Tolly lab test creating major dust-up among Cisco and HP data center gurus

Cisco moves quickly to discredit results of a lab test that unfavorably compared Cisco's UCS with HP's BladeSystem.

Kevin Houston's excellent blog - Blades Made Simple, has generated a fascinating "sparring match" between Cisco and HP data center gurus. This ongoing "technical duel" is being fueled by the controversial results of The Tolly Group's recent lab test that was commissioned by HP:

HP BladeSystem c7000 with ProLiant BL460c G6 Servers vs Cisco UCS 5100 with B200 Servers Network Bandwidth Scalability Comparison

Source: The Tolly Group Even Kevin Tolly has made an appearance within the sparring match: "I would like to clear up a misconception in some of the postings about the test. The test was not utilizing the uplinks on the HP Virtual Connect for anything but a small amount (less than 100Kbps) of management traffic. "The test compares intra-chassis communications in the case of HP this traffic is within the c7000 chassis vs. a Cisco UCS (a logical system created by a single blade Chassis+Fabric Extenders (FEX)+Fabric Interconnect)."

Tolly continued, "For the Cisco UCS the wire from the FEX to the Fabric Interconnect is probably better described as a server downlink (see: What are the supported expansion modules and license requirement in UCS - 'The uplink ports are connected to the external infrastructure and the downlink ports are connected to the fabric extenders in the UCS chassis')." Tolly added, "So what we see in the test is simple physics, two Cisco UCS blades servers share a wire and therefore the bandwidth is shared between the two but is less than what would have been if it is not shared. Hence the oversubscription issue. HP intra-chassis traffic has no such constraint. Thus, we were able to run the HP tests from any-to-any blade within the chassis without seeing any difference in throughput. Such was not the case with the Cisco solution." Tolly concluded, "This issue is a caveat for the UCS approach and would even be more pronounced if, for example, if a user were trying to scale a logical UCS implementation to more than a single chassis. For example in the 320 server logical system with 40 enclosures each connected to a single port on a 40 Port Fabric Interconnect, the amount of 'downlink' sharing is significantly more than even than even the test pointed out." According to Cisco's Senior Data Center Solutions Manager - Omar Sultan: "The fundamental fault with the test was it was conducted with a mis-configured Cisco UCS. Essentially, the testing firm matched a normally running system from our competitor against a Cisco UCS in its failover state. "Let me explain: each Cisco UCS 8-blade chassis supports 2 FEX modules, each with 4 x 10GbE uplinks, resulting in 80Gb of total uplink bandwidth. Typical design best practices recommend you run these FEX in an active-active mode with half the blades using one FEX as their primary and the rest of the blades using the other FEX (see the figure below). Now, you can do the math on your fingers for this: 8 blades with 80Gb of bandwidth = 10Gb/blade. Now, in a failover scenario, all blades will fail over to the remaining FEX without loss of connectivity—which is how our system was tested." Source: Cisco Systems Sultan continued, "The report did include a number of more equitable testing scenarios that did not involve using the Cisco UCS in a failover mode—in those tests, the Cisco UCS consistently outperformed the competitor’s system. For example, with two pairs of blades exchanging 10Gb data streams, UCS aggregate throughput was 36.59 Gbps or 760Mbps faster than the other system. In fact, one of the things the testing firm inadvertently revealed is how good our QoS is—the crippled UCS shared the remaining bandwidth equitably per default policy, which is actually an important, real-world consideration—if you take the time to create policy to ensure certain traffic is prioritized—say storage traffic or key application traffic—you also want to have some degree of comfort that the policy will actually be followed." View more Cisco vs. Competitor Lab Tests.

What's your take on Tolly's test results?

BradReese.Com Cisco Refurbished - Enabling Affordable Cisco Networks Check with us, when you have failed Cisco equipment. We repair Cisco at the component level. Contact: Brad Reese

  1. Cash appears to be Cisco's 4th most valuable product
  2. Cisco competitor Extreme Networks looking to capitalize on Nexus 5000 shipping delays
  3. Force10 targets the large installed base of Cisco's end of life Catalyst 6509 chassis
  4. HP ProCurve leveraging know-how of Cisco's certified engineers
  5. U.S. Supreme Court denies bid by Cisco's cofounders to overturn $19.5 million punitive damage award
  6. Alcatel-Lucent knocked off Juniper and is now No. 2 in SP edge router market share
  7. U.S. software engineer piloted plane in domestic terrorist attack on Austin, Texas
  8. Together, Cisco and Juniper lost 10% of the worldwide router market in 2009
  9. Cisco's storied past as the most valuable company on earth
  10. How to setup Cisco's Flexible NetFlow (FNF) with LEGO Blocks
  11. Cisco CEO John Chambers sells 2.2 million shares of his Cisco stock 5 days after announcing Cisco was back to record profits
  12. 61 CCIEs dropped out of Cisco's highly coveted cert program over the last 30 days
  13. Cisco IP phones praised in email to then Alaska Governor Sarah Palin and First Dude, Todd Palin
  14. New markets for Cisco not generating revenue, Chambers says
  15. Cisco's F2Q10 accounts receivable soar $1.34 billion year over year!
  16. Cisco joins growing laundry list of entities paying Melissa Hathaway to be senior security advisor
  17. Turmoil at Vyatta as Cisco prepares to announce its Q2FY10 earnings?
  18. Brocade BCNE most valuable cert on earth
  19. Pineapple ratings get dished out to Cisco blogs that rock for 2010
  20. View Brad Reese on Cisco Story Archives
Join the Network World communities on Facebook and LinkedIn to comment on topics that are top of mind.

Copyright © 2010 IDG Communications, Inc.