|Thread Links||Date Links|
|Thread Prev||Thread Next||Thread Index||Date Prev||Date Next||Date Index|
There have been a number of proposals: buffering, flow control, IPG stripping, preamble stripping, etc. One thought that came to me this morning is that a system designer would know what type of network is being used (i.e. is the port a LAN port or a WAN port), and an implementation specific form of rate control could be implemented at a higher layer. My preference would be to do this in the PHY, because it would make things a bit cleaner by eliminating a lot of proprietary solutions. I know that designing the PHY layer to perform this operation will increase the PHY cost for the WAN solution above that of the LAN solution, but I think that users will be willing to pay that extra to be able to used their installed base of fiber.
Level One Communications, Austin Design Center
(512) 407-2135 office
(512) 589-4438 cellular
From: Rogers, Shawn [SMTP:s-rogers@xxxxxx]
Sent: Thursday, July 22, 1999 8:21 AM
To: 'Booth, Brad'; HSSG
Subject: 10.0 vs 9.584640: That's the PHY's Job
Brad, more like a quarter's worth. How would you architect the LAN-WAN rate
matching connection? That's obviously not in the PHY.
From: Booth, Brad [mailto:bbooth@xxxxxxxxxx]
Sent: Wednesday, July 21, 1999 9:22 PM
Subject: RE: 9.584640
I really liked the proposal that Kevin Daines put on the overhead. One of
the reasons that I liked the proposal is that it matched what I pictured in
my mind. :-) But there were other technical reasons why I liked it. The
proposal for those that missed it was to leave the MAC/PLS data rate at 10.0
Gb/s, but to have the PHYs determine what data rate was required. In the
case of a LAN PHY, the data rate would be 10.0 Gb/s... a direct match to the
MAC/PLS data rate. In the case of a WAN (or OC-192) PHY, the data rate
would be 9.58464 Gb/s and the PHY would obtain that data rate by either some
form of flow control or buffering scheme.
I like this because it allows the LAN architectures to remain cost effective
while offering the ability to easily concentrate links (i.e. ten 1 GbE links
map nicely into one 10 GbE link). This architecture puts a bit of a cost
burden on the WAN PHY, but I think that this still results in a cost
effective solution for OC-192. The WAN solution may not be as low cost as
the LAN solution, but show me a Gb/s WAN solution today that is as cost
effective as a Gb/s LAN solution.
The other part that I like is that the only real difference between the WAN
and LAN solutions in Kevin's proposal is the PHY. Everything above the PHY
(including interface to PHY) remains relatively unchanged. Yes, it's all
going much faster, but that's an implementation issue, not a standards
issue. At least that's my impression. :-)
Just my 2 cents worth,
Level One Communications, Austin Design Center
(512) 407-2135 work
(512) 589-4438 cell
From: Rich Taborek [SMTP:rtaborek@xxxxxxxxxxxxxxxx]
Sent: Wednesday, July 21, 1999 7:39 PM
To: Paul Bottorff; HSSG
Subject: Re: 9.584640
Vacation!!! What's a vacation???
Thanks for taking the time out to respond. I'd like you to review my
on this thread to see where you stand based on your agreement that 9.584640
as being the "perfect" Ethernet for matching to OC-192 SONET. Here is the
In my conversations with several folks on both sides of the issue
Montreal meetings, I've come to the conclusion that the root reasons to
either a 10 or 9.584640 Gbps are purely ease-of implementation based and
architectural basis whatsoever. I believe this to be true on both sides of
argument with the choice of one over the other, rendering the implementation
(i.e. product cost) of the losing side only slightly more difficult. Please
allow me to explain the basis of this contention:
1) SONET, and specifically synchronous transport, is legacy in the
MAN and WAN,
will never be replaced by Ethernet completely or even quickly. Ethernet will
make inroads into "green-field" applications, but SONET will be king for
time to come;
2) Ethernet, and specifically packet-based transport, is legacy in
the LAN, is
growing in its dominance in the LAN, and will likely gain market share in
LAN as well as encroach on other non-traditional Ethernet transports
MAN, SAN, and some WAN. I don't include WAN access in WAN. Instead I include
access in LAN or MAN;
3) The existing WAN infrastructure does a great job of transporting
packets end-to-end today. However, much protocol conversion and equipment to
between packets and TDM bits exists in mapping Ethernet to the WAN at each
Considerable savings can be realized by architecting a more seamless
SONET connection. This issue seems to be at the root of the 10 vs. 9.584640
4) There seems to be no intent by either side to consider any other
speed as a HSSG objective. Therefore, Ethernet will remain a simple, general
purpose, packet-based transport, and SONET will remain a specific purpose
(MAN/WAN), synchronous transport no matter which way the decision goes.
5) Consider a Ethernet to OC-192 line card (feeding a fiber or
operation. Assume that receive and transmit paths are separate on the SONET
and related (i.e. full duplex) on the Ethernet side:
a) Ethernet -> SONET @ 9.584640 Gbps: The Ethernet side can continuously
the SONET link with no flow control required.
b) Ethernet -> SONET @ 10 Gbps: The Ethernet side must be flow controlled
prevent over-feeding the SONET link
c) SONET -> Ethernet @ 9.584640 or 10 Gbps: The Ethernet side can
source SONET data but will flow control or drop packets downstream whenever
network is congested.
Therefore, the issue boils down to one of implementation of existing
mechanisms such as 802.3x flow control or a reasonable facsimile on the line
card versus complicating the implementation of all Ethernet products which
support a MAC/PLS rate which is not a multiple of 10. These implementation
difficulties include multiple clocks which may "beat" against each other,
being able to easily feed 10 slower links into one faster one, and numerous
other difficulties which are best listed by Ethernet product implementers.
My intention is not to make light of the problem but rather to agree
solution direction along the line proposed by Dan Dove of HP at the Montreal
meeting. I believe that Dan's general direction was to tradeoff a simple
architectural change with respect to MAC operation to enable cost effective
Gbps to SONET implementations. I don't particularly agree with resolving
implementation cost issues between two dominant legacy protocols by tweaking
with the underlying architecture, but I'll raise my hand in support of this
solution to the problem.
Such a solution would enable the implementation of a 10 Gbps
Ethernet to SONET
OC-192 line card without requiring a full MAC.
I'll let Dan fill in the details of his proposal so I don't get it
wrong if it
is still applicable.
Paul Bottorff wrote:
> Toshio, Rich:
> Sorry for dropping in a little late, but I'm supposed to be on vacation.
> The 9.584640 is the exact rate of a OC-192 payload. Running at this rate
> will allow the data to be encoded onto an OC-192 directly at rate. In
> addition, this data rate allows running over the installed base of 10 G
> DWDM regenerator networks.
> To encode a 9.584640 G Ethernet steam on an OC-192 the encoding system
> not expand the data like 8b/10b does. Both the Nortel and the Lucent
> proposals are capable of providing an encode which can be transported a
> 9.584640 G Ethernet data stream over OC-192.
> At 02:29 PM 7/20/99 -0700, Rich Taborek wrote:
> >I believe that the framing solution is a second-order task and that the
> >order task is to determine if there is any possibility of supporting an
> >Ethernet stream, consisting of variable sized packets at ANY MAC/PLS data
> >which would eliminate any flow control requirements between Ethernet and
> >Is 9.584640 Gbps this data rate? If not, is there any data rate that
> >above requirement? If not, the HSSG speed objective should be 10.0 Gbps.
> >Best Regards,
> >Toshio Ooka wrote:
> >> Rich,
> >> > I have assumed that the proponents of the 9.584640 Gbps MAC/PLS
> >> > payload rate have selected that rate specifically to allow a SONET
> links to
> >> > accept Ethernet payload at full rate as indicated in my #5a (below).
> >> I believe that the rate specifically to allow a SONET links to accept
> >> Ethernet payload
> >> is great idea.
> >> But to realize this idea, I think we need to have some framing
> >> After framing process, the length of the data on SONET will not
> >> the content of the Ethernet payload data. POS solution is not suitable
> >> this.
> >> Send Ethernet 10B code to SONET may be to fit SONET byte stream world.
> >> Thank you for your prompt reply.
> >> Best Regards,
> >> Toshio
> >> ----
> >> Toshio Ooka @Sumitomo Electric U.S.A., Inc.
> >> 3235 Kifer Rd, #150, Santa Clara, CA 95051-0185
> >> Phone:(408)737-8517x232 Fax(408)737-0134
> >Richard Taborek Sr. Tel: 650 210 8800 x101 or 408 370 9233
> >Principal Architect Fax: 650 940 1898 or 408 374 3645
> >Transcendata, Inc. Email: rtaborek@xxxxxxxxxxxxxxxx
> >1029 Corporation Way http://www.transcendata.com
> >Palo Alto, CA 94303-4305 Alt email: rtaborek@xxxxxxxxxxxxx
> Paul A. Bottorff, Director Switching Architecture
> Bay Architecture Laboratory
> Nortel Networks, Inc.
> 4401 Great America Parkway
> Santa Clara, CA 95052-8185
> Tel: 408 495 3365 Fax: 408 495 1299 ESN: 265 3365
> email: pbottorf@xxxxxxxxxxxxxxxxxx
Richard Taborek Sr. Tel: 650 210 8800 x101 or 408 370 9233
Principal Architect Fax: 650 940 1898 or 408 374 3645
Transcendata, Inc. Email: rtaborek@xxxxxxxxxxxxxxxx
1029 Corporation Way http://www.transcendata.com
Palo Alto, CA 94303-4305 Alt email: rtaborek@xxxxxxxxxxxxx