HP StorageWorks P9000 Performance Advisor Software v5.2 User and Troubleshooting Guide (T1789-96315, June 2011)

consumer's average utilization of the CPU cycles across the collection cycles during the selected
duration. Those consumers whose average utilization percentage is high when compared to the other
associated consumers are categorized as the top 20 consumers.
Select an MP blade ID (cluster #, blade location) from MP Blades in the component selection tree and
choose the MP Blade Util - Top 20 Consumers metric by clicking more in the Choose Metrics box. For
more information, see “MP Blades navigation path” on page 274.
A column graph is displayed in a separate Utilization Metrics chart window, where each column
depicts the average MP blade utilization by each consumer. The X-axis represents the consumer IDs
(includes the consumer type and the processing type) and the Y-axis represents the average MP blade
utilization. The chart title includes the P9000 disk array DKC number, the MP blade ID, and the metric
name for which the graph is plotted. The legends on the top right corner of the column graph helps
you to identify the corresponding consumers.
Figure 25 on page 301 displays a column graph for the top 20 consumers of the MPB-1MA.
Figure 25 MP blade utilization - top 20 consumers
.
Place the pointer over a column to view the following details for the respective consumer:
Example (see Figure 25)
MP blade utilization by top
20 consumers
LDEV:0:18 (Backend)
A consumer's association with a processing type provides an understanding on the number of
processing cycles used by the consumer with different processing types.
For example, an LDEV 0:09 might be involved in processing frontend and backend requests. Its
processing type reveals whether the frontend or the backend requests have been high. Further to
the above-mentioned example:
• If the average utilization shown for the Frontend processing type is 30% and 25% is contributed
by the LDEV 0:09
• If the average utilization shown for the Backend processing type is 25% and 15% is contributed
by the LDEV 0:09
This data indicates that the LDEV 0:09 has been addressing high frontend requests when compared
to the backend activities.
NOTE:
The average utilization of an MP Blade is always on a scale of 1 - 100%.
Consumer type, Consumer ID,
and the processing type
HP StorageWorks P9000 Performance Advisor Software User Guide 301