Re: Gearbox reality check
Sure. The buffering requirements for the Serial LAN PHY, with 64B/66B as it's
PCS are very small, implementation specific, and at worst perhaps one or two
hundred bytes or so to perform all of the following functions:
1) Implementation specific clock tolerance compensation only for the case where
multiple clock domains are implemented;
2) Implementation specific Gearbox input and output buffering;
3) Link synchronization stream buffering;
4) General implementation specific buffering requirements.
For the WAN PHY, buffering requirements are one to two orders of magnitude
greater (~10K bytes?), and include all the above plus buffering to perform all
of the following functions:
1) Rx and Tx buffering to account for SONET overhead bytes present in each row;
2) General SONET framing and scrambling implementation specific buffering
64K of buffering sounds pretty wild. A memory manager... for what? One is
certainly not required for the LAN PHY. It would be a stretch to call the ~10K
buffer management circuitry of a WAN PHY a "memory manager".
I'm sure that what you call a "gearbox" for PoS bears no resemblance whatsoever
to the 66:16 gearbox for 10 GbE.
Roy Bynum wrote:
> Finally, someone is coming close to defining the "gear box", the piece of "magic" that everyone is referring to in order to make the
> WIS work. Now, can you codify the amount of buffering required, and the flow differential alignments required to provide for the
> total possible adjustment needed between the SONET framer and the 64B/66B PCS? For example, would 64k of multi-port memory as a
> FIFO buffer, with asynchronous clocked registers on either side to provide for the bit and a robust memory manager provide the
> required functionality? Is 64K enough. Is it more than what is needed? Are FIFO registers required? Is a memory manager needed,
> and if so, what kind?
> The reason that I ask this question is that in my years of experience with PoS, which uses a "gear box", it has proven to have a
> massive lack reliability compared to 802.3 Ethernet. For example, the GbE transport error rate is about 3e-8 to 2e-10 errored
> frames, depending on
> the frame size. Compare this to the goal of only 3e10-2 dropped and errored packets over IP/PoS, and other services at 2e10-3 frame
> error rate.
> ATM with a HEC frame structure has a much better reliability, 1e-8 to 1e-10 depending on the service. Is P802.3ae willing to take a
> chance with a technology architecture that is associated with un-reliable data communications or would it rather use something that
> is associated with reliable data communications? As a customer, it is very important for me to know.
> Thank you,
> Roy Bynum
Richard Taborek Sr. Phone: 408-845-6102
Chief Technology Officer Cell: 408-832-3957
nSerial Corporation Fax: 408-845-6114
2500-5 Augustine Dr. mailto:rtaborek@xxxxxxxxxxx
Santa Clara, CA 95054 http://www.nSerial.com