Hitachi MK-96RD617-08 - Manual (Page 19)

About Performance Manager Options 2-3
Hitachi Universal Storage Platform V/VM Hitachi Performance Manager User’s Guide
Overview of Performance Monitor
Performance Monitor tracks your storage system and lets you obtain statistics
about the following:
• resources in your storage system
• workloads on disk and ports
If your system encounters some problem (for example, if server hosts suffer
delayed response times), Performance Monitor can help you detect the cause
of the problem.
Performance Monitor can also display the status of remote copies by TrueCopy,
TrueCopy for IBM z/OS, Universal Replicator, and Universal Replicator for IBM
z/OS. The displayed contents are the same as those displayed in the Usage
Monitor windows of each remote copy function.
The Export Tool enables you to save information on the Performance
Management window into files, so you can use spreadsheet or database
software to analyze the monitoring results. For detailed information about the
Export Tool, see Overview of Export Tool.
Understanding Statistical Storage Ranges
Performance Monitor has two kinds of periods (ranges) for collecting and
storing statistics: short range and long range. The difference of the two ranges
and the statistics at which they are targeted is as follows:
• Storing in short range
If the number of CUs to be monitored is 64 or less, Performance Monitor
collects statistics at a user-specified interval that is between 1 and 15
minutes, and stores them between 1 and 15 days.
If the number of CUs to be monitored is 65 or more, Performance Monitor
collects statistics at a user-specified interval that is 5, 10 or 15 minutes,
and stores them between 8 hours and 1 day.
All the statistics that can be monitored by Performance Monitor are
collected and stored in short range.
• Storing in long range
Performance Monitor collects statistics at fixed 15-minutes interval, and
stores them for 3 months (i.e., 93 days).
The usage statistics about resources in the storage system are collected
and stored also in long range, in parallel with in short range. However,
some of the usage statistics about resources cannot be collected in long
range.