Cisco Blogs


Cisco Blog > Data Center and Cloud

OpenStack@Cisco – Havana release and IceHouse Summit

Earlier in this month the OpenStack community came out with the biannual OpenStack release – Havana. According to the OpenStack Foundation, not only did Havana add close to 400 new features across Compute (Nova), Storage (Swift), Networking (Neutron) and other core services, it also provided users with more application-driven capabilities and more enterprise features.  Two new projects – Heat (orchestration) and Ceilometer (metering) were integrated into OpenStack during the Havana release as well.

One area of focus in Havana for Cisco was on the Neutron project.  This included contributions to enhance the Neutron Cisco plugin framework, feature additions to the Nexus plugin for physical Cisco Nexus switches, introduction of the new Cisco Nexus 1000v virtual switch plugin and actively leading and participating in the design of the Neutron Modular Layer 2 plugin framework. This datasheet captures more information on the new features of the Cisco Nexus Neutron plugin (for physical switches) for OpenStack Havana. Cisco’s contribution in these and other areas, such as Layer 3, Firewall and VPN network services are reflected in this Stackalytics  report of Neutron contributions for the Havana release.

 pie  table

We are now just a few days away from the OpenStack IceHouse Summit taking place in Hong Kong. Cisco is premier sponsor for the Summit and is also participating in several sessions and panels to make the Summit a success. To secure a slot in the General Session track at the Summit, interested candidates including Cisco’s OpenStack team submitted speaking proposals in August that went through an OpenStack community voting process. The details of the proposals can be found in this blog. Based on these results, Cisco’s team is now leading or participating in 10 session and panel discussions. The following table (sorted by session timings) captures details of the accepted sessions –

Track Session Details
General Session Panel: The CTOs of Cloud November 5 2:50pm -- 3:30pm
AsiaWorld-Summit-Hall 2 (AsiaWorld-Expo)
Apps on OpenStack OpenStack for Enterprise Developers: Should they care? November 5 3:40pm -- 4:20pm
SkyCity Grand Ballroom A&B (SkyCity Marriot Hotel)
Related OSS Projects Panel: OpenDaylight: An Open Source SDN for your OpenStack Cloud November 6 11:15am -- 11:55am
Skycity Grand Ballroom A&B (SkyCity Marriott Hotel)
Strategy OpenStack, IaaS and the Future of Application Aware Infrastructure November 6 12:05pm -- 12:45pm
Expo Breakout Room 1 (AsiaWorld-Expo)
Panel: The Future of Networking in the Cloud November 6 2:00pm -- 2:40pm
Expo Breakout Room 1 (AsiaWorld-Expo)
Product & Services Deploying OpenStack with Cisco Networking, Compute and Storage November 6 3:40pm -- 4:20pm
Expo Breakout Room 1 (AsiaWorld-Expo)
Panel: Agile Networking with OpenStack November 6 4:40pm -- 5:20pm
Expo Breakout Room 1 (AsiaWorld-Expo)
Operations Deploying federated Openstack deployments on ipv6 backbones Experiences, Directions and Architecture November 7 9:00am -- 9:40am
Expo Breakout Room 2 (AsiaWorld-Expo)
Community Building Panel: Ideas, tools and examples for OpenStack Groups November 8 9:50am -- 10:30am
Expo Breakout Room 1 (AsiaWorld-Expo)
Technical Deep Dive OpenStack Neutron Modular Layer 2 Plugin Deep Dive November 8 11:00am -- 11:40am
Expo Breakout Room 2 (AsiaWorld-Expo)

In addition to the above General Session tracks, the Cisco OpenStack team is also leading the design sessions in the Neutron project on Connectivity Group extensions for applications, Modular Layer 2 plugin, Network Function Virtualization with Service VM’s and Services Framework.  An enhanced constraint based solver scheduler will also be discussed with the community within the Nova project. The schedule for the general sessions is here and for the design sessions here. If you are interested in attending any of the general or design sessions be sure to mark your calendar.

Finally, we are showcasing in the demo theater “Scaling OpenStack with Cisco UCS and Nexus” on Wednesday, November 6th 12:40pm-12:55pm and will be present at the Cisco booth (booth B6 in the exhibit hall) with the following demos  –

Demos

Quad Hours

  • OpenStack UCS demo
  • N1KV demo on OpenStack
  • Seamless-Cloud on OpenStack demo
  • Constraint-based Smarter Scheduler for OpenStack demo (short demo here)
  • Tuesday, November 5th from 10:45am to 6:00pm
  • Wednesday, November 6th from 10:45am to 6:00pm
  • Thursday, November 7th from 8:00am to 4:00pm

We are excited to be there at the OpenStack Hong Kong Summit and we hope to see you there as well ! For latest information, visit us here.

Tags: , , , , , , , ,

UCS E-series Meets Applications | Inside the Branch

Needle and thread. Fire and wood.  Peanut butter and jelly.  Just a few things that are essential together so that you can sew, keep warm and well, is just yummy.  So what happens when the data center-class server blade for the branch meets applications?  That’s the topic discussed in the 2nd episode of the Inside the Branch: UCS E-series episodes.

Last week was the series premier of our 5 part series on UCSE.  Hugo and Jay discussed the basics of the product and some key facts we should know.  In this episode, Hugo met with Vidya, our guru in charge of Cisco applications for UCSE.

Read More »

Tags: , , , , , , ,

Blade Server Architecture Comparison – Important Differences Abound

October 18, 2013 at 3:06 pm PST

I recently wrote a blog titled Blade Server TCO and Architecture – You Cannot Separate Them and thought a little more on the architecture side would be a good thing.

 With so much misinformation (dis-information?) about UCS running around in the ether, I thought the straight forward comparison offered here would be valuable. It is important to dispel myths and analyze reality before making the important decisions around server and networking refreshes / upgrades, which by necessity affect long term data center architecture. I hope you will find this presentation -- Cisco UCS, HP and IBM -- A Blade Architecture Comparison, useful in your decision making process.

Cisco UCS HP and IBM A Blade Architecture Comparison from Cisco Data Center

For me, there are three primary drivers that differentiate the Cisco UCS architecture from everyone else’s designs and they can be divided into the buckets below:

You could, and probably should, ask what is left out? That’s pretty easy. I did not specifically call out Performance and TCO, for a good reason. If you can execute on the three bullets above like Cisco UCS does, Performance and TCO are the natural derivatives. You shouldn’t have to target them separately. It’s kind of a “If you build it, they will come” scenario. That’s why I made the statements in the TCO and Architecture blog that “…Server cost is irrelevant (to OpEx) because: changing its contribution to total TCO has a vanishingly small impact….” and “…It [architecture] is the single most important component of OpEx…”   For more on this and how server cost and TCO intersect, please check out this blog -- Blade Server TCO and Architecture – You Cannot Separate Them.  It takes a look at the OpEx and CapEx components of TCO, and how altering either of them effects the actual total  3-year TCO.  You may be surprised.

Cisco is providing trade-in credits for customers’ old generation servers and blade chassis,  helping ease the transition and upgrade to a new UCS blade architecture.  The UCS Advantage presentation below has more details on this fantastic program that can further enhance the already compelling TCO benefit of upgrading to Cisco UCS.

UCS Advantage -- Refresh to UCS from Cisco Data Center

Special note: For more on the benefit that Cisco UCS delivers for I/O and throughput, I suggest a great blog by Amit Jain -- How to get more SAN mileage out of UCS FI.  Amit does an excellent compare / contrast of FC and FCoE technologies (“…8 Gb FC yields 6.8 Gb throughput while 10 Gb FCoE yields close to 10 Gb throughput…”).

Tags: , , , , , , , , , , , , , , , , , , ,

Now is the time to refresh to Cisco UCS!

October 17, 2013 at 12:57 pm PST

Intel estimates1 that one-third of the servers in production are more than four years old. At first, one might think that it is great to get this much service out of a capital investment, but the operational costs to run these outdated servers would pay for a complete technology refresh increasing performance and reliability while reducing total costs. How is this possible? With the Intel® Xeon® Processor E5-2600 v2 product family and Cisco’s Unified Computing System. Read More »

Tags: , , , , , , , , , , , , , , , , , , , , ,

Inside the Branch: UCS E-series 101

Recently, I was chatting with Hugo Vliegen, Director of Technical marketing, Enterprise Networks, and he was telling me all of the questions he had been getting from customers about the Cisco UCS E-Series.  Questions such as:

  • What’s this rumor I’ve heard that Cisco has a server that sits on a branch router?
  • You’re telling me the UCS E-Series is enterprise-class? What does that even mean?
  • What’s new on the Cisco ISR series?

So I suggested we do an interview series with Hugo – something short and fun where he could get the Cisco experts on the record and help our customers learn a little more about the UCS E-Series. Read More »

Tags: , , , , , ,