[e2e] TCP, retransmissions, and ISPs with byte caps
Philippe Strauss
philou at philou.ch
Tue Jun 18 09:35:23 PDT 2002
On Tue, Jun 18, 2002 at 11:24:29AM -0400, RJ Atkinson wrote:
>
> On Tuesday, June 18, 2002, at 08:57 , David P. Reed wrote:
> >At 08:17 AM 6/18/2002 +0200, Philippe Strauss wrote:
> >>But about delays, CATV systems have an interesting characeristic:
> >>a ~20ms minimum delay in the ACK path (direction from home
> >>to the hub, upstream or return path in catv speak).
> >
> >I have been pinging various targets through my LANCity cable modem for
> >years now and I have regularly gotten 7 msec. ping RTT to lcs.mit.edu
> >which is a few hops (11 at the moment) away. This morning the average
> >is 13 ms. Where's the 20ms minimum? How did you determine it?
>
> Of course latency varies with the technology used (DVB, LANcity, CDLP,
> DOCSIS, etc)
> and with the actual distance as the copper/fibre runs from CM to CMTS.
>
> And LANcity is an interesting case. In LANcity the upstream is the
> same as the downstream in LANcity (half-duplex, symmetric, 10 Mbps,
> and coupled-together). This is a nice counter-example to Phillipe's
> assertion that the upstream is always different than the downstream.
terayon teracomm 1000 too - 8Mbit/s both way, same modulation both way.
the assymetry I was referring is only this one:
from the plant to the home, one equipement (the headend) communicate
with, let say, 500 modems.
from each home to the plant, 500 modems must coordinate somehow
to do a multiplexing of each modem toward the headend.
you have a N -> 1 problem in one direction, N -> 1 in the other.
the same goes for noise: in the upstream, it's potentialy 500 source of
noise summing up (with attenuation blah blah ok) to the headend.
so, it's a technology independant problem: you have more
probability of data corruption in the upstream, and the allocation
scheme is more difficult to do well in the 500 -> 1 direction.
regards.
> Ran
--
Philippe Strauss
http://philou.ch/
L'indifférence est le plus grand risque de notre temps,
la forme civilisée de la cruauté. -- Zenta Maurina
--
More information about the end2end-interest
mailing list