[c-nsp] Understanding 10G line card oversubscription

[Mack McBride]

Just guessing but it would appear that the NAXOS act as two port asics.
These feed data to the R2D2/ASHWINI pair.
My guess is the ASHWINI are between the NAXOS and R2D2 chip since we know
>From the 6704 that the R2D2 can interface directly with the Metro.
Since the R2D2 has a 10G interface, I think it is safe to say the 6716
only has 10G for each 4 port group as Tim stated.
So from a strictly port group over-subscription perspective the 6716 is 
a worse blade than the 6708.

Mack

-----Original Message-----
From: Phil Mayers [mailto:p.mayers at imperial.ac.uk] 
Sent: Monday, March 21, 2011 4:26 PM
To: Mack McBride
Cc: cisco-nsp at puck.nether.net
Subject: Re: [c-nsp] Understanding 10G line card oversubscription

On 03/21/2011 09:26 PM, Mack McBride wrote:
> There is the 4 port group which I believe is the same as a port pair on a 6708. Ie. No free switching.
> Based on some comments by Tim Stevenson, the link between the four port group and the fabric asic is 10G
> rather than the 16G in the 6708.  But he mentions some of the same chips (metro, r2d2) so the architecture
> can't be much different from the 6708.
>
> Then there is the fabric group which is switched locally without going over the fabric.
>
> show asic slot<x>

Module in slot 1 has 7 type(s) of ASICs
         ASIC Name      Count      Version
              KUMA          2      (3.0)
       METRO_ARGOS          2      (3.0)
     METRO_KRYPTON          2      (3.0)
               SSA          2      (9.0)
             NAXOS          8      (1.0)
              R2D2          4      (3.0)
           ASHWINI          4      (0.6)


> sh int<interface>  capabilities | inc ASIC

TenGigabitEthernet1/1
   Ports-in-ASIC (Sub-port ASIC) : 1-8 (1-4)
TenGigabitEthernet1/5
   Ports-in-ASIC (Sub-port ASIC) : 1-8 (5-8)
TenGigabitEthernet1/9
   Ports-in-ASIC (Sub-port ASIC) : 9-16 (9-12)
TenGigabitEthernet1/13
   Ports-in-ASIC (Sub-port ASIC) : 9-16 (13-16)


> Short answer seems to be that the 6716 is basically the same despite claims to the contrary
>

Hmm. I wonder if anyone from Cisco will comment ;o)