Glossary-6
Compaq ProLiant Clusters HA/F100 and HA/F200 Administrator Guide
Compaq Confidential – Need to Know Required
Writer: Bryan Hicks Project: Compaq ProLiant Clusters HA/F100 and HA/F200 Administrator Guide Comments: Final
Part Number: 380362-003 File Name: k-glossary.doc Last Saved On: 8/24/00 12:06 PM
RAID
See
Redundant Array of Inexpensive Disks
Redundant Array
of Inexpensive
Disks
A method of using hard disk drives in an array to
provide data redundancy to increase system reliability
and performance. RAID is classified in the following
levels:
RAID 0
Data striping. This RAID level stripes
data across all drives of the array, but
does not incorporate a method to create
redundant data. RAID 0 does not provide
fault tolerance.
RAID
0+1
Data striping with mirroring. This level
stripes data across the drives of the array
but duplicates the data through mirroring
to create a level of fault tolerance.
RAID 1
Drive mirroring. This level creates fault
tolerance by storing two sets of duplicate
data on a pair of disk drives.
RAID 4
Data guarding. This level involves the use
of a single, designated drive containing
parity data. If a drive fails, the controller
uses the data on the parity drive and the
remaining drives to reconstruct data from
the failed drive.
RAID 5
Distributed data guarding. This level
stores parity data across all the drives in
the array. Spreading the parity across all
the drives allows more simultaneous read
operations and higher performance than
data guarding (RAID 4).
Redundancy
The provision of multiple, interchangeable
components to perform a single function in order to
cope with failures and errors. A RAID set is
considered to be redundant when user data is recorded
directly to one member and all of the other members
include associated parity information.
Reliability
The continuous integrity of a system (server, storage,
network, or cluster).
Summary of Contents for ProLiant Clusters HA/F100
Page 8: ......
