[Bug 1647] Modular SuperCore Scheduler

bugzilla-daemon at rtems.org bugzilla-daemon at rtems.org
Fri Aug 6 20:32:21 CDT 2010


--- Comment #5 from Joel Sherrill <joel.sherrill at oarcorp.com> 2010-08-06 20:32:20 CDT ---
(In reply to comment #3)
> Although I did my best to maintain the original scheduling code, there is one
> lingering issue that needs to be addressed.  The scheduler and ready queue
> assume that they are called with protection enabled (i.e. with interrupts
> disabled).  However, they do not take any arguments to help them to disable
> protection, for example to do an ISR_Flash(level).
> So although the functionality is identical, my refactoring introduces some
> change to the interrupt latency of the scheduling code.
> I would appreciate thoughts on how to address this deficiency.  For
> uni-processor scheduling we can simply pass 'level' as an argument to the
> scheduler; however, for SMP this will not work.

I really don't know how to address that at the moment.  My design thought was
to have processor interrupts off locally while you owned an "interrupt
disable lock".  So it may work just fine if the SMP interrupt disable
lock is known.

Configure bugmail: https://www.rtems.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching all bug changes.

More information about the rtems-bugs mailing list