Home
QNX Momentics IDE User's Guide
Analyzing Performance
QNX Momentics IDE works with the Application Profiler and Valgrind (pronounced val-grinned) Cachegrind tools, which measure the performance of programs running on QNX targets. It also offers the QNX System Information perspective for viewing performance-related metrics.
Investigating performance bottlenecks
The profiling results tell you which functions are called frequently and which ones have the longest execution times. You can then analyze the target system or measure other aspects of an application's performance, to learn why certain functions are performance bottlenecks and to get ideas about how to optimize them.

QNX Momentics IDE User's Guide
- Working with QNX Momentics IDE
  QNX Momentics IDE provides a graphical environment for developing, running, debugging, and profiling applications.
- Developing Projects with the IDE
  To use the QNX Momentics IDE to write applications targeted for QNX OS systems, you must define projects, which are containers that store your source code, configuration files, and binary files.
- Debugging Applications
  The IDE allows you to debug a running application, a library used by the application, or a core file.
- Unit Testing
  The IDE lets you use commercial test frameworks to write unit tests and then execute them by launching a project. While running a test program, you can use the Code Coverage tool to determine how much of the code is exercised (covered) by your tests.
- Analyzing Memory Usage and Finding Memory Problems
  QNX Momentics IDE lets you run Memory Analysis and several Valgrind (pronounced val-grinned) tools to find memory problems such as leaks and corruption, and to measure memory usage of programs. It also provides the QNX System Information perspective so you can learn which processes are consuming memory or other resources excessively.
- Analyzing Performance
  QNX Momentics IDE works with the Application Profiler and Valgrind (pronounced val-grinned) Cachegrind tools, which measure the performance of programs running on QNX targets. It also offers the QNX System Information perspective for viewing performance-related metrics.
  - Monitoring performance
    The QNX System Information perspective displays realtime data about the processes running on a target machine, including CPU usage statistics. These statistics help you find processes or threads that are consuming many CPU cycles.
  - Profiling applications
    From the IDE, you can build an application for profiling and launch it. The Application Profiler then displays, in the QNX Analysis perspective, how much execution time is consumed by different functions.
  - Investigating performance bottlenecks
    The profiling results tell you which functions are called frequently and which ones have the longest execution times. You can then analyze the target system or measure other aspects of an application's performance, to learn why certain functions are performance bottlenecks and to get ideas about how to optimize them.
    - Analyzing cache usage with Valgrind Cachegrind
      Valgrind Cachegrind simulates cache memory and measures a program's reads and writes and its misses at various cache levels. It also reports branch misprediction rates. Cachegrind writes these statistics into the analysis results, which the IDE then parses to display performance data.
  - Configuring shared library support
    The integrated performance measurement tools produce results that contain statistics for individual functions. To include information about functions from shared libraries, the active tool must have access to library copies with debug symbols and possibly, profiling instrumentation.
  - Measuring application performance from the command line
    You can run an application built with profiling instrumentation or run Valgrind Cachegrind on an application from the command line, outside of QNX Momentics IDE. This option gives you more control over how an analysis tool is configured while still allowing you to view the analysis results in the IDE.
  - Controlling profiling at runtime
    You can configure the initial profiling settings through the Application Profiler in the IDE or through command-line settings. While an instrumented binary runs, you can further control profiling by using signals or API calls.
  - Importing performance analysis results
    The IDE can import session data generated by a performance-measuring tool while an application ran. This allows you to view the results of previous analyses, including those shared by other team members or those from sessions that you ran outside of the IDE.
  - Exporting performance analysis results
    The IDE can export session data generated by a performance-analyzing tool while an application ran. This allows you to share analysis results or view them outside of the IDE.
- Analyzing System Behavior
  Many IDE tools allow you to find errors and optimize applications, but to ensure that your embedded system behaves well, you need to use system-wide diagnostic tools. The QNX System Information and QNX System Profiler tools help you understand process and thread interaction on the target, reduce application and system startup times, and debug deadlock and improper CPU usage levels.
- Building QNX OS Images
  Using the IDE's QNX System Builder feature, you can generate OS images, which are bootable images that contain startup code, the QNX OS, your applications, and any data files used by your applications. The IDE supports image building by allowing you to transfer an image to a target board.
- Reference
  The reference topics provide information about QNX Momentics IDE features and workflows that isn't covered in the chapters related to developing projects or debugging, testing, and analyzing applications.
- JTAG: Debugging with Lauterbach TRACE32
  The Lauterbach TRACE32® In-Circuit Debugger (TRACE32-ICD) supports the JTAG onchip interface so you can perform hardware debugging of QNX OS systems through the QNX Momentics IDE.
QNX Software Development Platform
QNX Software in the Cloud
QNX Toolkit for Visual Studio Code
This User's Guide describes the QNX Toolkit for Visual Studio Code. The guide introduces you to the QNX Toolkit by explaining the QNX development environment and how to build, run, and debug your QNX OS applications and systems.
Typographical Conventions, Support, and Licensing
This section describes the typographical conventions used throughout the documentation and explains how to obtain technical support.

Investigating performance bottlenecks

QNX Tool SuiteIntegrated Development Environment User's GuideDeveloperSetup

The profiling results tell you which functions are called frequently and which ones have the longest execution times. You can then analyze the target system or measure other aspects of an application's performance, to learn why certain functions are performance bottlenecks and to get ideas about how to optimize them.

Some common causes of bad performance are:

Heavy heap usage — If a function allocates and frees a lot of heap memory many times, this slows execution because of the overhead of heap operations. You can analyze the program's heap usage to see which areas of code do this.
Impact of other processes — On the target machine, other processes could be negatively impacting the performance of a given application. You can run a kernel event trace and examine the System Profiler results to see if problems such as starvation or priority inversion may be slowing the application at a particular point.
Inefficient cache usage — If an application is doing data-intensive work but most of the working set isn't kept in cache memory, the frequent accesses to slower memory can noticeably reduce performance. Valgrind Cachegrind profiles a process's cache usage and reports statistics for each function and line of code, so you can pinpoint the exact sources of inefficient cache usage.

Page updated: May 17, 2024