El 08/05/2013 14:49 p.m., Gilles Chanteperdrix escribió:
On 05/08/2013 08:39 PM, Sebastian Pavez wrote:

Obviously Xenomai can't utilize the 100% of CPU,

Xenomai can utilize 100% of the CPU, the problem is that if it does so
for a too long time, the system crashes eventually.
Ok, thanks for the clarification
so my question is: If I
try to work in Xenomai, with some task that are not able to execute
completely, the CPU will try to utilize resource that doesn't have?

I do not understand this question.
I will explain all again at the end of the email
In regard the changes I made, how are related the Xenomai scheduler and
the Linux one? where I could find some detailed documentation about this
(to put in my references)? Is there something like an scheduler of
schedulers that take the execution of Xenomai's task and then the Linu'x
ones?

Linux as a whole is seen as one task by Xenomai scheduler, executed when
Xenomai scheduler has no other task to execute.

A confirmation of why my previous test (both tasks running with Xenomai)
was a dead end would be great. Some souce of information (more formal
than a suggestion) would also be quite appreciated.

You never showed a test that I could run on my machine to try and
understand what you are trying to prove. And I still do not understand.
Please make a test program, using rt_timer_spin to simulate the cpu
load, and explain me, in very simple word, or with a printf in the test
code, or with a comment in the test code, the problem you observe. Is it
a latency problem?

Just some points to clarify,

- First of all my problem isn't with the functioning of Xenomai. That works jus fine ... I think. - The whole idea of my code is to explain the theory behind a real time system - In the theory if you have 2 tasks, the one with the highest priority (T1) will execute before the other (T2), if there's sometime left it will be executed - On the other hand, if there's not enough time to execute the task with lowest priority (T2) it will be paused by the other one. - I do that with a same period for both tasks and increasing the execution time of T1 order to reduce the time left to T2. - So for instance, if I have a period of 50us for each task. The execution time for T2 is 20us, and for T1 is variable (call it 'E1'). - If 'E1' is less than 30us everything will be ok, both tasks will be executed entirely (Case1) - But, when 'E' is over 30us T2 will not have enough time to complete (Case2)

- Whit this in mind, if I have two tasks in Xenomai (with different priority) is possible to see this effect, I mean for Case1 everything goes fine. But when I try Case2 the computer hangs up for a while and the execution ends. With proc/xenomai/stat I'm able to see that the utilization of CPU arrives closely to 100% (That explain the hang up).

All this lead me to the question: What I'm tring to do isn't possible to do (based on this results)? I mean, is this state true?: I'll never be able to see the effect I'm looking for because Xenomai won't allow me to have tasks that are not able to execute entirely? (If you could recommend some documentation to read about this would be great).

That's led me to try what I said previously, having one task with Xenomai and the other in Linux. This gave me the results I expected related with the theory, and that's all I need. But I would like to be sure if what I was trying to do before it (both tasks with Xenomai) were a dead end. And again, if you could suggest some documentation to read about the relation with the schedulers of Xenomai and Linux would be just awesome. And if there's something about the behaviour of a task created with (priority=0 and policy=OTHER) would be great too, because what I read wasn't clear enough for me.

I hope this explanation is more straight, and sorry if it isn't. Like I said, my problem isn´t related with a malfunction or error with Xenomai, it is if what I'm trying to do doesn't have a foundation.

Thanks, once again.

_______________________________________________
Xenomai mailing list
[email protected]
http://www.xenomai.org/mailman/listinfo/xenomai

Reply via email to