On 12/18/06, Erik Mouw <mouw@xxxxxxxxxxxx> wrote:
Or 4) :
4) figure out how your scheduler works and put it into plugsched.
pro: uses an established framework
pro: probably less work for future kernels, especially if you push your
patch upstream
contra: needs work figuring out how your scheduler works
See http://lwn.net/Articles/212183/ .
Thanks for pointing the patch out, I was not aware of it. But if I am
not mistaken I won't be able to use the framework since we need to
work with the periodic and sporadic task model (RT scheduling). I
still hope that I will be able to salvage enough of the existing code
to make a redevelopment unnecessary. If that doesn't work and I have
to start over plugsched looks like a good starting point.
- Bjoern
--
Kernelnewbies: Help each other learn about the Linux kernel.
Archive: http://mail.nl.linux.org/kernelnewbies/
FAQ: http://kernelnewbies.org/faq/
