Constant Bandwidth Server

[Gedare Bloom]

Hi Joel Pinto,

On Thu, Feb 7, 2019 at 8:13 AM Joel Oliveira Pinto <jollp at isep.ipp.pt>
wrote:

> Hello everyone,
>
>
> After studying the implementation of the Constant Bandwidth Server (CBS)
> scheduler in RTEMS, I realized that it does not respect what is proposed in
> the original paper by Abeni and Buttazzo. For instance, RTEMS
> implementation does not support the following:
>
> • Serve several threads within a server and deal with their deadlines
> accordingly;
>
> • Replenish the budget of the server and postpone its deadline when the
> server budget is exhausted;
>
>
> I’ve been implementing a new version of CBS that supports the rules above
> and that resembles the original paper as much as possible and I’m currently
> testing it at the moment. Thus, I would like to know from the community if
> there are some specific test cases/benchmarks (besides the X tests that
> already exists for CBS) that should be used to test this CBS version or
> generally speaking any scheduler in RTEMS?
>
>
I've added in CC the author of the CBS implementation in case he has some
further insights. I don't think we had any additional, specific tests
besides those you can find in testsuites.


>
> Regards,
> Joel Pinto
> [image: Sent from Mailspring]
> _______________________________________________
> devel mailing list
> devel at rtems.org
> http://lists.rtems.org/mailman/listinfo/devel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.rtems.org/pipermail/devel/attachments/20190207/9afc7da9/attachment-0002.html>