[LITMUS^RT] Base_task when executed does not give the correct debug output as rtspin does

[Susan S]

Hi,

Please do let me know why the st-trace-schedule output does not give the
all the cpus actually used for the base_task.

Regards,
Susan Rose.


On Mon, Mar 12, 2018 at 10:59 AM, Susan S <susanrosethomas2001 at gmail.com>
wrote:

> Hi,
>
> Thank you for the quick reply.
>
> The issue is in my base_task I used a program to utilize 100% CPU by
> writing the prime number calculation.By using the "top" command I have
> verified that the program runs in all cores and all CPUs are 100% utilized.
>
> The issue is in the st-trace-schedule output.It shows only one cpu as
> used.Please do let me know where I have gone wrong.I am running this on
> Xeon D-1548 processor which has 16 logical cpus.
>
> I have attached the base_task program,with the debug file output and
> st-trace output also along with this mail.
>
> Regards,
> Susan Rose.
>
>
>
> On Thu, Mar 8, 2018 at 2:19 PM, Björn Brandenburg <bbb at mpi-sws.org> wrote:
>
>>
>> > On 8. Mar 2018, at 09:31, Susan S <susanrosethomas2001 at gmail.com>
>> wrote:
>> >
>> > I am new to litmus-rt. I am trying to study the flow of the GSN-EDF ,
>> so analyzed the rtspin output using the debug file by using command "cat
>> /dev/litmus/log > debug.txt &".
>> >
>> > This debug.txt of rtspin gives the correct flow of gsnedf scheduler.But
>> when i wrote a job in base_task and executed the output debug file doesnot
>> contain the contents as for rtspin.
>> >
>> > I want to know if only rtspin can be used for testing the scheduler
>> functions or is there any other method by which I can test my application
>> program with the litmus-rt schedulers.
>>
>> Any task that uses the LITMUS^RT API should work fine. There is nothing
>> special about rtspin.
>>
>> >
>> > Since there is limited help from my institute please do guide me how to
>> test a simple program and verify its output for different schedulers.
>>
>> Happy to help, but without knowing your code and how exactly you launched
>> the processes and any output there’s not much that we can say. If you can
>> share additional details, we can take a look.
>>
>> - Björn
>>
>>
>> _______________________________________________
>> litmus-dev mailing list
>> litmus-dev at lists.litmus-rt.org
>> https://lists.litmus-rt.org/listinfo/litmus-dev
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.litmus-rt.org/pipermail/litmus-dev/attachments/20180314/fb26e09a/attachment.html>