Raid Group Load Test

"RAID" – the Redundant Array of Independent Disks - is now used as an umbrella term for computer data storage schemes that can divide and replicate data among multiple hard disk drives. RAID's various designs all involve two key design goals: increased data reliability or increased input/output performance. When multiple physical disks are set up to use RAID technology, they are said to be in a RAID array/group. This array distributes data across multiple disks, but the array is seen by the computer user and operating system as one single disk.

For every RAID group auto-discovered on a Hitachi AMS storage device, this test monitors the I/O load on the group.

Target of the test : A Hitachi AMS storage device

Agent deploying the test : A remote agent

Outputs of the test : One set of results for each RAID group on the storage device monitored.

Configurable parameters for the test
Parameter Description

Test Period

How often should the test be executed.

Host

The IP address of the storage device.

UnitName

Specify the name of the storage unit to be monitored. To determine the unit name registered with the Storage Navigator Client for the AMS SAN device, run the following commands, one after another, from the C:\Program Files\Storage Navigator Modular CLI directory on the Storage Navigator Client:

startnsmen

auunitref

The output of the command includes the Name of the storage unit. DF700M_75011118 is a sample unit name.

MCType

Indicate the machine type. The value can be AMS or WMS. By default, this parameter is set to AMS.

SNClientLocation

Specify the full path to the install directory of the storage navigator.

Timeout

Indicate the duration (in minutes) for which this test should wait for a response from the storage device. By default, this is set to 5 minutes.

Measurements made by the test
Measurement Description Measurement Unit Interpretation

IO rate

Indicates the number of read/write commands executed on this RAID group per second.

IOPS

If this measure reports a high value or if the value of the measure increases consistently, it is indicative of unusually high I/O activity on this RAID group.  Comparing the value of this measure across groups can accurately indicate which RAID group is currently experiencing heavy workloads. Observing the variations in this measure over a period of time will enable you to figure out bottlenecks in load balancing.

Read rate

Indicates the number of read operations performed on this RAID group per second.

IOPS

 

Write rate

Indicates the number of write commands issued on this RAID group per second.

IOPS

 

Read hit

Indicates the percentage of read requests that were served from this RAID group.

Percent

Ideally, the value of this measure should be high. A low value is a cause for concern, as it indicates that a majority of read requests have failed.

Write hit

Indicates the percentage of data written to this RAID group.

Percent

Ideally, the value of this measure should be high. A low value is a cause for concern, as it indicates that not all data is getting written to this RAID group; this could be owing to an I/O bottleneck, which might require further investigation.

Data transfer rate

Indicates the transfer size of read/write commands per second.

KB/sec

 

Read transfer rate

Indicates the transfer size of read commands per second.

KB/sec

 

Write transfer rate

Indicates the transfer size of write commands per second.

KB/sec