Thanks for your reply, but I still can't agree with your calculation I am afraid.
when 1 F2 modules forwards packets through Switch Fabric (5 Switch Fabrics support up to 550Gbps BW), then 480Gbps of Switch Fabrics have been exclusively occupied by that F2 modules in that moment, and only 550-480=70Gbps is left in Switch Fabric for the other F2 modules.
What is more, each F2 modules has up to 480Gbps Fabric Connection, which mean it can achieve throughput of 480Gbps when packet ingress and egress on the same module, (no Switch Fabirc will be occupied).
So, the scenario for N7K to achieve its max throughput will be 1 F2 module forwards traffic throught Switch Fabric and all other 15 F2 modules just forward traffic locally (packets forwarded no through Switch Fabric).
Max Throughput would be [480Gbps x 15 + 550Gbps ] x 2 (full duplex).
Wasn't good example when I mentioned the F2 module, let's forget the linecards itself for a moment.
Considering the Nexus 7018 for the calculation, excluding the 2 supervisors, we got 16 rooms for modules.
Five fabric2 today can delivery 550Gbps for module. Then: 550Gbps x 16 = 8.8Tbps x 2 (full-duplex) = 17.6Tbps.
The throughput the swicth is calculated by the capacity to forward packets to the modules, no matter whether we are using modules M1, F1, F2, F3, F4, F17... . the total capacity the switch will be the same.
Today we don't have avaliable one module that can delivery 550Gbps to the fabrics, but the fabrics is already there and can process more than is requested today by the F2 linecard in the Nexus 7000.
Take a look to Fabric2 avaliable for Nexus 7700. Just because of the fabric, the swicth throughput capacity increased up to 83Tbps. We still don't have module to get there, either applications to push that.
Thanks for your reply. My query is partially answered now.
Just one thing to confirm, does Fabric Switch provide 550Gbps BW for each I/O module concurrently or 550Gbps is shared by those 16 modules in a time-division way? I think this is the root cause of my query.
BTW, why I raise this query? -- I am recently involved in a DataCenter rollout project which drives me to begin self-learning of Cisco Nexus 7K/5K/2K Switches. I was confused when I came accross this Capacity parameters in the data sheet. So I just want to get to the bottom and do not want any confusion uncleared along with my Nexus trip.
The unmanaged mode is also known as Network only switching, which is introduced in Brazos release. It adds the flexibility for customer to use only network automation for service appliance.
If a device is configured a...
Usually, we can access ESXi Shell by pressing Alt+F1 from ESXi DCUI (Direct Console User Interface).
But on HyperFlex system, it just shows black window.
This is expected behavior because HyperFlex redirects ESXi Shell output to SoL...
Configuring an Export Policy Using the GUI
This procedure explains how to configure an Export policy using the APIC GUI. Follow these steps to trigger a backup of your data:
On the menu bar, choose Admi...