Performance graphs and guidelines
The Performance page provides graphs and tables of data that enable you to assess the storage array's performance in several key areas.
Performance functions allow you to accomplish these tasks:
-
View performance data in near real-time to help you determine whether a storage array is experiencing problems.
-
Export performance data to construct a historical view of a storage array and identify when a problem started or what caused a problem.
-
Select the objects, performance metrics, and time frame you want to view.
-
Compare metrics.
You can view performance data in three formats:
-
Real-time graphical — Plots performance data on a graph in near real-time.
-
Near real-time tabular — Lists performance data in a table in near real-time.
-
Exported CSV file — Allows you to save tabular performance data in a file of comma-separated values for further viewing and analysis.
Characteristics of performance data formats
Type of performance monitoring | Sampling interval | Length of time displayed | Maximum number of objects displayed | Ability to save data |
---|---|---|---|---|
Real-time graphical, live Real-time graphical, historical |
10 sec (live) 5 min (historical) Data points shown depend on selected time frame |
Default time frame is 1 hour. Choices:
|
5 |
No |
Near real-time tabular (table view) |
10 sec -1 hr |
Most current value |
Unlimited |
Yes |
Comma-separated values (CSV) file |
Depends on selected time frame |
Depends on selected time frame |
Unlimited |
Yes |
Guidelines for viewing performance data
-
Performance data collection is always on. There is no option to turn it off.
-
Each time the sampling interval elapses, the storage array is queried and the data is updated.
-
For graphical data, the 5-minute time frame supports 10-second updating averaged over 5 minutes. All other time frames are updated every 5 minutes, averaged over the selected time frame.
-
Performance data in the graphical views is updated in real time. Performance data in the table view is updated in near real time.
-
If a monitored object changes during the time data is collected, the object might not have a complete set of data points spanning the selected time frame. For example, volume sets can change as volumes are created, deleted, assigned, or unassigned; or drives can be added, removed, or failed.