Online SNIA Dictionary
A glossary of storage networking, data, and information management terminology. To learn more about the SNIA Dictionary click here.
Select from the alphabetical list, search for terms and/or filter by context.
[Hardware]
A stack of multiple layers of NAND memory cells.
[Data Communication]
An algorithm for encoding data for transmission in which each 64-bit data word is converted to a 66-bit transmission character.
Each transmission character is prefixed with either binary "01" or binary "10". This, combined with scrambling, gives the signal desirable engineering properties, yet incurs a much lower overhead than the traditional 8b/10b encoding.
[Data Communication]
An algorithm for encoding data for transmission in which each eight-bit data byte is converted to a 10-bit transmission character.
8B/10B encoding is used in transmitting data on Fibre Channel, ESCON, Gigabit Ethernet, and Serial Attached SCSI. It supports continuous transmission with a balanced number of ones and zeros in the code stream and detects single bit transmission errors.
[Data Security]
Acronym for Authentication, Authorization, and Accounting.
[Data Security]
The opportunity to make use of an information system resource.
[File System] [Data Security]
A single entry in an Access Control List, which either denies or grants access to a given resource by one principal (a user or a group of users and/or groups).
[Network] [Data Security] [File System]
A persistent list, commonly composed of Access Control Entries (ACEs), that enumerates the rights of principals (users and groups of users and/or groups) to access resources.
A process by which nodes are provided access to a Fibre Channel arbitrated loop independently of other nodes' activity.
[Operating System]
1. The means used to access a physical transmission medium in order to transmit data.
2. In IBM Corporation's OS/390 operating system and its precursors, a file organization method, such as sequential, random, indexed, etc., and the operating system software used to implement it.
[Storage System]
The combination of adapters, addresses and routes through a switching fabric used by a computer to communicate with a storage device.
Some configurations support multiple access paths to a single device. See multi-path I/O.
[Data Security]
An established relationship between a principal and a computer, network or service.
[Data Security]
1. The property enabling principals' actions to be attributed to them in such a way that there is little possibility for denying responsibility for those actions.
2. The security goal that generates the requirement for actions of an entity to be traced uniquely to that entity.
This supports non-repudiation, deterrence, fault isolation, intrusion detection and prevention, and after-action recovery and legal action. [NIST SP 800-33]
[File System] [Data Security]
Acronym for Access Control Entry.
[File System] [Data Security]
Acronym for Access Control List.
[Data Recovery]
Acronym for Automated Cartridge System.
1. The state of a Fibre Channel Sequence Initiator between the start of transmission of the first data frame of a sequence and the completion of transmission of the last data frame in the sequence.
2. The state of a Fibre Channel Sequence Recipient between the start of reception of the first data frame of a sequence and the completion of reception of the last data frame in the sequence.
[Long-Term Retention]
A long-term data retention system that allows online access to retained file and object data.
[Storage System]
A system component that requires electrical power to operate, such as a power supply, fan, or controller.
[Data Management]
Data that is immediately accessible to an application without the need to stage it in from a lower tier of storage.
See near-online data.
[Windows]
A Microsoft technology for the central and hierarchical administration of large groups of computers, users and groups.
[Energy]
The power consumption of a system when powered on and under normal workload.
[Storage System]
Synonym for dual active components or controllers.
[Storage System]
Synonym for hot standby components or controllers.
[Windows]
Acronym for Active Directory.
[General]
A hardware device, typically an add-in card or specialized component on a system board, that converts the timing and protocol of one bus or interface to another, to enable a computer system's processing hardware to access peripheral devices.
A Fibre Channel Host Bus Adapter and an Ethernet Network Interface Card are both kinds of adapters.
[Storage System]
A disk array that is capable of changing its virtual-to-physical location mapping algorithm (e.g., from mirrored to parity RAID) while the array is operating.
[Hardware] [SCSI]
1. Acronym for Analog Digital Converter.
2. Acronym for the INCITS T10 Automation/Drive Interface Commands standards family.
[Computer System] [SCSI] [Network]
1. A fixed length bit pattern that uniquely identifies a block of data stored on a disk or tape.
2. A fixed-length bit pattern that uniquely identifies a location (bit, byte, word, etc.) in a computer memory.
3. An identifier whose value uniquely identifies a SCSI port connected to a SCSI interconnect for purposes of communication.
4. A bit pattern that uniquely identifies a device on a network.
[Network]
1. Any protocol used to obtain a mapping from a higher layer address to a lower layer address; when abbreviated as ARP, the Ethernet Address Resolution Protocol (see 2) is most often meant.
2. The protocol used by an IP networking layer to map IP addresses to lower level hardware (i.e., MAC) addresses.
[Computer System]
An algorithm by which areas of fixed disk, removable cartridge media, or computer system main memory are uniquely identified.
See block addressing, C-H-S addressing, explicit addressing, implicit addressing.
[Storage System]
A computer that manages one or more storage subsystems (e.g., filers, disk array subsystems, tape subsystems, etc.).
[Storage System] [Data Security]
A person charged with the installation, configuration, and management of a computer system, network, storage subsystem, database, or application.
[Data Security]
A cryptographic algorithm designated by NIST [NIST FIPS 197] as a replacement for DES.
[Storage System]
A standard designed to connect storage devices to computer systems.
ATA is also the official name for Integrated Drive Electronics (IDE).
[Legal]
Inference that destroyed or missing evidence (data) would have been harmful to a party who failed to provide it.
[Data Security]
Acronym for Advanced Encryption Standard.
[Storage System]
Acronym for All Flash Array.
[General]
A program that performs one or more services (such as gathering information from the Internet), acting for or as a principal.
[Network] [Storage System]
A process related to consolidation, consisting of combining multiple similar and related objects or operations into a single one.
Acronym for Augmented ISL.
A set of AISLs that connect the controlling switches that are part of a distributed switch.
[Storage System]
Acronym for Advanced Intelligent Tape.
[Computer System]
Use of an algorithm to translate from one data addressing domain to another.
If a volume is algorithmically mapped, the physical location of a block of data may be calculated from its virtual volume address using known characteristics of the volume (e.g., stripe depth and number of member disks). See dynamic mapping, tabular mapping.
[General]
An alternate name for an entity, sometimes used to create names that are more easily human readable.
One or more address identifiers that may be recognized by an N-Port in addition to its N-Port Identifier, used to form groups of N-Ports so that frames may be addressed to a group rather than to individual N-Ports.
See multicast group.
[Storage System]
A synonym for all solid state array.
[Storage System]
A storage subsystem or array where all persistence is provided by Solid State Storage.
[Data Recovery]
The process of restoring files to a different client than the one from which they were backed up.
[Data Recovery]
The process of restoring files to a different directory than the one from which they were backed up.
[General]
1. The state of always having power applied (systems) or of being continually active (communication links).
2. A state of an operational link of always being powered on and continually transmitting either data frames, idles or fill words, in contrast to bursty transmissions and listening for a quiet line in earlier 10 and 100 Mbit/sec Ethernet.
Acronym for Arbitrated Loop Physical Address.
[Standards]
A body that coordinates the development and use of voluntary consensus standards in the United States and represents the needs and views of U.S. stakeholders in international standardization forums around the globe.
ANSI accredits both standards certification organizations and standards development organizations. The IEEE Standards Association (which standardizes Ethernet and many other technologies) and INCITS (which standardizes SCSI, Fibre Channel, MPEG, and many other technologies) are two of over 100 ANSI accredited standards organizations.
[Hardware]
A device that converts a continuously valued (analog) input to a discretely valued (digital) output.
[Standards]
Acronym for American National Standards Institute.
[Standards]
The standards development committee accredited by INCITS to develop SCSI standards for communication between initiators (i.e., host devices) and targets (e.g., storage device controllers).
The full name of this committee is the INCITS SCSI Storage Interfaces Technical Committee (INCITS TC T10).
[Standards]
The standards development committee accredited by INCITS to develop standards related to Fibre Channel, related serial storage interfaces, and certain storage management interfaces.
The full name of this committee is the INCITS Fibre Channel Interfaces (T11) Technical Committee (INCITS TC T11). T11.2 (physical) and T11.3 (protocol) are current task groups in ANSI T11.
[Standards]
The standards development committee accredited by INCITS to develop ATA standards for communication between a host and a storage device.
The full name of this committee is the INCITS ATA Storage Interfaces Technical Committee (INCITS TC T13).
[General]
Acronym for Application Programming Interface.
[General]
An intelligent device programmed to perform a single well-defined function, such as providing file, web, network or print services.
Appliances differ from general purpose computers in that their software is normally customized for the function they perform, pre-loaded by the vendor, and not alterable by the user. See filer.
[Storage System]
A client of a storage system.
Applications range from desktop productivity applications to enterprise-wide federated applications spanning multiple databases and file systems.
[General]
An interface used by an application program to request services.
The term API is usually used to denote interfaces between applications and the software components that comprise the operating environment (e.g., operating system, file system, volume manager, device drivers, etc.).
[Standards]
An Open Group technical standard, being developed in both The Open Group and the Distributed Management Task Force, which defines function calls for transaction monitoring.
[Computer System]
An integrated circuit designed for a particular application, such as interfacing to a SCSI interconnect.
[Storage System]
I/O requests made by storage clients, as distinguished from I/O requests made by a storage subsystem's own control software.
1. A Fibre Channel interconnect topology in which each port is connected to the next, forming a loop.
At any instant, only one port in a Fibre Channel Arbitrated Loop can transmit data. Before transmitting data, a port in a Fibre Channel Arbitrated Loop must participate with all other ports in the loop in an arbitration to gain the right to transmit data. The arbitration logic is distributed among all of a loop's ports.
2. The version of the Fibre Channel protocol used with the arbitrated loop physical topology.
An 8-bit value used to identify a participating device in an Arbitrated Loop.
[General]
Any process by which a user of a shared resourcesuch as a port connected to a shared busnegotiates with other users for the (usually temporary) right to use the resource (in the given example, by transmitting data on the bus).
[Data Management]
1. A collection of data objects, perhaps with associated metadata, in a storage system whose primary purpose is the long-term preservation and retention of that data.
2. An organization of people and systems that have accepted the responsibility to protect, retain, and preserve information and data and make it available for a Designated Community. (Source: ISO 14721)
[General] [Computer System]
1. Acronym for Application Response Measurement.
2. A common microprocessor architecture, as well as the name of the company that created the architecture.
[Network]
Acronym for Address Resolution Protocol.
[Storage System]
A storage array, i.e., a disk array or tape array.
[Storage System]
1. Assignment of the disks and operating parameters for a disk array by setting parameters such as stripe depth, RAID model, cache allowance, spare disk assignments, etc. See configuration, physical configuration.
2. The arrangement of disks and operating parameters that results from such an assignment.
[Computer System]
Acronym for Application Specific Integrated Circuit.
[Fibre Channel]
Acronym for A_Port Switch Link.
[Storage System]
The amount of space on a system or data container which has been allotted to be written.
On thin provisioning systems, an assigned capacity number represents a promise of the amount of space that is available on demand; usable capacity is allocated as the container is written. On fully provisioned systems, usable capacity must be committed at the same time the container is allocated. See thin provisioning.
[Fibre Channel]
A value that uniquely identifies an NVMe-oF/FC association
[Data Security]
A process for demonstrating that the security goals and objectives for an IT product or system are met on a continuing basis.
[Data Security]
The measure of confidence that the security features, practices, procedures, and architecture of an information system accurately mediate and enforce the security policy.
[Data Security]
Cryptography that uses an asymmetric cryptosystem.
[Data Security]
A cryptographic algorithm in which different keys are used to encrypt and decrypt a single message or block of stored information.
One of the keys is kept secret and referred to as a private key; the other key can be freely disclosed and is called a public key.
[Storage System]
An I/O operation whose initiator does not await its completion before proceeding with other work, enabling an initiator to have multiple concurrent I/O operations in progress.
[Storage System]
A request to perform an asynchronous I/O operation.
[Storage System]
Deprecated synonym for asynchronous replication.
[Storage System]
A replication technique in which data must be committed to storage at only the primary site and not the secondary site before the write is acknowledged to the host. Data is then forwarded to the secondary site as the network capabilities permit.
[Network]
A connection-oriented data communications technology based on switching 53 byte fixed-length units of data called cells.
ATM transmission rates are multiples of 51.840 Mbits per second. Each cell is dynamically routed. In the United States, a public communications service called SONET uses ATM at transmission rates of 155, 622, 2048, and 9196 Mbits per second. These are called OC-3, OC-12, OC-48, and OC-192 respectively. A similar service called SDH is offered in Europe. ATM is also used as a LAN infrastructure, sometimes with different transmission rates and coding methods than are offered with SONET and SDH.
[Storage System]
Acronym for Advanced Technology Attachment.
[Network]
Acronym for Asynchronous Transfer Mode.
[General]
An operation that, from an external perspective, occurs either in its entirety or not at all.
For example, database management systems that implement the concept of business transactions treat each business transaction as an atomic operation on the database. This means that either all of the database updates that comprise a transaction are performed or none of them are performed; it is never the case that some of them are performed and others not. RAID arrays must implement atomic write operations to properly reproduce single-disk semantics from the perspective of their clients.
[Data Security]
Attempt to destroy, expose, alter, disable, steal or gain unauthorized access to or make unauthorized use of an asset. [ISO/IEC 27000:2018]
[Network]
The power loss between an optical or electrical transmitter and a receiver, typically expressed in units of decibels (dB).
[General]
Independent review and examination of records and activities to assess the adequacy of controls, to ensure compliance with established policies and operational procedures, and to recommend necessary changes in controls, policies, or procedures.
[Data Security]
Synonym for audit trail.
[Network] [Data Security]
A chronological record of system activities that enables the reconstruction and examination of a sequence of events and/or changes in a system such as an information system, a communications system or any transfer of sensitive material and/or information.
An E_Port to E_Port link used by the FC-SW redundancy protocol.
[General]
Being genuine, or accurate in representation of facts.
[Legal] For evidence, being found by a jury (or trier of fact) to be what it purports to be and thus being worthy of trust, reliance, or belief.
[Data Security] [Legal]
1. The act of verifying the identity claimed by a party to an interaction.
2. The act of meeting the threshold level for admissibility, but not necessarily of authenticity, of evidence (e.g., ESI).
[Data Management] [Data Security] [Legal]
1. Synonym for data integrity.
2. The property of being genuine and being able to be verified and trusted; confidence in the validity of a transmission, a message, or message originator. [NIST SP 800-53]
3. The property, condition, or quality of being worthy of trust, reliance, or belief because the proponent (offeror) has shown enough corroborating evidence to a jury (or trier of fact) to warrant such.
[Network] [Data Security]
1. The process of determiningfor example via access controlthat a requestor is allowed to receive a service or perform an operation.
2. The limiting of usage of information system resources to authorized users, programs, processes or other systems, formally described as controlling usage by subjects of objects.
[Computer System]
Abbreviation for automatic swap.
[Storage System]
Synonym for automated storage tiering.
[Storage System]
Automatic movement of data between storage tiers based on policy.
The tiers may be within a single storage system or may span storage systems, including a cloud storage tier.
[Data Recovery]
A backup triggered by an event (e.g., a schedule point, or a threshold reached) rather than by human action.
[Computer System]
The substitution of a replacement unit (RU) in a system for a defective one, where the substitution is performed by the system itself while it continues to perform its normal function (possibly at a reduced rate of performance).
Automatic swaps are functional rather than physical substitutions, and do not require human intervention. Ultimately, however, defective components must be replaced in a physical hot, warm, or cold swap operation. See cold swap, hot swap, warm swap, hot spare.
[Storage System]
Deprecated synonym for automatic failover.
[Storage System]
The ability of a storage system to self-regulate attributes such as capacity, performance, and resiliency based on application demands, without any administrative intervention.
[General]
1. The amount of time that a system is available during those time periods when it is expected to be available, often measured as a percentage of an elapsed year.
For example, 99.95% availability equates to 4.38 hours of downtime in a year (0.0005 * 365 * 24 = 4.38) for a system that is expected to be available all the time. See data availability, high availability.
2. The property of being accessible and usable upon demand by an authorized entity.
[ISO/IEC 27000]
[Data Management] [Storage System]
Synonym for free space.
A type of port used to communicate within a Fibre Channel distributed switch.
A link connecting one A_Port to another A_Port.
[Data Recovery]
1. A collection of data stored on (usually removable) non-volatile storage media for purposes of recovery in case the original copy of data is lost or becomes inaccessible; also called a backup copy or replica.
To be useful for recovery, a backup must be made by copying the source data image when it is in a consistent state.
2. The act of creating a backup. See archive.
[Data Recovery]
A computer system containing online data to be backed up.
[Data Recovery]
A collection of data stored on (usually removable) non-volatile storage media for purposes of recovery in case the original copy of data is lost or becomes inaccessible; also called a backup or replica.
[Data Recovery]
An application program whose purpose is to schedule and manage backup operations.
[Data Recovery]
Rules for how and when backup should be performed.
The policy includes which data is to be backed up, the schedule on which backups should occur, which devices and media are eligible to receive the backups, how many copies are to be made, and actions to be performed if a backup does not succeed.
[Data Recovery]
Backup onto disk drive(s).
[Data Recovery]
An interval of time during which a set of data can be backed up without affecting applications that use the data.
[Data Recovery]
The amount of time required to create a backup.
For example, if a backup uses different resources (storage devices, I/O paths, processing power) than an application, as is common with split mirror point-in-time copies, then the backup window duration is the time required to create the image. If an online backup shares resources with the applications using the data, as is common with copy-on-write point in time copies, the backup window duration may be increased due to resource contention. For an offline backup, the backup window duration is the time during which applications are not allowed to modify the data while the backup operation completes.
[General] [Data Communication]
1. The numerical difference between the upper and lower frequencies of a band of electromagnetic radiation.
2. A deprecated synonym for data transfer capacity that is often incorrectly used to refer to throughput.
[Network]
A figure of merit for optical fiber, usually expressed as MHz*kilometer.
As an example, a Fibre Channel link operating at 1 Gb/s using a fiber with a bandwidth-length product of 500 MHz*kilometer will support a link distance of approximately 500 meters.
[Network]
The maximum rate of signal state changes per second on a communications circuit.
If each signal state change corresponds to a code bit, then the baud rate and the bit rate are the same. It is also possible for signal state changes to correspond to more than one code bit, so the baud rate may be lower than the code bit rate.
[Fibre Channel]
Acronym for buffer-to-buffer credit.
[General]
Acronym for Best Current Practice.
[Fibre Channel]
For a data stream using 8B/10B encoding, the running disparity present at a transmitter or receiver when an ordered set is initiated.
[Network] [Storage System]
Acronym for Bit Error Rate.
[Storage System]
A classification of disk array data protection and mapping techniques developed by Garth Gibson, Randy Katz, and David Patterson in papers written while they were performing research into I/O subsystems at the University of California at Berkeley.
There are seven Berkeley RAID Levels, usually referred to by the names RAID Level 0 through RAID Level 6. See RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5, RAID 6. Many other levels such as RAID 10, RAID 50 and so on have since been proposed.
[General]
A recommendation for what is currently believed to be the best manner of proceeding.
[Network]
A class of service that does not guarantee delivery of packets, frames, or datagrams, but for which the network, fabric, or interconnect makes every reasonable delivery effort.
[Data Security]
Synonym for mutual authentication.
[Computer System]
A characterization of datasets that are too large to be efficiently processed in their entirety by the most powerful standard computational platforms available.
[Computer System]
A format for the storage and transmission of binary data in which the most significant bits are stored at the numerically lowest addresses, or are transmitted first on a serial link.
[Computer System]
A program that resides in programmable, non-volatile memory on a computer and that is responsible for booting that computer and performing certain operating system independent I/O operations.
Standard BIOS interrupts are defined to allow access to the computer's disk, video and other hardware components (for example, INT13 for disk access).
[Computer System]
A binary digit.
[Network] [Storage System]
The probability that a transmitted bit will be erroneously received at the point of measurement.
The BER at a measurement point is determined by counting the number of bits in error at that measurement point and dividing by the total number of bits in the transmission. BER is typically expressed as a negative power of 10.
[Computer System]
A computer or storage system composed of a chassis that provides power, cooling and other common infrastructure, and one or more removable server or storage units, usually called blades.
Blade systems are designed as a scalable solution to efficiently package and operate multiple processing or storage units in a single enclosure, and are designed for technicians to be able to easily add or replace hot-swappable boards in the field.
[General] [Energy]
A solid plate that mounts over unused slots to maintain efficient air flow through components.
[Hardware]
The ability of pairs of components to be connected without the connection points being visible.
Blind mating is usually accomplished by mechanical guides (e.g., slots and rails) on the components.
[Storage System]
1. A unit in which data is stored and retrieved on storage media.
[Fibre Channel] 2. A unit of application data from a single information category that is transferred within a single sequence.
[Storage System]
A form of addressing data on storage media where units (blocks) of data are identified by integers that are typically sequential.
See C-H-S addressing.
[Data Security]
A symmetric encryption algorithm that operates on a block of plaintext, i.e., a string of bits of a defined length, to yield a block of ciphertext. [ISO/IEC 10116]
[Storage System]
A subsystem that provides block level access to storage for other systems or other layers of the same system.
See block.
[Storage System]
The act of applying virtualization to a block based (storage) service for the purpose of providing a new aggregated, higher level (e.g., richer, simpler, more secure) block service to clients.
Block virtualization functions can be nested. A disk drive, RAID system or volume manager all perform some form of block address to (different) block address mapping or aggregation. See file virtualization.
[Computer System]
A property of an operation that it may stop and wait for other operations to occur.
For example, an operation on file 1 blocks (i.e., stops and waits) for another operation on file 1 to complete.
[Network]
A type of coaxial cable connector formerly used in Ethernet applications; the specification is contained in EIA/TIA 403-A and MIL-C-39012.
[Computer System]
The process of loading Operating System code from a disk or other storage device into a computer's memory and preparing it to run.
Bootstrapping typically occurs in steps, starting with a very simple program (BIOS) that initializes the computer's hardware and reads a sequence of data blocks from a fixed location on a pre-determined disk, into a fixed memory location. The data thus read is the code for the next stage of bootstrapping, usually an operating system loader. The loader completes the hardware setup and results in an executing operating system, in memory.
[Storage System]
Remove a component from a mirror and make it an independent volume in the system, ending its synchronization with the other mirror components.
[Network]
1. A technology that enables traffic from a source device using one physical transport network technology to be transmitted to the destination device using an alternative physical transport network technology.
In some cases this "Bridge" is also referred to as a physical transport gateway, or storage router.
[Network] 2. A device that connects multiple LAN segments at the physical address layer.
As opposed to a hub, which indiscriminately rebroadcasts everything from one segment to the other, a bridge only retransmits traffic from one segment to another when the traffic is intended for the destination segment.
[Fibre Channel] 3. A Fibre Channel technology that provides a transparent fabric extension between two switch E-Ports through the use of 2 B-Ports tunneling through some alternative technology, resulting in an Inter-Switch Link (ISL) that "appears" to be a direct link between switches.
For example, a bridge pair can take an incoming Fibre Channel frame from one B-Port on a Bridge, encapsulate that frame using FCIP (Fibre Channel over IP) and transmit the frame as payload over an IP network to the remote Bridge where the original frame is forwarded to the remote Fibre Channel Fabric switch E-Port through the remote Bridge's B-Port.
[Computer System]
A solid state memory device or programming construct, used to hold data momentarily as it moves along an I/O path or between software components.
[Fibre Channel]
Flow control that occurs between two directly connected Fibre Channel ports, e.g., an N-Port and its associated F-Port.
A port indicates the number of frames that can be sent to it (its buffer-to-buffer credit) before the sender is required to stop transmitting and wait for the receipt of a "ready" indication. Buffer-to-buffer flow control is used only when an NL-Port is logged into another NL-Port on an Arbitrated Loop or when an Nx-Port is logged into an FX-Port." or "Flow control that occurs between two directly connected Fibre Channel ports, e.g., an N_Port and its associated F_Port or between two E_Ports. A port indicates the number of frames that can be sent to it (its buffer-to-buffer credit), before the sender is required to stop transmitting and wait for the receipt of additional credit.
Value used to determine how many frames can be sent to a recipient when buffer-to-buffer flow control is in use.
See Credit.
[Data Security]
Capability of an organization to continue the delivery of products or services at acceptable predefined levels following a disruption [ISO 22300:2018]
[Fibre Channel]
A circuit that removes a device from a data path (such as a Fibre Channel arbitrated loop) when valid signaling is lost, or a controller directs the removal of the device for any reason.
[Computer System]
An 8 bit unit of data.
Byte and bit ordering and meaning vary depending on context. It is necessary to consult the standards that apply in a given context to determine ordering and meaning.
[Fibre Channel]
The bridge port within a bridge used to extend a Fibre Channel inter-switch link.
[Storage System]
Acronym for Cylinder-Head-Sector addressing.
[Data Security]
Acronym for Certificate Authority.
[Network]
All of an installation's passive communications elements (e.g., optical fiber, twisted pair, coaxial cable, connectors, splices, etc.) between transmitters and receivers.
[Computer System]
1. To store data temporarily for expedited access.
2. The location in which data is stored temporarily for expedited access.
There are a variety of cache types. Read cache holds data in anticipation that it will be requested. Write cache holds data written by a client until it can be stored on other (typically slower) storage media such as disk or tape. See buffer, disk cache, write back cache, write through cache.
[Storage System]
An enclosure for one or more storage devices.
A canister is usually designed to mount in a shelf or other enclosure that supplies power, cooling, and I/O interconnect services. It is used to minimize RF emissions and to simplify insertion and removal in multi-device storage subsystems. See shelf.
A hypothesis that it is impossible for a distributed system to provide Consistency, Availability, and Partition Tolerance guarantees at the same time.
See eventual consistency.
[Storage System]
Methods which reduce the consumption of space required to store a data set, such as compression, data deduplication, thin provisioning, and delta snapshots.
RAID 5 and RAID 6 may also be considered as capacity optimizing methods, as they use less space than ordinary mirroring to perform a necessary function: protecting data from storage device failure.
[Storage System]
A system which employs at least one capacity optimization method.
[General]
The process of optimizing supply of a given resource to satisfy current and future demand for that resource.
Common methods used for capacity planning include tracking, trending, forecasting and scenario planning to predict future demand.
[Data Recovery]
A library or a component of a library in which the media are stored in and selected from a rotating assembly.
The process of connecting two or more hubs or switches together to increase the number of ports or extend distances.
[Data Security]
Acronym for Cipher Block Chaining.
[Data Security]
Acronym for Common Criteria.
[SCSI]
Acronym for Command Descriptor Block.
[Standards]
Acronym for Cloud Data Management Interface.
[Data Recovery]
Acronym for Continuous Data Protection.
[Network]
Acronym for Converged Ethernet.
[Data Security]
A data structure signed with a digital signature that is based on a public key and which asserts that the key belongs to a subject identified in the structure.
[Data Security]
In a Public Key Infrastructure (PKI), the authority and organization responsible for issuing and revoking user certificates, and ensuring compliance with the PKI policies and procedures.
The reputation of the certificate authority determines the trust that may be placed in the identity assurance provided by the certificates issued by the authority.
[Data Security]
A time-stamped list of certificates, signed by the issuing Certification Authority, that have been revoked by that CA.
The CRL is made available to entities that need to rely on a certificate for authentication.
[Legal]
A process that tracks the movement of evidence through its collection, safeguarding, and analysis lifecycle by documenting each person who handled the evidence, the date/time it was collected or transferred, and the purpose for the transfer. [NIST SP 800-72]
[Data Security]
A step in an authentication dialog that must be answered using either a secret or process assumed to be known only by the other party.
A challenge can be as simple as "What's your password?" or as complex as "Send me the result of a retinal scan of your right eye."
[Data Security]
A password-based authentication protocol that uses a challenge to verify that a user has access rights to a system.
A hash of the supplied password with the challenge is sent for comparison so the cleartext password is never sent over the connection.
[Storage System] [Computer System]
1. The electrical circuits that sense or cause the state changes in recording media and convert between those state changes and electrical signals that can be interpreted as data bits.
2. Synonym for I/O interconnect.
The term channel has other meanings in other branches of computer technology. The definitions given here are commonly used when discussing storage and networking. See device channel, I/O interconnect, host I/O bus.
[Computer System]
A 10-bit information unit transmitted and received certain protocols, consisting of 8 bits of data encoded as a 10 bit transmission character using 8B/10B encoding
[Data Recovery] [File System]
1. [Data Recovery] (noun) The recorded state of an application at an instant of time, including data, in-memory variables, program counter, and all other context that would be required to resume application execution from the recorded state.
2. [File System] (verb) An activity of a file system, such as the High Performance File System, (HPFS) or the Andrew File System (AFS), in which cached metadata (data about the structures of the file system) is periodically written to the file system's permanent store, allowing the file system to maintain consistency if an unexpected stop occurs.
[Data Security]
A value computed across a set of data, used to detect change.
A checksum is often used for error and manipulation detection.
[Hardware]
Acronym for Cylinder Head Sector.
[iSCSI]
Acronym for Connection Identifier.
[File System]
Acronym for Common Internet File System.
[Management]
Acronym for Common Information Model.
[Data Security]
A cryptographic system where plaintext is rearranged through transposition and/or substitution under direction of a cryptographic key.
When a cipher is applied to plaintext to produce ciphertext, the process is called encryption. When the cipher is applied to ciphertext to produce plaintext, the process is called decryption.
[Data Security]
A block cipher mode of operation, in which each block of plaintext is XORed with the previous ciphertext block before being encrypted, making each ciphertext block dependent on all preceding plaintext blocks.
[Data Security]
A named combination of a key exchange algorithm (for authentication), a bulk encryption algorithm, a message authentication code (MAC) algorithm, and a pseudorandom function (PRF) that may be negotiated and used to establish the security settings for a network connection using the Transport Layer Security (TLS) or Secure Sockets Layer (SSL) network protocol.
[Storage System]
Acronym for Count-Key-Data.
[Fibre Channel]
A connection-oriented class of Fibre Channel communication service in which the entire data transfer rate of the link between two ports is dedicated for communication between the ports and not used for other purposes.
Class 1 is also known as dedicated connection service, and is not widely implemented. See intermix.
[Fibre Channel]
A connectionless Fibre Channel communication service which multiplexes frames from one or more N-Ports or NL-Ports.
Class 2 frames are explicitly acknowledged by the receiver, and notification of delivery failure is provided. This class of service includes end to end flow control.
[Fibre Channel]
A connectionless Fibre Channel communication service that multiplexes frames to or from one or more N-Ports or NL-Ports.
Class 3 frames are datagrams, that is they are not explicitly acknowledged, and delivery is on a "best effort" basis.
[Network] [Fibre Channel]
1. [Network] A mechanism for managing traffic in a network by specifying message or packet priority or delivery acknowledgement.
Network mechanisms include identification and grouping of data packets based on a priority label (in the packet header) or via mechanisms such as "per hop behavior", defined by the IETF's Differentiated Services.
2. [Fibre Channel] The characteristics and guarantees of the transport layer of a Fibre Channel network.
Fibre Channel classes of service include connection-based services (Class 1), acknowledged frame delivery with end to end flow control (Class 2), and packetized frame datagrams (Class 3). Different classes of service may simultaneously exist in a fabric. The form and reliability of delivery in Class 3 circuits may vary with the topology.
[Data Security]
Alternative term for plaintext. Stating that data is in cleartext implies that the data is not scrambled or rearranged, and is in its raw form.
[Computer System]
Acronym for Command Line Interface.
[Computer System] [General]
1. An intelligent device or system that requests services from other intelligent devices, systems, or appliances.
See server.
2. An asymmetric relationship with a second party (a server) in which the client initiates requests and the server responds to those requests.
[Data Management]
Synonym for snapshot.
Clones and snapshots are full copies. See delta snapshot.
[Cloud]
A party trusted conduct independent assessment of cloud services, information system operations, performance and information security of the cloud implementation. [ISO/IEC 17788]
[Cloud]
An intermediary that provides connectivity and transport of cloud services between cloud providers and cloud consumers. [ISO/IEC 17788]
[Cloud]
A person or organization that uses cloud services. [ISO/IEC 17788]
[Cloud] [Standards]
[Standards] A SNIA Technical Position for Data storage as a Service (DaaS).
[Cloud] CDMI is an interface for both the data path and the control path of cloud storage. CDMI can also be used to manage storage in Cloud Computing deployments.
[Cloud]
A set of data processing components that can be automatically provisioned by consumers, accessed over a network and that provide secure multitenancy. [ISO/IEC 17788]
[Cloud]
An entity responsible for making cloud services available to cloud consumers. [ISO/IEC 17788].
[Cloud] [Data Security]
Systematic evaluation of a cloud system by assessing how well it conforms to a set of established security criteria. [ISO/IEC 17788]
[Cloud]
A function useful to a cloud consumer provided by a cloud provider. [ISO/IEC 17788]
[Services]
Synonym for Data storage as a Service. [ISO/IEC 17788]
[Computer System]
A collection of computers that are interconnected (typically at high speeds) for the purpose of improving reliability, availability, serviceability, load balancing and/or performance.
Often, clustered computers have access to a common pool of storage and run special software to coordinate the component computers' activities.
[Management] [Network]
Acronym for Common Management Information Protocol.
[Storage System]
Acronym for conventional magnetic recording.
[Computer System]
A bit (binary digit) of an encoded datum.
Sequences of code bits make up symbols, each of which corresponds to a data element (word, byte, or other unit). For an example see 8b/10b encoding.
[Fibre Channel]
The error condition that occurs when a received transmission character cannot be decoded into a valid data byte or special code using the validity checking rules specified by the transmission code.
[Data Recovery]
Synonym for offline backup.
See hot backup, online backup.
[Data Management]
Data that is accessed infrequently.
[Data Management]
Data storage device, system, or service used to store cold data at a cost that is at least an order of magnitude less than the cost of primary storage.
Cold Storage features large capacity, energy saving and long-term data preservation, in order to achieve low-cost rather than performance.
[Computer System]
The substitution of a replacement unit (RU) in a system for a defective one, where external power must be removed from the system in order to perform the substitution.
A cold swap is a physical substitution as well as a functional one. See automatic swap, hot swap, warm swap.
[Computer System]
A form of human interface to intelligent devices characterized by non-directive prompting and character string user input.
CLIs are used by system consoles and remote shell sessions (RSH, SSH). They are very useful for scripting and other administrative purposes.
[Storage System]
Data that has been written to stable storage.
[Data Security]
A multi-part International Standard that is meant to be used as the basis for evaluation of security properties of IT products and systems.
The CC is specified in ISO/IEC 15408-1:1999, ISO/IEC 15408-2:1999, and ISO/IEC 15408-3:1999.
[Data Management] [Network]
An object oriented description of the entities and relationships in a business' management environment maintained by the Distributed Management Task Force.
CIM is divided into a Core Model and Common Models. The Core Model addresses high-level concepts (such as systems and devices), as well as fundamental relationships (such as dependencies). The Common Models describe specific problem domains such as computer system, network, user or device management. The Common Models are subclasses of the Core Model and may also be subclasses of each other.
[Management]
An OASIS standard language used to define a model over which an OData service acts.
For more information and current state see https://www.odata.org/documentation/.
[Network] [Data Security]
Protection of information while it's being transmitted, particularly via telecommunications.
A particular focus of communications security is message authenticity. Communications security may include cryptography, transmission security, emission security, and physical security.
[Cloud]
A cloud infrastructure shared by several organizations and supporting a specific community that has shared concerns (e.g., mission, security requirements, policy, and compliance considerations).
[Data Security]
A way - also known as a band-aid - of mitigating a known risk where it may not be feasible to deploy specific technical enablement.
[General] [Legal]
1. The state of being in accordance with a standard, specification, or clearly defined requirements.
2. The state of being in accordance with legal requirements.
The "compliance market" is centered around storage and systems that support the retention and discovery of data as required by law or regulation.
[Data Communication]
A test pattern for jitter testing.
[General]
Synonym for data compression.
[Storage System]
A space reduction ratio that is the ratio of the size of the uncompressed data to the size of the compressed data.
[Data Security]
An incident that subjects data to unauthorized disclosure, modification, destruction, or loss.
[Computer System]
Architectures that provide Computational Storage Functions (CSF) coupled to storage, offloading host processing or reducing data movement.
These architectures enable improvements in application performance and/or infrastructure efficiency through the integration of compute resources (outside of the traditional compute & memory architecture) either directly with storage or between the host and the storage. The goal of these architectures is to enable parallel computation and/or to alleviate constraints on existing compute, memory, storage, and I/O.
[Computer System]
A collection of Computational Storage Devices, control software, and optional storage devices.
[Computer System]
A Computational Storage Drive, Computational Storage Processor, or Computational Storage Array.
[Computer System]
A storage element that contains one or more Computational Storage Engines (CSE) and persistent data storage.
[Computer System]
A Component that is able to execute one or more Computational Storage Functions (CSF)
[Computer System]
Specific operations that may be configured and executed by a Computational Storage Engine (CSE)
[Computer System]
A component that contains one or more Computational Storage Engines (CSE) for an associated storage system without providing persistent data storage.
[Computer System]
Resource available for a host to provision a Computational Storage Device (CSx) that enables that CSx to be programmed to perform a Computational Storage Function (CSF)
[Computer System]
Software that enables a single server hardware platform to support multiple concurrent instances of an operating system and applications.
[Data Security]
Measures and controls that ensure confidentiality, integrity, and availability of information system assets including hardware, software, firmware, and information being processed, stored, and communicated.
[Computer System]
The property of overlapping in time, often in reference to the execution of I/O operations or I/O requests.
[Data Security]
The property that data cannot be accessed by unauthorized parties.
Confidentiality may be created by the use of encryption or access controls.
[General]
The management of system features and behaviors through the control of changes made to hardware, software, firmware documentation and related resources throughout the life cycle of an information system.
[Computer System]
A condition that occurs when more services have been requested than are able to be delivered.
[Network]
A notification mechanism that supports congestion management for long-lived data flows within network domains of constrained data transfer rate.
[Fibre Channel]
A value that uniquely identifies an NVMe-oF/FC connection.
[iSCSI]
An identifier generated by the initiator and sent to the target upon logging in or out, that uniquely identifies each connection within a session.
[Network]
A frame used in a connectionless service (i.e., Class 2, and Class 3 frames referred to individually or collectively).
[Network] [Data Security]
A security service that provides data integrity service for an individual IP datagram by detecting modification of the datagram without regard to the ordering of the datagram in a stream of datagrams.
[Fibre Channel]
Communication between two N_Ports or NL_Ports for connectionless frames.
[Storage System]
A collection of replication sets grouped together to ensure write order consistency across all the replication sets' primary volumes.
An operation on a consistency group, such as changing replication from asynchronous to synchronous, applies to all the replication sets within the consistency group, and consequently their volumes.
[Storage System] [File System]
1. [Storage System] A volume that satisfies the consistency criteria of the system on which it is hosted.
2. [File System] In LTFS, a volume in which all partitions are complete, and the last LTFS Index in the Index partition has a back pointer to the last LTFS Index in the data partition.
If an LTFS volume is not consistent, some form of recovery may be necessary.
[Computer System]
1. A device for graphical or textual visual output from a computer system.
2. In systems, network and device management, an application that provides graphical and textual feedback regarding operation and status, and that may accept operator commands and input influencing operation and status.
Sophisticated consoles designed for the management of many systems from one location are sometimes called enterprise management consoles.
[Storage System]
A data deduplication method that does not require awareness of specific application data formats.
[Storage System]
A data deduplication method that leverages knowledge of specific application data formats.
[Data Recovery]
A class of mechanisms that continuously capture or track data modifications enabling recovery to previous points in time.
[Network]
A transmission control algorithm in which the frames containing the subblocks that comprise a block of information are transmitted strictly in the order of the subblocks.
Continuously increasing relative offset offers simpler reassembly and detection of lost frames compared to random relative offset.
[Computer System]
The portion of a system that controls the operation of the system.
Also see data plane.
[Computer System]
A body of software that provides common control and management.
When it executes on a device, control software is often referred to as firmware.
[Hardware] [NVMe] [Storage System] [Management]
1. [Hardware] A device or component of a system that performs a control function.
2. [Storage System] The control logic in a disk or tape that performs command decoding and execution, host data transfer, serialization and deserialization of data, error detection and correction, and overall management of device operations.
3. [Management] The control logic in a storage subsystem that performs command transformation and routing, aggregation (RAID, mirroring, striping, or other), high-level error recovery, and performance optimization for multiple storage devices.
4. [NVMe] The interface between a host and an NVM subsystem.
[Storage System]
A disk array whose control software executes in a disk subsystem controller.
[Storage System]
A cache that resides within a controller and whose primary purpose is to improve storage performance.
See cache, disk cache, host cache.
[Fibre Channel]
A controlling switch that supports lossless Ethernet MACs.
[Fibre Channel]
A switch able to control a set of FCDFs in order to create a distributed switch.
[Network]
A set of Ethernet technologies and protocols defined in IEEE 802.3 that combine to reduce packet loss.
[Computer System]
The pooling of compute, storage, and networking resources using either common management tools or common (shared) physical resources.
[Data Recovery]
A technique for maintaining a point in time copy of a collection of data such that when a logical data location is written, a new physical location is chosen for the existing data, and the existing data is copied to that new physical location.
See pointer remapping.
[Storage System]
Deprecated synonym for rebuild / rebuilding.
A set of entities with the same Core Switch_Name that may host multiple Virtual Switches.
A Core Switch may be a set of ports in a physical chassis, or in multiple physical chassis.
An N-Port-Name associated with the Physical N-Port of a VFT Tagging N-Port, and not with any other FC-Port within the scope of its Name_Identifier format.
In a Virtual Fabric capable Switch, the Switch-Name identifying the Core Switch.
[Storage System]
A disk data organization model in which the disk is assumed to consist of a fixed number of tracks, each having a maximum data capacity.
Multiple records of varying length may be written on each track of a Count-Key-Data disk, and the usable capacity of each track depends on the number of records written to it. The CKD architecture derives its name from the record format, which consists of a field containing the number of bytes in the key and data fields and a record address, an optional key field by which particular records can be easily recognized, and the data itself. CKD is the storage architecture used by IBM Corporation's mainframe computer systems. See fixed block architecture.
[Data Security]
Any action, device, procedure, technique, or other measure that reduces the vulnerability of or threat to a system.
[Data Security]
An unintended and/or unauthorized communications path that can be used to transfer information in a manner that violates a security policy.
[Data Recovery]
Abbreviation for copy on write.
[Hardware]
Acronym for Central Processing Unit.
[Data Communication] [Storage System]
Acronym for Cyclic Redundancy Check.
[Data Security]
Information, passed from one entity to another, used to establish the sending entity's identity and/or access rights.
[Fibre Channel]
The maximum number of receive buffers at a recipient to receive frames from a transmitting FC_Port.
[Data Security]
Acronym for Certificate Revocation List.
[General]
Acronym for Customer Replaceable Unit.
[Data Security]
A set of operations performed in converting encrypted information to plaintext without initial knowledge of the algorithm and/or key employed in the encryption.
[Data Security]
An algorithm whose outputs have cryptanalytic security properties with respect to its inputs, or vice versa.
[Data Security]
Method of sanitization in which the encryption key for the encrypted target data is sanitized, making recovery of the decrypted target data infeasible. [ISO/IEC 27040]
[Data Security]
A method for rendering encrypted data unrecoverable by securely deleting the keying material required to decrypt the data.
The encrypted data itself is not modified. The protection offered by cryptographic erasure is bounded by the work factor involved in discovering the decryption key or mounting a cryptanalytic attack on the encryption algorithm itself.
[Data Security]
A function that maps plaintext strings of any length to bit strings of fixed length, such that it is computationally infeasible to find correlations between inputs and outputs, and such that given one part of the output, but not the input, it is computationally infeasible to predict any bit of the remaining output.
Cryptographic hash functions have many information security applications, notably in digital signatures, message authentication codes (MACs), and other forms of authentication. The output from a cryptographic hash function is known as a message digest or hash value.
[Data Security]
The principles, means and methods for rendering information unintelligible, and for restoring encrypted information to intelligible form.
[Data Security]
The time span during which a specific key is authorized for use or in which the keys for a given system or application may remain in effect. [NIST SP 800-57 Part 1]
[Data Security]
A system for encrypting and decrypting data.
[Management]
Acronym for Common Schema Definition Language.
[Network]
Acronym for Carrier Sense Multiple Access with Collision Detection.
[Data Recovery]
A backup in which all data objects modified since the last full backup are retained as the backup.
To restore data when cumulative incremental backups are in use, only the latest full backup and the latest cumulative incremental backup are required.
The running disparity present at a transmitter when the encoding of a valid data byte or special code is initiated, or at a receiver when the decoding of a transmission character is initiated.
[Network] [Fibre Channel]
The running disparity present at a transmitter when 8B/10B encoding of a data byte or special code is initiated, or at a receiver when 8B/10B decoding of a Transmission Character is initiated
[General]
A unit, or component of a system that is designed to be replaced by "customers;" i.e., individuals who may not be trained as computer system service personnel.
A switching technique that allows a routing decision to be made and acted upon as soon as the destination address of a frame is received.
[Network] [Fibre Channel]
Synonym for cut through switching.
[Network] [Fibre Channel]
A switching technique that allows a routing decision to be made and acted upon as soon as the destination address of a frame is received.
[Data Communication] [Storage System]
A scheme for checking the integrity of data that has been transmitted or stored and retrieved.
A CRC consists of a fixed number of bits computed as a function of the data to be protected, and appended to the data. When the data is read or received, the function is recomputed, and the result is compared to that appended to the data. Cyclic redundancy checks differ from error correcting codes in that they can detect a wide range of errors, but are not capable of correcting them. See error correcting code.
[Storage System]
A form of addressing data stored on a disk in which the cylinder, head/platter combination, and relative sector number on a track are specified.
See block addressing.
[Data Security] [Hardware]
1. Acronym for Discretionary Access Control.
2. Acronym for Digital Analog Converter.
[Operating System]
A process that is kept running on a computer system to service a particular set of requests.
By way of example, lpd is a daemon in UNIX that handles printing requests. Daemons are independent processes, and not part of an application program. Application requests may be serviced by a daemon.
[Storage System]
Acronym for Direct Attached Storage.
[Computer System]
The digital representation of anything in any form.
[Data Security]
Data stored on stable non-volatile storage. [ISO/IEC 27040].
[Legal]
The process of substantiating that the data is an accurate representation of what it purports to be. [SWGDE/ SWGIT Glossary]
[Storage System]
The amount of time that data is accessible by applications during those time periods when it is expected to be available.
[Data Security]
A compromise of security that leads to the accidental or unlawful destruction, loss, alteration, unauthorized disclosure of, or access to protected data transmitted, stored or otherwise processed. [ISO/IEC 27040]
[Network] [Storage System]
A byte of user data as presented to a storage or communication facility.
See code byte, data character.
[Network]
The suite of Ethernet protocol extensions defined for reliable storage transports such as FCoE.
DCB includes the following protocols: IEEE 802.1Qau (CN), IEEE 802.1Qaz (ETS and DCBX), and IEEE 802.1Qbb (PFC).
A data center bridge implements the above protocols and capabilities for use in the data center.
[Network]
Any transmission character associated by the transmission code with a valid data byte.
[Data Management]
An organization of data into groups for management purposes.
A frequent purpose of a classification scheme is to associate service level objectives with groups of data based on their value to the business.
[General]
The process of encoding data to reduce its size.
Lossy compression (i.e., compression using a technique in which a portion of the original information is lost) is acceptable for some forms of data (e.g., digital images) in some applications, but for most IT applications, lossless compression (i.e., compression using a technique that preserves the entire content of the original data, and from which the original data can be reconstructed exactly) is required.
[Storage System]
The replacement of multiple copies of data—at variable levels of granularity—with references to a shared copy in order to reduce use of storage space and/or amount of data transferred.
See also inline data deduplication, post-process data deduplication.
[Storage System]
A space reduction ratio that only includes the effects of data deduplication.
[Data Security]
Synonym for data in motion.
[Data Security]
Data being transferred from one location to another [ISO/IEC 27040:2015].
These transfers typically involve interfaces that are accessible and do not include internal transfers (i.e., never exposed to outside of an interface, chip, or device).
[Data Security] [Legal]
1. Synonym for data in motion.
2. Data in motion across a jurisdictional boundary.
Jurisdictions (usually nation states) may have policies and enforcement points that determine whether data may cross their borders.
[Data Security]
Data in the process of being created, retrieved, manipulated, updated, or deleted.
[Data Management]
A process for depositing data into a storage system.
[Data Security] [Data Management]
The property that data has not been altered or destroyed in an unauthorized manner [ISO 7498-2:1988].
The property that data has not been altered or destroyed, in an unintended manner, due to physical or logical events.
[Data Management]
A large repository for storing data in an unstructured way, in anticipation of future analytics.
This term originated in the big data community.
[Data Management]
The policies, processes, practices, services and tools used to align the business value of data with the most appropriate and cost-effective storage infrastructure from the time data is created through its final disposition.
Data is aligned with business requirements through management policies and service levels associated with performance, availability, recoverability, cost, etc. DLM is a subset of ILM.
[Management]
The discipline and function of oversight and control of data resources.
[Data Management]
A set of services that control of data from the time it is created until it no longer exists.
Data Management Services are not in the data path; rather, they provide control of, or utilize, data in the delivery of their services. This includes services such as data movement, data redundancy, and data deletion.
[File System]
A computer program whose primary purpose is to present a convenient view of data to applications, and map that view to an internal representation on a system, subsystem or device.
File systems and database management systems are the most common forms of a data manager.
[Data Management]
A repository-specific representation of a data model.
A database representation of the CIM schemas is an example of a data model.
[Storage System]
The process of reducing the amount of storage space used to store ingested data, using capacity optimization methods.
[Computer System]
The portion of a system that moves user data.
In a storage system the data plane is responsible for storing and retrieving data.
Also see control plane.
[Data Communication]
The ability to transfer data from one system to another without being required to recreate or reenter data descriptions.
[Data Management]
The processes of ensuring the fidelity and continued existence of stored data over a period of time.
[Data Management]
The combination of data integrity, data availability, and confidentiality.
[Data Management]
The length of the statistically expected continuous span of time over which data stored by a population of identical storage subsystems can be correctly retrieved, expressed as Mean Time to Data Loss (MTDL).
[Storage System]
Continuously maintaining a secondary copy of datapossibly at a remote sitefrom a primary volume for the purposes of providing high availability and redundancy.
Data replication is used for disaster recovery and business continuance, among other uses.
[Data Security]
Implementation of a collection of data along with data access and control mechanisms, such as search, indexing, storage, retrieval and security. [ISO/IEC 20944-1:2013]
EXAMPLE: A repository might support services such as search, indexing, storage, retrieval and security.
[Management]
The category of resources that exclusively encompass data services.
[Long-Term Retention]
Preserving the existence and integrity of data for some period of time or until certain events have transpired, or any combination of the two.
Retention requirements are expressed either as a time period, an event (e.g., the death of a patient), or a combination (e.g., 3 years after said death). Multiple requirements may be active, and some (e.g., judicial holds) may trump others.
[Data Management]
A set of functions that treat data without interpretation.
This treatment may, for example, involve copying, movement, security and/or protection, but not the actual storage of the data.
[Data Management]
A process for deleting data that is intended to make the data unrecoverable.
One such process consists of repeated overwrites of data on disk. Data shredding is not generally held to make data completely unrecoverable in the face of modern forensic techniquesthat requires shredding of the disks themselves. Forensic techniques, however, do require physical access to the storage media.
[Services]
Delivery of appropriately configured virtual storage and related data services over a network, based on a request for a given service level.
Typically, DSaaS hides limits to scalability, is either self-provisioned or provisionless and is billed based on consumption.
[Storage System]
Synonym for user data extent stripe depth.
[Storage System]
A disk array data mapping technique in which fixed-length sequences of virtual disk data addresses are mapped to sequences of member disk addresses in a regular rotating pattern.
Disk striping is commonly called RAID Level 0 or RAID 0 because of its similarity to common RAID data mapping techniques. It includes no redundancy, however, so strictly speaking, the appellation RAID is a misnomer.
[Computer System]
The maximum rate at which data can be transmitted.
See throughput, data transfer rate.
[SCSI]
A removable media storage device in a library.
Examples are magnetic disk drives, cartridge tape drives, optical disk drives, and CD-ROM drives.
[Computer System]
The amount of data per unit time actually moved across an I/O interconnect in the course of executing an I/O load.
The data transfer capacity of an I/O subsystem is an upper bound on its data transfer rate for any I/O load. For disk subsystem I/O, data transfer rate is usually expressed in MBytes/second (millions of bytes per second, where 1 million = 106) or Gbits/second (billions of bits per second, where 1 billion = 109). See data transfer capacity.
[Computer System]
An I/O intensive application that makes largeusually sequentialI/O requests.
[Database]
An set of computer programs with a user and/or programming interface that supports the definition of the format of a database and the creation of and access to its data.
A database management system removes the need for a user or program to manage low level database storage. It also provides security for and assures the integrity of the data it contains. Types of database management systems are relational (table-oriented), network, hierarchical and object oriented.
[Network]
A message sent between two communicating entities for which no explicit link level acknowledgement is expected.
Datagrams are often said to be sent on a best effort basis.
[Database]
Acronym for Database Management System.
[Network]
Acronym for Data Center Bridging.
[Hardware]
Acronym for Double Data Rate.
The number after the DDR term designates the generation of the memory (e.g., DDR4 is the fourth generation of a DDR bus).
Validity checking of received transmission characters and generation of valid data bytes and special codes from those characters.
[Data Security]
The operations performed in converting encrypted information to plaintext with full knowledge of the algorithm and key(s) used to encrypt it.
Decryption is the intended method for an authorized user to decrypt encrypted information.
A communication circuit between two N-Ports maintained by a Fibre Channel fabric.
The port resources used by a dedicated connection cannot be used for other purposes during the life of the dedicated connection.
See data deduplication.
[Data Security]
An information assurance strategy integrating people, technology, and operations capabilities to establish multiple security barriers across layers and dimensions of a protected system. [NIST SP 800-53]
[Data Security]
1. A procedure that renders data unreadable by applying a strong magnetic field to the media.
2. Applying a degaussing procedure.
Degaussing is also called demagnetizing and erasure. Both of these terms are misleading, because in magnetic digital media the individual magnetic domains are not erased or demagnetized, but simply made to line up in the same direction, which eliminates any previous digital structure.
[Storage System]
A mode of RAID array operation in which not all of the array's member disks are functioning, but the array as a whole is able to respond to application read and write requests to its virtual disks.
An ordered set used to indicate a frame boundary.
[Data Recovery]
A type of point in time copy that preserves the state of data at an instant in time, by storing only those blocks that are different from an already existing full copy of the data.
[Storage System]
A method of performing data deduplication by storing or transmitting data in the form of differences from a baseline point in time copy.
[Network]
Acronym for Directory Enabled Network.
[Data Security]
Prevention of authorized access to a system resource or the delaying of system operations and functions, with resultant loss of availability to authorized users. [ISO/IEC 27033-1:2015]
[Management] [Network]
Initiative that became a precursor to the Distributed Management Task Force (DMTF).
An address contained in a Fibre Channel frame that identifies the destination of the frame.
[Storage System]
Synonym for storage device.
[Storage System]
Synonyms for I/O interconnect.
[Storage System]
A channel used to connect storage devices to a host bus adapter or an intelligent controller.
The preferred term is I/O interconnect.
[Storage System]
The ability of a storage controller to connect host computers to multiple storage devices using a single host I/O interconnect address.
Device fanout allows computer systems to connect to substantially more storage devices than could be connected directly.
Acronym for Destination Fabric_Identifier.
[Data Security]
Acronym for Diffie-Hellman augmented Challenge Handshake Authentication Protocol.
[Network]
Acronym for Dynamic Host Control Protocol.
[SCSI]
A SCSI electrical signaling technique in which each control and data signal is represented by a voltage differential between two signal lines.
Differential signaling can be used over longer distances than the alternative single ended signaling. See single ended (signaling).
[Data Recovery]
A backup in which data objects modified since the last full backup or incremental backup are copied.
To restore data when differential incremental backups are in use, the newest full backup and all differential backups newer than the newest full backup are required. See cumulative incremental backup, full backup.
[Management]
A protocol defined by the IETF for managing network traffic based on the type of packet or message being transmitted.
The Differentiated Services protocol is often abbreviated as DiffServ. DiffServ rules define how a packet flows through a network based on a 6 bit field (the Differentiated Services Code Point) in the IP header. The Differentiated Services Code Point specifies the "per hop behavior" for the packet or message.
[Data Security]
A key agreement protocol that was developed by W. Diffie and M. E. Hellman in allowing two entities to exchange a secret key over an insecure medium without any prior secrets.
[Data Security]
A password based Authentication and key management protocol that uses the CHAP algorithm (RFC 1994) augmented with an optional Diffie-Hellman algorithm.
DH-CHAP provides bidirectional and may provide unidirectional Authentication between a Fibre Channel Initiator and Responder. DH-CHAP is defined by Fibre Channel – Security Protocols - 2 (FC-SP-2).
[Management]
Abbreviation for Differentiated Services.
[Data Security]
A binary string of some fixed length derived by a computationally efficient function from a binary input string of arbitrary length.
A key feature of cryptographic digests is that given a digest, it is computationally infeasible to find another plaintext string that generates the same digest.
[Hardware]
A device that converts a discretely valued (digital) input to a continuously valued (analog) output.
[Data Management]
A storage repository or service used to secure, retain, and protect digital information and data for periods of time less than that of long-term data retention.
A digital archive can be an infrastructure component of a complete digital preservation service, but is not sufficient by itself to accomplish digital preservation, i.e., long-term data retention.
[Legal]
The identification, collection, preservation and analysis of digital evidence for use in legal proceedings.
[Data Recovery]
A family of tape device and media technologies.
[Long-Term Retention]
A methodology to verify and detect threats to the validity of digital preservation objects.
Digital object auditing is a process of routine periodic testing of stored digital objects, usually using cryptographic techniques, by comparing their previous signatures and time stamps to their current to verify that change, loss of access, or data loss has not occurred.
[Long-Term Retention]
Ensuring continued access to, and usability of, digital information and records, especially over long periods of time.
[Long-Term Retention]
A collection of data, metadata and possibly other resources treated as a unit for digital preservation purposes.
A preservation object provides the functionality required to assure the future ability to use, secure, interpret, and verify authenticity of the metadata, information, and data in the container and is the foundational element for digital preservation of information and data.
[Long-Term Retention]
A service providing digital preservation.
A digital preservation service includes a comprehensive management and curation function that controls its supporting infrastructure, information, data, and storage services in accordance with the requirements of the information objects it manages to accomplish the goals of digital preservation.
[Data Security]
A cryptographically derived binary string used to assure information authenticity, integrity, and nonrepudiation.
Digital signatures can generally be externally verified by entities not in possession of the key used to sign the information. For example, a secure hash of the information encrypted with the originator's private key when an asymmetric cryptosystem is used. Some algorithms that are used in digital signatures cannot be used to encrypt data. (e.g., DSA).
[Data Security]
A subset of the Digital Signature Standard that represents a specific public key algorithm that is only used for digital signatures.
The secret key used in DSA operates on the message hash generated by SHA-1; to verify a signature, one recomputes the hash of the message, uses the public key to decrypt the signature and then compares the results.
This algorithm is obsolete.
[Data Security]
A standard for digital signature that is published by the National Institute of Standards and Technology (NIST) in Federal Information Processing Standard (FIPS) Publication 186-4.
DSS specifies DSA as the algorithm for digital signatures and SHA-x for hashing.
[Hardware]
Acronym for Dual Inline Memory Module.
[Storage System]
One or more dedicated storage devices connected to one or more servers.
[Storage System]
Synonym of direct attach storage.
[SCSI]
A method used by expanders to route connection requests to directly attached devices, including other expanders.
[File System] [Management]
1. A mechanism for organizing information.
Directories are usually organized hierarchically. I.e., a directory may contain both information about files and objects, and other directories. They are used to organize collections of files and other objects for application or human convenience.
2. A file or other persistent data structure in a file system that contains information about other files.
3. An LDAP-based repository consisting of class definitions and instances of those classes.
Microsoft's Active Directory (AD) and Novell's NetWare Directory Service (NDS) are examples of enterprise-wide LDAP directories.
[Management] [Network]
An initiative of the DMTF to map the CIM schema to an LDAP Directory.
DEN's goals are to provide a consistent and standard data model to describe a network, its elements and its policies/rules. Policies are defined to provide quality of service or to manage to a specified class of service.
[File System]
A collective term for a directory, all of its files, and the directory trees of each of its subdirectories.
[General]
The recovery of data, access to data and associated processing through a comprehensive process of setting up a redundant site (equipment and work space) with recovery of operational data to continue business operations after a loss of use of all or part of a data center.
This involves not only an essential set of data but also an essential set of all the hardware and software to continue processing of that data and business. Any disaster recovery may involve some amount of down time.
The process of removing a dedicated connection between two N_Ports.
[Legal] [Storage System] [Network]
1. Process by which each party obtains information held by another party or non-party concerning a matter.
[ISO/IEC 27050-1]
Discovery is applicable more broadly than to parties in adversarial disputes. Discovery is also the disclosure of hardcopy documents, Electronically Stored Information and tangible objects by an adverse party. In some jurisdictions the term disclosure is used interchangeably with discovery.
2. The process of finding devices attached to a storage infrastructure.
3. The process of finding network interfaces in a networking infrastructure.
[Data Security]
A type of access control that allows a principal owning an object to grant or deny access to other principals.
[Storage System]
A non-volatile, randomly addressable, re-writable data storage device.
This definition includes rotating magnetic and optical disks and solid-state disks, or non-volatile electronic storage elements. It does not include specialized devices such as write-once-read-many (WORM) optical disks, nor does it include so-called RAM disks implemented using software to control a dedicated portion of a host computer's volatile random access memory.
[Storage System]
A set of disks from one or more commonly accessible disk subsystems, combined with a body of control software.
The control software presents the disks' storage capacity to hosts as one or more virtual disks. Control software is often called firmware or microcode when it runs in a disk controller. Control software that runs in a host computer is usually called a volume manager.
[Storage System]
A disk subsystem that includes control software with the capability to organize its disks as disk arrays.
[Storage System]
The unit in which data is stored and retrieved on a fixed block architecture disk.
Disk blocks are of fixed usable size (with the most common being 512 bytes), and are usually numbered consecutively. Disk blocks are also the unit of on-disk protection against errors; whatever mechanism a disk employs to protect against data errors (e.g., ECC) protects individual blocks of data. See sector.
[Storage System]
1. A cache that resides within a disk.
2. A cache that resides in a controller or host whose primary purpose is to improve disk or array I/O performance. See cache, controller cache, host cache.
[Data Recovery] [Windows]
A backup consisting of a copy of each of the blocks comprising a disk's usable storage area.
A disk image backup incorporates no information about the objects contained on the disk beyond what is stored in the image itself, and hence cannot always be used for individual object restoration.
[Storage System]
A function that reads all of the user data and check data blocks in a RAID array and relocates them if media defects are found.
[Storage System]
Synonym for data striping.
[Storage System]
A storage subsystem that supports only disk devices.
For a data stream using 8B/10B encoding, the difference between the number of ones and the number of zeros in a transmission character.
[Legal]
Range of processes associated with implementing records retention, destruction or transfer decisions that are documented in disposition authorities or other instruments.
[ISO 15489-1:2016]
[Data Management]
A policy that defines when lifecycle deletion should occur, and/or what actions to perform.
A set of FDFs associated with at least one controlling FCF that controls the operations of the set of FDFs.
A set of FCDFs associated with at least one controlling switch that controls the operations of the set of FCDFs.
[Data Management]
Acronym for Data Lifecycle Management.
[Storage System]
Acronym for Digital Linear Tape.
[Computer System]
Acronym for Direct Memory Access.
[Management] [Network]
Acronym for Desktop Management Interface.
[Management]
Acronym for Distributed Management Task Force.
[Network]
Acronym for Domain Name Service.
[Standards]
In XML, a specification of the permissible tags or "markup codes" in a document, and their meanings.
XML tags are delimited by the characters, "<" and ">". When a DTD is available for a document, a universal reader (program) can parse the document and display or print it.
[General] [Network]
1. A shared user authorization database that contains users, groups, and their security policies.
2. A set of interconnected network elements and addresses that are administered together and that may communicate.
3. The highest level in a three-level addressing hierarchy used in the Fibre Channel address identifier. A domain typically is associated with a single Fibre Channel switch.
[Windows]
1. A Windows server that contains a copy of a user account database. A Windows domain may contain both primary and backup domain controllers.
2. The control function accessible directly by an N-Port attached to a switch and also addressable in other domains using the Domain Controller address identifier of ""FF FC nn"" hex, where nn is the remote Domain Controller being accessed.
[Network]
A computer program that converts between IP addresses and symbolic names for nodes on a network in a standard way.
Most operating systems include a version of DNS. The service is defined by the IETF Standard RFCs 974, 1034, 1035, 1122, and 1123, and over a hundred subsequent RFCs that have not yet achieved full standard status.
[Data Security]
Acronym for Denial of Service.
[Computer System]
A technique used to increase data transfer rate by constantly keeping two I/O requests for consecutively addressed data outstanding.
A software component begins a double-buffered I/O stream by making two I/O requests in rapid sequence. Thereafter, each time an I/O request completes, another is immediately made, leaving two outstanding. If a disk subsystem can process requests fast enough, double buffering allows data to be transferred at a disk or disk array's full volume transfer rate.
[General]
Acronym for Disaster Recovery.
[Hardware]
Acronym for Dynamic Random Access Memory.
[Storage System]
Synonym for storage element (e.g., disk drive or tape drive).
[Windows]
A single letter of the alphabet by which applications and users identify a partition or physical or virtual disk to the Windows operating system.
[Computer System]
Synonyms for I/O driver.
[Data Security]
Acronym for Digital Signature Algorithm.
[Services]
Acronym for Data storage as a Service.
[Data Security]
Acronym for Digital Signature Standard.
[General]
Acronym for Document Type Definition.
[Computer System]
A pair of components, such as the controllers in a failure tolerant storage subsystem that share a task or class of tasks when both are functioning normally, but take on the entire task or tasks when one of the components fails.
Dual active controllers are connected to the same set of storage devices, and improve both I/O performance and failure tolerance compared to a single controller. Dual active components are also called active-active components.
[Hardware]
A set of random access memory integrated circuits or chips mounted on a circuit board, providing a 64-bit or greater data path using connectors on both sides of a single edge.
[Storage System]
An extension of single parity RAID techniques in which parity data is stored in two independent locations.
Dual parity is applicable to multiple RAID levels (e.g., RAID 3, 4, and 5); the result is some form of RAID 6.
[Data Security]
The responsibility that managers and their organizations have a duty to provide for information security to ensure that the type of control, the cost of control, and the deployment of control are appropriate for the system being managed. [NIST SP 800-30]
[Storage System]
Data which is redundant with data that is already in a dataset or I/O stream.
[Network]
An Internet protocol that allows nodes to dynamically acquire ("lease") network addresses for periods of time rather than having to pre-configure them.
DHCP greatly simplifies the administration of large networks, and networks in which nodes such as laptops frequently join and depart.
[Storage System]
A form of mapping in which the correspondence between addresses in the two address spaces can change over time.
[Hardware]
Byte-addressable computer memory that requires periodic refreshing.
A three-byte field encoding the Destination-ID, that contains the address identifier of the destination Nx_Port.
[Legal]
Short for electronic discovery.
[Data Security]
Acronym for Evaluation Assurance Level.
[Hardware]
Acronym for energy assisted magnetic recording.
[Standards]
Acronym for European Broadcast Union.
[Storage System] [Data Communication]
Acronym for Error Correcting Code.
[Energy]
Heat exchanger technology used to leverage colder external air to provide data center cooling.
Dry side economizers use cooler outdoor air; wet side economizers use cooling towers or chillers.
[Storage System] [Standards]
A family of SNIA standards for storage power management and related technologies.
A buffer associated with end-to-end flow control.
A credit scheme used to manage end-to-end flow control during the exchange of frames between two communicating devices.
[Storage System]
The amount of data stored on a storage system, plus the amount of unused formatted capacity in that system.
There is no way to precisely predict the effective capacity of an unloaded system. This measure is normally used on systems employing space optimization technologies.
An estimated calculation may be made as follows. Let D = the size of data already stored, Fd be the formatted capacity used to store that data, and Ft be the total formatted capacity on the system. Then the estimated effective capacity Ee is given by the formula Ee = D / (Fd / Ft). No unused formatted capacity is used in the estimation calculation.
[Storage System]
The ratio of the effective capacity of an idle storage system to the amount of power required to maintain the system in a ready idle state.
An entity within a Routing Function that performs the egress routing function role.
A process within a Routing Function that validates the frame, translates the S-ID, and then forwards the frame to the Native Fabric.
[Computer System]
The efficiency of any electrical device which transforms one type of power into another.
Efficiency is defined as output power divided by input power expressed as a percentage. All electrical components in a computer system, such as PDUs, UPSs and power supplies, incur some degree of power loss. Determining the total power loss in smaller systems with one power supply can be done by straightforward measurement of wall plug power and the total power supplied at the power supply's outputs. Larger systems require more complex methods.
[Legal]
Discovery that includes the identification, preservation, collection, processing, review, analysis, or production of Electronically Stored Information. [ISO/IEC 27050-1]
Although electronic discovery is often considered a legal process, its use is not limited to the legal domain.
[Storage System]
Synonym for Solid State Disk.
[Legal]
Data or information of any kind and from any source, whose temporal existence is evidenced by being stored in, or on, any electronic medium. [ISO/IEC 27040]
Electronically Stored Information (ESI) includes traditional e-mail, memos, letters, spreadsheets, databases, office documents, presentations, and other electronic formats commonly found on a computer. ESI also includes system, application, and file-associated metadata (3.26) such as timestamps, revision history, file type, etc. Electronic medium can take the form of, but is not limited to, storage devices and storage elements.
[Storage System]
An intelligent storage controller that mounts in a host computer's housing and attaches directly to a host's internal I/O interconnect, which is attached to storage devices mounted inside the host computer's housing.
Embedded controllers obviate the need for host bus adapters and external host I/O interconnects. Embedded storage controllers differ from host bus adapters in that they provide functions beyond I/O interconnect protocol conversion (e.g., RAID).
[Storage System]
SNIA Emeraldâ„¢ Power Efficiency Measurement Specification or SNIA Emeraldâ„¢ Program.
[Storage System]
SNIA Emeraldâ„¢ Power Efficiency Measurement Specification.
Defines a uniform taxonomy of storage subsystems and a standard way of measuring power efficiency of the storage subsystems defined in the taxonomy. For more detailed information, please consult the SNIA Emerald Program website (https://www.snia.org/emerald).
[Data Security]
A component of IPsec that permits the specification of various confidentiality mechanisms.
Generation of transmission characters from valid data bytes and special codes.
[Data Security]
The conversion of plaintext to encrypted text with the intent that it only be accessible to authorized users who have the appropriate decryption key.
An encapsulation header used for forwarding FC frames from a source Routing Function to a destination Routing Function.
[Data Security]
Encryption of information at its origin and decryption at its intended destination without intermediate decryption.
[Network]
1. Control of message flow between the two end parties to a communication on a network.
2. Flow control that occurs between two communicating Fibre Channel Nx-Ports.
[Data Security]
Safeguarding information in an information system from point of origin to point of destination. [CNSSI-4009]
[Hardware]
A recording technique that directs energy at the media to aid the recording process of an HDD.
[Computer System]
The power efficiency of a system over time.
While power and energy efficiency look about the same to a layman, the numbers may be different (even neglecting the units) on account of temporal variations in supply voltages, power and load factors and so on.
[Network]
The MAC address used by the ENode during the FCoE Initialization Protocol (FIP).
[Management] [Network]
Software that manages all aspects of an organization's assets, systems, services and functions.
ERM systems manage a set of resources in the wider perspective of an organization's entire business. Managing in an enterprise context requires that entities be named uniquely and locatable within the enterprise, that heterogeneity of platforms and services may be assumed, and that the dynamic nature of the environment is taken into account.
[Storage System]
A 200 Mbps serial I/O interconnect used on IBM Corporation's Enterprise System 9000 data center computers.
Similar to Fibre Channel in many respects, ESCON is based on redundant switches to which computers and storage subsystems connect using serial optical connections.
[Data Security]
A measure of the amount of uncertainty that an attacker faces to determine the value of a secret. [NIST SP 800-63]
The value is sometimes measured in bits of security strength, where a value of 0 indicates no security strength (i.e., full predictability or no randomness) and a positive value indicates increasing security strength.
[File System]
1. Acronym for End of Frame.
2. A designation or marker for the end of a file.
[Data Recovery]
A forward error correction technology used to provide data resiliency and long-term data integrity, by spreading data blocks and parity information across multiple storage devices or systems that may be in multiple physical locations.
Both the level of resiliency and where erasure coding is applied (at the array, at the node, or at the system level) can significantly affect how much processing overhead it consumes.
[Management] [Network]
Acronym for Enterprise Resource Management.
[Storage System] [Data Communication]
A scheme for checking the correctness of data that has been stored and retrieved, and correcting it if necessary.
An ECC consists of a number of bits computed as a function of the data to be protected, and appended to the data. When the data and ECC are read, the function is recomputed, the result is compared to the ECC appended to the data, and correction is performed if necessary. Error correcting codes differ from cyclic redundancy checks in that the latter can detect errors, but are not generally capable of correcting them. See cyclic redundancy check.
[Storage System]
Acronym for Enterprise Systems Connection.
[Legal]
Acronym for Electronically Stored Information.
[Data Security]
Acronym for Encapsulating Security Payload.
[Network]
A local area networking technology based on packetized transmissions between physical ports over a variety of electrical and optical media.
Ethernet can transport any of several upper layer protocols, the most popular of which is TCP/IP. Ethernet standards are maintained by the IEEE 802.3 committee.
The unqualified term Ethernet usually refers to 10 Mbps transmission on multi-point copper. Fast Ethernet is used to denote 100 Mbps transmission, also on multipoint copper facilities. Ethernet and Fast Ethernet both use CSMA/CD physical signaling. Gigabit Ethernet (abbreviated GBE) transmits at 1250 Megabaud (1 Gbit of data per second) using 8b/10b encoding with constant transmission detection.
[Network]
An adapter that connects an intelligent device to an Ethernet network., usually called an Ethernet network interface card, or Ethernet NIC.
See NIC.
[Standards]
An alliance of public service media organizations, with members in 56 countries.
In the domains of networks and storage systems, the EBU cooperates with relevant organizations including SMPTE, VSF, AMWA and others.
A behavior of a distributed system that does not provide immediate consistency guarantees.
See CAP Theorem.
[Data Recovery]
Acronym for External Volume Serial Number.
[General]
Shorthand for 1,000,000,000,000,000,000 (1018) bits.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,152,921,504,606,846,976, i.e., 260) common in computer system and software literature.
See also Exbibit.
[General]
Shorthand for 1,000,000,000,000,000,000 (1018) bytes.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,152,921,504,606,846,976, i.e., 260) common in computer system and software literature.
See also Exbibyte.
[General]
Shorthand for 1,152,921,504,606,846,976 (260) bits.
Binary notation is most commonly used for semiconductor memory sizes.
See also Exabit.
[General]
Shorthand for 1,152,921,504,606,846,976 (260) bytes.
Binary notation is most commonly used for semiconductor memory sizes.
See also Exabyte.
A set of one or more non-concurrent related sequences passing between a pair of Fibre Channel ports.
An exchange encapsulates a "conversation" such as a SCSI task or an IP exchange. Exchanges may be bidirectional and may be short or long lived. The parties to an exchange are identified by an Originator Exchange-Identifier (OX-ID) and a Responder Exchange_Identifier (RX_ID).
A generic term denoting either an Originator Exchange Identifier (OX-ID) or a Responder Exchange Identifier (RX_ID).
A Class 1 dedicated connection without intermix.
[Computer System]
A collective term for optional adapters in the form of printed circuit modules that can be added to intelligent devices.
Expansion cards include host bus adapters, network interface cards, as well as NVRAM, console, and other special purpose adapters.
[Computer System]
A mounting and internal bus attachment device within an intelligent device into which expansion cards are inserted.
[Data Management]
Data that is no longer required to be retained for any reason, becoming a candidate for permanent deletion.
Data may become expired when it has reached its defined retention period or when an event makes it obsolete and it has no further value to the organization. See disposition policy.
[Storage System]
A form of addressing in which the data's address is explicitly specified in the access request.
See implicit addressing.
[Data Security]
A defined way to breach the security of an IT system through a vulnerability.
[Computer System]
1. Synonym for present, i.e., to cause to appear or make available.
2. To move objects, such as data, from within a system to a location outside the system, usually requiring a transformation during the move.
Disk array control software exports virtual disks to its host environment. In file systems, a directory may be exported or made available for access by remote clients.
A sequence of words that may be present in a frame between the SOF delimiter and the Frame_Header to support frame handling functions not enabled by the Frame_Header.
[Standards]
An interface standardized by the SNIA that provides applications with standard methods for storing data and associated metadata on fixed content storage.
The XAM Application Programming Interface (API) is being standardized by SNIA.
[Standards]
A universal format for structured documents and data on the World Wide Web.
The World Wide Web Consortium is responsible for the XML specification. See www.w3.org.
[Storage System]
1. A set of consecutively addressed FBA disk blocks that is allocated to consecutive addresses of a single file.
2. A set of consecutively located tracks on a CKD disk that is allocated to a single file.
3. A set of consecutively addressed disk blocks that is part of a single virtual disk-to-member disk array mapping.
A single disk may be organized into multiple extents of different sizes, and may have multiple (possibly) non-adjacent extents that are part of the same virtual disk-to-member disk array mapping. This type of extent is sometimes called a logical disk.
[Storage System]
An intelligent storage controller that mounts outside its host computer's enclosure and attaches to hosts via external I/O interconnects.
External storage controllers usually mount in the enclosure containing the disks they control.
[Data Communication]
The center region of an eye diagram that does not occur for correctly formed signals, that distinguishes presence of signal (region above the eye) from absence of signal (region below the eye).
[Data Communication]
A diagram used to specify optical or electrical signal transition characteristics for transmitters, in which the horizontal axis represents normalized time from pulse start and the vertical axis represents normalized amplitude.
[Data Communication]
Quantitative measure of the space in an eye diagram that does not occur for correctly formed signal transitions, and that prevents signal values from incorrectly being identified as high or low.
The "Expansion" port within a Fibre Channel switch that connects to another Fibre Channel switch or bridge device via an inter-switch link.
E_Ports are used to link Fibre Channel switches to form a multi-switch fabric.
[Network]
A MAC address that is assigned by an FCF and is fabric-wide unique.
An identifier assigned to each Fabric in an Inter-Fabric Routing environment.
A Name-Identifier associated with a fabric.
The process by which a Fibre Channel node establishes a logical connection to a fabric switch.
[Computer System]
The restoration of a failed system component's share of a load to a replacement component after a failback event.
When a failed controller in a redundant configuration is replaced, the devices that were originally controlled by the failed controller are usually failed back to the replacement controller to restore the I/O balance, and to restore failure tolerance. Similarly, when a defective fan or power supply is replaced, its load, previously borne by a redundant component can be failed back to the replacement part.
[Computer System]
A mode of operation for failure tolerant systems in which a component has failed and its function has been assumed by a redundant component.
A system that protects against single failures operating in failed over mode is not failure tolerant, since failure of the redundant component may render the system unable to function. Some systems (e.g., clusters) are able to tolerate more than one failure; these remain failure tolerant until no redundant component is available to protect against further failures.
[Computer System]
The automatic substitution of a functionally equivalent system component for a failed one.
The term failover is most often applied to intelligent controllers connected to the same storage devices and host computers. If one of the controllers fails, failover occurs, and the survivor takes over its I/O load.
[Computer System]
The ability of a system to continue to perform its function (possibly at a reduced performance level) when one or more of its components has failed.
Failure tolerance in disk subsystems is often achieved by including redundant instances of components whose failure would make the system inoperable, coupled with facilities that allow the redundant components to assume the function of failed ones.
[File System] [Network]
Acronym for File Area Network.
[Storage System]
Synonym for device fanout.
[SCSI]
A form of SCSI that provides 10 megatransfers per second.
Wide fast SCSI has a 16-bit data path, and transfers 20 MBytes per second. Narrow fast SCSI transfers 10 MBytes per second. See wide SCSI, Ultra SCSI, Ultra2 SCSI, Ultra3 SCSI.
[Computer System]
Synonym for failure tolerance.
[Storage System]
Acronym for Fixed Block Architecture.
Acronym for Fibre Channel.
The Fibre Channel protocol level that encompasses the physical characteristics of the interface and data transmission media.
[Network]
The interface between an FC Switching Device or an FC stack and the FCoE Entity.
Each FC Entity contains a single instance of either a VE-Port, a VF-Port, or a VN_Port.
The Fibre Channel protocol level that encompasses 8B/10B encoding, and transmission protocol
The Fibre Channel protocol level that encompasses signaling protocol rules and the organization of data into frames, sequences, and exchanges.
The Fibre Channel protocol sublevel, that routes frames between VN-Ports and LCFs, based on the D-ID in the Frame-Header and the VF-ID in the VFT_Header if there is a VFT_Header.
The Fibre Channel protocol sublevel, that defines the rules and provides mechanisms that shall be used to transfer frames via the FC-1 level.
The Fibre Channel protocol sublevel, that defines functions and facilities that a VN-Port may provide for use by an FC-4 level, regardless of the FC-1 that is used.
The Fibre Channel protocol level that defines a set of services that are common across multiple Nx-Ports of a node.
FC-3 includes protocols for Basic Link Services, Extended Link Services and Hunt Groups.
Shorthand for Fibre Channel Avionics Environment.
Shorthand for Fibre Channel Arbitrated Loop.
In this and other FC-related entries, the numbers denote versions of the spec, developed and maintained by the INCITS T11 committee, that bears that name. The listed version is current as of this writing.
Shorthand for Fibre Channel Audio Video.
Shorthand for Fibre Channel Backbone.
When used, the number denotes a version of the spec. The listed version is current as of this writing.
Shorthand for Fibre Channel Device Attach.
Shorthand for Fibre Channel Framing and Signaling.
When used, the number denotes a version of the spec. The listed version is current as of this writing.
Shorthand for Fibre Channel Generic Services.
When used, the number denotes a version of the spec. The listed version is current as of this writing.
Shorthand for Fibre Channel Inter-Fabric Routing.
Shorthand for Fibre Channel Link Services.
When used, the number denotes a version of the spec. The listed version is current as of this writing.
Shorthand for Fibre Channel Methodologies for Interconnects.
When used, the number denotes a version of the spec. The listed version is current as of this writing.
[Fibre Channel]
The standard that describes the NVMe-oF mapping onto Fibre Channel.
Shorthand for Fibre Channel Physical Interface.
When used, the number denotes a version of the spec. The listed versions are current as of this writing.
Shorthand for Fibre Channel Single Byte (command set).
Shorthand for Fibre Channel Security Protocols.
Shorthand for Fibre Channel Switched (fabric interconnect).
When used, the number denotes a version of the spec. The listed versions are current as of this writing.
Shorthand for Fibre Channel Virtual Interface.
Shorthand for Fibre Channel Association.
Shorthand for Fibre Channel Data-Plane Forwarder
Shorthand for FCoE Forwarder.
Shorthand for Fibre Channel Industry Association.
[Network]
Acronym for Fibre Channel over Ethernet.
[Network]
A functional entity, coupled with a Lossless Ethernet MAC, that instantiates VE-Ports, VF-Ports, and VN-Ports, and/or creates FCoE_LEPs.
[Network]
The interface between the FC Entity and a Lossless Ethernet MAC. Each FCoE Entity contains one or more FCoE_LEPs.
[Network]
A Fibre Channel Switching Device with one or more Lossless Ethernet MACs, each coupled with an FCoE Controller, and optionally one or more Lossless Ethernet bridging devices and optionally an FC Fabric interface.
An FCF forwards FCoE frames addressed to one of its FCF-MACs based on the D_ID of the encapsulated FC frames.
[Network]
A protocol that enables the discovery and instantiation, and maintenance of FCoE devices.
[Network]
The data forwarding component of an FCoE Entity that handles FC frame encapsulation/decapsulation, and transmission/reception of encapsulated frames through a single Virtual Link.
[Network]
A Fibre Channel Node with one or more Lossless Ethernet MACs, each coupled with an FCoE Controller.
Shorthand for Fibre Channel Protocol.
[SCSI]
A series of standards that describes the operation of the SCSI protocol over Fibre Channel links.
A port that is capable of transmitting and receiving Fibre Channel frames according to the FC-0, FC-1, FC-2, and FC-3 levels of the Fibre Channel standards.
An FC-Port includes an LCF and at least one Nx_Port. The following are FC_Ports: PN_Ports, L_Ports, F_Ports, FL_Ports, Fx_Ports, E_Ports, and B_Ports.
[Network]
Acronym for Fiber Distributed Data Interface.
[Network]
An adapter that connects an intelligent device to an FDDI network.
Both FDDI-fiber adapters that connect to optical fiber FDDI networks, and FDDI-TP adapters that connect to twisted copper pair FDDI networks exist. Although network interface cards are usually referred to as NICs rather than as adapters, the term FDDI adapter is more common than FDDI NIC. See NIC.
[Data Security]
Standards (and guidelines) produced by NIST for government-wide use in the specification and procurement of Federal computer systems.
[Storage System]
Deduplication across multiple storage systems.
[Management] [Network]
A specification that defines a set of Java APIs for heterogeneous storage resource and storage network management.
This specification is a central technology of Jiro.
[Network]
An ANSI standard for a token ring Metropolitan Area Networks (MANs), based on the use of optical fiber cable to transmit data at a rate of 100 Mbits/second.
Both optical fiber and twisted copper pair variations of the FDDI physical standard exist. FDDI is a completely separate set of standards from Fibre Channel. The two are not directly interoperable.
The international spelling of the American word fiber.
The British spelling was selected for the Fibre Channel technology, though the American spelling is used to describe the fiber optic technologies defined for Fibre Channel.
A serial I/O interconnect capable of supporting multiple protocols, including access to open system storage (FCP), access to mainframe storage (FICON), and networking (TCP/IP).
Fibre Channel supports point to point, arbitrated loop, and switched topologies with a variety of copper and optical links running at speeds from 1 Gb/s to 10 Gb/s. The committee standardizing Fibre Channel is the INCITS Fibre Channel (T11) Technical Committee.
A form of Fibre Channel interconnect in which up to 126 nodes are connected in a loop topology, with each node's L-Port transmitter connecting to the L-Port receiver of the next node on the loop.
Nodes connected to a Fibre Channel Arbitrated Loop arbitrate for the single transmission that can occur on the loop at any instant using a Fibre Channel Arbitrated Loop protocol that is different from Fibre Channel switched and point to point protocols. An arbitrated loop may be private (no fabric connection) or public (attached to a fabric by an FL_Port). The network is defined by the FC-AL-2 standard INCITS 332 - 1999 [R2004].
The technical report describing a specific subset of Fibre Channel for use in defense and avionic applications.
A standard that defines mappings for transporting Fibre Channel over different network technologies, including operation of Fibre Channel over Ethernet (FCoE).
A simplified FC switching entity that forwards FC frames via A_Ports and F_Ports through an FCDF Switching Element.
A technical report that selects and restricts logical options from the Fibre Channel Framing and Signaling, Fibre Channel Protocol for SCSI, Fibre Channel Arbitrated Loop, Fibre Channel Generic Services, and Fibre Channel Single Byte Command Set standards.
The intent of the technical report is to facilitate interoperability between devices whether they are connected in a loop or fabric topology.
A standard describing the framing and signaling requirements for Fibre Channel links.
A standard describing in detail the Generic Services introduced in FC-FS-2, i.e., the name services, management services, and discovery services.
A mutual benefit corporation formed under the non-profit corporation laws of the State of California, whose members consist of companies that manufacture Fibre Channel systems, components, software, and tools, as well as provide Fibre Channel education and services to end-user customers.
A standard that specifies a set of protocols and methods to enable selective communication among Nx_Ports connected to different Fabrics.
The set of Fibre Channel ports, devices, and Fabrics that are connected by Fibre Channel links or are accessible by a common instance of an administrative tool or tools.
A standard describing the Link Services for Fibre Channel links.
A technical report specifying common methodologies for both arbitrated loop and switched environments, with the intention of facilitating interoperability between devices whether they are connected in a loop or Fabric topology.
[Network]
A technology that encapsulates Fibre Channel frames in Ethernet frames, allowing FC traffic to be transported over Ethernet networks.
An ANSI standard that describes the protocols used to implement security in a Fibre Channel fabric.
This standard includes the definition of protocols to authenticate Fibre Channel entities, protocols to set up session keys, protocols to negotiate the parameters required to ensure frame-by-frame integrity and confidentiality, and protocols to establish and distribute policies across a Fibre Channel fabric.
The industry standard command protocol for ESCON over Fibre Channel.
The second and third versions of this protocol are known as FC-SB-2 and FC-SB-3 respectively.
A standard that describes the requirements for an interconnecting fabric consisting of multiple fabric switch devices to support the ANSI/INCITS Fibre Channel protocols.
A standard for application-level distributed interprocess communication based on Intel Corporation's V1.0 Virtual Interface (VI) Architecture; formerly known as VIA.
IBM Corporation's implementation of the Fibre Channel Single Byte Command Set standards., developed to provide a Fibre Channel compatible implementation of ESCON.
Acronym for Fibre Connect.
[Hardware]
An integrated circuit composed of an array of transistors that may be programmed after manufacture to perform a specific function.
[Computer System]
A unit, or component of a system that is designed to be replaced "in the field;" i.e., without returning the system to a factory or repair depot.
Field replaceable units may either be customer-replaceable, or their replacement may require trained service personnel. See Customer Replaceable Unit.
[File System]
An abstract data object made up of (a.) an ordered sequence of data bytes, (b.) a name by which the object can be uniquely identified, and (c.) a set of properties.
Unlike the permanent address spaces of storage media, files may be created and deleted, and in most file systems, may expand or contract in size during their lifetimes.
[File System]
A logically contiguous region of file data.
[File System]
Reduction of file copies by replacing duplicates with pointers to a single original file.
See data deduplication.
[File System]
A software component that imposes structure on the address space of one or more physical or virtual disks so that applications may deal more conveniently with abstract named data objects of variable size (files).
File systems are often supplied as operating system components, but are also implemented and marketed as independent software components.
Spelling filesystem as a single word is also correct, especially when the term is used as an adjective.
[File System]
1. The act of aggregating multiple file systems into one large virtual file system, so that users access data objects through the virtual file system and are unaware of the underlying partitioning.
2. The act of providing additional new or different functionality, e.g., a different file access protocol, on top of one or more existing file systems.
[File System]
1. The use of virtualization to present several underlying file or directory objects as one single composite file.
2. The use of virtualization to provide HSM like properties in a storage system.
3. The use of virtualization to present an integrated file interface when file data and metadata are managed separately in the storage system. See block virtualization.
[File System]
An intelligent network node whose hardware and software are designed to provide file services to client computers.
Filers are pre-programmed by their vendors to provide file services, and are not normally user programmable. See appliance, file server.
A transmission word that is an idle or an ARBx primitive signal.
Fill words are transmitted between frames, primitive signals, and primitive sequences to keep a fibre channel network active.
A transmission word that is an idle or an ARBx primitive signal.
Fill words are transmitted between frames, primitive signals, and primitive sequences to keep a fibre channel network active.
[Data Recovery]
Acronym for Frozen Image Method.
[Storage System]
An identifier derived from the data, used to detect redundancy.
[Data Security]
Acronym for Federal Information Processing Standard.
[Computer System]
Low-level software for booting and operating an intelligent device.
Firmware generally resides in read-only memory (ROM) on the device.
An optimization for the transmission, by an initiator, of the first DATA IU in a Data Series for a write operation.
[SCSI]
A model of disks in which storage space is organized as linear, dense address spaces of blocks of a fixed size.
Fixed block architecture is the disk model on which SCSI is predicated. See count-key-data.
[Data Management]
1. Content that does not change.
2. Content that is prevented from change by the storage container in which it is kept.
[Storage System]
Storage systems and technology specialized for storing fixed content (i.e., data that does not change).
[Storage System]
Partitioning a byte stream into parts that are a constant number of bytes when performing compression or hash-based data deduplication.
[Storage System]
Synonym for solid state storage array.
[Hardware]
A type of non-volatile memory used in solid state storage.
[Storage System]
Synonym for solid state storage array.
Short for Fabric LOGIn.
[Energy]
A UPS that uses the momentum of a spinning disk or wheel to temporarily generate electricity in the event of a data center power failure.
Flywheel energy storage technology provides the bridge between normal power distribution and backup diesel generators and can replace conventional battery rooms.
A "Fabric Loop" port within a Fibre Channel fabric switch, capable of Fibre Channel Arbitrated Loop operations and connected to one or more NL-Ports via a Fibre Channel Arbitrated Loop.
An FL-Port becomes a shared entry point for public NL-Port devices to a Fibre Channel fabric. FL-Ports are intermediate ports in virtual point-to-point links between end ports that do not reside on the same loop, for example the NL-Port on an end node to the FL-Port on a switch to the F-Port in that switch to the N_Port on that end node through a single Fibre Channel fabric switch.
[Solid State]
Industry-speak for the new out-of-the-box state of an FRU, especially in reference to flash storage.
[Data Security]
An accurate bit-for-bit reproduction of the information contained on an electronic device or associated media, whose validity and integrity has been verified using an accepted algorithm. [NIST SP 800-72]
[Storage System]
The total amount of bytes available to be written after a system or device has been formatted for use, e.g., by an object store, filesystem or block services manager.
Formatted capacity, also called usable capacity, is less than or equal to raw capacity. It does not include areas set aside for system use, spares, RAID parity areas, checksum space, host- or filesystem-level remapping, "right sizing" of disks, disk labeling and so on. However, it may include areas that are normally reservedsuch as snapshot setasidesif they can alternatively be configured for ordinary data storage by the storage admin.
[Storage System]
The preparation of a disk for use by writing required information on the media.
Disk controllers format disks by writing block header and trailer information for every block on the disk. Host software components such as volume managers and file systems format disks by writing the initial structural information required for the volume or file system to be populated with data and managed.
[Data Recovery]
A set of algorithms that perform corrections that allow for recovery of one or more bit errors.
[Hardware]
Acronym for Field Programable Gate Array.
An ordered series of words that is the basic unit of data transmission in a Fibre Channel network.
A Fibre Channel frame consists of a Start of Frame Word (SoF) (40 bits); a Frame Header (8 Words or 320 bits); data (0 to 524 Words or 0 to 2192 ten bit encoded bytes; a CRC (One Word or 40 bits); and an End of Frame (EoF) (40 bits). See data frame.
The information contained in a frame between its Start-of-Frame and End-of-Frame delimiters, excluding the delimiters.
A technique for lowering the electromagnetic emission from Fibre Channel equipment by encoding frame content in a way to minimize repetitive bit sequences.
Frame Scrambling is required for operation at 8GFC.
Deprecated synonym for free space.
[Storage System] [Data Management]
1. The amount of capacity reported to an end user as unused assigned capacity.
In a simple world, free space is normally the same as assigned capacity less the amount of assigned capacity already written. But restrictions such as quotas, thin provisioning, and interactions between systems using different arithmetic may cause the reported free space to vary from the actual quantity.
2. The amount of capacity reported to the storage admin as unused formatted capacity.
A domain presented by a front domain switch.
A switch within an Inter-Fabric Router that provides connectivity to the Fabrics that are interconnected by the Inter-Fabric Router.
[Data Recovery]
Synonym for point in time copy.
[Computer System]
Acronym for Field Replaceable Unit.
Acronym for Fibre Channel Service Protocol.
[Data Recovery]
A backup in which all of a defined set of data objects are copied, regardless of whether they have been modified since the last backup.
A full backup is the basis from which incremental backups are taken. See cumulative incremental backup, differential incremental backup.
[Data Communication]
Concurrent transmission and reception of data on a single link.
[Storage System]
The average rate at which a single disk transfers a large amount of data (e.g., more than one cylinder) in response to one I/O request.
The full-volume data transfer rate accounts for any delays (e.g., due to inter-sector gaps, inter-track switching time and seeks between adjacent cylinders) that may occur during the course of a large data transfer. Full volume transfer rate may differ depending on whether data is being read or written. If this is true, it is appropriate to speak of full-volume read rate or full-volume write rate. Also known as spiral data transfer rate.
The "Fabric" port within a Fibre Channel fabric switch that provides a point-to-point link attachment to a single N_Port.
F_Ports are intermediate ports in virtual point-to-point links between end system ports, for example the N_Port on an end node to the F_Port on a switch to the F_Port in that switch to the N_Port on the other end node using a single Fibre Channel fabric switch. An F_Port is assumed to always refer to a port to which non-loop PN_Ports are attached to a Fabric, and does not include FL_Ports [FC-FS-2].
A Name-Identifier associated with an F-Port.
fabric
An entity consisting of one or more Switches that interconnect various Nx-Ports attached to it, and capable of routing frames using only the D-ID information in an FC-2 frame header.
[Computer System]
The process of reclaiming resources that are no longer in use.
Garbage collection has uses in many aspects of computing and storage. For example, in flash storage, background garbage collection can improve write performance by reducing the need to perform whole block erasures prior to a write. See also trim.
[Network]
A device that receives data via one protocol and transmits it via another.
[General]
Short for Gigabytes gigabytes per watt.
GB/W is a metric for evaluating the storage capacity provided per unit of power.
[Network]
Shorthand for Gigabit Ethernet.
Acronym for Gigabit Interface Converter.
[General]
Short for Gigabits per second per watt.
Gbps/W is a metric for evaluating data transfer rate provided per unit of power.
[Storage System]
The mathematical description of the layout of blocks on a disk.
The primary aspects of a disk's geometry are the number of recording bands and the number of tracks and blocks per track in each, the number of data tracks per cylinder, and the number and layout of spare blocks reserved to compensate for media defects.
[General]
Short for Gibibytes per watt.
GiB/W measures capacity in units of 230 bytes/watt, while GB/W uses units of 109 bytes/watt.
[General]
Shorthand for 1,073,741,824 (230) bits.
Binary notation is most commonly used for semiconductor memory sizes.
See also Gigabit.
[General]
Shorthand for 1,073,741,824 (230) bytes.
Binary notation is most commonly used for semiconductor memory sizes.
See also Gigabyte.
[General]
Short for Gibibits per second per watt.
Gibps/W measures data transfer rate in units of 230 bits/second/watt, in contrast to Gbps/W, which measures it in units of 109 bits/second/watt.
[Management] [Data Security]
Abbreviation for "group identifier" (Group IDentifier).
[General]
Shorthand for 1,000,000,000 (109) bits.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,073,741,824, i.e., 230) common in computer system and software literature.
For Fibre Channel, this refers to a bit transmission rate of 1,062,500,000 bits per second.
See also Gibibit.
[Network]
A group of Ethernet standards in which data is transmitted at 1 Gbit per second, using a 1250 Megabaud line rate and an adaptation of the Fibre Channel Physical Layer 8b/10b encoding.
GBE standards are handled by IEEE 802.3.
A transceiver that converts between electrical signals internal to a Fibre Channel or Ethernet device and the external optical or electrical interface of that device.
These devices are obsolete and have been replaced by smaller, cheaper, and faster devices, including SFP, SFP+, XFP and related XAUI-based modules.
[General]
Shorthand for 1,000,000,000 (109) bytes.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,073,741,824, i.e., 230) common in computer system and software literature.
See also Gibibyte.
Acronym for Gigabaud Link Module.
[Computer System]
A form of user interface to intelligent devices characterized by pictorial displays and highly structured, forms oriented input.
A GUI is valued for perceived ease of use compared with a command line interface.
[Standards] [Energy]
An initiative within the SNIA with a special interest in marketing, education, promotion and development of green storage technologies and support for the technical work of the Green Storage TWG.
[Energy]
A result of excessive marketing and ineffective engineering.
In fond memory of Tom Clark, who penned this definition ca. 2008.
[Data Security]
A collection of computer user identifiers and possibly other group identifiers used as a convenience in assigning resource access rights or operational privileges.
[Data Security]
Shorthand for group identifier.
[Standards]
Acronym for the SNIA Green Storage Initiative.
[Network]
Acronym for Gigabyte System Network.
[Computer System]
Acronym for Graphical User Interface.
A "Generic" Fabric Port, that can operate as either an E-Port or an F-Port.
A G-Port can determine the operating mode at switch port initialization, F-Port when an N_Port attachment is determined, E_Port when an E_Port attachment is determined.
[Data Security]
An unauthorized user who attempts to gain and/or succeeds in gaining access to an information system.
[Computer System]
To stop all activity in a computer system in an orderly manner.
[Hardware]
Acronym for heat assisted magnetic recording
[Storage System]
Rotating magnetic non-volatile disk drive.
[File System]
A path that provides a different name for a file.
Hard links are independent references to the same file; the file content is not deleted until every hard link to the file is deleted.
A zone consisting of zone members that are permitted to communicate with one another via the fabric.
Hard zones are enforced by fabric switches that prohibit communication among members not in the same zone on a frame by frame basis, based on the source and destination addressing. Well-known addresses are implicitly included in every zone.
[Data Management]
A value deterministically derived from data and assumed to be unique enough within the domain of that data for the purposes of its application.
[Storage System]
A method of performing data deduplication by calculating and comparing hash values.
[Data Security]
A value calculated over the contents of a message (usually using a cryptographic hash algorithm) that can be used to demonstrate that the contents of the message have not been changed during transmission.
[Computer System]
Acronym for Host Bus Adapter.
[Storage System]
Acronym for Hard Disk Drive
[Hardware]
Synonym for Read/Write head.
[Hardware]
A recording technique that directs heat at the media to aid the recording process of an HDD.
[General]
An approximation for a calculation that is too expensive to perform in its entirety.
[Data Management]
The automated migration of data objects among storage devices, usually based on inactivity.
Hierarchical storage management is based on the concept of a cost-performance storage hierarchy. By accepting lower access performance (higher access times), one can store objects less expensively. By automatically moving less frequently accessed objects to lower levels in the hierarchy, higher cost storage is freed for more active objects, and a better overall cost to performance ratio is achieved.
[Computer System]
The ability of a system to perform its function continuously (without interruption) for a significantly longer period of time than the reliabilities of its individual components would suggest.
High availability is most often achieved through failure tolerance. High availability is not an easily quantifiable term. Both the bounds of a system that is called highly available and the degree to which its availability is extraordinary must be clearly understood on a case-by-case basis.
[Network] [Standards]
An ANSI standard for an 800 Mbit/second I/O interface primarily used in supercomputer networks.
The subsequent 6400 Mbit per second I/O interface standard, HIPPI-6400, is more commonly referred to as the Gigabyte System Network (GSN) standard.
A form factor that allows quick connect/disconnect for Fibre Channel copper interfaces.
[Network] [Standards]
Acronym for High Performance Parallel Interface.
[Data Security]
Acronym for Hashed Message Authentication Code.
[Computer System]
[Computer System]
Synonym for host bus adapter.
[Storage System]
A disk array whose control software executes in one or more host computers rather than in a disk controller.
The member disks of a host-based array may be part of different disk subsystems. See controller based array.
[Computer System]
Virtualization implemented in a host computer.
[Computer System]
Synonym for host I/O interconnect.
[Computer System]
An I/O adapter that connects a host computer bus to an I/O interconnect.
Adapter is the preferred term for Fibre Channel and SCSI interconnects. The term NIC is used for networking interconnects such as Ethernet and token ring.
[Storage System]
A cache that resides within a host computer whose primary purpose is to improve disk or array I/O performance.
Host cache may be associated with a file system or database, in which case, the data items stored in the cache are file or database entities. Alternatively, host cache may be associated with the device driver stack, in which case the cached data items are sequences of disk blocks. See cache, controller cache, disk cache.
[Computer System]
Any computer system to which disks, disk subsystems, or file servers are attached and accessible for data storage and I/O.
Mainframes, servers, workstations and personal computers, as well as multiprocessors and clustered computer complexes, are all referred to as host computers in SNIA publications.
[Computer System]
A storage subsystem's host computer or host computers, inclusive of operating system and other required software instance(s).
The term host environment is used in preference to host computer to emphasize that multiple host computers are being discussed, or to emphasize the importance of the operating system or other software in the discussion.
[Computer System]
An I/O interconnect used to connect a host computer's host bus adapter to storage subsystems or storage devices.
See I/O interconnect, channel.
[Capacity Optimization]
Deprecated synonym for source data deduplication.
[Energy]
Arranging IT equipment in racks such that heat is exhausted in designated aisles while cool air is supplied in the alternating aisles.
[Data Recovery]
Synonym for online backup.
See cold backup, offline backup.
[Storage System]
A range of addresses that are accessed with relatively high frequency.
[Storage System]
The use of hot bands in a workload for test purposes to reward cache behavior.
[Storage System]
A disk whose capacity to execute I/O requests is saturated by the aggregate I/O load directed to it from one or more applications.
[File System]
A frequently accessed file.
Hot files are generally the root cause of hot disks, although this is not always the case. A hot disk can also be caused by operating environment I/O, such as paging or swapping.
[Storage System]
A disk being used as a hot standby component.
[Computer System]
A redundant component in a failure tolerant subsystem that is powered and ready to operate, but that does not operate as long as all of its target primary components are functioning.
Hot standby components increase storage subsystem availability by allowing systems to continue to function when a component such as a controller fails. When the term hot standby is used to denote a disk, it specifically means a disk that is spinning and ready to be written to, for example, as the target of a rebuilding operation.
[Computer System]
The substitution of a replacement unit (RU) in a system for a defective unit, where the substitution can be performed while the system is performing its normal functioning normally.
Hot swaps are physical operations typically performed by humans. See automatic swap, cold swap, warm swap.
[Computer System]
An adapter that can be hot swapped into or out of an intelligent device.
Some adapters that are called hot swap adapters should more properly be termed warm swap adapters, because the function they perform is interrupted while the substitution occurs.
[General]
The term used to describe flip/flopping; when an opinion continually switches back and forth between two or more choices.
For example: Design choice "A" is selected; but a week later, design choice "B" is selected; then after another week of consideration, the design choice is switched back to "A".
[Data Recovery]
Acronym for Hierarchical Storage Management.
Acronym for High Speed Serial Direct Connect.
[Standards]
Acronym for HyperText Markup Language.
[Standards]
Acronym for HyperText Transfer Protocol.
[Network]
A communications infrastructure element to which nodes on a multi-point bus or loop are physically connected.
Commonly used in Ethernet and Fibre Channel networks to improve the manageability of connecting devices to a bus structure, both managing physical cables and supporting the addition or removal of nodes from the bus while it is operating. Hubs maintain the logical loop topology of the network of which they are a part, while creating a “hub and spoke” physical star layout. Unlike switches, hubs do not aggregate data transfer capacity.
A port on a Fibre Channel hub whose function is to pass data transmitted on the physical loop to the next port on the hub.
Hub ports include loop healing port bypass functions. Some hubs have additional management functionality. There is no definition of a hub port in any Fibre Channel standard.
[Storage System]
A storage array consisting of multiple types of storage devices.
[Cloud]
A composition of two or more clouds (private, community, or public) that remain unique entities but are bound together by standardized or proprietary technology that enables data and application portability.
[Hardware]
A dual in-line memory module that contains multiple types of volatile and non-volatile memory technologies.
[Storage System]
A disk drive that consists of multiple types of storage media.
[Standards]
A computer language consisting of a set of tags or "markup" codes that describe how a document is displayed by a web browser.
HTML tags are delimited by the characters "<" and ">". For example, the markup code "<p>" indicates that a new paragraph is beginning, while "</p>" indicates that the current paragraph is ending.
[Computer System]
Shorthand for input/output.
I/O is the process of moving data between a computer system's main memory and an external device or interface such as a storage device, display, printer, or network connected to other computer systems. This encompasses reading, or moving data into a computer system's memory, and writing, or moving data from a computer system's memory to another location.
[Computer System]
An adapter that converts between the timing and protocol requirements of a system's memory bus and those of an I/O interconnect or network.
In the context of storage subsystems, I/O adapters are contrasted with embedded storage controllers, that not only adapt between buses and interconnects, but also perform transformations such as device fan-out, data caching, and RAID. host bus adapters (HBAs) and Ethernet NICs are types of I/O adapters.
[Computer System]
Any resource in the I/O path (e.g., device driver, host bus adapter, I/O interconnect, intelligent controller, or disk) whose performance limits the performance of a storage subsystem as a whole.
[Computer System]
Synonym for I/O interconnect.
[Computer System]
Synonym for I/O adapter.
[Computer System]
A host computer software component (usually part of an operating system) whose function is to control the operation of peripheral controllers or adapters attached to the host computer.
I/O drivers manage communication and data transfer between applications and I/O devices, using host bus adapters as agents. In some cases, drivers participate in data transfer, although this is rare with disk and tape drivers, since most host bus adapters and controllers contain specialized hardware to perform data transfers.
[Computer System]
A characterization of applications that describes how strongly their performance depends on the performance of the I/O subsystem that provides their I/O services.
I/O intensive applications may be either data transfer intensive or I/O request intensive or both.
[Computer System]
Any path used to transfer data and control information between components of an I/O subsystem.
An I/O interconnect consists of wiring (either cable or backplane), connectors, and all associated electrical drivers, receivers, transducers, and other required electronic components. I/O interconnects are typically optimized for the transfer of data, and tend to support more restricted configurations than networks. See channel, device channel, network.
[Computer System]
A sequence of I/O requests made to an I/O subsystem.
The requests that comprise an I/O load include both user I/O and host overhead I/O, such as swapping, paging, and file system activity.
[Computer System]
Synonym for load balancing.
[Computer System]
A read, write, or control function performed to, from or within a computer system.
See I/O request.
[Storage System]
1. The ratio of maximum IOPS deliverable by a system, to the input power required to deliver those IOPS.
2. The ratio of data transfer rate readable or writable by a system, to the input power required to achieve that data transfer rate.
[Computer System]
A request by an application to read or write a specified amount of data.
In the context of real and virtual disks, I/O requests specify the transfer of a number of blocks of data between consecutive disk block addresses and contiguous memory locations. See I/O operation.
[Computer System]
A collective term for the set of devices and software components that operate together to provide data transfer services.
A storage subsystem is one type of I/O subsystem.
[Network]
The first generation of a hardware bus typically used to connect management related devices to a system.
[Hardware]
The second generation of a hardware bus typically used to connect management related devices to a system.
[Services]
Acronym for Infrastructure as a Service.
[Network]
Acronym for Internet Control Message Protocol.
[Storage System]
Acronym for Integrated Drive Electronics.
[General]
A property of an operation in which the same result is obtained no matter how many times the operation is performed.
In an environment with a single writer, writing a block of data to a disk is an idempotent operation, whereas writing a block of data to a tape is not, because writing a block of data twice to the same tape results in two adjacent copies of the block.
[Computer System]
A property of an operation in which a single effect occurs no matter how many times the operation is invoked.
[Data Security]
The process of determining the unique identity of an entity.
[Data Security]
Representation of an actual user (or application or service or device).
An example is the assignment of the user name joej (the identity) to represent the human user Joe Jones for purposes of authentication and authorization.
[Storage System]
A state in which a storage system is serving no user-initiated I/O requests, but is ready to service them upon arrival with normal latency.
Storage systems may perform extensive system-initiated I/O during idle periods as they execute routine background housekeeping tasks.
[Energy]
The power consumption of a system when powered on but with no active workload.
In a data stream using 8B10B encoding, an ordered set of four transmission characters normally transmitted between frames to indicate that a fibre channel network is idle.
[Data Security]
Acronym for Intrusion Detection System.
[Network] [Standards]
Acronym for Internet Engineering Task Force.
[Storage System]
A gateway-to-gateway protocol that provides fibre channel fabric services to fibre channel devices over a TCP/IP network.
[Network] [Data Security]
Acronym for Internet Key Exchange.
[Data Management]
Acronym for Information Lifecycle Management.
[iSCSI]
Acronym for iSCSI Management API.
[Storage System]
A form of addressing usually used with tapes in which the data's address is inferred from the form of the access request.
Tape commands that do not include an explicit block address but implicitly specify the next or previous block from the current tape position, from which the block address must be inferred by the device. See explicit addressing.
[SCSI]
Synonym for entry/exit slot.
[Storage System]
Deprecated synonym for inline data deduplication.
[Computer System]
Virtualization functions or services that are in the data path.
In a system that implements in-band virtualization, virtualization services such as address mapping are performed by the same functional components used to read or write data. See out-of-band virtualization
[Data Security]
An occurrence that actually or potentially jeopardizes the confidentiality, integrity, or availability of an information system or the information the system processes, stores, or transmits or that constitutes a violation or imminent threat of violation of security policies, security procedures, or acceptable use policies. [NIST FIPS 200]
[Data Security]
A method of sanitization that reduces a storage device or element to ash, in an approved facility. [ISO/IEC 27040]
[Standards]
Shorthand for International Committee for Information Technology Standards.
INCITS is one of about 100 standards organizations accredited by ANSI to prepare national standards and make recommendations to ANSI concerning international standards. INCITS assigns technical committees to prepare standards associated with information technology, including JPEG, computer security, biometric information, SCSI (Technical Committee T10), Fibre Channel (Technical Committee T11), and many more.
[SCSI] [Standards]
The INCITS SCSI Storage Interfaces Technical Committee (INCITS TC T10).
The INCITS T10 Technical Committee is the standards development committee accredited by INCITS to develop SCSI standards for communication between from host devices (initiators) to storage device controllers (targets).
[Standards]
The INCITS Fibre Channel Interfaces Technical Committee (INCITS TC T11).
The INCITS T11 Technical Committee is the standards development committee accredited by INCITS to develop standards related to Fibre Channel, related serial storage interfaces, and certain storage management interfaces.
[Standards]
The INCITS T13 Technical Committee is the standards development committee accredited by INCITS to develop ATA standards for communication between a host and a storage device.
[Data Recovery]
Any backup in which only data objects modified since the time of some previous backup are copied.
Incremental backup is a collective term for cumulative incremental backups and differential incremental backups. See cumulative incremental backup, differential incremental backup, full backup.
[Storage System]
A disk array whose data mapping is such that different member disks can execute multiple application I/O requests concurrently.
[Computer System]
A interconnect between computer system(s) and computer system component(s).
This includes computer system to computer system connectivity and computer system component to computer system component connectivity.
A term indicating that at the FC-2 level, the amount of buffering available at the Sequence Recipient is assumed to be unlimited.
Buffer overrun must be prevented by each ULP by choosing an appropriate amount of buffering per sequence based on its maximum transfer unit size.
[Data Management]
Data that is interpreted within a context such as an application or a process.
[Data Security]
Measures that protect and defend information and information systems by ensuring their availability, integrity, authentication, confidentiality, and nonrepudiation.
Information assurance encompasses system reliability and strategic risk management, and includes providing for restoration of information systems using protection, detection, and reaction capabilities.
A frame header field indicating the category to which the frame payload belongs (e.g., Solicited Data, Unsolicited Data, Solicited Control and Unsolicited Control).
[Data Management]
The policies, processes, practices, services and tools used to align the business value of information with the most appropriate and cost-effective infrastructure from the time information is created through its final disposition.
Information is aligned with business requirements through management policies and service levels associated with applications, metadata and data.
[Data Management]
The discipline and function of oversight and control of information resources.
[Data Management]
The processes associated with managing information as it progresses through various lifecycle states associated with a Business Process.
These services exploit information about data content and relationships in making decisions. Examples include records management and content management applications.
[Data Management]
A repository-independent definition of entities (i.e., objects) and the relationships and interactions between these entities.
The CIM schemas are an example of an information model. An information model differs from a data model, which is repository-specific.
[Management]
The category of resources that exclusively encompass information services.
[Data Security]
Preservation of confidentiality, integrity and availability of information. [ISO/IEC 27000:2018]
In addition, other properties such as authenticity, accountability, non-repudiation and reliability can also be involved.
[Management]
A set of functions that treat data within an interpretation context.
[Data Security]
The entire infrastructure, organization, personnel and components for the collection, processing, storage, transmission, display, dissemination and disposition of information.
[General]
All aspects of information creation, access, use, storage, transport and management.
The term Information Technology addresses all aspects of computer and storage systems, networks, users and software in an enterprise.
[SCSI]
1. An related collection of data specified by FC-4 to be transferred as a single FC-2 sequence.
2. A delimited and sequenced set of information in a format appropriate for transport by the service delivery subsystem.
A SCSI IU may contain a command, data, response, or task management request.
[Services]
Delivery over a network of an appropriately configured virtual computing environment, based on a request for a given service level.
Typically, IaaS is either self-provisioned or provisionless and is billed based on consumption.
[Computer System]
Virtualization implemented in the storage fabric, in separate devices designed for the purpose, or in network devices.
Examples are separate devices or additional functions in existing devices that aggregate multiple individual file system appliances or block storage subsystems into one such virtual service, functions providing transparent block or file system mirroring functions, or functions that provide new security or management services.
A process within a Routing Function that translates the D-ID, translates embedded N-Port-IDs and stores the Exchange context if needed, adds the IFR-Header and Enc-Header if needed, and then forwards the frame to the next hop Routing Function or Egress Routing Function.
[Computer System]
The cost of a system expressed in terms of the number and type of components it contains.
The concept of inherent cost allows technology-based comparisons of disk subsystem alternatives by expressing cost in terms of number of disks, ports, modules, fans, power supplies, cabinets, etc. Because it is inexpensively reproducible, software is generally assumed to have negligible inherent cost.
The relative offset of the block or sub-block transmitted by the first frame in a sequence, specified by an upper layer protocol.
The initial relative offset need not be zero.
1. The startup and initial configuration of a device, element, system, piece of software or network.
2. For FC-1, the period beginning with power on and continuing until the transmitter and receiver at that level become operational.
[Computer System] [SCSI]
1. The system component that originates an I/O command over an I/O interconnect.
2. The endpoint that originates a SCSI I/O command sequence.
I/O adapters, network interface cards, and intelligent I/O interconnect control ASICs are typical initiators. See LUN, originator, target, target port identifier.
[Fibre Channel]
NVMe-Port that is the NVMe host port for an NVMe-oF/FC association.
[SCSI]
The interconnect address of an initiator.
[iSCSI]
The unique identifier that an initiator assigns to its end point of the session.
When combined with the iSCSI Initiator Name, the Initiator Session Identifier provides a worldwide unique name for its SCSI Initiator Port.
[Storage System]
Data deduplication performed before writing the deduplicated data.
[File System]
A persistent data structure in a UNIX or UNIX-like file system that describes the location of some or all of the disk blocks allocated to the file.
[General]
The creation of an instance of a class or object oriented abstraction.
[Computer System]
A type of hardware interface widely used to connect hard disks, CD-ROMs and tape drives to a PC, but also used in other systems.
The IDE interface is officially known as the ATA specification.
[Data Security]
Property of accuracy and completeness. [ISO/IEC 27000:2018]
[Storage System]
Synonym for storage controller.
[Computer System]
A computer, storage controller, storage device, or appliance.
[Network]
A high-performance standards-based I/O interconnect.
[Management]
A protocol used to perform management and monitoring operations on a system independent of the host system components.
The entire interconnection of Fabrics and Inter-Fabric Routers.
A device that performs Inter-Fabric Routing and consists of a Routing Function, Translate Domain switches, and Front Domain switches.
The process of forwarding frames through a specific Routing Function, including the translation of N_Port_IDs.
[Computer System]
A physical facility by which system elements and devices are connected together and through which they can communicate with each other.
I/O buses and networks are both interconnects.
An optical or electrical connector that connects the media to the Fibre Channel transmitter or receiver.
An interface connector consists of both a receptacle and a plug.
A process within a Routing Function that validates the frame headers, updates the IFR-Header, removes and adds a new Enc_Header, then forwards the frame to the next hop Routing Function.
A Fibre Channel class of service that provides a full data transfer capacity dedicated Class 1 connection, but allows connectionless Class 2 and Class 3 traffic to share the link during intervals when data transfer capacity is unused.
[Standards]
A worldwide federation of national standards bodies from more than 145 countries; a non-governmental organization whose work results in international agreements that are published as International Standards and other types of ISO documents.
[Network] [Data Security] [Standards]
A large open international community of network designers, operators, vendors, and researchers concerned with evolution and smooth operation of the Internet.
The IETF is the standards body responsible for Internet standards called RFCs, including SNMP, TCP/IP and policy for QoS. The IETF has a web site atwww.ietf.org.
[Network] [Data Security]
A protocol specified by the IETF that performs mutual authentication between two parties and establishes an IKE Security Association (SA) that includes shared secret information that can be used to efficiently establish SAs for Encapsulating Security Payload (ESP) or Authentication Header (AH) and a set of cryptographic algorithms to be used by the SAs to protect the traffic that they carry.
IKEv2 is defined in RFC-4306.
IKE Version 2 (IKEv2) is not compatible with Version 1.
[Network]
A protocol that provides connectionless best effort delivery of datagrams across heterogeneous physical networks.
[Computer System]
The ability of systems to work with or use data and protocols from other systems.
[Computer System]
A hardware or software signal that causes a computer to stop executing its instruction stream and switch to another stream.
Software interrupts are triggered by application or other programs. Hardware interrupts are caused by external events, to notify software so it can deal with the events. The ticking of a clock, completion or reception of a transmission on an I/O interconnect or network, application attempts to execute invalid instructions or reference data for which they do not have access rights, and failure of some aspect of the computer hardware itself are all common causes of hardware interrupts.
[Computer System]
A human-activated switch present on some intelligent devices that is used to generate interrupts.
Interrupt switches are usually used for debugging purposes.
A Fibre Channel specification for copper cabling that allows up to 13m total cable length within a single enclosure, which may contain multiple devices.
[Data Security]
Unauthorized access to a network or a network-connected system, that is, deliberate or accidental unauthorized access to information systems, to include malicious activity against information systems, or unauthorized use of resources within information systems. [ISO/IEC 27039:2015]
[Data Security]
The process of identifying that an intrusion has been attempted, is occurring, or has occurred.
[Data Security]
Technical system that is used to identify that an intrusion has been attempted, is occurring, or has occurred and possibly respond to intrusions in information systems and networks. [ISO/IEC 27039:2015]
[Storage System]
Shorthand for I/O Operations per second.
IOPs can also be the plural of IOP (short for I/O operation), depending on context.
[Energy]
Input/Output Operations per Second per Watt.
IOPS/W is a metric for evaluating storage I/O performance per unit of power.
[Network]
Acronym for Internet Protocol.
[Network] [Data Security]
A suite of cryptographic algorithms, protocols and procedures used to protect information, authenticate communications, control access, and provide non-repudiation at the IP layer.
The two key protocols in IPsec are the Authentication Header (AH) and Encapsulating Security Payload (ESP) protocols.
[Computer System]
Acronym for Intelligent Peripheral Interface.
[Hardware]
Acronym for Intelligent Platform Management Interface.
[Network] [Data Security]
Shorthand for IP Security.
[Storage System]
Acronym for Internet Small Computer Systems Interface.
[iSCSI]
A SCSI Device using an iSCSI service delivery subsystem, in other words an iSCSI-specific transport mechanism for SCSI commands and responses (information units).
[iSCSI]
Another name for the iSCSI initiator; an iSCSI Node within the iSCSI Client Network Entity.
[iSCSI]
Another name for a SCSI Initiator Port used for iSCSI.
[iSCSI]
The layer that builds/receives iSCSI PDUs and relays/receives them to/from one or more TCP connections that form an iSCSI session.
[iSCSI]
A component of an iSCSI Network Entity that has a TCP/IP address and can be used by a node within that entity for connections to another iSCSI node.
An Initiator iSCSI Network Portal is identified by its IP address. A target iSCSI Network Portal is identified by its IP address and listening TCP port.
[iSCSI]
A set of iSCSI Network Portals within an iSCSI Node.
When a session has multiple connections, all connections in a session must use the portals in a single iSCSI Portal Group.
[iSCSI]
A tag identifying all portals in an iSCSI Portal Group within an iSCSI Node.
All portals in the group have the same iSCSI Portal Group Tag.
[iSCSI]
Another name for the iSCSI target, i.e., an iSCSI Node within the iSCSI Server Network Entity.
[iSCSI]
Another name for a SCSI Target Port used for iSCSI.
[iSCSI]
Acronym for Initiator Session Identifier.
[iSCSI]
Acronym for Internet Storage Name Service.
[iSCSI]
Grouping of storage nodes for facilitating discovery and login control of these nodes.
[Standards]
Acronym for International Organization for Standardization.
[General]
Acronym for Information Technology.
[Data Security]
All aspects related to defining, achieving, and maintaining confidentiality, integrity, availability, non-repudiation, accountability, authenticity, and reliability of information assets.
[General]
Shorthand for Information Unit.
[Network] [Storage System]
The Internet Wide Area Remote Direct Memory Access Protocol
[SCSI]
A relationship specified in SAM-2 between a SCSI Initiator Port and a SCSI Target Port.
[Computer System]
An object oriented computer programming language that is similar to C++.
[Storage System]
Shorthand for Just a Bunch Of Disks.
Originally used to mean a collection of disks without the coordinated control provided by control software; today the term JBOD most often refers to a cabinet of disks whether or not RAID functionality is present. See disk array.
[Computer System]
A Java-based architecture and supporting services for publishing and discovering devices and services on a network.
Deviation in timing that a bit stream encounters as it traverses a physical medium.
A special 10-bit character used to indicate the beginning of a Fibre Channel command.
[Data Security]
A sequence of bits used for cryptographic operations and/or for producing other keys.
The same plaintext encrypted with different keys yields different ciphertexts, each of which requires a different key for decryption. In a symmetric cryptosystem the encryption and decryption keys are the same. In an asymmetric cryptosystem the encryption and decryption keys are different.
[Data Security]
A process used in a cryptographic system that can restore access to data by providing for key deposit and recovery.
Key backup is sometimes used as a replacement term for key escrow, which has become encumbered with additional meanings.
[Data Security]
A process in which the storage of a cryptographic key is entrusted to a third party escrow agent who will disclose it only to the owner or another authorized user.
Key escrow systems are used to ensure that access to encrypted data can be restored in case of key loss due to error, disaster or a malicious act.
[Data Security]
A cryptographic protocol and procedure in which two communicating entities determine a shared key in a fashion such that a third party who reads all of their communication cannot effectively determine the value of the key.
A common approach to key exchange requires such a third party to compute a discrete logarithm over a large field in order to determine the key value, and relies for its security on the computational intractability of the discrete logarithm problem.
[Data Security]
The supervision and control of the process, usually in accordance with a security policy, by which cryptographic keys are generated, stored, protected, distributed, applied, archived, revoked and destroyed.
[Data Security]
An OASIS standard that establishes a single, comprehensive protocol for communication between enterprise key management servers and cryptographic clients.
[Data Security]
A public key and its corresponding private key as used in public key cryptography (i.e., asymmetric cryptosystems).
[Data Security]
A system characterized by the presence of some mechanism for obtaining exceptional access to a cryptographic key in case of loss by error, disaster, or malicious intent.
See also key escrow.
[Storage System]
A type of object storage interface where a key is used to address the associated object.
[Data Security]
A method of encrypting keys (along with associated integrity information) that provides both confidentiality and integrity protection using a symmetric key. [NIST SP 800-57 Part 1]
[Data Security]
A key or authentication information in physical or magnetic form.
[General]
Shorthand for 1,024 (210) bits.
Binary notation is most commonly used for semiconductor memory sizes.
See also Kilobit.
[General]
Shorthand for 1,024 (210) bytes.
Binary notation is most commonly used for semiconductor memory sizes.
See also Kilobyte.
[General]
1,000 (103) bytes.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,024, or 210) common in computer system and software literature.
See also Kibibit.
[General]
1,000 (103) bytes.
The SNIA uses the base 10 convention commonly found in I/O-related and scientific literature rather than the base 2 convention (1,024, or 210) common in computer system and software literature.
See also Kibibyte.
[Data Security]
Acronym for Key Management Interoperability Protocol.
[Data Recovery]
An identifier associated with a removable media or cartridge.
Labels may be humanly readable, machine readable, or both. See external volume serial number, media ID.
[Data Security]
Use of sophisticated signal recovery equipment in a laboratory environment to recover information from data storage media. [NIST SP 800-88]
Magnetic force microscopes and other similar equipment can be used to recover data from magnetic media that has been erased or damaged.
[Network]
Acronym for Local Area Network.
[Fibre Channel]
One of multiple point-to-point physical connections that make up a single link.
[Storage System]
An I/O request that specifies the transfer of a large amount of data.
‘Large' depends on the context, but typically refers to requests for 64 KBytes or more of data. See small I/O request.
[Network]
In the context of serial data communication networks, a solid-state element that emits light, usually in the near-infrared or infrared spectrum, modulated to carry binary information at very high data rates along an optical fiber.
The term laser was originally an acronym for "light amplification by stimulated emission of radiation."
[Computer System]
1. Synonym for I/O request execution time, the time between the making of an I/O request and completion of the request's execution.
2. Short for rotational latency, the time between the completion of a seek and the instant of arrival of the first block of data to be transferred at the disk's read/write head.
[Computer System]
A failure of a system component that has not been recognized because the failed aspect of the component has not been exercised since the occurrence of the failure.
A field-developed media defect on a disk surface is a latent fault until an attempt is made to read the data in a block that spans the defect.
[Storage System]
Acronym for Logical Block Address.
[Network]
An optical fiber connector complying with international standard IEC 61754-20:2002.
LC connectors are the most common connector in optical data communications networks, including Ethernet and Fibre Channel. A dual LC connector is used, carrying separate fibers for transmitted and received data.
[Network]
Acronym for Lightweight Directory Access Protocol.
[Storage System]
Acronym for Logical Disk Manager.
[Data Security]
The security objective of granting users only those accesses they need to perform their official duties. [NIST SP 800-12]
[Computer System]
Acronym for Light Emitting Diode.
[Legal]
Process of suspending the normal disposition or processing of records and Electronically Stored Information as a result of current or anticipated litigation, audit, government investigation or other such matters. [ISO/IEC 27050-1]
The issued communication that implements the legal hold can also be called a "hold," "preservation order," "suspension order," "freeze notice," "hold order," or "hold notice."
[Storage System]
A storage device containing a robotic media handler capable of storing multiple pieces of removable media and loading and unloading them from one or more drives in arbitrary order.
[Storage System]
The deletion of data at the end of its lifecycle.
See disposition policy.
[Network]
An IETF protocoloriginally a subset of the X.500 protocolfor creating, accessing and removing objects and data from a directory.
LDAP provides the ability to search, compare, add, delete and modify directory objects, as well as modifying the names of these objects. It also supports bind, unbind and abandon (cancel) operations for a session. LDAP got its name from its goal of being a simpler form of DAP (Directory Access Protocol).
[File System]
1. A self-describing, self-contained tape storage format intended for interchange of data between different software systems.
See ISO/IEC 20919.
2. A software or hardware implementation of a file system using the LTFS tape format.
[Tape]
An open standard magnetic tape technology developed in cooperation by HP, IBM and Quantum.
[General]
1. A physical connection (electrical or optical) between two nodes of a network.
2. Two unidirectional fibers or conductors transmitting in opposite directions and their associated transmitters and receivers.
3. The full-duplex FC-0 level association between FC-1 entities in directly attached ports.
4. The point to point physical connection from one element of a Fibre Channel fabric to the next.
5. A collection of multiple lanes.
Acronym for Loop Initialization Primitive.
Acronym for Loop Initialization Select Master.
[Legal]
Synonym for legal hold.
[Computer System]
The adjustment of system and/or application components and data so that application I/O or computational demands are spread as evenly as possible across a system's physical resources.
I/O load balancing may be done manually (by a human) or automatically (by some means that does not require human intervention). See load optimization, load sharing.
[Hardware] [Computer System]
Hardware and software environment executing the workload generator to drive the system under evaluation.
[Computer System]
The manipulation of an I/O load in such a way that performance is optimal by some objective metric.
Load optimization may be achieved by load balancing across several components, or by other means, such as request reordering or interleaved execution. See load balancing, load sharing.
[Storage System]
The division of an I/O load or task among several storage subsystem components, without any attempt to equalize each component's share of the work.
[Computer System]
A CPU architecture in which memory is only accessed through load and store instructions, and all other instructions access data in registers only.
[Computer System]
Operations that move data between CPU registers and memory.
[Network]
A communications infrastructuretypically Ethernetdesigned to use dedicated wiring over a limited distance (typically a diameter of less than five kilometers) to connect a large number of intercommunicating nodes.
See wide area network.
[Network]
A collection of protocols and services that combine to create an emulated local area network using ATM as the underlying network.
Local area network emulation enables intelligent devices with ATM connections to communicate with remote LAN-connected devices as if they were directly connected to the LAN.
[Data Recovery]
A backup methodology that utilizes host resources to copy data to a backup location that is under control of the same host.
[General]
Any method of managing concurrent access to a resource.
[Storage System]
A block of data stored on a disk or tape, and associated with an address for purposes of retrieval or overwriting.
The term logical block is typically used to refer to the host's view of data addressing on a physical device. Within a storage device, there is often a further conversion between the logical blocks presented to hosts and the physical media locations at which the corresponding data is stored. See physical block, virtual block.
[Storage System]
The address of a logical block, i.e., the offset of the block from the beginning of the block address space of the logical device that contains it.
Logical block addresses are typically used in hosts' I/O commands. The SCSI disk command protocol, for example, uses logical block addresses.
[Storage System]
A set of consecutively addressed disk blocks that is part of a single virtual disk to physical disk mapping.
Logical disks are used in some array implementations as constituents of logical volumes or partitions. Logical disks are normally not visible to the host environment, except during array configuration operations. See extent,virtual disk.
[Windows]
A name for the volume management control software in the Windows NT operating system.
[SCSI]
1. The SCSI identifier of a logical unit within a target.
2. Industry shorthand, when phrased as "lun", for the logical unit indicated by the logical unit number.
[Storage System]
A virtual disk, also called a virtual disk, or volume set, made up of logical disks.
A laser with a wavelength 1300 nm or longer; usually 1300 or 1550 nanometers; widely used in the telecommunications industry.
[Data Management]
The practice of archiving data for extended periods of time, including ‘forever'.
Issues related to security and media, application and display formats must all be addressed for successful long-term retention. See data preservation.
[Long-Term Retention]
The act of maintaining information, in a correct and independently understandable form, over a period of decades or longer.
See digital preservation.
The protocol by which a Fibre Channel Arbitrated Loop network initializes upon power up or recovers after a failure or other unexpected condition.
A Fibre Channel primitive used to (1) initiate a procedure that results in unique addressing for all nodes, (2) indicate a loop failure, or (3) reset a specific node.
During a LIP, the nodes present on the arbitrated loop identify themselves and acquire addresses on the loop for communication. No data can be transferred on an arbitrated loop until a LIP is complete.
The process by which a temporary Fibre Channel arbitrated loop master is determined during loop initialization.
Logic that monitors and performs the tasks required for initialization and access to a Fibre Channel arbitrated loop.
A Fibre Channel switch operating at the layer 2 level allowing multiple dynamic point-to-point connections between devices using the FC-AL protocol.
Loop switches do not implement the Fibre Channel Switch Fabric protocols (FC-SW-x standards).
An FC-1 operational mode in which information passed to the FC-1 transmitter is shunted directly to the FC-1 receiver.
When a Fibre Channel interface is in loopback mode, the loopback signal overrides any external signal detected by the receiver.
[Network]
An Ethernet bridging function supporting the minimum required capabilities of Lossless Ethernet MACs.
[Network]
A full duplex Ethernet MAC that supports at least 2.5KB jumbo frames and implements extensions to avoid Ethernet frame loss due to congestion (e.g., the Ethernet Pause mechanism).
[Network]
An Ethernet network composed only of full duplex links, Lossless Ethernet MACs, and Lossless Ethernet bridging elements.
[File System]
Acronym for Linear Tape File System.
[File System]
Metadata which describes the file data types and locations on an LTFS volume.
[Storage System]
Acronym for Linear Tape Open.
[SCSI]
Acronym for Logical Unit.
[SCSI]
Acronym for Logical Unit Number.
Acronym for Long Wavelength Laser.
An FC-Port that contains functions associated with the Arbitrated Loop topology.
[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.
[Hardware]
Acronym for microwave assisted magnetic recording.
[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.
A DMTF-defined protocol that supports management communication between internal hardware components.
MCTP is carried over an underlying bus (e.g., SMBus/I2C, serial links, PCI Express, or USB).
[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 data transfer rate.
[Management]
Acronym for Management Component Transport Protocol
[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.
[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 (e.g., storage, processing, data transfer rate, and active user accounts) appropriate to a given type of service, 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.
[Hardware]
The smallest physical storage entity within a NAND flash device.
[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]
A measuring capability of resources (e.g., storage, processing, data transfer rate/capacity, and active user accounts) appropriate to the type of service.
[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.
[Hardware]
A recording technique that directs microwaves at the media to aid the recording process of an HDD.
[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.
[Storage System]
A RAID 1 volume, consisting of separate components with identical contents on each component, that can be accessed independently by the storage system.
[Storage System]
Common term for a disk array that implements RAID Level 1.
[Storage System]
Maintaining two or more identical copies of data in separate locations.
[Storage System]
The disks of a mirrored array.
[Hardware]
Acronym for Multi-Level Cell
[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.
[Hardware]
A memory cell that stores two bits of data.
This is not a generic term for all memory cell types greater than one.
[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.
[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.
[Data Security]
A process that verifies the identity of both entities prior to establishing communication.
[Network] [Standards]
Acronym for Network Address Authority.
[Network]
1. A distributed service provided by the fabric to register and discover the attributes of Fibre Channel N-Ports.
Once registered, the attributes may be viewed by requesting N-ports.
2. A server, such as a DNS server, that resolves textual names to machine addresses and vice versa.
[File System] [General] [Management]
1. The set of valid names recognized by a file system.
2. In XML, a document at a specific Web address (URL) that lists the names of data elements and attributes that are used in other XML files.
3. In CIM and WBEM, a collection of object definitions and instances that are logically consistent.
A 64-bit identifier, with a 60-bit value preceded by a 4-bit Network_Address_Authority Identifier, used to identify entities in Fibre Channel (e.g., Nx-Port, node, F_Port, or Fabric).
[Computer System]
The mapping of address space to a set of objects.
Naming is typically used either for human convenience (e.g., symbolic names attached to files or storage devices), or to establish a level of independence between two system components (e.g., identification of files by inode names or identification of computers by IP addresses).
[Hardware]
A type of non-volatile memory commonly used in flash memory.
[Network] [Storage System]
Acronym for Network Attached Storage.
[Standards] [Data Security]
A non-regulatory federal agency within the U.S. Commerce Department's Technology Administration.
NIST's mission is to develop and promote measurement, standards, and technology to enhance productivity, facilitate trade, and improve the quality of life. Specifically, the Computer Security Division within NIST's Information Technology Laboratory managed the Advanced Encryption Standard (AES) program.
[Legal]
The original, non-derived format and structure of data, together with its associated metadata.
Where data is unstructured, native file format means the original format of a file. While structured or unstructured data may be read by other programs, native data format means data whose state and integrity are unchanged since generation by its instantiating application.
In inter-fabric routing (IFR), the local fabric where the Native Nx_Port resides.
A role of an Nx_Port in an IFR environment.
A Native Nx_Port is physically attached to the local fabric.
[Management] [Network]
Acronym for Network Data Management Protocol.
[Data Management]
Data that is accessible within some moderate length of time, usually some number of seconds.
See active data, offline data.
[Energy]
Storage systems with first data access times > 80 ms and less than several seconds, as specified in the SNIA Emeraldâ„¢ Power Efficiency Measurement Specification.
[Network]
An interconnect that enables communication among a collection of attached nodes, consisting of optical or electrical transmission media, infrastructure in the form of hubs and/or switches, and protocols that make message sequences meaningful.
In comparison to I/O interconnects, networks are typically characterized by large numbers of nodes that act as peers, large inter-node separation, and flexible configurability. See channel, I/O interconnect, local area network, storage area network.
[Network]
An adapter that connects an intelligent device to a network, also called a network interface card, or NIC.
See Ethernet adapter, NIC.
A 4-bit field used to identify the controlling authority for guaranteeing uniqueness of World Wide Names (WWNs).
In a Fibre Channel environment, several Naming Authorities can be active at the same time, therefore Fibre Channel prepends the NAA field to World Wide Names to guarantee global uniqueness. An NAA =1, for example, indicates IEEE 48-bit Identifiers. The NAA also identifies one of several WWN formats, for example Format 1, Format 2 and Format 5.
[Storage System] [Network]
1. A term used to refer to storage devices that connect to a network and provide file access services to computer systems.
These devices generally consist of an engine that implements the file services, and one or more devices, on which data is stored.
2. A class of systems that provide file services to host computers using file access protocols such as NFS or CIFS.
See storage area network.
[Data Recovery]
A communications protocol that allows data storage devices, robotic library devices, and backup applications to intercommunicate for the purpose of performing backups.
NDMP is an open standard protocol for network-based backup of NAS devices. It allows a network backup application to control the retrieval of data from, and backup of, a server without third-party software. The control and data transfer components of backup and restore are separated. NDMP is intended to support tape drives, but can be extended to address other devices and media in the future. The SNIA has developed a v4 reference implementation, based on donation to it of the original code from NetApp and PDC.
[File System] [Standards]
A distributed file system and its associated network protocol, commonly implemented in UNIX systems.
The IETF maintains the NFS standard. NFS clients and/or servers are available for all major platforms at this point.
[Network]
An I/O adapter that connects a computer or other type of node to a network.
A NIC is commonly a plug-in circuit board, however, the term is also used to denote an ASIC or set of ASICs on a computer system board that perform the network I/O adapter function. The term NIC is universally used in Ethernet and token ring contexts. In Fibre Channel contexts, the terms host bus adapter, HBA and adapter are used in preference to NIC. See host bus adapter, I/O adapter.
[SCSI]
A temporary relationship between two SCSI devices, consisting of at least a target identifier and initiator identifier.
A full working nexus, known as an I_T_L_Q nexus, also contains a Logical Unit Number (LUN) and a Queue tag.
[File System] [Standards]
Acronym for Network File System.
[Network]
Acronym for Network Interface Card.
[Data Security]
Shorthand for National Institute of Standards and Technology.
A "Node Loop" port, i.e., an Nx-Port that is communicating via an Arbitrated Loop.
NL-Ports are end points for Fibre Channel communication via Arbitrated Loop topologies that are attached to a Fabric, for example NL-Port to FL-Port to F-Port to N-Port using a single Fibre Channel Fabric switch. See F-Port, FL-Port, Nx-Port, L_Port.
[Network] [Storage System]
An addressable entity connected to an I/O interconnect or network.
The term node is used to refer to computers, storage devices, storage subsystems and network interconnection devices such as switches, routers and gateways. The component of a node that connects to the bus or network is a port.
A Name-Identifier that is associated with a Fibre Channel node.
[Network] [Computer System]
- [computer system] A property of an operation that it does not stop and wait for other operations to occur.
- [Network] A property of a switch that does not block traffic.
[Hardware] [Computer System]
Support for continued availability of data during all FRU service operations.
Some examples of non-disruptive serviceability are: code patches, software/firmware upgrades, configuration changes, data migrations, and system expansion done during production time.
Service operations may result in performance impacts to data availability but shall not result in a loss of access.
[Data Management]
Content that cannot be deleted except in accordance with a retention policy.
[Storage System]
Any form of tabular mapping in which there is not a fixed size correspondence between the two mapped address spaces.
Non-linear mapping is required in disk arrays that compress data, since the space required to store a given range of virtual blocks depends on the degree to which the contents of those blocks can be compressed, and therefore changes as block contents change. See algorithmic mapping, dynamic mapping, tabular mapping.
[Computer System]
A failover from one component of a redundant system to another that is visible to the external environment.
An example is a controller failover in a redundant disk subsystem if the surviving controller exports the other's virtual disks at different host I/O interconnect addresses or on a different host I/O interconnect. See transparent failover.
[Computer System]
A computer architecture that enables memory to be shared by multiple processors, but with different processors having different access speeds to different parts of the memory.
[Storage System]
A cache that retains data through power cycles.
[Hardware]
A dual inline memory module that operates as standard RAM while also having persistence across power cycles.
[Computer System]
Computer system random access memory that has been made impervious to data loss due to power failure through the use of UPS, batteries, or implementation technology such as flash memory.
[Storage System]
The property of an electronic device that data is preserved even when electrical power is removed.
[Data Security]
Assurance that a subject cannot later deny having performed some action.
For communication, this may involve providing the sender of data with proof of delivery and the recipient with proof of the sender's identity, so neither can later deny having participated in the communication. Digital signatures are often used as a non-repudiation mechanism for stored information in combination with timestamps.
[Computer System]
A state of a system in which the system is functioning within its prescribed operational bounds.
For example, a disk array subsystem is operating in normal mode when all disks are up, no extraordinary actions (e.g., reconstruction) are being performed, and environmental conditions are within operational range. Sometimes called optimal mode.
A receiver or transmitter that is not capable of receiving or transmitting an encoded bit stream based on rules defined by FC-FS-2 for error control.
Acronym for N_Port_ID Virtualization.
[NVMe]
Shorthand for NVMe Qualified Name.
[Computer System]
Shorthand for Non-Uniform Memory Architecture.
[Hardware]
Acronym for Non-Volatile Dual Inline Memory Module.
[Hardware]
A dual in-line memory module that is accessed using a block access protocol.
This appears in a separate address space from DRAM and may provide different performance than DRAM.
[Hardware]
A dual in-line memory module that operates as persistent DRAM.
The DRAM access methods are either byte- or block-oriented. This may not provide the same performance as volatile DRAM.
[Hardware]
A dual in-line memory module that operates as persistent DRAM (NVDIMM-N) and also as a block-accessed drive (NVDIMM-F) using non-volatile memory media.
[Computer System]
[Storage System]
A host controller interface that includes a register set and command set designed for use over PCI Express® or fabrics.
[NVMe] [Management]
A protocol for managing an NVMe subsystem that is carried over MCTP.
[NVMe]
An integrated collection of one or more NVMe controllers, one or more ports, and may contain non-volatile storage.
[NVMe]
An acronym for NVM Express™.
[NVMe]
A command issued by an NVMe host to an NVMe controller.
[NVMe]
] A circular buffer used to return status for completed NVMe commands.
[NVMe]
An entity that submits NVMe commands to an NVMe controller for processing and receives NVMe command completions from that controller.
[NVMe]
A protocol that supports message-based NVMe operations over a network fabric.
Example network fabrics include Ethernet, Fibre Channel, and InfiniBand.
[Fibre Channel]
Protocol defined by the FC-NVMe standards.
[NVMe]
A circular buffer used to submit NVMe commands for processing.
[NVMe]
A component that processes NVMe commands.
[NVMe] [Management]
Abbreviation for NVM Express Management Interface.
[NVMe]
Shorthand for NVMe over Fabrics.
[Fibre Channel]
Shorthand for NVM Express over Fibre Channel.
See FC-NVMe.
[Fibre Channel]
An NVMe/FC layer abstraction for an exclusive communication relationship between an NVMe host and an NVMe controller connected by an initiator port and a target port.
[Fibre Channel]
An NVMe/FC layer abstraction representing an NVMe Submission Queue and NVMe Completion Queue pair.
[Fibre Channel]
A Fibre Channel Exchange that is uniquely associated with any NVMe command.
[Fibre Channel]
An NVMe_Port connecting one or more NVMe hosts or NVM subsystems in a Fibre Channel environment.
[Fibre Channel]
The FC-NVMe Information Unit for data frame(s) transfers.
[Computer System]
Shorthand for Non-Volatile Random Access Memory.
[Storage System]
A quantity of NVRAM used as a cache.
NVRAM cache is particularly useful in RAID array subsystems, filers, database servers, and other intelligent devices that must keep track of the state of multi-step I/O operations even if power fails during the execution of the steps. It also allows arrays to reply to writes before they are committed to disk, as the NVRAM becomes the non-volatile store for the writes.
An end point for Fibre Channel frame communication, having a distinct address identifier and Name-Identifier, providing an independent set of Fibre Channel functions to applications, and having the ability to act as an Originator, a Responder, or both, for Exchanges and Sequences.
A "Node" port that connects via a point-to-point link to either a single N-Port or a single F-Port.
N-Ports handle creation, detection, and flow of message units to and from the connected systems. N-Ports are end ports in virtual point-to-point links through a fabric, for example the N-Port on an end node to F-Port on a switch to F-Port in that switch to the N-Port on the other end node using a single Fibre Channel fabric switch. An N-Port is assumed to always refer to an Nx-Port in a direct Fabric-attached PN_Port, and does not include NL_Ports
The ability for a single physical Fibre Channel node or switch to support more than one Nx_Port on a single point-to-point link.
A Name-Identifier associated with an N_Port.
[General]
Short name for the Organization for the Advancement of Structured Information Standards (OASIS), a consortium for developing standards (e.g., KMIP).
[General] [Data Security] [Data Management]
1. An instantiated instance of a class in an Object Oriented system.
2. In the context of access control, an entity such as an information system resource to which access is controlled and/or usage of which is restricted to authorized subjects.
3. The encapsulation of data and associated metadata.
[Storage System]
A storage element that directly provides object services.
[General]
A methodology for decomposing an entity or problem by its key abstractions, versus by its procedures or steps.
The key abstractions become classes in an information or data model, and embody well-defined behaviors called methods, with a unique set of data attributes. Instances of a class are called objects.
[Storage System]
Object-level access to storage.
[Storage System]
A storage device that provides object services.
Object storage includes DSaaS.
[Storage System]
An object-based storage standard defined by SNIA and INCITS T10.
[Network]
A data rate that is a multiple of the fundamental SONET rate of 51.84 Mbits/sec.
OC-3 (155 Mbits/sec), OC-12 (622 Mbits/sec), OC-48 (2488 Mbits/sec) and OC-192 (9953 Mbits/sec) are currently in common use. See Asynchronous Transfer Mode.
[Management]
The Open Data Protocol.
OData is an OASIS standard protocol that enables the creation and consumption of RESTful APIs.
[Management]
A service conforming to the OData standard.
OData allows resources, identified using Uniform Resource Locators (URLs) and defined in a model, to be published and edited by Web clients using simple HTTP messages.
[Data Recovery]
A form of backup in which the data being backed up is not accessed by applications for the duration of the backup.
[Data Management]
Data that may not be accessible for an extended period of time, for example data on removable media at a remote site.
See near-online data.
[Capacity Optimization]
Deprecated synonym for post-process data deduplication.
A designation for a multimode optical fiber with a 62.5 micrometer core diameter and a bandwidth-length product of 200 MHz*km for 850 nm optical signals.
This fiber is typical of FDDI installations. Specified by ISO 11801 second edition.
A designation for a multimode optical fiber with a 50 micrometer core diameter and a bandwidth-length product of 500 MHz*km for 850 nm optical signals.
This fiber is typical of 1 Gb/s Ethernet and Fibre Channel installations. Specified by ISO 11801 second edition.
A designation for a multimode optical fiber with a 50 micrometer core diameter and a bandwidth-length product of 2000 MHz*km for 850 nm optical signals.
Optical fiber is available with considerably higher bandwidth-length products. Specified by ISO 11801 second edition.
[Data Recovery]
A form of backup in which the data being backed up may be accessed by applications during the backup.
Online backup of a set of data is usually accomplished through the use of a frozen image of the data.
[General]
Acronym for Object Oriented.
[General]
1. Any system or aspect of a system whose function is governed by a readily accessible standard rather than by a privately owned specification.
2. Not electrically terminated, as an unplugged cable.
3. A period of time that begins when a sequence or exchange is initiated and ends when the sequence or exchange is normally or abnormally terminated.
[General]
A cross-industry consortium for open systems standards and their certification.
UNIX, management and security standards are developed within the Open Group, homed atwww.opengroup.org.
[Computer System]
Synonym for standard interconnect.
[Computer System]
A collective term for the hardware architecture and operating system of a computer system.
[Storage System]
Any protocol command that is delivered from a client to a storage system, including I/O operations.
See also OPS.
[Data Recovery]
Recovery of one or more applications and associated data to correct operational problems such as a corrupt database, user error or hardware failure.
OR may use a point in time copy or other techniques that create a consistent set of recoverable data.
[Standards]
Characteristics of a standard that are specified by the standard but not required for compliance, but which must be implemented as defined in the standard if they are implemented at all.
[Data Recovery]
Acronym for Operational Recovery.
A transmission word (sequence of four 10-bit code bytes) with a special character in its most significant (first on the link) position and data characters in the remaining three positions.
An ordered set is identified by the combination of special codes and data bytes that, when encoded, result in the generation of the transmission characters specified for the ordered set. Ordered sets are used for low-level Fibre Channel link functions such as frame demarcation, signaling between the ends of a link, initialization after power on, and some basic recovery actions.
An identifier assigned by an Exchange Originator to identify an Exchange.
An OX-ID is used by both the Exchange Originator and the Exchange Responder to identify the Exchange with respect to the Exchange Originator.
[Storage System]
Acronym for Object Storage Device.
[Network]
Transmission of a separate data stream, such as management information, over a dif