[LITMUS^RT] DFLP migration

[施俊杰]

​
 rtspin.c
<https://drive.google.com/file/d/0BzQeXKE20dc-RXRZTlJ5Y3FoSEU/view?usp=drive_web>
​​
 chunktest.sh
<https://drive.google.com/file/d/0BzQeXKE20dc-dndYNTlhaFlIaXc/view?usp=drive_web>
​
I have rewritten to make sure that I can simulate more than one critical
section within one task. Also there is one bash file to show how I allocate
the tasks. When I change the protocol to DFLP, the task doesn't migrate to
different cpu when it come to the critical section. Thanks for your help!


2016-08-11 18:04 GMT+02:00 Björn Brandenburg <bbb at mpi-sws.org>:

>
> > On 11 Aug 2016, at 18:55, shijunjie92 <shijunjie92 at gmail.com> wrote:
> >
> > Hello all:
> >
> > I am trying to simulate the migration operation using DFLP_SEM included
> in P-FP. I have rewritten the 'chunk_lock_od = litmus_open_lock (different
> cpu)' in rtspin.c. The critical section's migration is working if I use
> DPCP, but it doesn't work when I using DFLP.
> > Could anyone can tell me, how to test the migration using DFLP_SEM
> > In my opinion, the -p option just allocate one cpu for the
> task(partition) , it doesn't matter to the migration of critical section.
> The migratiom of critical section can be set when the lock is opened.
>
> Mh, it’s difficult to say much based on your description. Can you please
> provide more details? Can you post your source code?
>
> - 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/20160811/2dec2603/attachment.html>