Evaluating performance impact – HP Surestore Disk Array 12h and FC60 User Manual
Page 250
250 Managing Disk Array Capacity
Evaluating Performance Impact
Several disk array configuration settings have a direct impact on I/O performance of the
array. When selecting a setting, you should understand how it may affect performance.
identifies the settings that impact disk array performance and what the impact is.
Note
The LUN binding process impacts disk array performance. While a LUN is being
bound, benchmarking tools should not be used to evaluate performance. Wait
until all LUNS are bound to get an accurate indication of disk array
performance.
Table 31 Performance Impact of Configuration Settings
Setting:
RAID level
Function: Sets the RAID level used by the LUN.
Performance Impact: The RAID level selected impacts the entire performance profile for the
LUN. Read I/O and write I/O performance are directly influenced by the RAID level. See
for more information on the performance characteristics of each
RAID level.
Setting:
Stripe segment size
Function: Sets the number of blocks of data the controller will write to or read from a single disk
before switching to the next disk in the LUN.
Performance Impact: Optimum performance is typically achieved when the segment size
matches the I/O size. In this case, only one disk is required to service an I/O, leaving the
remaining disk in the LUN available for other I/Os.
A large segment size provides good read performance in most RAID levels. The controller will
have to access fewer disks to retrieve the data, leaving the remaining drives available for other
I/O operations. Large segment sizes are typically useful for applications that require high I/O
throughput.
A small logical unit segment size is useful for most RAID 5 write applications, because the
controller firmware is capable of performing group writes (writing of data simultaneously to
multiple disks, while calculating the parity for the stripe, as opposed to the single-threaded read-
modify-write). Small segment sizes are typically useful for applications that require large
numbers of small I/Os to be processed quickly.