Solid-state storage (SSS) isnon-volatile computer storage that has no moving parts; it uses onlyelectronic circuits. Thissolid-state design dramatically differs from the commonly used competing technology ofelectromechanicalmagnetic storage which uses movingmedia coated withmagnetic material.[1][2]Generally, SSS is much faster but more expensive per unit of storage.[3][4][5]
SSSdevices typically useflash memory, but some use battery-backedrandom-access memory (RAM). Devices come in various types, form factors, storage sizes, andinterfacing options to satisfy application requirements for many computer systems and appliances.[4]
Historically, computer systemsecondary storage has been implemented to leverage magnetic properties of surface coatings applied to rotatingplatters (inhard disk drives andfloppy disks) or linearly moving strips ofplastic film (intape drives). Pairing such magnetic media withread/write heads allowsdata to be written by separately magnetizing small sections of theferromagnetic coating, and read later by detecting the transitions in magnetization. For the data to be read or written, exact sections of the magnetic media need to pass under the read/write heads that flow closely to the media surface; as a result, reading or writing data imposes delays required for the positioning of magnetic media and heads, with the delays differing depending on the actual technology.[6]
Over time, advancements incentral processing unit (CPU) speed has driveninnovation in secondary storage technology.[7] One such innovation,flash memory, is a non-volatile storage medium that can be electrically erased and reprogrammed.
Solid-state storage typically uses theNAND type of flash memory, which can be accessed in chunks smaller than the entire capacity of the device. The minimal chunk size (page) for a read operation is much smaller than the minimal chunk size (block) for a write/erase operation, resulting in an undesirable phenomenon calledwrite amplification that limits the random write performance and write endurance of a flash-based storage device.
Some solid-state storage devices use (volatile) RAM and a battery that preserves the contents of the RAM without system power as long as the battery continues to provide power. Flash-based storage does not suffer the limitation of a battery, but RAM-backed storage is faster and does not experience write amplification.[3][8][9]
As a result of having no moving mechanical parts, solid-state storage has no data accesslatency required to move the media as in an electromechanical storage device. This allows for significantly higherI/O operation rates (IOPS). Additionally, solid-state storage consumes less power, has better physical shock resistance, and produces less heat and no vibration.
Compared to electromechanical, solid-state devices tend to cost more for the same capacity, and generally are not available in the larger capacities available for electromechanical.
Also, flash-based devices experiencememory wear that reducesservice life resulting from limitations of flash memory that impose a finite number ofprogram–erase cycles used to write data. Due to this, solid-state storage is frequently used forhybrid drives, in which solid-state storage serves as acache for frequently accessed data instead of being a complete substitute for traditional secondary storage.[4][5][10]
Asolid-state drive (SSD) provides secondary storage for relatively complex systems includingpersonal computers,embedded systems,portable devices,large servers andnetwork-attached storage (NAS). To satisfy such a wide range of uses, SSDs are produced with various features, capacities,interfaces and physical sizes and layouts.[4]
Solid-state storage is also available asremovable media. Amemory card, such asMMC andSD, is shaped to fit into a special port for the card. AUSB flash drive connects viaUSB and is not constrained by shape and size as a card is.[2][11]
In general, an SSD uses a relatively fast interface such asSerial ATA (SATA) orPCI Express (PCIe) paired with a logical device interface such asAHCI orNVM Express (NVMe). Removable devices use simpler, slower interfaces such as theone-bit SD interface orSPI.[12][13]
| Key terminology | |||||
|---|---|---|---|---|---|
| Flash manufacturers | |||||
| Controllers |
| ||||
| SSD manufacturers | |||||
| Interfaces |
| ||||
| Configurations | |||||
| Related organizations | |||||
