From: owner-nanog@merit.edu [mailto:owner-nanog@merit.edu] On
Behalf Of Jared Mauch
Sent: Wednesday, March 30, 2005 7:06 PM
To: Paul Vixie
Cc: nanog@merit.edu
Subject: Re: Clearwire May Block VoIP Competitors
What i've done is rate-limit TCP inbound to be around
75-80% of the link speed to force things to back-off and
leave space for my UDP packet streams.
I think one of the major problems is that very few
people know how to, or are capable of sending larger g711
frames (at increased delay, but more data per packet) because
they can't set these more granular settings on their
systems.. this means you have a lot higher pps rates which I
think is the problem with the radio gear, it's just not
designed for high pps rates..
That's interesting. . . where's the intersection of the packet
size curve and the latency curve? I mean, where would you set
it, and can you offset some of that with fragmentation and
intervleaving?
I'm outside of that "very few people," but I could imagine
wanting dynamic control--one packet size (latency) for a certain
calling plan (calls within the LAN, maybe even to anywhere on
my network if I control end-to-end QoS, and local calls) but
another for long distance.
- jared
Lee
Thus spake "Howard, W. Lee" <L.Howard@stanleyassociates.com>
That's interesting. . . where's the intersection of the packet
size curve and the latency curve?
Many equipment vendors allow you to specify the number of ms of data to
include in each packet while others require you to specify byes; I'll assume
the former here since the latter is just a linear relation.
Toll-quality voice requires a one-way latency of under ~125ms including any
processing inside the endpoints. Increasing the packet size inherently adds
delay on the transmit side. Then you have the obvious network latency.
Finally, the receive side will have a buffer to smooth out jitter in the
network; most vendors' equipment is now adaptive, so the jitter buffer might
be anywhere from 10-50ms.
To keep under budget, at least one of these factors must be minimized.
Unfortunately, the public Internet has substantial jitter and high
coast-to-coast latency, so often the only factor under your control is the
transmit buffer.
OTOH, if you're going across a network with decent QoS or within the same
general area of the country, you can afford a larger transmit buffer without
risking the "walkie talkie" effect.
I mean, where would you set it, and can you offset some of
that with fragmentation and intervleaving?
F&I is a technique for reducing jitter on slow, congested links like the
last mile to a customer. It's often combined with a priority queue, since
the latter is not enough on such links (but is on faster ones). Neither has
much to do with the (tiny) sizes of voice packets.
S