Difference between revisions of "Benchmarking"

From ArchWiki
Jump to: navigation, search
Line 1: Line 1:
[[Category:Hardware (English)]][[Category:HOWTOs (English)]]
[[Category:Hardware (English)]][[Category:HOWTOs (English)]]
== Introduction ==
== Introduction ==

Revision as of 01:51, 2 March 2010

Tango-document-new.pngThis article is a stub.Tango-document-new.png

Notes: please use the first argument of the template to provide more detailed indications. (Discuss in Talk:Benchmarking#)


Benchmarking is the act of measuring performance and comparing the results to another system's results or a widely accepted standard through a unified procedure. This unified method of evaluating system performance can help answer questions such as:

  • Is the system performing as it should?
  • What driver version should be used to get optimal performance?
  • Is the system capable of doing task x?


Many tools can be used to determine system performance, the following provides a list of tools available.

Stand alone tools

glxgears (and why not to use this as a benchmark)

Glxgears is a popular OpenGL test that renders a very simple OpenGL performance and outputs the framerate. Though glxgears can be usefull as a test of direct rendering capabillities of the graphics driver, glxgears is an outdated tool that is not representative of the current state of linux graphics and overall OpenGL possibilities.

So to summarize, glxgears only tests a small part of what you typically see in a 3D game. You could have glxgears FPS performance increase, but your 3D game
performance decrease. Likewise, you could have glxgears performance decrease and your 3D game performance increase. source




This benchmark application is designed to benchmark interactivity in Linux.

It is designed to measure the effect of changes in Linux kernel design or systemnconfiguration changes such as cpu, I/O scheduler and filesystem changes and options. With careful benchmarking, different hardware can be compared.

interbench is available in the AUR: http://aur.archlinux.org/packages.php?ID=2093


(n)ttcp measures point-to-point bandwidth over any network connection, the binary must be provided on both nodes between wich you want to determine bandwidth. nttcp is a a much more convenient rewrite of ttcp.

nttcp is available on the AUR: http://aur.archlinux.org/packages.php?ID=11469


The time command provides timing statistics about the command run by displaying the time that passed between invocation and termination. Time is available on most basic linux systems.

time tar -zxvf archive.tar.gz


unigine (Tropics and Sanctuary OpenGL Benchmark)

Unigine has produced several modern OpenGL benchmarks based on their graphics engine with features as:

* Per-pixel dynamic lighting
* Normal & parallax occlusion mapping
* 64-bit HDR rendering
* Volumetric fog and light
* Powerful particle systems: fire, smoke, explosions
* Extensible set of shaders (GLSL / HLSL)
* Postprocessing: depth of field, refraction, glow, blurring, color correction and much more.

unigine-topics is available in the AUR: http://aur.archlinux.org/packages.php?ID=25420

TODO AUR package for unigine-sanctuary

Software suites


This C++ rewrite of the original Bonnie benchmarking suite is aimed at performing several tests of hard drive and filesystem performance.

Bonnie++ is available in the AUR: http://aur.archlinux.org/packages.php?ID=24114


HardInfo can gather information about your system's hardware and operating system, perform benchmarks, and generate printable reports either in HTML or in plain text formats. Hardinfo performs CPU and FPU benchmarks and has a very clean GTK UI.

hardinfo is available in community

Phoronix Test Suite

The Phoronix Test Suite is the most comprehensive testing and benchmarking platform available for the Linux operating system. This software is designed to effectively carry out both qualitative and quantitative benchmarks in a clean, reproducible, and easy-to-use manner. This software is based upon the extensive Linux benchmarking work and internal tools developed by Phoronix.com since 2004 along with input from leading tier-one computer hardware vendors. This software is open-source and licensed under the GNU GPLv3. The Phoronix Test Suite consists of a lightweight processing core (pts-core) with each benchmark consisting of an XML-based profile with related resource scripts. The process from the benchmark installation, to the actual benchmarking, to the parsing of important hardware and software components is heavily automated and completely repeatable, asking users only for confirmation of actions.

source: http://www.phoronix-test-suite.com/?k=home

This suite is available in [community] and can be installed through your favorite package manager

pacman -S phoronix-test-suite

To enable the GUI

phoronix-test-suite gui

Arch Linux Standardized Testing

To be able to compare results within the Arch Linux community in a standardized manner, the following standards have been set.

General System Information Script

When comparing results, it is essential to include a complete overview of your hardware configuration and such things as driver and versions thereof. To simplify this, a system information script will be written wich output all the basic information to a humenly readable format.

In the future, a script will be provided that invokes the installed benchmarking applications of your choise and compiles a list of results along with system information.


proposal: superpi with 1M digits (20 bit number) --stefanwilkens 22:27, 25 October 2009 (EDT)


proposal: phoronix-test-suite with a selection of tests aimed at graphics, preferably without having to provide a large number of dependencies.--stefanwilkens 06:40, 26 October 2009 (EDT)

list of tests:

  • smokin-guns (req: openal)--stefanwilkens 06:40, 26 October 2009 (EDT)
  • ..
  • ..


Hard Drive







proposal: a combination of nttcp and ping should do the job here--stefanwilkens 06:43, 26 October 2009 (EDT)



Related Links