Panagiotis Issaris panagiotis.issaris at mech.kuleuven.ac.be
Sat Oct 16 12:49:36 CEST 2004

Philippe Gerum wrote:

>On Fri, 2004-10-15 at 23:29, Panagiotis Issaris wrote:
>>I've created a simple RTAI LiveCD (16MB), which through
>>a series of menus, guides the user to run the
>>RTAI testsuite and submit the results and system
>>configuration information to an Internet database.
>>I've created a webpage for this LiveCD, including
>>a HOWTO illustrated with screenshots and
>>a webpage listing the results. PCI device information
>>is also avaible for each testrun.
>>Any feedback and/or testresults are appreciated!
>>The current version uses RTAI 3.1 with Linux 2.6.7
>>and ADEOS r8c4.
>>The webpage does not contain many queries yet; you
>>can only list all submitted testresults and view device
>>information for each testresult.
>>I'm about to add a query to show all testresults when
>>a user enters a keyword. Such that if one queries
>>for "845", he will receive the testresults for PC's using
>>"Intel 82845 845 (Brookdale) Host Bridge".
>>With friendly regards,
>This is probably the best idea I've ever seen implemented for RTAI since
>the creation of the project itself. Thanks for this.
It still has a few problems though:
1. The actual method of running the test. The tests are now
being executed (somewhat simplified) as follows:
find / &
hackbench 5 &
timestamp 1 (for calculating runtime)
timestamp 2 (for calculating runtime)

Several questions/problems here:
* Are the shown applications good for generating an artificial load?
  I normally use pingflooding as well. Should I add it to the test? Any
  other apps I could add to the test?
* If hackbench is of any use for evaluating RTAI's performance
   under stress, deciding which parameter to use is not that simple.
   If the parameter is to big, the machine get loads of 600 and more
   and is unresponsive _for a long time_. If it is too small, it is 
   to add it.
* When find is run for the first time, it intensively accesses the HD. But,
   on the second run, all seems to be cached, and I assume that therefore
   the find does not contribute to stresstesting RTAI?
* For the latency tests, I only upload the maximum latency. Is it usefull
  to also add the average and possibly the minimal latency? The data from
  the other tests (preempt and switch) are not being uploaded to the
  database. Any suggestions on what data is most useful for those tests?

The last point requires modification of the database, so I'd like to fix 
one as soon as possible.

With friendly regards,

Panagiotis Issaris
Katholieke Universiteit Leuven
Division Production Engineering,
Machine Design and Automation
Celestijnenlaan 300B              panagiotis.issaris at mech.kuleuven.ac.be
B-3001 Leuven Belgium                 http://www.mech.kuleuven.ac.be/pma

More information about the Rtai mailing list