| Skip Navigation Links | |
| Exit Print View | |
|
Oracle Solaris Studio 12.3: Performance Analyzer Oracle Solaris Studio 12.3 Information Library |
| Skip Navigation Links | |
| Exit Print View | |
|
|
Oracle Solaris Studio 12.3: Performance Analyzer Oracle Solaris Studio 12.3 Information Library |
1. Overview of the Performance Analyzer
3. Collecting Performance Data
4. The Performance Analyzer Tool
The OpenMP Parallel Region Tab
The Threads Chart Controls Tab
Setting Data Presentation Options
Recording Experiments from Analyzer
Saving Performance Analyzer Settings
Enabling Comparison Mode By Default
5. The er_print Command Line Performance Analysis Tool
6. Understanding the Performance Analyzer and Its Data
To start the Performance Analyzer, type the following on the command line:
% analyzer [control-options] [experiment-list]
The experiment-list command argument is a blank-separated list of experiment names, experiment group names, or both. If you do not provide an experiment list, the Analyzer starts and automatically opens the Open Experiment dialog box so you can navigate to an experiment and open it.
You can specify multiple experiments or experiment groups on the command line. If you specify an experiment that has descendant experiments inside it, all descendant experiments are automatically loaded. The data from the initial founder process and all the descendants is aggregated. To load individual descendant experiments you must specify each experiment explicitly or create an experiment group. You can also put an en_desc directive in an .er.rc file (see en_desc { on | off | =regexp}).
To create an experiment group, you can use the -g argument to the collect utility. To manually create an experiment group, create a plain text file whose first line is as follows:
#analyzer experiment group
Then add the names of the experiments on subsequent lines. The file extension must be erg.
You can also use the File menu in the Analyzer window to add experiments or experiment groups. To open experiments recorded on descendant processes, you must type the file name in the Open Experiment dialog box (or Add Experiment dialog box) because the file chooser does not permit you to open an experiment as a directory.
When the Analyzer displays multiple experiments, data from all the experiments is aggregated by default. The data is combined and viewed as if the data is from one experiment. However, you can also choose to compare the experiments instead of aggregating the data. See Comparing Experiments.
You can preview an experiment or experiment group for loading by single-clicking on its name in either the Open Experiment dialog or the Add Experiment dialog.
You can also start the Performance Analyzer from the command line to record an experiment as follows:
% analyzer [Java-options] [control-options] target [target-arguments]
The Analyzer starts up with the Collect window showing the named target and its arguments, and settings for collecting an experiment. See Recording Experiments from Analyzer for details.
You can also open a “live” experiment – an experiment that is still being collected. When you open a live experiment, you see only the data that had already been collected when you opened the experiment. The experiment is not automatically updated as new data comes in. To update, you can open the experiment again.
These options control the behavior of the Analyzer and are divided into three groups:
Java options
Control options
Information options
These options specify settings for the JVM that runs the Analyzer.
Specify the path to the JVM software for running the Analyzer. When the -j option is not specified, the default path is taken first by examining environment variables for a path to the JVM, in the order JDK_HOME and then JAVA_PATH. If neither environment variable is set, the JVM found on your PATH is used. Use the -j option to override all the default paths.
Specify the JVM options. You can specify multiple options. For example:
To run the 64–bit Analyzer, type:
analyzer -J-d64
To run the Analyzer with a maximum of JVM memory of 2 Gbytes, type:
analyzer -J-Xmx2G
To run the 64–bit Analyzer with a maximum JVM memory of 8 Gbytes, type:
analyzer -J-d64 -J-Xmx8G
These options control the font size of the GUI, and display the version and runtime information before starting the Analyzer.
Specify the font size to be used in the Analyzer GUI.
Print version information and Java runtime arguments before starting.
These options do not invoke the Performance Analyzer GUI, but print information about analyzer to standard output. The individual options below are stand-alone options; they cannot be combined with other analyzer options nor combined with target or experiment-list arguments.
Print version information and exit.
Print usage information and exit.
The Analyzer uses resource files named .er.rc to determine default values for various settings upon startup. The system wide er.rc defaults file is read first, then an .er.rc file in the user’s home directory, if present, then an .er.rc file in the current directory, if present. Defaults from the .er.rc file in your home directory override the system defaults, and defaults from the .er.rc file in the current directory override both home and system defaults. The .er.rc files are used by the Analyzer and the er_print utility. Any settings in .er.rc that apply to source and disassembly compiler commentary are also used by the er_src utility.
See the sections Default Settings for Analyzer for more information about the .er.rc files. See Commands That Set Defaults and Commands That Set Defaults Only For the Performance Analyzer for information about setting defaults with er_print commands.
|