HP StorageWorks P9000 Performance Advisor Software v5.3 User and Troubleshooting Guide (T1789-96322, August 2011)

The overall usage status of an XP or a P9000 disk array in a category is based on the usage of
components in that category. The usage data is collected only on those metrics whose threshold limits
are set on the Threshold Settings screen.
For example, assume that you have set the threshold limit for only the RG Seq Reads (IOPS) (Avg Seq
Reads) metric in the Backend category. The status icon displayed in the XP/P9000 Array Health
section in the Backend category is based on the usage of individual components corresponding to
the RG Seq Reads (IOPS) (Avg Seq Reads) metric during the specified threshold duration.
Dashboard statistics
Click a status icon in the XP/P9000 Array Health section in the Frontend, Cache, Backend, or the MP
Blade category to view the associated components and their average usage data in the respective
Statistics section. The following image shows the frontend statistics for 10116, which belongs to the
XP24000 Disk Array type.
P9000 Performance Advisor considers the following factors to arrive at the average usage data for
a component in the Frontend, Cache, Backend, and the MP Blade categories:
• Threshold limits set for metrics in the Frontend, Cache, Backend, or the MP Blade category
• Threshold duration (6 hours, 12 hours, or 24 hours)
After the threshold limits are defined for the categories and the corresponding metrics on the Threshold
Settings screen, P9000 Performance Advisor does the following for the XP or the P9000 disk arrays:
1. Monitors the usage of every component in the XP or the P9000 disk array and retrieves the ap-
propriate values. It is based on the categories and the corresponding metrics for which the
threshold limits are defined:
• The average overall I/Os and MB/s on individual ports
• The average overall utilization of MPs that belong to a CHA
• The cache usage (%) and writes pending (%)
• The average sequential backend read tracks on individual RAID groups
• The average non-sequential backend read tracks (also known as random backend reads) on
individual RAID groups
HP StorageWorks P9000 Performance Advisor Software User Guide 131