Glossary

This glossary includes terms for the IBM® System Storage® SAN Volume Controller.

This glossary includes selected terms and definitions from A Dictionary of Storage Networking Terminology (www.snia.org/education/dictionary), copyrighted 2001 by the Storage Networking Industry Association, 2570 West El Camino Real, Suite 304, Mountain View, California 94040-1313. Definitions derived from this book have the symbol (S) after the definition.

The following cross-references are used in this glossary:

See

Refers the reader to one of two kinds of related information:

A term that is the expanded form of an abbreviation or acronym. This expanded form of the term contains the full definition.
A synonym or more preferred term.

See also

Refers the reader to one or more related terms.

Numerics

2145: A hardware machine type for the IBM System Storage SAN Volume Controller. Models of the SAN Volume Controller are expressed as the number 2145 followed by "-xxx", such as 2145-8G4. Hardware models for the 2145 include 2145-4F2, 2145-CF8, 2145-8F2, 2145-8F4, 2145-8G4, and 2145-8A4.

A

access mode: One of three different modes in which a logical unit (LU) in a disk controller system can operate. See also image mode, managed space mode, and unconfigured mode.
Address Resolution Protocol (ARP): A protocol that dynamically maps an IP address to a network adapter address in a local area network.
agent code: An open-systems standard that interprets Common Information Model (CIM) requests and responses as they transfer between the client application and the device.
application server: A host that is attached to the storage area network (SAN) and that runs applications.
ARP: See Address Resolution Protocol.
array: An ordered collection, or group, of physical storage devices that are used to define logical volumes or devices.
association: A class that contains two references that define a relationship between two referenced objects.
asymmetric virtualization: A virtualization technique in which the virtualization engine is outside the data path and performs a metadata-style service. The metadata server contains all the mapping and locking tables while the storage devices contain only data. See also symmetric virtualization.
auxiliary virtual disk: The virtual disk that contains a backup copy of the data and that is used in disaster recovery scenarios. See also master virtual disk.
availability: The ability of a system to continue working, with perhaps a decrease in performance, after individual components fail.

B

bandwidth: The range of frequencies an electronic system can transmit or receive. The greater the bandwidth of a system, the more information the system can transfer in a given period of time.
bitmap: A coded representation in which each bit, or group of bits, represents or corresponds to an item; for example, a configuration of bits in main storage in which each bit indicates whether a peripheral device or a storage block is available or in which each group of bits corresponds to one pixel of a display image.
blade: One component in a system that is designed to accept some number of components (blades). Blades could be individual servers that plug into a multiprocessing system or individual port cards that add connectivity to a switch. A blade is typically a hot-swappable hardware device.
block: A unit of data storage on a disk drive.
block virtualization: The act of applying virtualization to one or more block-based (storage) services for the purpose of providing a new aggregated, higher-level, richer, simpler, or 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 also virtualization.
Boolean: Pertaining to the processes used in the algebra formulated by George Boole.

C

cache: A high-speed memory or storage device used to reduce the effective time required to read data from or write data to lower-speed memory or a device. Read cache holds data in anticipation that it will be requested by a client. Write cache holds data written by a client until it can be safely stored on more permanent storage media such as disk or tape.
Call Home: In SAN Volume Controller, a communication service that sends data and event notifications to a service provider. The machine can use this link to place a call to IBM or to another service provider when service is required.
capacity licensing: A type of licensing that grants you the use of a number of terabytes (TB) for virtualization, a number of terabytes for Metro Mirror and Global Mirror relationships, and a number of terabytes for FlashCopy® mappings.
cascading: The process of connecting two or more fibre-channel hubs or switches together to increase the number of ports or extend distances.
Challenge Handshake Authentication Protocol: An authentication protocol that protects against eavesdropping by encrypting the user name and password.
CHAP: See Challenge Handshake Authentication Protocol.
CIM: See Common Information Model.
CIM object manager (CIMOM): The common conceptual framework for data management that receives, validates, and authenticates the CIM requests from the client application. It then directs the requests to the appropriate component or service provider.
CIMOM: See CIM object manager.
class: The definition of an object within a specific hierarchy. A class can have properties and methods and can serve as the target of an association.
CLI: See command line interface.
client: A computer system or process that requests a service of another computer system or process that is typically referred to as a server. Multiple clients can share access to a common server.
client application: A storage management program that initiates Common Information Model (CIM) requests to the CIM agent for the device.
cluster: In SAN Volume Controller, up to four pairs of nodes that provide a single configuration and service interface.
command-line interface (CLI): A type of computer interface in which the input command is a string of text characters.
Common Information Model (CIM): A set of standards developed by the Distributed Management Task Force (DMTF). CIM provides a conceptual framework for storage management and an open approach to the design and implementation of storage systems, applications, databases, networks, and devices.
concurrent maintenance: Service that is performed on a unit while it is operational.; In SAN Volume Controller, the ability for one node in the cluster to be turned off for maintenance without interrupting access to the VDisk data provided by the cluster.
configuration node: A node that acts as the focal point for configuration commands and manages the data that describes the cluster configuration.
connected: In a Global Mirror relationship, pertaining to the status condition that occurs when two clusters can communicate.
consistency group: A group of copy relationships between virtual disks that are managed as a single entity.
consistent copy: In a Metro or Global Mirror relationship, a copy of a secondary virtual disk (VDisk) that is identical to the primary VDisk from the viewpoint of a host system, even if a power failure occurred while I/O activity was in progress.
consistent-stopped: In a Global Mirror relationship, the state that occurs when the secondary virtual disk (VDisk) contains a consistent image, but the image might be out-of-date with respect to the primary VDisk. This state can happen when a relationship was in the consistent-synchronized state when an error occurred that forced a freeze of the consistency group. This state can also happen when a relationship is created with the create-consistent flag set to TRUE.
consistent-synchronized: In a Global Mirror relationship, the status condition that occurs when the primary virtual disk (VDisk) is accessible for read and write I/O operations. The secondary VDisk is accessible for read-only I/O operations. See also primary virtual disk and secondary virtual disk.
container: A data storage location; for example, a file, directory, or device.; A software object that holds or organizes other software objects or entities.
contingency capacity: Initially, a fixed amount of unused real capacity that is maintained on a space-efficient virtual disk that is configured to automatically expand its real capacity. It is also the difference between the used capacity and the new real capacity when the real capacity is changed manually.
copied: In a FlashCopy mapping, a state that indicates that a copy has been started after the copy relationship was created. The copy process is complete and the target disk has no further dependence on the source disk.
copying: A status condition that describes the state of a pair of virtual disks (VDisks) that have a copy relationship. The copy process has been started but the two virtual disks are not yet synchronized.
Copy Services: The services that enable you to copy virtual disks (VDisks): FlashCopy, Metro, and Global Mirror.
counterpart SAN: A nonredundant portion of a redundant storage area network (SAN). A counterpart SAN provides all the connectivity of the redundant SAN but without the redundancy. Each counterpart SANs provides an alternate path for each SAN-attached device. See also redundant SAN.
cross-volume consistency: In SAN Volume Controller, a consistency group property that guarantees consistency between virtual disks when an application issues dependent write operations that span multiple virtual disks.

D

data migration: The movement of data from one physical location to another without disrupting I/O operations.
degraded: Pertaining to a valid configuration that has suffered a failure but continues to be supported and legal. Typically, a repair action can be performed on a degraded configuration to restore it to a valid configuration.
dense wavelength division multiplexing (DWDM): A technology that places many optical signals onto one single-mode fiber using slightly different optical frequencies. DWDM enables many data streams to be transferred in parallel.
dependent write operations: A set of write operations that must be applied in the correct order to maintain cross-volume consistency.
destage: A write command initiated by the cache to flush data to disk storage.
device: In the CIM agent, the storage server that processes and hosts client application requests.; IBM definition: A piece of equipment that is used with the computer and does not generally interact directly with the system, but is controlled by a controller.; HP definition: In its physical form, a magnetic disk that can be attached to a SCSI bus. The term is also used to indicate a physical device that has been made part of a controller configuration; that is, a physical device that is known to the controller. Units (virtual disks) can be created from devices after the devices have been made known to the controller.
device provider: A device-specific handler that serves as a plug-in for the Common Information Model (CIM); that is, the CIM object manager (CIMOM) uses the handler to interface with the device.
directed maintenance procedures: The set of maintenance procedures that can be run for a cluster. These procedures are run from within the SAN Volume Controller application and are documented in the IBM System Storage SAN Volume Controller Troubleshooting Guide.
disconnected: In a Metro or Global Mirror relationship, pertains to two clusters when they cannot communicate.
discovery: The automatic detection of a network topology change, for example, new and deleted nodes or links.
disk controller: A device that coordinates and controls the operation of one or more disk drives and synchronizes the operation of the drives with the operation of the system as a whole. Disk controllers provide the storage that the cluster detects as managed disks (MDisks).
disk drive: A disk-based, nonvolatile, storage medium.
disk zone: A zone defined in the storage area network (SAN) fabric in which the SAN Volume Controller can detect and address the logical units that the disk controllers present.
Distributed Management Task Force (DMTF): An organization that defines standards for the management of distributed systems. See also Common Information Model.
DMP: See directed maintenance procedures.
DMTF: See Distributed Management Task Force.
domain name server: In the Internet suite of protocols, a server program that supplies name-to-address conversion by mapping domain names to IP addresses.
DRAM: See dynamic random access memory.
DWDM: See dense wavelength division multiplexing.
dynamic random access memory (DRAM): A storage in which the cells require repetitive application of control signals to retain stored data.

E

EC: See engineering change.
EIA: See Electronic Industries Alliance.
Electronic Industries Alliance (EIA): An alliance of four trade associations: The Electronic Components, Assemblies & Materials Association (ECA); the Government Electronics and Information Technology Association (GEIA); the JEDEC Solid State Technology Association (JEDEC); and the Telecommunications Industry Association (TIA). Prior to 1998, EIA was the Electronic Industries Association and the group dates back to 1924.
empty: In a Global Mirror relationship, a status condition that exists when the consistency group contains no relationships.
engineering change (EC): A correction for a defect of hardware or software that is applied to a product.
error code: A value that identifies an error condition.
ESS: See IBM TotalStorage® Enterprise Storage Server®.
EUI: See extended-unique identifier.
exclude: To remove a managed disk (MDisk) from a cluster because of certain error conditions.
excluded: In SAN Volume Controller, the status of a managed disk that the cluster has removed from use after repeated access errors.
extended-unique identifier: A unique iSCSI name that identifies an iSCSI target adapter or an iSCSI initiator adapter as defined by the iSCSI standard (RFC 3722).
extent: A unit of data that manages the mapping of data between managed disks and virtual disks.

F

fabric: In fibre-channel technology, a routing structure, such as a switch, that receives addressed information and routes it to the appropriate destination. A fabric can consist of more than one switch. When multiple fibre-channel switches are interconnected, they are described as cascading. See also cascading.
fabric port (F_port): A port that is part of a fibre-channel fabric. An F_port on a fibre-channel fabric connects to the node port (N_port) on a node.
failover: In SAN Volume Controller, the function that occurs when one redundant part of the system takes over the workload of another part of the system that has failed.
FCIP: See Fibre Channel over IP.
fibre channel: A technology for transmitting data between computer devices at a data rate of up to 4 Gbps. It is especially suited for attaching computer servers to shared storage devices and for interconnecting storage controllers and drives.
fibre-channel extender: A device that extends a fibre-channel link over a greater distance than is supported by the standard, usually a number of miles or kilometers. Devices must be deployed in pairs at each end of a link.
Fibre Channel over IP (FCIP): A network storage technology that combines the features of the Fibre Channel Protocol and the Internet Protocol (IP) to connect distributed SANs over large distances.
Fibre Channel Protocol (FCP): A protocol that is used in fibre-channel communications with five layers that define how fibre-channel ports interact through their physical links to communicate with other ports.
field replaceable unit (FRU): An assembly that is replaced in its entirety when any one of its components fails. An IBM service representative performs the replacement. In some cases, a field replaceable unit might contain other field replaceable units.
FlashCopy mapping: A relationship between two virtual disks.
FlashCopy relationship: See FlashCopy mapping.
FlashCopy service: In SAN Volume Controller, a copy service that duplicates the contents of a source virtual disk (VDisk) to a target VDisk. In the process, the original contents of the target VDisk are lost. See also point-in-time copy.
F_port: See fabric port.
FRU: See field replaceable unit.

G

gateway: An entity that operates above the link layer and translates, when required, the interface and protocol used by one network into those used by another distinct network.
GB: See gigabyte.
GBIC: See gigabit interface converter.
gigabit interface converter (GBIC): An interface module that converts the light stream from a fibre-channel cable into electronic signals for use by the network interface card.
gigabyte (GB): In decimal notation, 1 073 741 824 bytes.
Global Mirror: An asynchronous copy service that enables host data on a particular source virtual disk (VDisk) to be copied to the target VDisk that is designated in the relationship.
grain: In a FlashCopy bitmap, the unit of data represented by a single bit.
graphical user interface (GUI): A type of computer interface that presents a visual metaphor of a real-world scene, often of a desktop, by combining high-resolution graphics, pointing devices, menu bars and other menus, overlapping windows, icons and the object-action relationship.
GUI: See graphical user interface.

H

hardcoded: Pertaining to software instructions that are statically encoded and not intended to be altered.
HBA: See host bus adapter.
HLUN: See virtual disk.
hop: One segment of a transmission path between adjacent nodes in a routed network.
host: An open-systems computer that is connected to the SAN Volume Controller through a fibre-channel interface.
host bus adapter (HBA): In SAN Volume Controller, an interface card that connects a host bus, such as a peripheral component interconnect (PCI) bus, to the storage area network.
host ID: In SAN Volume Controller, a numeric identifier assigned to a group of host fibre-channel ports for the purpose of logical unit number (LUN) mapping. For each host ID, there is a separate mapping of Small Computer System Interface (SCSI) IDs to virtual disks (VDisks).
host zone: A zone defined in the storage area network (SAN) fabric in which the hosts can address the SAN Volume Controllers.
hub: A fibre-channel device that connects nodes into a logical loop by using a physical star topology. Hubs will automatically recognize an active node and insert the node into the loop. A node that fails or is powered off is automatically removed from the loop.; A communications infrastructure device 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 physical cables. 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 bandwidth. Hubs typically support the addition or removal of nodes from the bus while it is operating. (S) See also switch.

I

IBM System Storage Productivity Center (SSPC): An integrated hardware and software solution that provides a single point of entry for managing SAN Volume Controller clusters, IBM System Storage DS8000® systems, and other components of a data storage infrastructure.
IBM TotalStorage Enterprise Storage Server (ESS): An IBM product that provides an intelligent disk-storage system across an enterprise.
ID: See identifier.
identifier (ID): A sequence of bits or characters that identifies a user, program device, or system to another user, program device, or system.
idle: In a FlashCopy mapping, the state that occurs when the source and target virtual disks (VDisks) act as independent VDisks even if a mapping exists between the two. Read and write caching is enabled for both the source and the target.
idling: The status of a pair of virtual disks (VDisks) that have a defined copy relationship for which no copy activity has yet been started.; In a Metro or Global Mirror relationship, the state that indicates that the master virtual disks (VDisks) and auxiliary VDisks are operating in the primary role. Consequently, both VDisks are accessible for write I/O operations.
idling-disconnected: In a Global Mirror relationship, the state that occurs when the virtual disks (VDisks) in this half of the consistency group are all operating in the primary role and can accept read or write I/O operations.
illegal configuration: A configuration that will not operate and will generate an error code to indicate the cause of the problem.
image mode: An access mode that establishes a one-to-one mapping of extents in the managed disk (MDisk) with the extents in the virtual disk (VDisk). See also managed space mode and unconfigured mode.
image VDisk: A virtual disk (VDisk) in which there is a direct block-for-block translation from the managed disk (MDisk) to the VDisk.
IML: See initial microcode load.
inconsistent: In a Metro or Global Mirror relationship, pertaining to a secondary virtual disk (VDisk) that is being synchronized with the primary VDisk.
inconsistent-copying: In a Global Mirror relationship, the state that occurs when the primary virtual disk (VDisk) is accessible for read and write input/output (I/O) operations, but the secondary VDisk is not accessible for either. This state occurs after a start command is issued to a consistency group that is in the inconsistent-stopped state. This state also occurs when a start command is issued, with the force option, to a consistency group that is in the idling or consistent-stopped state.
inconsistent-disconnected: In a Global Mirror relationship, a state that occurs when the virtual disks (VDisks) in the half of the consistency group that is operating in the secondary role are not accessible for either read or write I/O operations.
inconsistent-stopped: In a Global Mirror relationship, the state that occurs when the primary virtual disk (VDisk) is accessible for read and write input/output (I/O) operations, but the secondary VDisk is not accessible for either read or write I/O operations.
indication: An object representation of an event.
initial microcode load (IML): In SAN Volume Controller, the process by which the run-time code and data for a node are loaded into memory and initialized.
initiator: The system component that originates an I/O command over an I/O bus or network. I/O adapters, network interface cards, and intelligent controller device I/O bus control ASICs are typical initiators. (S) See also logical unit number.
input/output (I/O): Pertaining to a functional unit or communication path involved in an input process, an output process, or both, concurrently or not, and to the data involved in such a process.
instance: An individual object that is a member of some class. In object-oriented programming, an object is created by instantiating a class.
integrity: The ability of a system to either return only correct data or respond that it cannot return correct data.
Internet Protocol (IP): In the Internet suite of protocols, a connectionless protocol that routes data through a network or interconnected networks and acts as an intermediary between the higher protocol layers and the physical network. IPv4 is the dominant network layer protocol on the Internet, and IPv6 is designated as its successor. IPv6 provides a much larger address space, which enables greater flexibility in assigning addresses and simplifies routing and renumbering.
interswitch link (ISL): The physical connection that carries a protocol for interconnecting multiple routers and switches in a storage area network.
I/O: See input/output.
I/O group: A collection of virtual disks (VDisks) and node relationships that present a common interface to host systems.
I/O throttling rate: The maximum rate at which an I/O transaction is accepted for this virtual disk (VDisk).
IP: See Internet Protocol.
IP address: The unique 32-bit address that specifies the location of each device or workstation in the Internet. For example, 9.67.97.103 is an IP address.
IQN: See iSCSI qualified name.
iSCSI name: A name that identifies an iSCSI target adapter or an iSCSI initiator adapter. An iSCSI name can be an iSCSI qualified name (IQN) or an extended-unique identifier (EUI).
iSCSI qualified name: A unique name that identifies an iSCSI target adapter or an iSCSI initiator adapter as defined by the iSCSI standard (RFC 3722).
ISL: See interswitch link.
ISL hop: A hop on an interswitch link (ISL). Considering all pairs of node ports (N-ports) in a fabric and measuring distance only in terms of interswitch links (ISLs) in the fabric, the number of ISLs traversed is the number of ISL hops on the shortest route between the pair of nodes that are farthest apart in the fabric.

J

JBOD (just a bunch of disks): IBM definition: See non-RAID.; HP definition: A group of single-device logical units not configured into any other container type.

L

LBA: See logical block address.
least recently used (LRU): An algorithm used to identify and make available the cache space that contains the least-recently used data.
line card: See blade.
local fabric: In SAN Volume Controller, those storage area network (SAN) components (such as switches and cables) that connect the components (nodes, hosts, switches) of the local cluster together.
local/remote fabric interconnect: The storage area network (SAN) components that are used to connect the local and remote fabrics together.
logical block address (LBA): The block number on a disk.
logical unit (LU): An entity to which Small Computer System Interface (SCSI) commands are addressed, such as a virtual disk (VDisk) or managed disk (MDisk).
logical unit number (LUN): The SCSI identifier of a logical unit within a target. (S)
longitudinal redundancy check (LRC): A method of error checking during data transfer that involves checking parity.
LRC: See longitudinal redundancy check.
LRU: See least recently used.
LU: See logical unit.
LUN: See logical unit number.
LUN masking: A process that allows or prevents I/O to the disk drives through the host-bus-adapter (HBA) device or operating-system device driver.

M

managed disk (MDisk): A Small Computer System Interface (SCSI) logical unit that a redundant array of independent disks (RAID) controller provides and a cluster manages. The MDisk is not visible to host systems on the storage area network (SAN).
managed disk group: A collection of managed disks (MDisks) that, as a unit, contain all the data for a specified set of virtual disks (VDisks).
Managed Object Format (MOF): A language for defining Common Information Model (CIM) schemas.
managed space mode: An access mode that enables virtualization functions to be performed. See also image mode and unconfigured mode.
Management Information Base (MIB): Simple Network Management Protocol (SNMP) units of managed information that specifically describe an aspect of a system, such as the system name, hardware number, or communications configuration. A collection of related MIB objects is defined as a MIB.
mapping: See FlashCopy mapping.
master console: A single point from which to manage the IBM System Storage SAN Volume Controller. For SAN Volume Controller version 4.2.1 and earlier, the master console was purchased either as software that was installed and configured on a server or as a hardware platform with preinstalled operating system and master console software. See IBM System Storage Productivity Center.
master virtual disk: The virtual disk (VDisk) that contains a production copy of the data and that an application accesses. See also auxiliary virtual disk.
MB: See megabyte.
MDisk: See managed disk.
megabyte (MB): In decimal notation, 1 048 576 bytes.
mesh configuration: A network that contains a number of small SAN switches configured to create a larger switched network. With this configuration, four or more switches are connected together in a loop with some of the paths short circuiting the loop. An example of this configuration is to have four switches connected together in a loop with ISLs for one of the diagonals.
method: A way to implement a function on a class.
Metro Mirror: A synchronous copy service that enables host data on a particular source virtual disk (VDisk) to be copied to the target VDisk that is designated in the relationship.
MIB: See Management Information Base.
migration: See data migration.
mirrored virtual disk: A virtual disk (VDisk) with two VDisk copies.
mirrorset: IBM definition: See RAID-1.; HP definition: A RAID storageset of two or more physical disks that maintain a complete and independent copy of the data from the virtual disk. This type of storageset has the advantage of being highly reliable and extremely tolerant of device failure. Raid level 1 storagesets are referred to as mirrorsets.
MOF: See Managed Object Format (MOF).

N

namespace: The scope within which a Common Information Model (CIM) schema applies.
node: One SAN Volume Controller. Each node provides virtualization, cache, and Copy Services to the storage area network (SAN).
node name: A name identifier associated with a node. (SNIA)
node port (N_port): A port that connects a node to a fabric or to another node. N_ports connect to fabric ports (F_ports) or to other N_ports of other nodes. N_ports handle creation, detection, and flow of message units to and from the connected systems. N_ports are end points in point-to-point links.
node rescue: In SAN Volume Controller, the process by which a node that has no valid software installed on its hard disk drive can copy the software from another node connected to the same fibre-channel fabric.
non-RAID: Disks that are not in a redundant array of independent disks (RAID). HP definition: See JBOD.
N_port: See node port.

O

object: In object-oriented design or programming, a concrete realization of a class that consists of data and the operations associated with that data.
object model: A representation, such as a diagram, of objects in a given system. Using symbols similar to standard flowchart symbols, an object model depicts the classes the objects belong to, their associations with each other, the attributes that make them unique, and the operations that the objects can perform and that can be performed on them.
object name: An object that consists of a namespace path and a model path. The namespace path provides access to the Common Information Model (CIM) implementation managed by the CIM agent, and the model path provides navigation within the implementation.
object path: An object that consists of a namespace path and a model path. The namespace path provides access to the Common Information Model (CIM) implementation managed by the CIM agent, and the model path provides navigation within the implementation.
offline: Pertaining to the operation of a functional unit or device that is not under the continual control of the system or of a host.
online: Pertaining to the operation of a functional unit or device that is under the continual control of the system or of a host.
operating set: In SAN Volume Controller, the set of nodes that are operating together to deliver storage services.
overallocated volume: See space-efficient virtual disk.
oversubscription: The ratio of the sum of the traffic that is on the initiator N-node connections to the traffic that is on the most heavily loaded interswitch links (ISLs), where more than one ISL is connected in parallel between these switches. This definition assumes a symmetrical network and a specific workload that is applied equally from all initiators and sent equally to all targets. See also symmetrical network.

P

partition: IBM definition: A logical division of storage on a fixed disk.; HP definition: A logical division of a container represented to the host as a logical unit.
partner node: The other node that is in the I/O group to which this node belongs.
partnership: In Metro or Global Mirror operations, the relationship between two clusters. In a cluster partnership, one cluster is defined as the local cluster and the other cluster as the remote cluster.
paused: In SAN Volume Controller, the process by which the cache component quiesces all ongoing I/O activity below the cache layer.
pend: To cause to wait for an event.
petabyte (PB): In decimal notation, 1 125 899 906 842 624 bytes.
PDU: See power distribution unit.
physical disk licensing: A type of licensing that grants you the use of a number of physical disks for virtualization. You can also license the use of the Metro Mirror and Global Mirror feature, the use of the FlashCopy feature, or both of these features.
PLUN: See managed disk.
point-in-time copy: The instantaneous copy that the FlashCopy service makes of the source virtual disk (VDisk). In some contexts, this copy is known as a T₀ copy.
port: The physical entity within a host, SAN Volume Controller, or disk controller system that performs the data communication (transmitting and receiving) over the fibre channel.
port ID: An identifier associated with a port.
power distribution unit (PDU): A device that distributes electrical power to multiple devices in the rack. It typically is rack-mounted and provides circuit breakers and transient voltage suppression.
power-on self-test: A diagnostic test that servers or computers run when they are turned on.
prepared: In a Global Mirror relationship, the state that occurs when the mapping is ready to start. While in this state, the target virtual disk (VDisk) is offline.
preparing: In a Global Mirror relationship, the state that occurs when any changed write data for the source virtual disk (VDisk) is flushed from the cache. Any read or write data for the target VDisk is discarded from the cache.
primary virtual disk: In a Metro or Global Mirror relationship, the target of write operations issued by the host application.
property: In the Common Information Model (CIM), an attribute that is used to characterize instances of a class.
PuTTY: A client program that allows you to run remote sessions on your computer through specific network protocols, such as SSH, Telnet, and Rlogin.

Q

qualifier: A value that provides additional information about a class, association, indication, method, method parameter, instance, property, or reference.
quorum: A set of nodes that operates as a cluster. Each node has a connection to every other node in the cluster. If a connection failure causes the cluster to split into two or more groups of nodes that have full connection within the group, the quorum is the group that is selected to operate as the cluster. Typically, this is the larger group of nodes, but the quorum disk serves as a tiebreaker if the groups are the same size.
queue depth: The number of I/O operations that can be run in parallel on a device.
quorum disk: A managed disk (MDisk) that contains a reserved area that is used exclusively for cluster management. The quorum disk is accessed in the event that it is necessary to determine which half of the cluster continues to read and write data.
quorum index: A number that can be either: 0, 1 or 2

R

rack: A free-standing framework that holds the devices and card enclosure.
RAID: See redundant array of independent disks.
RAID 0: IBM definition: RAID 0 allows a number of disk drives to be combined and presented as one large disk. RAID 0 does not provide any data redundancy. If one drive fails, all data is lost.; HP definition: A RAID storageset that stripes data across an array of disk drives. A single logical disk spans multiple physical disks, allowing parallel data processing for increased I/O performance. While the performance characteristics of RAID level 0 is excellent, this RAID level is the only one that does not provide redundancy. Raid level 0 storagesets are referred to as stripesets.
RAID 1: SNIA dictionary definition: A form of storage array in which two or more identical copies of data are maintained on separate media. (S); IBM definition: A form of storage array in which two or more identical copies of data are maintained on separate media. Also known as mirrorset.; HP definition: See mirrorset.
RAID 5: SNIA definition: A form of parity RAID in which the disks operate independently, the data strip size is no smaller than the exported block size, and parity check data is distributed across the array's disks. (S); IBM definition: See the SNIA definition.; HP definition: A specially developed RAID storageset that stripes data and parity across three or more members in a disk array. A RAIDset combines the best characteristics of RAID level 3 and RAID level 5. A RAIDset is the best choice for most applications with small to medium I/O requests, unless the application is write intensive. A RAIDset is sometimes called parity RAID. RAID level 3/5 storagesets are referred to as RAIDsets.
RAID 10: A type of RAID that optimizes high performance while maintaining fault tolerance for up to two failed disk drives by striping volume data across several disk drives and mirroring the first set of disk drives on an identical set.
real capacity: The amount of storage that is allocated to a virtual disk copy from a managed disk group.
redundant ac-power switch: A device that provides input power redundancy by attaching a SAN Volume Controller to two independent power sources. If the main source becomes unavailable, the redundant ac-power switch automatically provides power from a secondary (backup) source. When power is restored, the redundant ac-power switch automatically changes back to the main power source.
redundant array of independent disks (RAID): A collection of two or more disk drives that present the image of a single disk drive to the system. In the event of a single device failure, the data can be read or regenerated from the other disk drives in the array.
redundant SAN: A storage area network (SAN) configuration in which any one single component might fail, but connectivity between the devices within the SAN is maintained, possibly with degraded performance. This configuration is normally achieved by splitting the SAN into two, independent, counterpart SANs. See also counterpart SAN.
reference: A pointer to another instance that defines the role and scope of an object in an association.
rejected: A status condition that describes a node that the cluster software has removed from the working set of nodes in the cluster.
relationship: In Metro or Global Mirror, the association between a master virtual disk (VDisk) and an auxiliary VDisk. These VDisks also have the attributes of a primary or secondary VDisk. See also auxiliary virtual disk, master virtual disk, primary virtual disk, and secondary virtual disk.
reliability: The ability of a system to continue to return data even if a component fails.
remote fabric: In Global Mirror, the storage area network (SAN) components (switches and cables) that connect the components (nodes, hosts, and switches) of the remote cluster.
roles: Authorization is based on roles that map to the administrator and service roles in an installation. The switch translates these roles into SAN Volume Controller administrator and service user IDs when a connection is made to the node for the SAN Volume Controller.

S

SAN: See storage area network.
SAN Volume Controller fibre-channel port fan in: The number of hosts that can see any one SAN Volume Controller port.
SATA: See Serial Advanced Technology Attachment.
schema: A group of object classes defined for and applicable to a single namespace. Within the CIM agent, the supported schemas are the ones that are loaded through the managed object format (MOF).
SCSI: See Small Computer Systems Interface.
SCSI back-end layer: The layer in a Small Computer Systems Interface (SCSI) network that performs the following functions: controls access to individual disk controller systems that are managed by the cluster; receives requests from the virtualization layer, processes them, and sends them to managed disks; addresses SCSI-3 commands to the disk controller systems on the storage area network (SAN).
SCSI front-end layer: The layer in a Small Computer Systems Interface (SCSI) network that receives I/O commands sent from hosts and provides the SCSI-3 interface to hosts. SCSI logical unit numbers (LUNs) are mapped to virtual disks (VDisks) in this layer as well. Thus, the layer converts SCSI read and write commands that are addressed to LUNs into commands that are addressed to specific VDisks.
SDD: See subsystem device driver (SDD).
secondary virtual disk: In Metro or Global Mirror, the virtual disk (VDisk) in a relationship that contains a copy of data written by the host application to the primary VDisk.
Secure Shell (SSH): A program to log in to another computer over a network, to run commands in a remote machine, and to move files from one machine to another.
Secure Sockets Layer (SSL): A security protocol that provides communication privacy. With SSL, client/server applications can communicate in a way that is designed to prevent eavesdropping, tampering, and message forgery.
sequential VDisk: A virtual disk that uses extents from a single managed disk.
Serial Advanced Technology Attachment (SATA): The evolution of the ATA interface from a parallel bus to serial connection architecture. (S)
Serial ATA: See Serial Advanced Technology Attachment.
server: In a network, the hardware or software that provides facilities to other stations; for example, a file server, a printer server, a mail server. The station making the request of the server is usually called the client.
Service Location Protocol (SLP): In the Internet suite of protocols, a protocol that identifies and uses network hosts without having to designate a specific network host name.
fibre-channel SFP connector: See small form-factor pluggable connector.
Simple Mail Transfer Protocol (SMTP): An Internet application protocol for transferring mail among users of the Internet. SMTP specifies the mail exchange sequences and message format. It assumes that the Transmission Control Protocol (TCP) is the underlying protocol.
Simple Network Management Protocol (SNMP): In the Internet suite of protocols, a network management protocol that is used to monitor routers and attached networks. SNMP is an application-layer protocol. Information on devices managed is defined and stored in the application's Management Information Base (MIB).
SLP: See Service Location Protocol.
Small Computer System Interface (SCSI): A standard hardware interface that enables a variety of peripheral devices to communicate with one another.
small form-factor pluggable (SFP) connector: A compact optical transceiver that provides the optical interface to a fibre-channel cable.
SMI-S: See Storage Management Initiative Specification.
SMTP: See Simple Mail Transfer Protocol.
SNIA: See Storage Networking Industry Association.
SNMP: See Simple Network Management Protocol.
solid-state drive (SSD): A data storage device that uses solid-state memory to store persistent data.
space-efficient VDisk: See space-efficient virtual disk.
space-efficient virtual disk: A virtual disk that has different virtual capacities and real capacities.
SSD: See solid-state drive (SSD).
SSH: See Secure Shell.
SSPC: See IBM System Storage Productivity Center (SSPC).
SSL: See Secure Sockets Layer.
stand-alone relationship: In FlashCopy, Metro Mirror, and Global Mirror, relationships that do not belong to a consistency group and that have a null consistency group attribute.
stop: A configuration command that is used to stop the activity for all copy relationships in a consistency group.
stopped: The status of a pair of virtual disks (VDisks) that have a copy relationship that the user has temporarily broken because of a problem.
storage area network (SAN): A network whose primary purpose is the transfer of data between computer systems and storage elements and among storage elements. A SAN consists of a communication infrastructure, which provides physical connections, and a management layer, which organizes the connections, storage elements, and computer systems so that data transfer is secure and robust. (S)
Storage Management Initiative Specification (SMI-S): A design specification developed by the Storage Networking Industry Association (SNIA) that specifies a secure and reliable interface that allows storage management systems to identify, classify, monitor, and control physical and logical resources in a storage area network. The interface is intended as a solution that integrates the various devices to be managed in a storage area network (SAN) and the tools used to manage them.
Storage Networking Industry Association (SNIA): An association of producers and consumers of storage networking products whose goal is to further storage networking technology and applications. See www.snia.org.
striped: Pertains to a virtual disk (VDisk) that is created from multiple managed disks (MDisks) that are in the MDisk group. Extents are allocated on the MDisks in the order specified.
stripeset: See RAID 0.
subsystem device driver (SDD): An IBM pseudo device driver designed to support the multipath configuration environments in IBM products.
superuser authority: Can issue any command-line interface (CLI) command. A superuser can view and work with the following panels: View users, Add cluster, Remove cluster, Add users, and Modify users. Only one Superuser role is available.
suspended: The status of a pair of virtual disks (VDisks) that have a copy relationship that has been temporarily broken because of a problem.
switch: A network infrastructure component to which multiple nodes attach. Unlike hubs, switches typically have internal bandwidth that is a multiple of link bandwidth, and the ability to rapidly switch node connections from one to another. A typical switch can accommodate several simultaneous full link bandwidth transmissions between different pairs of nodes. (S) See also hub.
symmetrical network: A network in which all the initiators are connected at the same level and all the controllers are connected at the same level.
symmetric virtualization: A virtualization technique in which the physical storage in the form of Redundant Array of Independent Disks (RAID) is split into smaller chunks of storage known as extents. These extents are then concatenated, using various policies, to make virtual disks (VDisks). See also asymmetric virtualization.
synchronized: In Metro or Global Mirror, the status condition that exists when both virtual disks (VDisks) of a pair that has a copy relationship contain the same data.
system: A functional unit, consisting of one or more computers and associated software, that uses common storage for all or part of a program and also for all or part of the data necessary for the execution of the program. A computer system can be a stand-alone unit, or it can consist of multiple connected units.

T

terabyte: In decimal notation, 1 099 511 628 000 bytes.
thinly provisioned volume: See space-efficient virtual disk.
topology: The logical layout of the components of a computer system or network and their interconnections. Topology deals with questions of what components are directly connected to other components from the standpoint of being able to communicate. It does not deal with questions of physical location of components or interconnecting cables. (S)
trigger: To initiate or reinitiate copying between a pair of virtual disks (VDisks) that have a copy relationship.

U

UID: See unique identifier.
unconfigured mode: A mode in which I/O operations cannot be performed. See also image mode and managed space mode.
uninterruptible power supply: A device that is connected between a computer and its power source that protects the computer against blackouts, brownouts, and power surges. The uninterruptible power supply contains a power sensor to monitor the supply and a battery to provide power until an orderly shutdown of the system can be performed.
unique identifier (UID): An identifier that is assigned to storage system logical units when they are created. It is used to identify the logical unit regardless of the logical unit number (LUN), status of the logical unit, or whether alternate paths exist to the same device. Typically, a UID is only used once.
unmanaged: An access mode that pertains to a managed disk (MDisk) that is not used by the cluster.

V

valid configuration: A configuration that is supported.
VDisk: See virtual disk (VDisk).
VDisk copy: See virtual disk copy.
virtual capacity: The amount of storage that is available to a server on a virtual disk (VDisk) copy. In a space-efficient virtual disk, the virtual capacity can be different from the real capacity. In a standard virtual disk, the virtual capacity and real capacity are the same.
virtual disk copy: A physical copy of the data that is stored on a virtual disk (VDisk). Mirrored VDisks have two such copies. Nonmirrored VDisks have one copy.
virtual disk (VDisk): A device that host systems in a storage area network (SAN) recognize as a Small Computer System Interface (SCSI) disk.
virtualization: In the storage industry, a concept in which a pool of storage is created that contains several disk subsystems. The subsystems can be from various vendors. The pool can be split into virtual disks that are visible to the host systems that use them.
virtualized storage: Physical storage that has virtualization techniques applied to it by a virtualization engine.
virtual storage area network (VSAN): A fabric within the SAN.
vital product data (VPD): Information that uniquely defines system, hardware, software, and microcode elements of a processing system.
VLUN: See managed disk.
VPD: See vital product data.
VSAN: See virtual storage area network.

W

WBEM: See Web-Based Enterprise Management.
Web-Based Enterprise Management (WBEM): A tiered, enterprise-management architecture that was developed by the Distributed Management Task Force (DMTF). This architecture provides the management design framework that consists of devices, device providers, the object manager, and the messaging protocol for the communication between client applications and the object manager.
worldwide node name (WWNN): An identifier for an object that is globally unique. WWNNs are used by Fibre Channel and other standards.
worldwide port name (WWPN): A unique 64-bit identifier that is associated with a fibre-channel adapter port. The WWPN is assigned in an implementation- and protocol-independent manner.
WWNN: See worldwide node name.
WWPN: See worldwide port name.

Z

zoning: In fibre-channel environments, the grouping of multiple ports to form a virtual, private, storage network. Ports that are members of a zone can communicate with each other, but are isolated from ports in other zones.