Krause, Karl-Heinz wrote:
> Hi Philippe
> as promised some time ago, I'd like to let you know the result of our work.
> Attached are 
> -          a few recycled slides from a presentation describing motivation, 
> features and results
> -          the patch file for a  adeos-ipipe-2.6.15-i386-1.3-04.patch  
> patched kernel2.6.15.4 

You attached the glibc patches, but your ipipe variant is missing. Could
you also explain a bit what kind of optimisations your ipipe version
contains, maybe they are of generic interest and we can discuss a
potential integration? And a description of the features/hooks it adds
would be good as well. That might help to restart a discussion if there
is more common ground and a chance to merge.

> Since some parts of the kernel functionality (clock registration, realtime 
> capable message queues) and 
> most parts of the glibc changes are also of  interest for the  RT_PREEMPT 
> solution we are in contact with 
> Thomas Gleixner trying to leverage the work.
> An update to newer versions of  kernel and glibc (basically  because of the 
> PI mutexes) is planned for later,
> presumably when RT_PREEMPT  has become mainline status.

Hmm, so your approach is locked to 2.6.15 for now? What is blocking
kernel / ipipe updates?

> If you need any further information just let me know.

According to your slides, you did a lot of concrete testing. Do you
happen to have comparative numbers of recent Xenomai's POSIX skin as
well (forgetting about the ABI issue for the moment)? Or do you have a
releasable test suite?


Attachment: signature.asc
Description: OpenPGP digital signature

Xenomai-core mailing list

Reply via email to