UCS and QoS

Answered Question
Dec 8th, 2010
User Badges:
  • Blue, 1500 points or more


The UCS ecosystem leverages a port aggregation solution to chassis I/O, namely, the FEX modules.

The  FEX modules are not fully featured switches. Nor do they possess any  forwarding policy intelligence at all. Instead, the FEX modules deploy a  "pinning" approach in which downlinks (those that face the blade  server's NIC's, LOMs, mezzanine cards) are mapped to an uplink port  (those that face a 6100 Fabric Interconnect) to form what can be  described as an aggregator group.

The  result is a simplified approach to blade I/O in which the traffic  patterns are predictable and failover is deterministic. Moreover, there  is no need to configure STP because the ports are uplinked in a manner  as to preclude any possibility of a bridging loop.

This  having been said, is there some merit to the argument that this port  aggregation design places a hole in the middle of a QoS deployment since  the scheduling of packets on the uplink ports facing the 6100 Fabric  Interconnect is not performed in a manner that recognizes priority?

To  elaborate a bit more, one can have a VMware deployment and leverage  NetIOC or perhaps configure QoS on a 1000v switch (whose uplink ports  are mapped to a port on the Palo VIC) and configure QoS on the VIC, and  then on the 6100 Fabric Interconnect. But, since the FEX is not  scheduling traffic to the 6100 Fabric Interconnect according to any  priority, the QoS deployment has a hole in the middle, so to speak.


Correct Answer by brhedlun about 6 years 6 months ago


I have posted a response to your question here:


Hope this helps.



  • 1
  • 2
  • 3
  • 4
  • 5
Overall Rating: 5 (1 ratings)
adambaum1 Wed, 12/08/2010 - 06:03
User Badges:

Have you reviewed Brad's article on UCS QoS?  http://bradhedlund.com/2010/09/15/vmware-10ge-qos-designs-cisco-ucs-nexus/   It may answer some questions.  Based on his article, it looks like you can do some bandwidth manipulation at the blade level. 

I see why you think there may be a "hole" at the FEX level.  It's a good question.  I wonder what would happen if you had two blades on the uplink, both with the highest class of service.  A 10GbE port is still a 10GbE port.  Do they drop down to 5Gb each or does some other mechanism come into play?


adambaum1 Wed, 12/08/2010 - 07:44
User Badges:

So I posted your  question to Brad and here is his response:

"In short, the FEX pushes congestion back to the adapter (PFC), where the adapter decides traffic scheduling"


lamav Wed, 12/08/2010 - 08:28
User Badges:
  • Blue, 1500 points or more

Thanks, Adam.

Yes, I am aware of Brad's blog. Read it all the time. And I read the QoS section.

I cant say I understand his answer to this, though...wish he would elaborate. I also posted the question on his blog a few nights ago...not sure if hes answered me yet. Will check.


lamav Wed, 12/08/2010 - 10:23
User Badges:
  • Blue, 1500 points or more

Brad, good stuff! I read your blog all the time. I especially like the 10-part Best Practices video series. You pay excruciating attention to detail, which is what any engineer should do. I hope Cisco takes care of you, if you know what I mean. :-)

Anyway, I read you answer quickly. I'll try to digest it as I meet some clients. I may get back to you on it.

If not, let me say thnk you now for your time and answer. Much appreciated.

And by the way, I only ask these types of questions so that I can fully understand the solution, not to say "gotcha." Its necessary to play devil's advocate sometimes - you know your clients will!


This Discussion