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

Re: [802.3_50G] CAUI-4 operating modes



Chris,

I'm not advocating that we eliminate FEC on the optical links; although, there has been some recently promising announcements for 100GBASE-SR4 optical links to achieve 20-30 meters without FEC. With the PAM4 modulation, my gut sense is that some FEC will be required to, as you stated, to "deal with the error floor."

My primary concern is that we've started throwing FEC at every interface: C2C, C2M, CRx, SRx, etc. There is an impact to these systems when we start doing that especially in applications that are latency sensitive like storage replication and compute clusters. These links are typically short (< 30m) but are also the most cost-sensitive due to the high volume.

I'm attempting to advocate that we provide options for these shorter links. Whether that option is no FEC or a very low latency FEC is a decision I believe we can work on in Task Force phase.

Thanks,
Brad

On Wed, Feb 24, 2016 at 2:57 PM, Chris Cole <chris.cole@xxxxxxxxxxx> wrote:

Gary,

 

Your summary is accurate, including pointing out that the differences between LAUI and xAUI-2 with KR4 and KP4 FEC modes are more complex than the differences between CAUI-4 with no FEC and with FEC modes.

 

LAUI-2 with no FEC is not an option because of  error floors in optical 50G PAM4 links. We have seen some demonstrations of electrical 50G PAM4 links operating error free with no FEC, but that cannot be extrapolated to optical links. The proposal is to have LAUI-2 with KR4 FEC for backwards interoperability with existing MSA defined interface. We would also bring in this interface definition into the IEEE. We can handle it the same way as we handle KR4 FEC for CAUI-4, leave all the FEC gain for the optical link. 

 

If the latency of KR4 FEC is excessive, as brought up by Brad and Phil, we would need to define a new, lower latency FEC for use with 50G PAM4 optical links to deal with the error floor.

 

Chris

 

From: Gary Nicholl (gnicholl) [mailto:gnicholl@xxxxxxxxx]
Sent: Wednesday, February 24, 2016 2:42 PM
To: Chris Cole; STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

Chris,

 

I presume you were joking about the chipmunks !

 

So can you clarify  what you are proposing then ? 

 

For LAUI and CAUI-2, it is probably not practical to run with no FEC anyway, so in  both cases the AUI will have to steal some FEC gain from the end-to-end FEC in use. I can update my diagrams to reflect this. For LAUI-2 is is still not clear to me if you are thinking of stealing  some of the RS-528 FEC gain for the LAUI-2 itself, or whether you would rather use all the FEC gain for the PMD (as we did for CAUI-4) ?

 

In any case what you are proposing still  results in two different specifications for LAUI, LAUI-2 and CAUI-2 for the two different FEC modes, because the bit rate and the BER requirements will be different between the two FEC operating modes. This is very different to the case of CAUI4, where the CAUI-4 specification did not change (same bit rate and 1e-15 BER) between the two operating modes (no FEC and RS-528). This is the point that I was trying to make in my original email.

 

It also results in two different 50G PCS blocks being required in the ASIC (at the end of the day this may not be a big deal, but I am pointing it out in the interest of full disclosure), and also two different 50G PCS Clauses to be defined in  the standard (and one Clause with no supported PHYs, and therefore no entrees in the equivalent of Table 80-2). 

 

I want to make it clear that I am not necessarily against with your proposal. At this point I am just trying to ensure I fully understand it and all of the associated implications, both in terms of hardware implementations and IEEE standards.

 

Gary 

 

 

From: Chris Cole <chris.cole@xxxxxxxxxxx>
Date: Wednesday, February 24, 2016 at 5:09 PM
To: Gary Nicholl <gnicholl@xxxxxxxxx>, "STDS-802-3-50G@xxxxxxxxxxxxxxxxx" <STDS-802-3-50G@xxxxxxxxxxxxxxxxx>
Subject: RE: [802.3_50G] CAUI-4 operating modes

 

Gary

 

I had not proposed adding a no FEC mode to LAUI, LAUI-2 or CAUI-2. That was proposed by Brad and others for low latency applications.

 

My proposal is that LAUI, LAUI-2, and CAUI-2 have two FEC operating modes: KR4 RS-528 and KP4 RS-544.


Chris

 

From: Gary Nicholl (gnicholl) [mailto:gnicholl@xxxxxxxxx]
Sent: Wednesday, February 24, 2016 1:59 PM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

I am sending this again because I am not sure the reflector was working the first time.

 

Gary 

 

From: Gary Nicholl <gnicholl@xxxxxxxxx>
Date: Wednesday, February 24, 2016 at 4:36 PM
To: Jeffery Maki <jmaki@xxxxxxxxxxx>, "STDS-802-3-50G@xxxxxxxxxxxxxxxxx" <STDS-802-3-50G@xxxxxxxxxxxxxxxxx>
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

I was getting confused so I started to draw out what I think Chris wants. Please see attached. 

 

For now I have only  focused on 50G. 

 

I have also assumed that  FEC, if required,  would  be included in a single  PCS Clause (like we did for 400G).

 

Rocks  welcomed :) 

 

Gary 

 

From: Chris Cole <chris.cole@xxxxxxxxxxx>
Reply-To: Chris Cole <chris.cole@xxxxxxxxxxx>
Date: Wednesday, February 24, 2016 at 4:46 PM
To: "STDS-802-3-50G@xxxxxxxxxxxxxxxxx" <STDS-802-3-50G@xxxxxxxxxxxxxxxxx>
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

Mike,

 

The optics we would use with LAUI-2 with KR4 RS-528 FEC would be the same optics as those we would use with LAUI-2 with KP4 RS-544 FEC, except running at 3% lower rate. The SG will have to decide which we define in the project, and which outside of the project, if any.

 

Chris  

 

From: Mike Dudek [mailto:mike.dudek@xxxxxxxxxx]
Sent: Wednesday, February 24, 2016 12:05 PM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

But what PMD is LAUI-2 going to support.    If we don’t have an objective for a PMD that requires it then in my opinion it would be out of scope to develop it without an explicit objective. 

 

Mike Dudek 

QLogic Corporation

Director Signal Integrity

26650 Aliso Viejo Parkway

Aliso Viejo  CA 92656

949 389 6269 - office.

Mike.Dudek@xxxxxxxxxx

 

 

From: Kapil Shrikhande [mailto:kapils@xxxxxxxx]
Sent: Wednesday, February 24, 2016 11:32 AM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

To match the capabilities of CAUI-4 (4x25G), the LAUI-2 (2x25G) C2M interface should operate without FEC at a BER of 1e-15 or better (Gary also points to the BER requirement for CAUI-4), so that a no-FEC PHY using LAUI-2 could operate at 1e-12. And as stated by Chris, LAUI-2 will also support RS-FEC encoded signal (KR4 and KP4 FEC) for those PMDs that require FEC.

 

Kapil.

 

 

 

On Wed, Feb 24, 2016 at 10:53 AM, Brad Booth <bbooth@xxxxxxxx> wrote:

I like this topic as it does highlight one of the aspects previously mentioned in January about the need to have a low or zero FEC latency AUI.

 

For the 25G-based interface (CAUI-4), the task force(s) wisely provided the ability for the interface to operate with and without FEC. This has permitted flexibility in implementations. For example, the ability to use a CAUI-4 without FEC between an Ethernet adapter's ASIC and FPGA will permit a low latency interface; whereas, between the adapter's FPGA and the switch's ASIC, FEC can be used to provide end-to-end error correction.

 

It would be great if we continue to provide interfaces like CAUI-4 that can transport either FEC or non-FEC data. This would provide the greatest level of flexibility for various implementations that could occur.

 

I've requested time to make a presentation in Macau to discuss these use cases in both the 50G and 100G market.

 

Thanks,
Brad

 

On Wed, Feb 24, 2016 at 10:31 AM, John D'Ambrosia <jdambrosia@xxxxxxxxx> wrote:

Chris,

You are mistaken.

The FS FEC was developed and a 4 lane solution was developed but it was not CAUI-4.  That was done in 802.3bm.  There is no way I would ever try to steal that credit away from Dan Dove who had the fortitude of a saint with that effort.

 

I think the confusion is coming from FEC and non-FEC protected interfaces.

 

From what I see

802.3bj RS-FEC clause  developed to support the cr4, -kr4, -kp4

802.3bm developed CAUI-4 and specified its operation to 10^-15 without FEC.  However the architecture itself can be done in such a way that the CAUI-4 is carrying either non-FEC or FEC protected data.  802.3bm also developed -sr4 where FEC is mandatory.

 

So the AUI based on 25Gb/s signaling can be independent of whether there is FEC or not.

 

I think everyone is right, but it clearly points out we have to be very specific with language.

 

John

 

From: Chris Cole [mailto:chris.cole@xxxxxxxxxxx]
Sent: Wednesday, February 24, 2016 1:24 PM
To: John D'Ambrosia <jdambrosia@xxxxxxxxx>; STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: RE: [802.3_50G] CAUI-4 operating modes

 

CAUI-4 with KR4 RS-528 FEC was developed in the P802.3bj project you led to first support CR4. P802.3bm then defined SR4 with CAUI-4 with KR4 FEC. This enable subsequent efforts to quickly define optical PMDs that use KR4 FEC. P802.3bm also defined CAUI-4 with no FEC to support existing PMDs; LR4 and ER4.

 

So coming out of 802.3bm we had two CAUI-4 operating modes, one without FEC for backwards compatibility, and one with FEC for new PMDs.


Chris

 

From: John D'Ambrosia [mailto:jdambrosia@xxxxxxxxx]
Sent: Wednesday, February 24, 2016 10:04 AM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

Reading the spec – it looks more like the specification of CAUI-4 is done not assuming FEC, but a port type may include FEC that could go over the CAUI-4.

 

From: Rick Rabinovich [mailto:rrabinovich@xxxxxxxxxxx]
Sent: Wednesday, February 24, 2016 12:20 PM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: [802.3_50G] CAUI-4 operating modes

 

Correct, CAUI-4 does not include FEC.

 

Rick Rabinovich

Hardware Architect – Signal Integrity

cid:image007.png@01CE6DA7.29CB7A10

rrabinovich@xxxxxxxxxxx

Phone: +1 (818) 208-7328

26601 W. Agoura Rd.

Calabasas, CA 91302 US

visit: www.ixiacom.com

 

From: Gary Nicholl (gnicholl) [mailto:gnicholl@xxxxxxxxx]
Sent: Wednesday, February 24, 2016 9:18 AM
To: Rick Rabinovich <rrabinovich@xxxxxxxxxxx>
Cc: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: Re: CAUI-4 operating modes

 

Perhaps, but 802.3bj did not define CAUI-4 and Chris’s comment was  specifically on CAUI-4.

 

Gary 

 

From: Rick Rabinovich <rrabinovich@xxxxxxxxxxx>
Date: Wednesday, February 24, 2016 at 12:15 PM
To: Gary Nicholl <gnicholl@xxxxxxxxx>
Cc: "STDS-802-3-50G@xxxxxxxxxxxxxxxxx" <STDS-802-3-50G@xxxxxxxxxxxxxxxxx>
Subject: RE: CAUI-4 operating modes

 

Hi Gary,

 

Thank you for bringing this up . CAUI-4 defined in IEEE802.3bm was specified without FEC to eliminate the latency incurred.

 

Perhaps Chris was also referring to 4x25G as defined in IEEE802.3bj which includes RS-FEC for 100GBASE-CR4.

 

Cordially,

 

 

Rick Rabinovich

Hardware Architect – Signal Integrity

cid:image007.png@01CE6DA7.29CB7A10

rrabinovich@xxxxxxxxxxx

Phone: +1 (818) 208-7328

26601 W. Agoura Rd.

Calabasas, CA 91302 US

visit: www.ixiacom.com

 

From: Gary Nicholl (gnicholl) [mailto:gnicholl@xxxxxxxxx]
Sent: Wednesday, February 24, 2016 9:08 AM
To: STDS-802-3-50G@xxxxxxxxxxxxxxxxx
Subject: [802.3_50G] CAUI-4 operating modes

 

Following on from the discussion this morning I checked 802.3bm and there is only a single operating mode for CAUI-4. 

 

CAUI-4 C2M is defined in Annex 83E. There is only one operating mode and that assumes no FEC.

 

 

There is no separate FEC operating mode, where some of the FEC gain is used to relax the CAUI-4 electrical specifications. 

 

In 802.3bm if RS-FEC is being used, it is  carried completely transparently over the CAUI-4 interface, and all of the FEC gain is used for the PMD (i.e. 100GBASE-SR4). The CAUI-4 specification is completely independent  of whether FEC is being used on the link or not.  Perhaps this is what Chris meant by “two CAUI-4 operating modes” on the call this morning, even though from a CAUI-4 perspective there  is only a single operating mode? 

 

Another way to state this is that the FEC requirements for the host are defined by the PMDs to be supported and not the CAUI.

 

Gary