HP StorageWorks Scalable File Share - Manual (Page 350)

RAID rebuild timing information D–2
D.1 RAID rebuild information
The time taken for a RAID rebuild operation on an SFS20 array is divided into two parts:
• The time taken to rebuild the spare disk
• The time taken to rebuild subsequently to a replacement disk (when the disk has been added)
NOTE: All SFS20 arrays are configured with a spare disk; as a result of this, the rebuild to the spare disk
takes place immediately.
The following criteria apply to the tests on which this information is based:
• The disk failure was simulated by pulling a disk from the array.
• The simulated load consists of eight clients writing files of 4GB repeatedly in 4MB chunks over a
high-performance interconnect.
• The clients wrote to the affected LUN only.
• Tests were carried out with the RAID rebuild priority set to
medium
and
high
.
(This parameter is set when the array is configured, using the
rebuild_priority
option with the
configure array
command.)
Tests were carried out on arrays containing 250GB disks and 500GB disks. For 160GB disks, the
corresponding times could be estimated from the times shown for 250GB disks, as follows:
Time shown/25*16
Table D-1 shows the time taken to rebuild to the spare disk (Failover) and from the spare disk to the
replacement disk (Failback) on disks with various configurations. The MB/sec numbers represent the
performance that was delivered to the application writing the data.
Table D-1 Rebuilding to and from the spare disk
Disk Size Redundancy
Type
Rebuild
Priority
Failover Failback
Time (Hours) MB/sec Time (Hours) MB/sec
250 RAID5 Medium 16 32 6 32
250 RAID5 High 3 4 2 (Approx) 9
250 ADG Medium 12 26 6 26
250 ADG High 5.5 4 2 4
500 ADG Medium 63.5 40 9 44
500 ADG High 13.5 11 3.5 11