[Arm-netbook] EOMA server standard

[luke.leighton]

On Wed, Oct 24, 2012 at 2:50 PM, Gordan Bobic <gordan at bobich.net> wrote:
> On 10/24/2012 02:14 PM, luke.leighton wrote:
>> On Wed, Oct 24, 2012 at 1:23 PM, Gordan Bobic<gordan at bobich.net>  wrote:
>>
>>> Possibly the best option might be a single 10G fibre port with
>>> additional 4-5 copper gigabit ports for people who aren't set up for fibre.
>>
>>   my only concern is: standards *have* to be based around
>> "non-optional-itis".  or, that whatever you put down it can have
>> auto-negotiation.
>
> Why does the number of external ports on the chassis have to be
> standardised? What is there to be gained from this?

 vendor-independent upgradeability.

> Normal servers don't have a "standard" number of network ports.

 good point.

 ok, the thought-patterns for standardising on the ports stems from
the ease with which it was possible to choose the ports for the "non"
server EOMA standard.  i say "ease" but you know what i mean.  8 wires
for 1000 Eth, 4 for SATA, 8 for USB3, that's hardly rocket science,
and it's more than adequate.

>>   basically, if you have fibre and also 4-5 copper gigabit ports, all
>> server card implementations *MUST* support fibre and also 4-5 copper
>> gigabit ports.  even if you have fibre and only 1 copper gigabit port,
>> all server cards *MUST* support *BOTH* interfaces, even if the I/O
>> boards don't use the fibre or don't use the copper.
>
> That's not something you'll put on the server EOMA card - that's
> something you'll put on the _chassis_.

 ok.

> I cannot imagine there being any point in having 10G ethernet directly
> on the EOMA card.
>
>>   you *CANNOT* have "optional" ports on the server card.  you just
>> can't - it causes complete chaos.
>
> We appear to have had a misunderstanding on what we are discussing here.
> I thought we were discussing possible server chassis standards. I really
> don't think there's any point in even contemplating 10G ethernet on the
> EOMA card itself. We're probably 2-3 SoC generations behind that being
> even remotely useful - and by then you can devise a new, more advanced
> standard for the more advanced SoCs when they are actually available.

 yeah.  i think the calxeda ECX-1000 is a bit "ahead of the curve" shall we say.

>>   this is why i was looking at 10GBase-T because you can use the
>> *exact* same 8 wires for 10/100/1000/10000 ethernet, it's all
>> auto-negotiated.
>
> Except the network port will suck up 5x more Watts than the whole of the
> rest of the card put together. I really don't see it as particularly
> desirable. :)
>
>>   setting a lowest-common-denominator standard (where its sub-standards
>> all have auto-negotiation), in a market that's about to expand, is
>> very very tricky!
>>
>>   this needs a lot of careful thought, or just to say "nuts to it" and
>> set a bar and tough luck for any SoCs that are below that level.
>
> Since there are no SoCs that can do 10G on the chip, it's pretty
> academic.

 it's not - the calxeda ECX-1000 can:
    http://www.calxeda.com/technology/products/processors/ecx-1000-techspecs/

 with an 80gbyte/sec internal crossbar to DMA, and a 72-bit-wide DDR3
memory bus, it's a pretty shit-hot CPU in under 5 watts.  XAUI is i
believe a standard interconnect: multiplexing-wise it can have up to 5
XAUI ports, up to 3 10G-Eth, etc. etc.

> And given the sort of power envelope we are looking at, the
> chances are that it will never actually be workable with the copper variant.