[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: new WRR sched, updated TBF and "real" ingres implementation

> > May be it is due to fack that our wireless link has varying
> > bw and CBQ code uses it to compute both time of packet's right
> > edge and integrated time.
> I dont understand why you think sampling at the right edge is a problem.

there is problem (as stated by Alexander's comments in code) in
determining exact time of right edge. We always know start time 
of packet transmit but not end time. Alexander aproximates it
by artifical time - but it is necessary to know exact bw of
output device because it is used in artifical time computations.
If is it possible to use left edges it kills dependence on 
known bw.
But I'm not sure whether is it possible at all .. I tried
to mail Alexander about it but with no success :-(.

> I have never experimented with this; so i dont know what the effect
> is. Maybe you could post some results?

I didn't too .. I was only interested in its principles.
Still I'd like to write CBQ but with TBF classifiers instead
of idle est. But I have not much time for it :-(