| Thread Links | Date Links | ||||
|---|---|---|---|---|---|
| Thread Prev | Thread Next | Thread Index | Date Prev | Date Next | Date Index |
|
Hi, I tend to agree with Marcus, Joel, Hugh,
and others who are saying we should move ahead with the 100GbE standard ASAP. I
agree that there are already available silicon for LAGs that could support
4x10Gbps (or higher) link aggregation, as quoted below. Marcus Duelk wrote: >aren't there already 40G (i.e. 4x10G) transceiver out
there ? >I know at least of one transceiver company that is
offering these devices today, there is also the X40 MSA group: > >http://www.x40msagroup.com/docs.html > >So I
get the impression that the PMDs (including SMF) are already existing, it is
maybe more a matter to have a MAC that supports this as >one logical 40G
pipe. But then we are back at that discussion what the difference to 4x10G LAG
is, I assume ... Joel Goergen wrote: Also, if the front end moves towards
4by25+FEC, which it appears to be based on the work so far, from a system
perspective, you would use the same data rate on the back end side with perhaps
different signaling. Further, spending another three years on a 40Gbps
back plane standard for such a small gain doesn't seem right. It was
pretty painful the last time around. You would end up defining 1by40Gbps,
4by10Gbps, 16by3.125Gbps. I just don't see the ROI. I propose that rather then do 40G,
we put that effort into working with 802.1 to resolve the perceived problems
with LAG. Thus when 100Gbps is complete, we will have a N-LAG ... or New
LAG ... that allows the end user to create ANY size pipe required for 1G, 10G,
and 100G core or ag implementations. Hugh Barrass wrote: There is
silicon available today that can run 4 x 10GBASE-KR as an aggregated link (4 x
10). It has the advantage that it can support links to multiple edge devices or
a 40G aggregated link between redundant switch fabrics. A single 40G link would
be the same cost and would take the same real estate as the 4 x 10 links. If
you invest to make a new generation that can support a single 40G MAC the added
value will be minuscule, I don't see how you could recoup the investment. On
the other hand, it would be a similar investment to develop the 100G MAC and
such a device is more suitable as an uplink for a switch fabric that is serving
16 x 10G blades. The 100G MAC, along with the attached fabric will be used for
the inter-switch links and will be more immediately useful, a 40G single MAC
would be marginally more useful than the 4 x 10 you already have. I know where
I would bet my investment dollars... In fact, there are already available
devices that could aggregate up to 16x3.125Gbps, or 8x6.375Gbps, which is
already more that 40Gbps LAG. The largest device of the 2SGX family could even
aggregate up to 20x6.375Gbps which is 127.5Gbps link-aggregated. I believe
there are other manufacturers who are also offering such transceivers. I don’t
see why we are not expediting the standardization of the 100GbE standard. I agree with Joel’s proposal to put
the effort of resolving LAG problems to 802.1. Regards, Daniel |