I have just come back from the Gartner Data Center conferences in London and Las Vegas where I got to witness the increasing relevance of Cisco in the data center. The critical role of the network to enable the world of many clouds has becomes evident, and Cisco continues to establish itself as an innovator in the server market. Our vision and solutions really grabbed the attention of the analysts and customers at a level that I certainly didn’t see last year.
Data center consolidation, server virtualization, and converged infrastructure continue to be chief concerns among decision makers. Emerging topics such as fabric –based infrastructure, hybrid cloud, and network programmability were definitely the focus of numerous presentations and endless conversations.
Cisco continues to innovate on all these fronts, and we had a lot of progress to present to the audiences in London and Vegas.
Three Insightful Conversations
I’d like to share with you three conversations I had at the Gartner DC Conference in Las Vegas. Two are with the sales and engineering leaders for Cisco Data Center, Frank Palumbo (@fpalumbo) and David Yen, and the third is with one of our partners, Siki Giunta from CSC, who participated on a panel on Cloud that I moderated.
Frank Palumbo on convergence, virtualization, network programmability, and SDN
In the first conversation, Frank Palumbo, VP Global Sales, reports some of the major concerns of the IT organization. Our conversation covers:
The new role of the “cylinders of excellence” — servers, network, storage and security teams — when the goal is to implement a convergence infrastructure;
The benefits of deploying unified computing in environments where virtualization coexists with “bare-metal” workloads; and
Network programmability and SDN.
David Yen on the evolving data center
My second conversation was with David Yen, Cisco SVP & GM, Data Center Group, who gave a great presentation to more than 600 attendees called “The Evolving Data Center: Past, Present, and Future.”
David — who brings in-depth knowledge of IT technologies from his years working with Sun Microsystems, Juniper, and Cisco – provides new perspective on the evolution of the data center.
In his presentation David explains how the convergence infrastructure, on the one hand, and network programmability, on the other hand, reshapes the data center landscape to make the world of many clouds possible.
Over the last several months, since Cisco announced its Open Network Environment strategy, there has been considerable progress on multiple fronts:
- Early field trials (EFTs) with several Enterprise and Service Provider customers
- Proof-of-concepts (PoCs) and customer feedback providing more insight into use-cases and product evolution
- Several acquisitions have been announced that complement the strategy we outlined
- Our engagement and leadership in all the standards bodies around various aspects of open networking continue to grow
During all of these activities and customer interactions, what stood out was the considerable appetite amongst customers and others to learn about these emerging concepts in a more structured way. They expressed a strong desire to break through some of the hype cycle that has pervaded the industry around some of these topics, causing some degree of confusion. They also asked Cisco to present information in an easily consumable manner.
Given the breadth of our portfolio and the diversity of our customer base, this was a bit of challenge for us. A lot of this information was disbursed across different landing pages, blog sites etc. So we had to take a fresh approach to accede to this request.
Based on efforts over the last several weeks, the team has built two foundational portals that serve the purpose of both information aggregation as well as hopefully a watering hole for knowledge seekers -
The Cisco ONE Knowledge portal: This is a centralized aggregated information repository of all the content that we are generating around the topic of open networking across the portfolio, whether it is more formal and structured, or more informal and social. The information here is organized in a more structured way, based on type of content and the chronology.
What you will see is some quality content manifest itself over time, as we bring the consolidated efforts from various Cisco thought leaders, customers, analysts etc. and assets including more demos, deployment use-cases, case-studies etc. We are also initiating a series of webcasts on this topic to do a deeper dive on technology topics with roughly a 4-6 week cadence, with Cisco CTOs across various technology groups mostly leading the sessions. The intent is to Educate in a more structured manner. For example, we’re kicking off the first of these Cisco ONE webinars with “An Introduction to OpenStack”. (If you have not registered for the webcast yet, please do so).
We sincerely welcome your feedback on how to continue to improve the content as well as experience with the Cisco ONE knowledge portal.
As expected a lot of talks, sessions and interest this year about the reality of the cloud deployment and hybrid cloud at Gartner DC Las Vegas.
Cisco is now perceived as a very credible player in cloud – In fact a quick electronic poll from the audience during one of the key notes speechs ranked Cisco as the number 2 amongst the vendors.
As a proof point of Cisco influence in the cloud computing evolution, both David Yen , Cisco SVP & GM Data Center Group, and John Manville Cisco SVP , Global Infrastructure for IT, presented Cisco vision and achievement in terms of infrastructure and foundation for cloud : Network programmability , and convergence infrastructure are at the core of the efforts driven by these Cisco executives and solution teams to deliver robust infrastructures for both our customers and Cisco IT organization.
If you are interested to know more about these sessions, stay tuned. I will post in the following days on this same blog the slide decks from David and John ,as well as two short and very interesting videos that I did these days:
-One one hand a short dialog between Giuliano Di Vitantonio, Cisco VP Marketing Data Center and Cloud, and David Yen.
Along the same lines , I also invited a panel of bloggers and tweeps , who attend Gartner DC to share with us their reaction to these presentations and their view on the current challenges faced by the IT organizations.
Now that we covered how LISP Routing works in Part 1 and Part 2 of this series, let dig into some of the things you can do with it. I would suggest you go back and read the first two posts if you are new to LISP since I am not going to cover that material again. So, lets look at three of the most popular use cases: 1) VM mobility, 2) IPv6 migration, and 3) smarter multi-homing. I am going to cover the generic use cases, then wrap with some real-world customer use cases.
Since it seems to be the hottest topic, let start with the mobility solution. From a networking perspective, there are a couple of things that are important with a live migration (ex. VMotion): we want to try and preserve TCP sessions (note: this does not mean “packets don’t get dropped”) and we want to maintain optimal routing (note to server folks: you too care about these things). We would also like global mobility—basically the server admin should be able to move her VM wherever she want and not be constrained by IP addressing considerations.
Let’s build on the scenario we have been using in the prior posts, where we have a host 192.168.1.12 is chatting with a VM 172.16.4.7. Assume that we have gone through the whole map-request/map-reply process, so we have something that looks like this:
So, lets dig into LISP Routing a little more. If you have not done so, I would recommend you read my first post, since I am not going to review the concepts here. In this post, I am going to break things down into three steps: 1) how packets are forwarded (i.e. the data plane operation), 2) how mapping information is propagated (i.e. control plane operation), and 3) how we internetwork with non-LISP locations.
For starters, lets head into the weeds and take a look at the LISP header format. In the last post, I mentioned there is some flexibility in how handles IP addressing. The two examples below show a couple of scenarios: pure IPv4 and a IPv4/IPv6 hybrid: