Mass storage

In computing, mass storage refers to the storage of large amounts of data in a persisting and machine-readable fashion. In general, the term "mass" in "mass storage" is used to mean "large" in relation to contemporaneous hard disk drives, but it has also been used to mean "large" relative to the size of primary memory as for example with floppy disks on personal computers.

Devices and/or systems that have been described as mass storage include tape libraries, RAID systems, and a variety of computer drives such as hard disk drives (HDDs), magnetic tape drives, magneto-optical disc drives, optical disc drives, memory cards, and solid-state drives (SSDs). It also includes experimental forms like holographic memory. Mass storage includes devices with removable and non-removable media. It does not include random access memory (RAM).

There are two broad classes of mass storage: local data in devices such as smartphones or computers, and enterprise servers and data centers for the cloud. For local storage, SSDs are on the way to replacing HDDs. Considering the mobile segment from phones to notebooks, the majority of systems today is based on NAND Flash. As for Enterprise and data centers, storage tiers have established using a mix of SSD and HDD.

Definition
The notion of "large" amounts of data is of course highly dependent on the time frame and the market segment, as storage device capacity has increased by many orders of magnitude since the beginnings of computer technology in the late 1940s and continues to grow; however, in any time frame, common mass storage devices have tended to be much larger and at the same time much slower than common realizations of contemporaneous primary storage technology.

Papers at the 1966 Fall Joint Computer Conference (FJCC) used the term mass storage for devices substantially larger than contemporaneous hard disk drives. Similarly, a 1972 analysis identified mass storage systems from Ampex (Terabit Memory) using video tape, Precision Industries (Unicon 690-212) using lasers and International Video (IVC-1000) using video tape and states "In the literature, the most common definition of mass storage capacity is a trillion bits.". The first IEEE conference on mass storage was held in 1974 and at that time identified mass storage as "capacity on the order of 1012 bits" (1 gigabyte). In the mid-1970s IBM used the term to in the name of the IBM 3850 Mass Storage System, which provided virtual disks backed up by Helical scan magnetic tape cartridges, slower than disk drives but with a capacity larger than was affordable with disks. The term mass storage was used in the PC marketplace for devices, such as floppy disk drives, far smaller than devices that were not considered mass storage in the mainframe marketplace.

Mass storage devices are characterized by:


 * Sustainable transfer speed
 * Seek time
 * Cost
 * Capacity

Storage media
Magnetic disks are the predominant storage media in personal computers. Optical discs, however, are almost exclusively used in the large-scale distribution of retail software, music and movies because of the cost and manufacturing efficiency of the molding process used to produce DVD and compact discs and the nearly-universal presence of reader drives in personal computers and consumer appliances. Flash memory (in particular, NAND flash) has an established and growing niche as a replacement for magnetic hard disks in high performance enterprise computing installations due to its robustness stemming from its lack of moving parts, and its inherently much lower latency when compared to conventional magnetic hard drive solutions. Flash memory has also long been popular as removable storage such as USB sticks, where it de facto makes up the market. This is because it scales better cost-wise in lower capacity ranges, as well as its durability. It has also made its way onto laptops in the form of SSDs, sharing similar reasons with enterprise computing: Namely, markedly high degrees of resistance to physical impact, which is again, due to the lack of moving parts, as well as a performance increase over conventional magnetic hard disks and markedly reduced weight and power consumption. Flash has also made its way onto cell phones.

The design of computer architectures and operating systems are often dictated by the mass storage and bus technology of their time.

Usage
Mass storage devices used in desktop and most server computers typically have their data organized in a file system. The choice of file system is often important in maximizing the performance of the device: general purpose file systems (such as NTFS and HFS, for example) tend to do poorly on slow-seeking optical storage such as compact discs.

Some relational databases can also be deployed on mass storage devices without an intermediate file system or storage manager. Oracle and MySQL, for example, can store table data directly on raw block devices.

On removable media, archive formats (such as tar archives on magnetic tape, which pack file data end-to-end) are sometimes used instead of file systems because they are more portable and simpler to stream.

On embedded computers, it is common to memory map the contents of a mass storage device (usually ROM or flash memory) so that its contents can be traversed as in-memory data structures or executed directly by programs.