[arin-ppml] Policy Proposal: A Modest Proposal for an Alternate IPv6 Allocation Process
bicknell at ufp.org
Fri Jun 5 16:50:41 EDT 2009
In a message written on Fri, Jun 05, 2009 at 12:55:05PM -0700, Ted Mittelstaedt wrote:
> There are real,
> >serious, expensive engineering challenges moving more than a couple
> >of Gigabits per second.
> Right, but those challenges ALSO exist to do things like, for example,
> run Windows 7 with acceptable speed. Heck they also exist to run Vista
> at an acceptable speed.
There is a lot less overlap in those challenges than you think.
The market for Windows 7 is probably a billion PC's. The market
for core routers might be 10,000. Might be 1,000.
4Gbps of hardware based forwarding in a 1RU form factor, available
with support for under $5k.
10 years ago, when a 7513 was still a useful box, it barely did
4Gbps in a chassis that cost $500,000. An OC-12 based backbone was
"big". I'd say moores law has done well.
Today the standard customer handoff is a GigE, bigger than the
backbone link in a 7513's day. A core router is expected to move
400Gbps, and that takes custom hardware and costs $2M.
Until we reach the point where consumer bandwidth growth levels,
the boxes need to get bigger at the same rate moores law makes them
cheaper, which keeps the cost constant; but the throughput keeps
Leo Bicknell - bicknell at ufp.org - CCIE 3440
PGP keys at http://www.ufp.org/~bicknell/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Size: 825 bytes
Desc: not available
More information about the ARIN-PPML