HP StorageWorks XP48 - Disk Array, Owner'S Manual

Page: 103 / 124

RAID Technology 103
Configuring Dynamic Spare Disks
You can configure the disk array with a minimum of 1 and a maximum of
16 spare disk drives. For both RAID0/1 and RAID5 array groups, any
dynamic spare drive can back up any other disk drive of the same capacity,
anywhere in the disk array, even if the failed disk and the spare disk are on
different array control processor (ACP) pairs. The RAID system uses
diagnostics and disk-scrubbing algorithms to detect and correct drive
errors. The system can encounter errors with the physical drive either from
a host I/O request or from background data integrity checking.
Figure 17. Normal Data Read Operation
If a drive error occurs during an I/O operation from a host, the system can
recover the target data using parity data and data stored on the other
nonfailing drives. The data can be recovered even when the array
subsystem cannot read the data because of errors occurring on the physical
drives. This feature ensures nondisruptive processing of applications in
case of drive errors. Figure 17 (page 103) shows a normal data read
operation. The figure below shows how data is reconstructed after a drive
error is encountered.
DKC
(RAID 5)
D2
M8 D6
D8
M6
M7
D5
D7
M5
M4 D2
D4
M2
M3 D1
D3
M1
P
(10-12)
D11
D10
D12
P
(7-9)
D7
D9 D8
P
(4-6)
D6 D5 D4
P
(1-3)
D1 D2 D3
DKC
RAID 0/1
D2
Disk 1 Disk 2 Disk 3 Disk 4 Disk 1 Disk 2 Disk 3 Disk 4
HOST
D2
HOST
D2