availability
The degree to which a system or resource
is capable of performing its normal

function. See data availability.

B

bay The physical space that is used for

installing SCSI, ESCON, and fibre-channel
host adapter cards. The DS8000 has four
bays, two in each cluster. See also service

boundary.

bit 1) Either of the digits 0 or 1 when used in

the binary numeration system. (T)
2) The storage medium required to store a
single binary digit. See also byte.

block A string of data elements recorded or

transmitted as a unit. The elements may
be characters, words, or physical records.
(T)
A group of consecutive bytes used as the
basic storage unit in fixed-block
architecture (FBA). All blocks on the
storage device are the same size (fixed
size). See also fixed-block architecture
and data record.

byte 1) A group of eight adjacent binary digits

that represent one EBCDIC character.
2) The storage medium required to store

eight bits. See also bit.

C

cache A special-purpose buffer storage, smaller

and faster than main storage, used to hold
a copy of instructions and data obtained
from main storage and likely to be needed
next by the processor. (T)
cache fast write
A form of the fast-write operation in which
the storage server writes the data directly
to cache, where it is available for later
destaging.
cache hit
An event that occurs when a read
operation is sent to the cluster, and the
requested data is found in cache. Contrast
with cache miss.
cache memory
Memory, typically volatile memory, that a
storage server uses to improve access
times to instructions or data. The cache
memory is typically smaller and faster
than the primary memory or storage
medium. In addition to residing in cache
memory, the same data also resides on
the storage devices in the storage unit.
cache miss
An event that occurs when a read
operation is sent to the cluster, but the
data is not found in cache. Contrast with

cache hit.

call home
A communication link established between
the DS8000 and a service provider. The
DS8000 can use this link to place a call to
IBM or to another service provider when it
requires service. With access to the
machine, service personnel can perform
service tasks, such as viewing error logs
and problem logs or initiating trace and
dump retrievals. See also heartbeat and
remote technical assistance information

network.

cascading
1) Connecting network controllers to each
other in a succession of levels to
concentrate many more lines than a single
level permits.
2) In high-availability cluster
multiprocessing (HACMP), cascading
pertains to a cluster configuration in which
the cluster node with the highest priority
for a particular resource acquires the
resource if the primary node fails. The
cluster node relinquishes the resource to
the primary node upon reintegration of the
primary node into the cluster.
catcher
A server that service personnel use to
collect and retain status data that an
DS8000 sends to it.

CCR See channel command retry.

CCW See channel command word.

CD See compact disc.

CEC See computer-electronic complex.

channel
For zSeries, the part of a channel
subsystem that manages a single I/O
interface between a channel subsystem
and a set of control units.

Glossary 327