWire has made external disk systems popular among regular users once again, especially for users who move large amounts of data between two or more locations, and most hard disk makers now make their disks available in external cases.

The capacity of hard drives has grown exponentially over time. With early personal computers, a drive with a 20 megabyte capacity was considered large. In the latter half of the 1990s, hard drives with capacities of 1 gigabyte and greater became available. As of 2006, the "smallest" desktop hard disk still in production has a capacity of 40 gigabytes, while the largest-capacity internal drives are a 3/4 terabyte (750 gigabytes), with external drives at or exceeding one terabyte by using multiple internal disks.

Drive families used in personal computers

Notable drive families include:

• MFM (Modified Frequency Modulation) drives required that the controller electronics be compatible with the drive electronics.
• RLL (Run Length Limited) drives were named after the modulation technique that made them an improvement on MFM. They required large cables between the controller in the PC and the hard drive, the drive did not have a controller, only a modulator/demodulator.

• ESDI (Enhanced Small Disk Interface) was an interface developed by Maxtor to allow faster communication between the PC and the disk than MFM or RLL.

• IDE (Integrated Drive Electronics) was later renamed to ATA, and then PATA.

The name comes from the way early families had the hard drive controller external to the drive. Moving the hard disk controller from the interface card to the drive helped to standardize interfaces, reducing cost and complexity.

The data cable was originally 40 conductor, but UDMA modes from the later drives requires using an 80 conductor cable (note that the 80 conductor cable still uses a 40 position connector.)

The interface changed from 40 pins to 39 pin. The missing pin acts as a key to prevent incorrect insertion of the connector, a common cause of drive and controller damage.

• SCSI (Small Computer System Interface) was an early competitor with ESDI, originally named SASI for Shugart Associates. SCSI drives were standard on servers, workstations, and Apple Macintosh computers through the mid-90s, by which time most models had been transitioned to IDE (and later, SATA) family drives. Only in 2005 did the capacity of SCSI drives fall behind IDE drive technology, though the highest-performance drives are still available in SCSI and Fibre Channel only. The length limitations of the data cable allows for external SCSI devices. Originally SCSI data cables used single ended data transmission, but server class SCSI could use differential transmission, and then Fibre Channel (FC) interface, and then more specifically the Fibre Channel Arbitrated Loop (FC-AL), connected SCSI hard drives using fibre optics. FC-AL is the cornerstone of storage area networks, although other protocols like iSCSI and ATA over Ethernet have been developed as well.

• SATA (Serial ATA). The SATA data cable has only one data pair for the differential transmission of data to the device, and one pair for receiving from the device. That requires that data be transmitted serially. The same differential transmission system is used in RS485, Appletalk,USB, Firewire,and differential SCSI. In 2005/2006 parlance, the 40 pin IDE/ATA is called "PATA" or parallel ATA, which means that there are 16 bits of data transferred in parallel at a time on the data cable.

• SAS (Serial Attached SCSI). The SAS is a new generation serial communication protocol for devices designed to allow for much higher speed data transfers and is compatible with SATA. SAS uses serial communication instead of the parallel method found in traditional SCSI devices but still uses SCSI commands for interacting with SAS

EIDE was an unofficial update (by Western Digital) to the original IDE standard, with the key improvement being the use of DMA to transfer data between the drive and the computer, an improvement later adopted by the official ATA standards. DMA is used to transfer data without the CPU or program being responsible to transfer every word. That leaves the CPU/program/operating system to do other tasks while the data transfer occurs.

Timeline of capacity and other technical improvements

• (CS) denotes an improvement in the consumer market.

1950s

• 1956 - first commercial hard disk, the IBM 350 RAMAC disk drive, 5 megabyte.

1960s

1970s

• 1973 - The IBM 3340 storage system held 1.7 MB per square inch

1980s

• 1980 - first 5.25-inch Winchester drive, the Shugart ST-506, 5 megabyte (CS)
• 1982 - Hitachi 1.2 GB H-8598 consisted of 10 14-inch platters and two read-write heads
• 1986 - Standardization of SCSI
• 1989 - Jimmy Zhu and H. Neal Bertram from UCSD proposed exchange decoupled granular microstructure for thin film disk storage media, still used today.

1990s

• 1990 - MR Technology introduced (=MagnetoResistive read sensor).
• 1991 - 2.5-inch 100 megabyte hard drive
• 1991 - PRML Technology (Digital Read Channel with 'Partial Response Maximum Likelihood' algorithm)
• 1994 - IBM introduces Laser Textured Landing Zones (LZT)
• 1995 - 2 gigabyte hard drive
• 1996 - IBM introduces GMR (Giant MR) Technology for read sensors
• 1997 - 10 gigabyte hard drive; Load/Unload Technology introduced in laptop HDDs
• 1998 - UltraDMA/33 and ATAPI standardized
• 1999 - IBM releases the Microdrive in 170 MB and 340 MB capacities

2000s

• 2002 - 137 GB addressing space barrier broken
• 2003 - Serial ATA introduced
• 2005 - First 500 GB hard drive shipping (Hitachi GST)
• 2005 - Serial ATA 3G standardized
• 2005 - Seagate introduces Tunnel MagnetoResistive Read Sensor (TMR) and Thermal Spacing Control
• 2005 - Introduction of faster SAS (Serial Attached SCSI)
• 2005 - Perpendicular recording introduced in consumer HDDs (Toshiba)
• 2006 - First 750 GB hard drive (Seagate)
• 2006 - First 200 GB 2.5" Hard Drive utilizing Perpendicular recording (Toshiba)
• 2006 - Seagate announces research into nanotube-lubricated HDDs with capacities of several terabits per square inch, making possible a 7.5 Terabyte 3.5" HDD^[6]
• 2006 - Western Digital produces world's first hard disk with a transparent polycarbonate cover

See also

• Disk storage
• Early IBM disk storage
• External hard drive
• File system
• Hybrid drive
• Kryder's law
• PRML
• Superparamagnetic effect

References

1. ^ ^a b Jorgensen, Finn. “The Complete Handbook of Magnetic Recording” McGraw-Hill, 1996
2. ^ Bertram, H Neal. “Theory of Magnetic Recording” Cambridge University Press 1994
3. ^ Apparently the CMI drives suffered from a higher soft error rate than IBM's other suppliers (Seagate and MiniScribe) but the bugs in Microsoft's DOS Operating system may have turned these recoverable errors into hard failures. At some point, possibly MSDOS 3.0, soft errors were reported as drive hard errors and a subsequent Microsoft patch turned soft errors into corrupted memory with unpredictable results (euphemistically, "crashes"). MSDOS 3.3 apparently resolved this series of problems but by that time it was too late for CMI.
4. ^ The first disk drive, the IBM RAMAC in 1956 had a capacity of 5 million 6 bit characters.
5. ^ http://www.ibm.com/ibm/history/exhibits/storage/storage_3340.html
6. ^ http://www.dailytech.com/article.aspx?newsid=3122&ref=y

External links

Wikimedia Commons has media related to:

Hard disk

• TechEncyclopedia about Hard Disks
• Inside a hard drive
• Hard disk interfaces pinouts
• Technical Whitepaper (non marketing): Comprehensive Overview of Modern Recording Techniques and Hard Disk Drive Technologies
• Windows NT Server Resource Kit: Disk Management Basics (See section "About Disks and Disk Organization")
• Behold the God Box - Less's Law and future implications of massive cheap hard disk storage
• How Hard Disks Work
• Digest 2005 - State of the art hard disk drives in 2005
• Laptop’s Hard Drives: Speed Also Matters
• 12.8 petabyte cubic cm hard drive
• War of the Disks: Hard Disk Drives vs. Flash Solid State Disks Despatches from the magneto / flash wars