RAIDBank4 Owner’s Manual
60
Performance
Performance is an important criterion on which a customer judges a RAID
controller. There are a number of popular benchmarking utilities that are available to
measure the I/O performance of a controller. Some of these utilities simulate specific real-life
applications and provide the user a score indicating the controller’s overall performance in
that niche. Others allow the user to specify tests with specific I/O characteristics and generate
throughput numbers corresponding to each specification. The nature of the tests a user may
wish to conduct on a controller depends on the application space in which that controller is
anticipated to be deployed.
Physical Drive
A single tangible drive is referred to as a physical drive.
Primary Storage
Main memory i.e., RAM is frequently referred to as primary storage.
RAID
Abbreviation of Redundant array of independent disks. It is a set of disk array
architectures that provides fault-tolerance and improved performance.
RAID Type
There are a number of RAID formats that are widely used. Some of the well-known
uni-level types are RAID 0, RAID 1, RAID 3, RAID 5 and RAID 6. The prevalent complex types
are RAID 10 and RAID 50. ,
RAID 0
RAID 0 utilizes simple striping, with the data being distributed across two or more
disks. No data redundancy is provided. The figure below illustrates a purely hypothetical
RAID 0 array comprised of three disks – disks A, B, and C – with four stripes – each uniquely
colored – across those disks.
Advantage:
Striping can improve the I/O throughput by allowing
concurrent I/O operations to be performed on multiple disks comprising the RAID 0 array.
However, this RAID type does not provide any data redundancy.
RAID 1
An array that uses a single pair of disks. Both disks in the pair contain the same
data It provides the best data protection but can’t improve system performance. And storage
space for the same data capacity should be double than in general cases. Hence storage cost
doubles. The capacity of RAID 1 will be the size of the smaller HDD, so we suggest you
connect HDDs of the same sizes to save HDD space.
Advantage:
RAID 1 ensures that if one
of the disks fails, its contents can be retrieved from the duplicate disk. Furthermore, a RAID
1 array can also improve the throughput of read operations by allowing separate reads to be
performed concurrently on the two disks.
RAID 3
RAID 3 utilizes a striped set of three or more disks with the parity of the strips (or
chunks) comprising each stripe written to a disk. Note that parity is not required to be written
to the same disk. Furthermore, RAID 3 requires data to be distributed across all disks in the
array in bit or byte-sized chunks. Assuming that a RAID 3 array has N drives, this ensures that
when data is read, the sum of the data-bandwidth of N – 1 drives is realized. The figure below
illustrates an example of a RAID 3 array comprised of three disks. Disks A, B and C comprise
the striped set with the strips on disk C dedicated to storing the parity for the strips of the
corresponding stripe. For instance, the strip on disk C marked as P(1A,1B) contains the parity
for the strips 1A and 1B. Similarly the strip on disk C marked as P(2A,2B) contains the parity
for the strips 2A and 2B.
Advantage:
RAID 3 ensures that if one of the disks in the striped
set (other than the parity disk) fails, its contents can be recalculated using the information
D-Glossary
