[c-nsp] Improved queuing in 12.4(20)T?

[Pelle]

On Tue, Aug 26, 2008 at 16:28, Rodney Dunn <rodunn at cisco.com> wrote:

> The difference I suspect is how the time intervals are handled. I worked
> on an issue once where we actually would slightly burst above the
> configured shape rate and it got worse the smaller the Tc was.
> With HQF the excess is handled different and resulted in more accurate
> shaping rates. I forgot all the nitty gritty details of how we did it.

Hmm, that's a good thing and a bad. The good thing is that HQF have
improved something that was suboptimal, the bad thing is that you need
HQF (read: it's not a bug).

The most worrying aspect is that you do use a shaper to handle excess
traffic, and when the shaper kicks in, the latencies increases a
magnitude (from <1 millisec to over 10 millisec). Not very nice to
real time traffic.

Will probably have to stick up with 12.4(20)T were we must, despite
the bleeding-edge nature.

-- 
Pelle