Cisco UCS Ethernet Frame Flows

In this post I am going to walk through the northbound frame flows in the Cisco UCS system. Hopefully this information will help you better understand UCS networking.

In other posts I will walk through the southbound and maybe east-west frame flows. I am breaking the posts down into multiple posts to make it easier for the reader to get through and understand.

I learned most of the information in this post from the Cisco Live 2010 session “Network Redundancy and Load Balancing Designs for UCS Blade Servers” presented by Sean McGee of Cisco. Some of the diagrams in this post were also taken from that same session.

Acronyms used in this post:

CNA – Converged Network Adapters on the mezzanine card

FEX – Fabric Extender 2104XP that lives in the chassis. There are usually two of these per chassis, one for Fabric A and on for Fabric B.

FI = Fabric Interconnect, the 6120s/6140s. Usually deployed as a pair in an HA configuration.

IOM – I/O Module, another name for the FEX.

First lets take a look at the physical components within the UCS System. Below is a logical and physical diagram of the components that make up UCS.



Now lets take a look at northbound frame flows. The following diagram lists the decision points that take place as the frame travels from the OS up through and out of UCS to the LAN.



First we will start with the northbound traffic leaving from the Operating System.

  1. OS creates the frame – The happens the same way in UCS as is it does in any other hardware.
  2. The OS then has to decide which PCIe Ethernet interface to forward the frame out of. If there multiple PCIe Ethernet interfaces the OS NIC teaming software decides which interface to use based on a hashing algorithm or a round robin mechanism. In the case of VMware and the VIC (Palo) this could be from 1 to 58 choices, realistically you probably will have less than 10.
  3. If there is just 1 PCIe interface and Fabric Failover is enabled then it is the UCS Menlo ASIC that makes the frame forwarding decision.

After the frame has entered the physical mezzanine CNA another decision must be made as to which one of the 2 physical CNA ports are used to send the frame to the FEX. This decision depends on how the vNIC was configured in UCSM. When configured a vNIC as part of a Service Profile in UCSM you must choose which fabric to place this vNIC on (A or B) and whether or not Fabric Failover is enabled. The screen shot below shows these configuration options.


With this configuration Fabric A will be used unless for some reason it is down and then Fabric B will be used because Fabric Failover is enabled. For the purpose of this post we will assume the frame is exiting CNA Port 1 that is physically pinned to FEX (Fabric Extension Module in the back of the chassis) 1 on the mid-plane of the chassis. FEX 1 is the left hand FEX as you are looking at the back of the chassis, see the diagram below.



The FEX have 8 10GE KR back-end mid-plane ports or traces and 4 front-end 10GE SFP+ ports. The picture below shows the 8 back-end ports and the 4 front-end ports on a FEX. The 8 back-end ports are not physically visible like the picture shows this is just a good picture that logically shows the ports.


The back-end FEX port that the frame goes across depends on which blade this particular OS is running on. In our example we will say blade 3. There is a blade CNA port to FEX back-end port pinning that happens. For blade 3 CNA 1 the back-end FEX port will be port 3 or Eth1/1/3.

Eth X/Y/Z where

  • X = chassis number
  • Y = mezzanine card number or CNA number
  • Z = FEX (IOM) port number

Below is a screen shot of the output of the cmd “show platform software redwood sts”. This command must be executed from the fex-1# context. To get here from the UCSM cli prompt first type “connect local-mgmt” then “ucs-A(local-mgmt)# connect iom 1” The 1 in this cmd is the chassis number.



Once the frame is in the FEX it has to be forwarded to the Fabric Interconnect across one of the 4 front-end 10GE SFP+ ports. The port the frame goes across depends on how many FEX to Fabric Interconnect cables are connected and which blade it originally came from. There is a blade to IOM uplink pinning that happens based on the number of uplinked SFP+ ports. This pinning is not user controllable.

Here is a table and diagram showing how the pinning works in the three different uplink options.

1 IOM-FI Cable 2 IOM-FI Cables 4 IOM-FI Cables
All blades CNA 1 goes out this one cable, 8:1 oversubscription slots 1,3,5,7 are pinned to one uplink and slots 2,4,6,8 are pinned to the other, 4:1 oversubscription slots 1,5 out 1
slots 2,6 out 2
slots 3,7 out 3
slots 4, 8 out 4



For our example there are 4 IOM-FI uplinks.

So to summarize the path the frame has traveled up to this point.

  1. OS generated frame.
  2. OS chose the PCIe Ethernet Interface using either NIC teaming software. In our case there was only one PCIe Ethernet vNIC assigned to the Service Profile on this blade.
  3. Frame was forwarded to CNA 1 because we set Fabric A as the preferred fabric unless it is down. The Fabric Failover ASIC chose CNA 1 because Fabric A is up.
  4. CNA 1 is pinned to IOM 3 because it is blade 3.
  5. The uplink IOM SFP+ port 2 was used to forward the frame to Fabric Interconnect A because it is blade 3 and there are 4 SFP+ uplinks connected from IOM-FI.

The next step is for Fabric Interconnect A to forward this frame to a northbound L2 LAN switch. Before this can happen the FI has to determine which northbound Ethernet port to send it out of. This decision process is as follows

  1. Are there any LAN Pin Groups? If manual pinning is configured for this blade’s vNIC 1 to go out a specific uplink or Port Channel then that port or Port Channel is used to forward the frame. If it is Port Channel then the specific interface of the Port Channel that is used is based on the Port Channel hashing algorithm.
  2. Are Port Channels in use? If it is Port Channel then the specific interface of the Port Channel that is used is based on the Port Channel hashing algorithm.

If there are no LAN Pin Groups or Port Channels then automatic pinning is used in a round robin fashion. If there are 8 blades in the chassis and 4 northbound Ethernet uplinks then there will be 2 blades pinned to each uplink. This works in much the same way the default VMware vSwitch teaming works if you familiar with that.

So I think that about covers the northbound Ethernet frame flows. I stated earlier I will be posting the corresponding south, west and east flows in follow on posts.


Cisco UCS Enhancements in Firmware 1.3

Cisco UCS firmware 1.3 was released last week. There are lots of new features in this latest update and Dave Alexander (ucs_dave) outlined most of those in his blog post –

What I will be covering here are the features that Dave didn’t cover nor were they mentioned in the release notes for 1.3 –

The feature I was most excited about was the advanced BIOS settings control from the Service Profile.

I updated our UCS lab this morning and on the the first login to UCSM after I finished the update I was surprised to see the Fabric Interconnects now have listed in their name what their current cluster role is. Before you had to drill down into each one to see this.


The next change I noticed was that the BMC had been renamed to CIMC (Cisco Integrated Management Controller). I personally like the new name better because I think it makes more since than BMC.


I was then looking around in the Admin tab and noticed a new section labeled Capability Catalog. The UCSM GUI Configuration Guide for 1.3 states this about the catalog

“The capability catalog is a set of tunable parameters, strings, and rules. Cisco UCS Manager uses the catalog to update the display and configurability of components such as newly qualified DIMMs and disk drives for servers.”

The catalog also has an Update Catalog function that can be used to update as Cisco updates it.


On the VM tab there is a new “Configure VMware Integration” wizard to assist in configuring VN-Link in hardware. (this requires the VIC adapter in the server blades and VEM installed on the ESX hosts)


Here are a few screen shots of the new BIOS settings that can be configured. These new settings are implemented via a BIOS Policy that is then tied to a Service Profile or Service Profile Template.




I am sure there may be a few more hidden gems in here but these are the ones I have noticed so far.

Cisco UCS Server Pools: Configuration

In my previous post I discussed Cisco UCS Server Pools and use cases. In this post I will be walking through the configuration of Server Pools, Server Pool Policies and Server Pool Policy Qualifications.

As stated in my previous post one of the use cases for Server Pools is in the server farm model where you have varying amounts of RAM and CPUs in your blades and and you want a way to efficiently deploy a farm of web server, ESX hosts and database servers without having to specifically choose a server blade.

In this configuration example I will walk through the configuration on an auto-populated Server Pool using Server Pool Policies and Server Pool Policy Qualifications.

The first step is to create a Server Pool. To do this go to the Servers tab, Pools.



Right-click on Server Pools to create a new pool


On the add server page temporarily add a blade and then remove it. If you don’t do this the Finish button stays grayed out. This is one of the UCSM nuances.


The next step is to create a Server Pool Policy Qualification


I am going to create a web server qualification that uses a Memory Qualification for 8 GB RAM


Now to tie it all together with a Server Pool Policy


To use this new auto-populating Server Pool associate a Service Profile Template to is so that when you deploy new Service Profiles from the template you don’t have to select a blade, it will be automatically selected if there is one available in the associated pool.



One important note is that if your blades have already been discovered you will need to re-acknowledge them before they will be added to a server pool.

Another important note is that if you re-acknowledge a blade it will reboot it without asking so you probably only want to re-acknowledge blades that are not associated with a Service Profile.

Cisco UCS Server Pools: Use Cases

This is a a two part blog post on Cisco UCS Server Pools. This first post will focus on what Server Pools are and use cases and the next post will focus on configuration.

Cisco UCS Server pools are one of the more mysterious features of UCS. I say mysterious because in my opinion the usage and configuration of them is not very intuitive. Let’s start with Cisco’s definition of a Server Pool, this definition was copied from the Cisco UCS Manager GUI Configuration Guide, Release 1.2(1) found here –

A server pool contains a set of servers. These servers typically share the same characteristics. Those characteristics can be their location in the chassis, or an attribute such as server type, amount of memory,local storage, type of CPU, or local drive configuration.”

You are probably thinking that doesn’t sound very mysterious and you are right it doesn’t until you start digging into the use cases and configuration of Server Pools.

Here are some characteristics of a Server Pool:

  • Can be manually populated or auto-populated
    • Manual is where you select the blades that you want to be part of a given pool.
    • Auto-populated works by creating Server Pool Qualifications and Server Pool Policies where you define the specific hardware characteristics and based on that the blades are placed into one pool or another.
  • A blade can be in multiple pools at the same time – For example lest say you have a multi-tenancy UCS environment and multiple Server Pools have the same blades in them. The blades are not actually tied to a specific organization in UCS and so when a user deploys a new service profile and uses a Server Pool for the assignment they will grab the next available server in their pool. This blade could have also been in any other Server Pool in any other UCS organization that met the qualification. It works on a first come first serve model. Once a blade is associated with a Service Profile is not available to any
  • A service profile template or service profile can be associated with a Server Pool for rapid blade deployments
  • A blade can be located in any chassis that is management by the UCS Cluster

Server Pool Use Cases

Server Farm Model – In this model you have an environment made up of varying applications that have varying hardware requirements.

For example:

  1. Web server farm that needs at least 8 GB RAM and 1 quad core CPU.
  2. Database server farm that needs at least 32 GB RAM and 2 quad core CPUs.
  3. An ESX server farm that needs at least 48 GB RAM, 2 quad core CPUs and a Cisco UCS VIC M81KR adapter.

Rapid Deployments – This would be a new UCS implementation where you are wanting to deploy new blades as fast and efficiently as possible without have to select specific blades to associate Service Profiles with.