[LITMUS^RT] CPU usage of real-time tasks

[Jonathan Herman]

The time() output would probably not be as accurate as the sched_trace
output. I dont know the details of time()s implementation, though, so I
could not say with certainty.


On Mon, Apr 1, 2013 at 1:31 PM, Youcef Amine Benabbas <
s9yobena at stud.uni-saarland.de> wrote:

> Hi Jonathan,
>
> Thank you for your reply. I am already doing what you described in your
> reply for my work.
>
> The point is, suppose the /usr/bin/time is executed as a real-time task
> under litmus; would the results it provides be suitable for evaluation
> purposes, from a real-time point of view?
>
> Regards,
> Youcef
>
> On Sun, 2013-03-31 at 11:56 -0400, Jonathan Herman wrote:
> > Hi Youcef,
> >
> >
> > The best way to do this would be to use the sched_trace
> > infrastructure. The process of capturing this data while a task is
> > running is described here:
> > https://wiki.litmus-rt.org/litmus/Tracing
> >
> >
> > You would have you write your own code to parse this data and output
> > task utilization. The unit-trace repository contains python code which
> > you can use as a guide:
> > http://cs.unc.edu/~mollison/unit-trace/
> >
> >
> > The file which parses the sched_trace data is
> > unit-trace/unit_trace/trace_reader.py. Sorry for not noticing your
> > email sooner.
> >
> > On Sun, Mar 24, 2013 at 11:55 AM, Youcef Amine Benabbas
> > <s9yobena at stud.uni-saarland.de> wrote:
> >         Hi everyone,
> >
> >         Is there a way to precisely know the cpu usage of a real-time
> >         task. For
> >         instance, rtspin (from liblitmus) receives as arguments a wcet
> >         and
> >         period; however the utilization of an rtspin task measured by
> >         the "time"
> >         command is different from wcet/period.
> >
> >         Since the time command will not run in the presence of
> >         real-time tasks,
> >         I would like to know if there exists an alternative to
> >         precisely know
> >         the cpu utilization of a real-time task (this may be needed if
> >         the
> >         performance of a real-time scheduling algorithm  has to be
> >         conducted
> >         based on the total utilization of a given task-set).
> >
> >         Kind regards,
> >         Youcef
> >
> >
> >         _______________________________________________
> >         litmus-dev mailing list
> >         litmus-dev at lists.litmus-rt.org
> >         https://lists.litmus-rt.org/listinfo/litmus-dev
> >
> >
> >
> >
> > --
> > Jonathan Herman
> > Department of Computer Science at UNC Chapel Hill
> > _______________________________________________
> > litmus-dev mailing list
> > litmus-dev at lists.litmus-rt.org
> > https://lists.litmus-rt.org/listinfo/litmus-dev
>
>
>
> _______________________________________________
> litmus-dev mailing list
> litmus-dev at lists.litmus-rt.org
> https://lists.litmus-rt.org/listinfo/litmus-dev
>



-- 
Jonathan Herman
Department of Computer Science at UNC Chapel Hill
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.litmus-rt.org/pipermail/litmus-dev/attachments/20130401/2a0a6aa1/attachment.html>