GPA Manual

Introducing GPA
Guardian Performance Analyzer (GPA) Manual—135081
1-2
How GPA Works
•
Provides PUP or SCF input (PUPIN/SCFIN) control statements for implementing
tuning recommendations and a PUP or SCF backout file (PUPBAK/SCFBAK) to
restore the system to its previous state, depending on the operating system.
•
Enables you to choose the optional reports that meet your specific requirements.
•
Analyzes any Tandem node with up to 16 processors of any type.
•
Installs and runs easily, and can provide its performance analysis results (in the form
of two reports) in roughly 2 to 30 minutes, depending on the size of the node, the
processor type the analyzer is executed on, and the amount of data to be analyzed.
How GPA Works
GPA bases its analysis on system performance data collected by Measure and on the
GPA internal model of a Tandem multiprocessor node.
As distributed, GPA consists of these files:
•
GPA performs the analysis.
•
TUNEDATA contains coded text statements for the “GPA Analysis Statements”
section of the GPA Standard Report.
•
OBEYTUNE executes the GPA analysis run.
Figure 1-1
illustrates the GPA analysis process and shows the relationship of three
structured data files, CPU, PROCESS, and DISC. These files are created and loaded
from the raw Measure data by MEASFH, the Measure file handler.