Light Reading

Virtual Machine Fabric Extender Performance

Light Reading
Series Column
Light Reading

EXECUTIVE SUMMARY: The Cisco UCS’s Virtual Machine Fabric Extender (VM-FEX) offers consistently increased network performance operations compared to virtual distributed switch installations.

In a standard Local Area Network, various hosts, laptops and PCs typically connect to a Layer 2 switch that aggregates the physical stations before handing them off to a router. Communication between two hosts on the same LAN can be done directly without reaching the router. Similarly, a virtual switching instance passes traffic either to a VM sitting in the same hardware, or pushes it out the physical port. Virtual Switches (such as the Cisco Nexus 1000v or VMware’s vNetwork Distributed Switch) operations are done in software and Virtual Switches (such as the Cisco Nexus 1000v or VMware’s vNetwork Distributed Switch) operations are done in software and therefore take resources away from the virtual machines hosted on the blade. Reducing the amount of resources available to the VMs.

Cisco's Nexus 1000v has a rich set of capabilities such as VLAN aggregation, forwarding policies and security. Cisco, however, found that not all VM installations require these features, and in such cases it makes sense to save the resources taken by the virtual switch and appropriate them to the customer needs.

Cisco claimed that their Virtual Machine Fabric Extender (VM-FEX) in VMDirect mode replaces the switch and shows a significant increase in CPU performance for network intensive applications. VM-FEX, installed on VMWare ESX 5.0, enables all VM traffic to be automatically sent out on the UCS's Virtual Interface Card (VIC). This meant more traffic on the physical blade network interface, but reduced CPU usage, which is typically the VM bottleneck. To verify that the VM-FEX really frees up CPU resources, we ran a series of tests comparing a VM-FEX-enabled UCS blade to a Nexus 1000v virtual switch setup. Both UCS blade installations were identical in all aspects apart from the use of the VM-FEX in one and Nexus 1000v in the other.

We started comparing the performance between the two setups using Ixia’s virtual tools. We installed four Ixia IxNetwork VMs on each of the two UCS blades and sent 3,333 Mbit/s of traffic from each of the first three VMs, toward the fourth for 120 seconds using 1,500-byte frames. In the VM-FEX case we recorded 2.186 percent frame loss, while in the distributed switch environment we recorded 16.19 percent frame loss.

We expected loss in both cases, given the almost 10Gbit/s load we were transmitting in the virtual space. The load was required in order to really keep the CPU busy. We deduced from this initial test result that in the VM-FEX environment less resources were used, which is why the frame loss we recorded was smaller than the loss recorded in the virtual distributed switch setup.

For the next test setup we installed one IxLoad VM on each of the two blades. We configured both IxLoad VMs as HTTP clients that requested traffic from a Web server Cisco configured. The IxLoad emulated clients were configured to try and use as much bandwidth as possible by requesting 10 different objects from 10 URLs repeatedly. The VM-FEX setup reached 9.87 Gbit/s while the distributed switch reached 7.78 Gbit/s. The CPU usage was also significantly higher in the virtual distributed switch setup when compared to the VM-FEX setup.

Using the Ixia test tools we recorded the performance difference we expected. Cisco recommended that we perform a test that relies more heavily on the Storage Area Network (SAN). For this test, Cisco helped us to set up 10 VMs on each of the two setups, and install IOmeter on each virtual machine. IOmeter was configured to read blocks from an iSCSI-based SAN as fast as it possibly could. We manually started each of the twenty IOmeter instances, and after 10 minutes we manually stopped each of them. At the end, we looked at three statistics -- Input/Output Operations per Second, Data Rate, and Average Response Time -- all three averaged across the 10 VMs in each setup. The VM-FEX performance was indeed higher for all three metrics. The data is shown in the graph below:

We were still curious what the difference would be when someone is running a common task on a single VM. We wrote a script to use the open source program mplayer to encode a DVD image file that was stored in the SAN into mpeg (for private use of course). We wrote two versions of the script -- one performed an additional round of encoding. The results of this test run actually showed that the act of fetching blocks off the network-attached DVD were not too resource intensive as the VM-FEX setup required only marginally less time to perform the encoding than the virtual distributed switch setup.

Perhaps the most interesting metric was not the performance, but rather the CPU utilization. How much of the CPU was used for the operation, and how much was left over for other operations and other users? As shown below, the VM-FEX setup used far less of CPU resources in all cases. This was expected, since the CPU was skipping an entire layer of virtual switching, and this was, after all, exactly what Cisco wanted to demonstrate.

Next Page: Virtual Security Gateway
Previous Page: Unified Fabric (UF) – UCS Manager

Back to the Cisco Test Main Page

(0)  | 
Comment  | 
Print  | 
Newest First  |  Oldest First  |  Threaded View        ADD A COMMENT
Educational Resources
sponsor supplied content
Educational Resources Archive
From The Founder
Light Reading's conference in November will attempt to answer all of the big questions around white box networks. No pressure...
Flash Poll
Live Streaming Video
CLOUD / MANAGED SERVICES: Prepping Ethernet for the Cloud
Moderator: Ray LeMaistre Panelists: Jeremy Bye, Leonard Sheahan
Telecom Innovators Video Showcase
Close-up on ConfD

10|12|15   |   10.21   |   (0) comments

Tail-f's Renée Robinson-Stromberg tells Steve Saunders about the powerful ConfD management interface.
Women in Comms Introduction Videos
Women in Comms: Highlights From Dallas

10|12|15   |   2:23   |   (1) comment

The best soundbites, quotes and words of wisdom from leading women from Intel, AT&T, Verizon and Genband at our recent WiC breakfast in Dallas.
Telecom Innovators Video Showcase
NetNumber Founder on Managing Signaling Control

10|12|15   |   6:36   |   (0) comments

NetNumber Founder and Chief Strategy Officer Doug Ranalli describes the essential complexity of real-world signaling-control and how NetNumber enables carriers to bring signaling-control "under-control". Learn why virtualization alone isn't the answer.
LRTV Documentaries
Verizon Gets Proactive on App Performance

10|12|15   |   04:50   |   (0) comments

SDN is turning traditional service models around to allow Verizon to measure and deliver performance at the application layer. As Shawn Hakl, VP of enterprise networking and managed solutions for Verizon, explains, the carrier had to develop new skill sets and change some of its internal operations, but the payoff was happier enterprise customers.
Telecom Innovators Video Showcase
Tail-f, Cisco & What the Future Holds

10|9|15   |   8:17   |   (0) comments

Steve Saunders meets with Tail-f's Director of Technology, Carl Moberg, in Stockholm to discuss becoming part of Cisco, ETSI MANO, virtualization and the need to combine science and business in order to create opportunities for service providers.
LRTV Interviews
Broadband Forum Embraces SDN & NFV

10|9|15   |   02:42   |   (1) comment

At Gigabit Europe 2015, Robin Mersh and Kevin Foster from the Broadband Forum explain how the industry body is adapting to meet the SDN, NFV and cloud needs of the access network sector.
LRTV Interviews
Top Tips for FTTH Operators

10|8|15   |   02:26   |   (0) comments

At Gigabit Europe 2015, Ventura Team co-founder Richard Jones talks about some of the key business case considerations for FTTH network operators.
LRTV Interviews
M-net Calls for FTTx Unity

10|8|15   |   03:45   |   (0) comments

At the Gigabit Europe event, Jörn Schoof from M-net, the Munich city network operator, calls for industry collaboration on fiber broadband access rollouts.
LRTV Documentaries
The Business Case Challenge for NFV

10|7|15   |   03:47   |   (0) comments

Virtual CPE is one of the early success stories for network functions virtualization, as service providers are finding flexible, programmable CPE solves a lot of logistics problems and reduces their cost. But even here, Masergy Communications faced a business case challenge, says CTO Tim Naramore.
LRTV Interviews
JT Offers Some Gigabit Lessons

10|7|15   |   4:08   |   (1) comment

Barna Kutvolgyi, managing director, Global Consumer, at JT, the incumbent operator on the island of Jersey, talks about how other service providers can learn from his company's gigabit broadband rollout experiences.
LRTV Interviews
AT&T's Chiosi on the Potential of Open Source

10|6|15   |   06:27   |   (0) comments

AT&T Distinguished Network Architect Margaret T. Chiosi talks to Light Reading's Carol Wilson about the potential for open source technology to liberate communications service providers.
LRTV Interviews
Network Security in a Gigabit World

10|6|15   |   05:52   |   (0) comments

Masergy's James Harrison talks about some of the network security and data center issues network operators need to consider as they expand their broadband services portfolios.
Upcoming Live Events
October 14-15, 2015, New Orleans Ernest N. Morial Convention Center, New Orleans, LA
November 5, 2015, Hilton Santa Clara, Santa Clara, CA
November 17, 2015, Santa Clara, California
December 1, 2015, The Westin Times Square, New York City
December 2, 2015, The Westin Times Square, New York City
All Upcoming Live Events
Network appliances have a strong value proposition in today's networks and will continue to do so in the NFV and SDN-enabled networks of tomorrow.
Hot Topics
Dell Buys EMC for $67B in Biggest Tech Deal Ever
Mari Silbey, Senior Editor, Cable/Video, 10/12/2015
M&A Speculation Swirls Around Juniper
Ray Le Maistre, Editor-in-chief, 10/6/2015
Cord Cutting? 'Fraid so.
Brett Sappington, 10/7/2015
Cisco Makes 'Martian' Connection
Mitch Wagner, West Coast Bureau Chief, Light Reading, 10/9/2015
Like Us on Facebook
Twitter Feed
Webinar Archive
BETWEEN THE CEOs - Executive Interviews
With so many new and exciting communications technologies now under development, it's easy to get caught up in the industry's escalating hype cycle. That's why the ...
Last week saw a big day in the 15-year history of Light Reading when Editor-in-Chief Ray Le Maistre and I were invited to interview the Deputy Chairman and Rotating ...
Cats with Phones
"What?! I'm on with Finisar about their stock price tanking" Click Here
Live Digital Audio

Think NFV is just about virtualization? Think again!

Network architects are learning that there's a lot more to the technology than first thought – more complexity, that is; but also, more potential benefits.

On May 29th 1 PM ET, Steve Saunders, founder and CEO of Light Reading, will be drilling into the "pains and gains" of NFV with Saar Gillai, SVP & GM, HP Communications Solutions Business at Hewlett-Packard Co. (NYSE: HPQ) (HP). He has defined a four-step NFV model describing a sequence of technology innovation. It's a must-read doc for any network architect looking to get to grips with their NFV migration strategy. Join us for the interview, and the chance to ask Saar your NFV questions directly!