Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: [HSSG] 40G MAC Rate Discussion

I believe there are 100GbE LAG devices today. However, these devices,
and equipment incorporating them, are non-standard devices/equipment
based on current protocols.

As an example, the largest device of the Stratix II GX family (2SGX130)
could LAG up to 20x6.375Gbps maximum. If exactly 100Gbps is needed, the
device can be clocked at a lower frequency to achieve 20x5Gbps=100Gbps
LAG. However, this device's maximum per-lane datarate is only 6.375Gbps.

As mentioned by others in the group, there are manufacturers who came up
with silicon that can produce a per-lane datarate of up to 10Gbps (or
higher?). I don't know how many lanes have been built into these
devices, but link aggregating them is possible, though this may mean
having to have a multi-device implementation, which could be costly and

As 100Gbps transceiver LAGs are already becoming available, what we need
now is a 100GbE standard, which would standardize, among other things,
the per-lane datarate and the pipe (or bus) width of the LAG.

-----Original Message-----
From: donnlee [mailto:donnlee@GMAIL.COM] 
Sent: Tuesday, April 10, 2007 3:47 PM
Subject: Re: [HSSG] 40G MAC Rate Discussion

As an end-user who presented to the HSSG along with other end-users
that 100GE is too late, I feel like our urgency and pain has fallen on
deaf ears when I see messages like those below. Does the IEEE want
end-user input or not?

To reiterate for those who did not hear the end-user presentations:

a. 10GE pipe is too small. We have hit the LAG & ECMP ceilings of 10GE
implementations today.

b. We have to use multiple 10GE LAGs and build a Clos network to keep
up with traffic demands. This results in a ridiculous number of cables
and an operational nightmare. 100GE links would greatly exorcize and
scale our networks. See "A Web Company's View on Ethernet", HSSG,

c. If 10GE LAGs have grown to nightmare-ish size today, imagine what
additional pent-up demand will be added between now and 2010?

d. The largest 10GE switch commercially available today is too small.
We would like much larger switches but because of (b), we really
require 100GE switches. See "Saturating 100G and 1T Pipes", HSSG,

e. When 100GE is available in 2010, we will have to LAG them on Day
One because a single 100GE will be too small.

f. I had no idea 10GE was a "failure" or "too early" until I visited
an IEEE meeting. As far as we're concerned, we can't buy enough of it.
Problem we have is the 10GE boxes do not have enough 10GE interfaces.
We need more; a lot more.

g. As 100GE is late, many of us are working with vendors who have
PRE-STANDARD 100GE plans. Because the need is so great, I have no
problems building a fabric of proprietary links as long as the links
on the outer edges of the fabric are standard.

Network Architecture Team
Google Inc.

On 4/6/07, OJHA,JUGNU <> wrote:
> Matt, to address your point about BMP for 40G, I can't help but think
> ironic when even the strongest proponents of 100G say that they do not
> see a market for more than 100's to 1000's of links in the next 5+
> years.  We departed from reality long ago....

On 4/6/07, OJHA,JUGNU <> wrote:
> My point earlier was that, based on everything we have heard from
> I certainly find it easier to see significant volumes for 40G than for
> 100G in the foreseeable future (8 years is an awfully long time in
> business).
> Regards,
> Jugnu