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

Re: Does only decimal system work for data rate specification?

At 09:55 AM 09-12-99 +0100, Fenghao Mu wrote:
>1) Why we prefer to only specify 10GE rather than suggest other 
>reasonable data rates related to gigabit Ethernet, say  2.5/5 gigabit 

suppose i turn the question around -- what would be the point of having many
more datarate communication standards, when we already have 1, 10, 100, and 
1000-base-whatever?  it isn't clear to me that finer granularity offers any useful

>2) Why we need Hari coding to tie four individual links together instead 
>of sending data separately?

Hari doesn't code anything.  Hari is a proposed method of standardizing
PMD interconnect that uses existing line codes.  otherwise, the four serial
links are separate, other than for issues related to word- or byte-striping.

>3) Does our data rate specification fit with market requirement and 
>technology progress well? 

yes, else there would not be much interest in developing a new standard
for interoperable, higher-datarate systems.  you should understand that
no one will be compelled to use any standards-based 10GbE system, 
other than for desire to participate in that market space.  that has been
true for all 802.3 stuff, since inception.

>1. From a customer point of view, only 1GE and 10GE give less choices 
>for one to build a good switching structure. He has to chose between two
>possible data rates, either 1GE or 10GE. It might be very difficult for him
>to upgrade his data links, in other words, 10GE is too luxurious and 1GE 
>is insufficient for his requirement. What is his best solution? 

there is already interest in developing a higher datarate standard.  issues
such as feasibility, interoperability, and so on are to be resolved in the 
standards development process.  there will always be technological 
and dollar cost barriers to general market entry, and though the standards
process helps to reduce that cost it cannot be removed entirely.

>2. Data rate evenly distributed networks are seldom met in reality, and it 
>exists only in people's imagination. Designing a switcher fabric based on
>this imagination will cause a big waste of resource. 

i think you will need to define your use of "wasted resource" more carefully
before anyone can address this.  do you want 100% capacity, 24 x 7?  you
won't find it here.  define your conditions and we can proceed.

>[...] If we could use 2.5/5/10 GE data 
>rates, we can individually assign a data rate for a path in a network 
>according different requirements. Multiple data rates can be very helpful
>for optimal I/O pad usage.

you can do that now, at 1, 10, 100, or 1000MBaud. (aside:  i offer this for 
the sake of completion.  does anyone know whether Starlan is still in use?)

>3. There is no reason why we only specify 10GE, which bonds 4 individual 
>links together. Probably there isn't any information source or sink today 
>which has to be specified at 10Gb/s.

if that were true, there would not be much interest in HSSG participation.

>5. At today's technology, few devices could support 10GE within one link
>for a meaningful distance. 

have you ever heard of OC-192/SDH-48?  you may want to try a search 

> From technology point of view, there isn't any
>remarkable breakthrough so that we can utilize a new and cheap device 
>to implement 10GE links. 

fast VCSELs, DMD-flattened M-M fiber, fast (linear) equalization, FEC, MAS
and the like all offer potentially cheap solutions for 10GbE.  you may want
to have a look at presentation notes at the reflector site.

>6. In fact, we could simply extend the Gigabit Ethernet standard to 
>2.5/5 GE specification by adapting new speed as a smooth move. If we 
>use 8B10B encoding, the speed will be 3.125/6.25 Gb/s, respectively. 
>Simple and efficient! Why not?

i gather that people considered that, early on.  seems there wasn't much