Messages in this thread | | | Date | Mon, 22 Nov 2004 13:30:54 -0800 | Subject | Re: Priority Inheritance Test (Real-Time Preemption) | From | Bill Huey (hui) <> |
| |
On Mon, Nov 22, 2004 at 09:16:18AM -0500, john cooper wrote: > I'd hazard a guess the reason existing implementations do not > do this type of dependency-chain closure is the complexity of a > general approach. Getting correct behavior and scaling on SMP > require some restrictions of how lock ownership is maintained, > otherwise fine grained locking is not possible. Another likely
What do you mean by that ? Are you talking about strict priority obedience by the system ?
> reason is the fact more mechanism is getting put in place for > less likely inversion scenarios. And when those scenarios do > exist the cost of effecting promotion closure may well be > greater than allowing the priority inversions to subside. > However this point of diminishing returns is application > dependent so there is no single, simple solution.
Yes, this is my point.
> That said I don't see anything in the current work which precludes > doing any of the above. To my eyes, the groundwork is already > in place.
Yes it is. :)
bill
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |