GPA Manual

Guardian Performance Analyzer (GPA) Manual—135081
4-1
4
Using GPA Information
Interpreting the Standard Report
A GPA analysis can detect and point to a number of causes of poor or inefficient system
performance. For some of the problems, such as a memory shortage or a load imbalance,
GPA can make appropriate tuning recommendations and even, in some cases, provide
the means for automatically implementing the recommendations. For other performance
issues, such as transient processing, GPA can reveal the condition, but the user must
decide how to correct it. (For a general discussion of system tuning, see Section 4 in the
Measure User’s Guide.)
This subsection discusses the various sections of the GPA Standard Report described in
Section 3, Description of GPA Reports
. In the discussion, we look at three GPA analysis
examples. One is for a node (\NODEA) in which the main problem is a serious shortage
of memory, one is for a node (\NODEB) that exhibits a CPU load imbalance, and one is
for a node (\NODEC) that requires a change in the configuration of its primary disk
processes.
With regard to these examples, keep in mind that GPA considers a shortage of memory
to be the most serious problem on a node. If the shortage is severe enough, as is the case
for \NODEA, GPA deals initially only with this issue even though the analysis may find
other tuning problems on the node. Once the memory shortage problem is corrected,
another GPA analysis would consider and make tuning recommendations for the
remaining problems.
System Performance Summary
The System Performance Summary gives you an overall picture of the system and
indicates, in general, how well or how poorly the system analyzed is performing. From
this section of the report, you can do the following:
•
Become familiar with the system’s characteristics.
•
Assess the general health of the system.
•
Spot quickly where any problems may lie.
•
Determine the potential for improved system performance.
Node Characteristics
The Node Characteristics subsection of the GPA report for \NODEA (Example 4-1)
shows the following:
•
The node has a total of 4 processors, 32 megabytes of memory, and 9 disk volumes.
•
There were 264 static (steady-state) processes and 11 dynamic (transient) processes
on the node during the measurement period.
•
The most utilized processor is CPU 1, the least utilized processor is CPU 3, and the
average processor busy time is 36.2 percent.