Re: allowed_cpus issue in rt_task_init_schmod call

Paolo Mantegazza <[email protected]>
Newsgroups gmane.linux.real-time.rtai
Message-ID <[email protected]>
How did you check it? Using "cat /rtai/sched"?
Clearly it may be a long time standing and undetected bug.
I've not 4 core handy, so can you check if it works when you force your 
task onto a single CPU (1, 2, 4, 8)?
It will help me restricting my eventual search of the code fix range.

Thanks, Paolo.

On 03/08/2016 03:09 PM, Emmanuel Pacaud wrote:
> Hi,
>
> I'm facing an issue with rt_task_init_schmod trying to assign a task 
> to a set of cpus.
>
> I have attached a sample program that shows this issue.
>
> The machine I'm using has 4 cores, and has rtai 5.0-test1. I want to 
> start several instances of a program on the first two cores, leaving 
> the last 2 ones for interrupt handling (they are isolated using 
> isolcpus 2,3).
>
> If I use 1 as allowed_cpus mask, all the instances are started on core 0.
> If I use 2, all the instances are started on core 1.
> If I use 3, instances run on either core 0, 1, 2 or 3, while I expect 
> them to be running only on core 0 and 1.
>
> Is there something wrong in my sample code ?
>
> Thanks,
>
>     Emmanuel.
>
>
> _______________________________________________
> Rtai mailing list
> [email protected]
> https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai

_______________________________________________
Rtai mailing list
[email protected]
https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.