You are here
Online SNIA Dictionary
[Hardware]
A card form factor and connector interface defined by the PCI-SIG that is most commonly used for solid state storage.
M.2 interfaces to PCI Express, SATA-IO, and USB.
[Network] [Data Security]
1. Acronym for Media Access Control.
2. Acronym for Message Authentication Code.
3. Acronym for Mandatory Access Control.
[Data Security]
Residual magnetic information remaining on a magnetic medium after the medium has been degaussed.
[Storage System]
Shorthand for Massive Array of Idle Disks.
[Computer System]
Malicious software designed specifically to damage or disrupt a system, attacking confidentiality, integrity and/or availability. [ISO/IEC 27033-1]
Examples are a virus, worm, Trojan horse, spyware, adware or other entity that infects a system.
[Storage System]
Acronym for Medium Auxiliary Memory.
[Network]
Acronym for Metropolitan Area Network.
[Management]
The syntax and formal description of the classes and associations in a CIM schema.
MOF can be translated to XML using a Document Type definition published by the DMTF.
[Management]
A structure and set of services exposed for use by management applications and other services in the management environment.
[Standards]
A provision in a standard that must be supported in order for an implementation of the standard to be compliant with the standard.
[Data Security]
A type of access control based on the security clearance of the subject and the classification of the object.
The control is mandatory in that a subject is not allowed to change either their security clearance or the classification of an object.
[Operating System]
The assignment of virtual addresses to a portion of a file (e.g., POSIX).
[Storage System]
Conversion between two address spaces, such as the conversion between physical disk block addresses and the block addresses of the virtual disks presented to operating environments by control software.
[Storage System]
A virtual disk block address of some significance to a disk array's mapping algorithms.
The first and last blocks of a user data space stripe or check data stripe are mapping boundaries.
[Storage System]
A storage system comprising an array of disk drives that are powered down individually or in groups when not required.
MAID storage systems reduce the power consumed by a storage array, at the cost of increased Mean Time To Data.
[Storage System]
Shorthand for Maximum Time to First Data.
[Storage System]
The maximum time required to start receiving data from a storage system to satisfy a read request for arbitrary data.
Max TTFD is used in the industry and in the SNIA Emeraldâ„¢ Power Efficiency Measurement Specification to distinguish classes of storage systems.
[Network]
The largest amount of data that it is permissible to transmit as one unit according to a protocol specification.
The Ethernet MTU is 1536 eight bit bytes. The Fibre Channel MTU is 2112 eight bit bytes.
[Computer System]
Shorthand for megabits per second, a measure of bandwidth or data transfer rate.
[Data Security]
A message-digest algorithm producing a 128-bit digest.
This algorithm is obsolete.
[General]
The expected time between consecutive failures in a system or component. [ISO/IEC/IEEE 24765]
[General]
The average time from start of use to first failure in a large population of identical systems, components, or devices.
[Storage System]
The average time required to stage a data stream from storage and make it available for reading by a client.
[Storage System]
The average time from startup until a component failure causes a permanent loss of user data in a large population of storage elements.
Mean time to data loss is similar to MTBF for disks and tapes, but is likely to differ in RAID arrays, where redundancy can protect against data loss due to component failures.
[Storage System]
The average time from startup until a component failure causes a loss of timely user data access in a large population of storage elements.
Loss of availability does not necessarily imply loss of data; for some classes of failures, (e.g., failure of non-redundant intelligent storage controllers), data remains intact, and can again be accessed after the failed component is replaced.
[General]
The average time between a failure and completion of repair in a large population of identical systems, components, or devices.
Mean time to repair comprises all elements of repair time, from the occurrence of the failure to restoration of complete functionality of the failed component. This includes time to notice and respond to the failure, time to repair or replace the failed component, and time to make the replaced component fully operational. In mirrored and RAID arrays, for example, the mean time to repair a disk failure includes the time required to reconstruct user data and check data from the failed disk on the replacement disk.
[Standards]
In a standard, a control field or bit that must be correctly interpreted by a receiver.
Control fields are either meaningful or "not meaningful." In the latter case they must be ignored.
[Services]
Metered dispensation of resources appropriate to a given type of service (e.g., storage, processing, bandwidth, and active user accounts), such that usage can be monitored, controlled, reported and billed.
[General]
Shorthand for 1,048,576 (220) bits.
Binary notation is most commonly used for semiconductor memory sizes.
See also Megabit.
[General]
Shorthand for 1,048,576 (220) bytes.
Binary notation is most commonly used for semiconductor memory sizes.
See also Megabyte.
[Storage System] [Network]
1. Synonym for storage media.
2. A physical link on which data is transmitted between two points.
[Data Recovery]
A machine-readable identifier written on a removable storage volume that remains constant throughout the volume's life.
[Data Recovery]
A backup software component responsible for tracking the location, contents, and state of removable storage volumes.
[Storage System]
Synonym for robotic media handler.
[Data Security]
A general term referring to the actions taken to render data written on media unrecoverable by both ordinary and extraordinary means. [NIST SP 800-88]
Making data unrecoverable by extraordinary means usually involves total destruction of the media.
[Storage System]
A robotic media handler in which media must be moved sequentially by the robot.
[Storage System]
A non-volatile memory (other than the recording medium) residing in a storage element (e.g., a tape cartridge) that is accessible to the storage device.
[SCSI]
Synonym for robotic media handler.
[Data Communication]
One million baud (elements of transmitted information) per second, including data, signaling and overhead.
[Computer System]
1,000,000 (106) bits.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,048,576, i.e., 220) common in computer system and software literature.
See also Mebibit.
[Computer System]
1,000,000 (106) bytes.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,048,576, i.e., 220) common in computer system and software literature.
See also Mebibyte.
[SCSI]
The transfer of one million data units per second.
The term is used to describe the characteristics of parallel I/O interconnects like SCSI, for which the data transfer rate depends upon the amount of data transferred in each data cycle. See SCSI, fast SCSI, Ultra SCSI, Ultra2 SCSI, wide SCSI.
[Data Security]
A method of sanitization that uses extreme heat to cause a device or component to change state, from solid to liquid and/or gas, in an approved facility. [ISO/IEC 27040]
[Storage System]
A disk that is in use as a member of a disk array.
[Data Security]
A cryptographic hash appended to a message to allow a receiver to ensure that the contents have not been changed in transit.
[Data Security]
Synonym for hash value.
[Data Security]
An algorithm that produces a secure hash.
[Data Management]
Data associated with other data.
[Services]
Providing a measuring capability appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts).
[Network]
A network that connects nodes distributed over a metropolitan (city-wide) area as opposed to a local area (campus) or wide area (national or global).
From a storage perspective, MANs are of interest because there are MANs over which block storage protocols (e.g., ESCON, Fibre Channel) can be carried natively, whereas most WANs that extend beyond a single metropolitan area do not currently support such protocols.
[Management]
Acronym for Management Information Base.
[Data Management]
A movement of data or information between information systems, formats, or media.
Migration is performed for reasons such as possible decay of storage media, obsolete hardware or software (including obsolete data formats), changing performance requirements (see tiered storage), the need for cost efficiencies etc.
[Network]
Acronym for Multipurpose Internet Mail Extensions.
[Data Recovery]
The process of making the contents of a split mirror identical with the contents of the storage devices from which the mirror was split.
Mirror resynchronization may entail copying the entire contents of the storage devices, or when fast mirror resynchronization is used, only the data items changed in the original since the instant of splitting.
[Storage System]
Common term for a disk array that implements RAID Level 1, or mirroring.
[Storage System]
A configuration of storage in which two or more identical copies of data are maintained on separate media; also known as RAID Level 1, disk shadowing, real-time copy, and T1 copy.
[Storage System]
The disks of a mirrored array.
[Management]
Acronym for Multipath Management API.
[Network]
Distortion in the optical signal transmitted through a multimode fiber caused by different time delays for the various modes of propagation, resulting in a smearing of the signal edges that increases with the length of the fiber, thereby limiting the maximum length as a function of the data rate.
[Data Security]
An algorithm for the cryptographic transformation of data that applies a symmetric key block cipher algorithm to one or more blocks of data.
[Management]
A set of entities and the relationships between them that define the semantics, behavior and state of that set.
[Management]
A language for describing the concepts of an information or data model.
A popular modeling language in use today is UML (Unified Modeling Language).
[Management]
Acronym for Managed Object Format.
[Computer System]
A program that executes in an operating environment and keeps track of system resource utilization.
Monitors typically record CPU utilization, I/O request rates, data transfer rates, RAM utilization, and similar statistics. A monitor program, which may be an integral part of an operating system, a separate software product, or a part of a related component, such as a database management system, is a necessary prerequisite to manual I/O load balancing.
[Storage System]
In the Network File System (NFS), a protocol and set of procedures to specify a remote host and file system or directory to be accessed, and their location in the local directory hierarchy.
[Computer System]
Acronym for Mean Time Between Failures.
[Computer System]
Acronym for Mean Time to Data Loss.
[General]
Acronym for Mean Time To Data.
[General]
Abbreviation for Mean Time to (first) Failure.
[General]
Acronym for Mean Time To Repair.
[Network]
Acronym for Maximum Transfer Unit.
[Data Security]
Verification of an individual's identity using more than one factor pertaining to knowledge, possession or biometrics.
A knowledge factor is something an individual knows; a possession factor is something an individual has, and a biometric factor is something an individual is or is able to do.
[Storage System]
A disk array with multiple levels of data mapping, in which the virtual disks created by one mapping level become the members of the next level.
The most frequently encountered multi-level disk arrays use mirroring at the first level, and stripe data across the resulting mirrored arrays at the second level.
[Storage System]
The facility for a host to direct I/O requests to a storage device on more than one access path.
This requires that devices be uniquely identifiable by some means other than by bus address.
[Storage System]
Synonym for unified storage.
[Data Security]
Allocation of physical and virtual resources such that multiple tenants and their computations and data are isolated from and inaccessible to one another. [ISO/IEC 17788]
[Computer System]
Having multiple concurrent or pseudo-concurrent execution sequences.
Multi-threaded processes are one means by which I/O request-intensive applications can make maximum use of disk arrays to increase I/O performance.
[Network]
A set of ports associated with an address or identifier that serves as the destination for multicast packets or frames that are to be delivered to all ports in the set.
[Data Security]
A security system that allows users and resources of different sensitivity levels to access a system concurrently, while ensuring that only information for which the user or resource has authorization is made available.
[Network]
Designed to carry multiple light rays or modes concurrently.
In optical fiber, each mode is transmitted at a slightly different reflection angle within the optical fiber core. Multimode fiber transmission is used for relatively short distances.
[Management]
A SNIA specification for discovery and management of the multipath devices on a host system and the associated local and device ports.
A Fibre Channel architectural object that provides the functions of the FC-2M sublevel, multiplexing and demultiplexing frames between a set of physical ports and a set of virtual ports.
Multiplexers are components of both nodes and switches.
Advancing Storage and Information Technology
Explore, discover, share, and meet other like-minded industry members. Get ahead, stay ahead, and create industry curves. Become a SNIA member today!