polling decreases throughput ~50%
youshi10 at u.washington.edu
Mon Aug 22 01:12:46 GMT 2005
On Aug 21, 2005, at 8:38 AM, Danial Thom wrote:
> --- Garrett Cooper <youshi10 at u.washington.edu>
> The problem with a "discussion" is that IQ isn't
> cumulative. So if no one in the discussion has a
> clue, then the conclusions don't mean much. If
> you argue the merits of polling based on wrong
> information (like the assumption that you'll get
> a hardware interrupt for each event), then you've
> just wasted a lot of time and learned nothing.
> You seem to have missed the point that hardware
> has hold-offs that negate ANY need for polling.
> Polling is a non-solution to a non-problem in the
> modern world.
Sorry. Obviously not everyone is as experienced and
knowledgeable as you are.
I didn't say that it was the best solution; I just said it was
discussed and while I may not have mentioned it previously, my
professor highly discouraged the use of polling but said it was a
viable way to solve _some_ problems. And of course, there are always
more ways than established in all cases to solve a problem; one must
think outside the box of course. And that is a design problem worthy
of any engineer.
More information about the freebsd-questions