Locking ReadyQueue in SMP

Sree Harsha Konduri sreehars at buffalo.edu
Sat Sep 14 16:25:14 UTC 2013


Hey Sebastian,

I've been working closely with Gedare over the summer and with his help, I
have a working G-EDF scheduler running now. I will send out the patches on
the devel list pretty soon, once I verify the operations of the scheduler.

Thanks,
Sree


On Sat, Sep 14, 2013 at 12:06 PM, Sebastian Huber <
sebastian.huber at embedded-brains.de> wrote:

> On 2013-09-14 17:51, Sree Harsha Konduri wrote:
>
>> Hello,
>>
>> I am working on the globaledf scheduler and need to lock the ready queue.
>> I've implemented the locking using CPU_SMP_lock_Control data structure in
>> i386.
>>
>
> Since we currently have only the Giant lock it is unnecessary to use other
> locking mechanisms.  The introduction of fine grained locking will be a
> major task.
>
> For a G-EDF scheduler please have a look at:
>
> http://git.rtems.org/rtems/**tree/cpukit/score/include/**
> rtems/score/schedulersmpimpl.h<http://git.rtems.org/rtems/tree/cpukit/score/include/rtems/score/schedulersmpimpl.h>
>
> http://git.rtems.org/rtems/**tree/cpukit/score/include/**rtems/score/**
> schedulerprioritysmp.h<http://git.rtems.org/rtems/tree/cpukit/score/include/rtems/score/schedulerprioritysmp.h>
>
> If you use this framework it should be pretty easy to implement a G-EDF
> scheduler.  You only have to replace the priority queue with the red-black
> tree operations.
>
>
>  I just want to make sure that locking in such way will ensure mutual
>> exclusion to operations of the ready queue.
>>
>> Thanks,
>> Sree
>>
>>
>
> --
> Sebastian Huber, embedded brains GmbH
>
> Address : Dornierstr. 4, D-82178 Puchheim, Germany
> Phone   : +49 89 189 47 41-16
> Fax     : +49 89 189 47 41-09
> E-Mail  : sebastian.huber at embedded-**brains.de<sebastian.huber at embedded-brains.de>
> PGP     : Public key available on request.
>
> Diese Nachricht ist keine geschäftliche Mitteilung im Sinne des EHUG.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.rtems.org/pipermail/devel/attachments/20130914/06d77b1d/attachment-0001.html>


More information about the devel mailing list