ONS summit 2014 starts Monday March 3, and for me it is my first time here. It hardly feels that way. For us in Cisco ACI (Application Centric Infrastructure) team, it is busy last few days as we are putting final touches to showcase our exciting ACI solutions, demos and presentations to customers at this premier SDN event. Early in 2014, Cisco ACI expert Mike Cohen has made insightful predictions on what awaits SDN in 2014 – Read his Blog
Mike zeroes in on key Data Center use cases for SDN, starting with Application Deployment Acceleration securely and at scale. No one can disagree with this. L4-L7 services chaining for physical and virtual devices is another killer use-case Mike enlightens the reader with, and at the ONS Solutions Expo this year, we are showing exciting demos to illustrate service automation using dynamic L4-L7 service chaining. Do not miss out our demos at Cisco Booth 302. We are also showing demos focused on Open Stack integration with ACI, another area of growing interest.
I strongly recommend you to attend Mike’s Theater presentation titled, “Role of Policy in SDN” on March 5, 12.40 PM. Learn all the benefits and value-props that a declarative policy based ACI approach brings to network operations that is today crippled by imperative management, lack of scalability and flexibility. You will be excited to discover how our Cisco ACI team is working with Open Stack, Open Daylight initiatives and driving an open eco-system. Mike will also touch on how ACI helps bring visibility across both physical and virtual infrastructures, and how today’s SDN network overlay problems can be overcome. Shashi Kiran posted a fantastic blog on SDN overlays in ACI deployments, last week, and it makes compelling read in the context of Mike’s session.
We wish you a great ONS summit this year and look forward to seeing you at Cisco Booth 302
Tags: ACI, Cisco ACI, Cisco APIC, L4-L7 service chaining, Open Daylight, Open Stack, SDN
This is a two-part blog series developed in association with Tom Edsall, a Cisco Fellow and CTO of Insieme Networks, recently acquired by Cisco Systems. The intent is to elaborate on foundational design principles of Application Centric Infrastructure (ACI), a transformational approach for next-generation and cloud deployments. While the vision of ACI is an expansive one, this blog series focuses on the role of SDN overlays, their deployment considerations, as well as benefits that customers could derive from the unique implementation of overlays in an ACI solution.
The philosophy of Application Centric Infrastructure
Cisco’s Application Centric Infrastructure approach focuses on the most important thing in the data-center: applications. Without applications, we would not even need a data center at all! Everything we do in the data center ultimately is used to support those applications and the data that they work on because that is what ultimately drives business value.
The modern data center must be able to deploy applications rapidly, using any and all resources (compute, storage, network) available in the data center at any time. It must also be possible to grow, shrink, and move applications as needed. This will drive business agility and efficient use of resources.
The problem is that classical networking systems were developed in a world where there was less focus on any application anywhere, any time. Instead the focus was on on building large, static, IP networks.
Our solution was to create an application centric infrastructure where the emphasis is on the application rather than on the network. In order to do this we had to change the abstraction of the network from one that is, well, network centric to one that is application centric. In addition, we had to employ some SDN techniques to change the network from a traditional static infrastructure to a more dynamic, agile, flexible infrastructure. Let’s look into some of these techniques in detail.
Integrating SDN concepts
We employ two important concepts used in typical SDN solutions: overlays and a centralized controller. Overlays give us network flexibility that was never possible before by separating the location of a device from its identity. The centralized controller gives us consistent network behavior wherever an application is deployed, the application centric abstraction of the network, and a single point of control. While these benefits are important, even fundamental, to building a data center capable of supporting the business requirements of application agility, they also introduce their own set of problems in traditional SDN deployments that must be addressed. We will discuss these issues and their solutions shortly.
The SDN overlay and application abstraction is built on top of networking hardware that must move data across the data center quickly and efficiently without requiring changes to the applications, servers or storage elements attached to it. The hardware must do this in an efficient, reliable manner and provide as much assistance as possible to the network operator when troubleshooting and monitoring those applications as they use the network. Lastly, this hardware must be cost effective, power efficient, and space efficient.
Read More »
Tags: ACI, application centric infrastructure, SDN Overlays, Shashi Kiran, Tom Edsall, VXLAN
As I was thinking about how best to advise you on how to “experiment” with SDN technologies, and more specifically why you should run a formal pilot to evaluate SDN technology options (a topic I covered in my previous blog), I was reminded of this “wipeout” picture I took last year at a “freeride” competition – the “Coe Cup“ -- at my local ski mountain, Glencoe Moutain Resort, here in the UK. Let me tell you why!
Why you may want to “pilot” new technology adoption!
Tags: ACI, Cisco onePK, cisco_services, network virtualization, OpenFlow, SDN, software defined network
Business intelligence begets better, more informed decision making—and, ultimately, success. But how do you get effective business intelligence? It starts with your tools and infrastructure…
With the proliferation of database and virtualization sprawl and the growing requirement for business insight that has increased I/O performance demand and complexity in the datacenter, enterprises are asking for a simplified approach. Cisco UCS offers industry-leading performance along with the flexible infrastructure you need to deploy, manage, move to the cloud and scale your bare metal or virtual SQL Server workloads
On March 18, join Industry thought leaders from Cisco, Microsoft, NetApp, EMC, and DesignMind to explore how Microsoft SQL Server and integrated infrastructures such as FlexPod and VSPEX enable you to more effectively turn data into a valuable strategic asset for business decision makers.
Make plans today to join us and learn how these infrastructures can help you:
- Make sure optimal access to mission-critical data is available
- Enable greater business agility
- Increase cost-efficiency and lower TCO for business intelligence initiatives
Read More »
Tags: Cisco, EMC, FlexPod, Microsoft, Microsoft SQL Server, netapp, vspex
So what exactly can you do in 16 minutes? Well, you can:
- Download and install your preferred tax prep software, because (if you’re in the US or Canada) April is coming
- Enjoy your 15 minutes of fame, then reminisce and/or lament about it for exactly 1 minute.
- Save 15% on your car insurance (you can supposedly get this done in 15 vs. 16 min.)
- Do some really unsavory things not suitable for mentioning on a nice blog post like this one.
Don’t care about any of those things? Neither do I. Let me come back to this in a moment…
If you’re familiar with our architecture portfolio for desktop virtualization, you may be aware that we’re continuing to invest in VSPEX-based reference architectures for Cisco Desktop Virtualization. This week, we just announced the latest addition to the Cisco Validated Design (CVD) portfolio – our solution for VMware Horizon View 5.3 with Cisco UCS and EMC VSPEX available here.
If you’re not already familiar with them, CVD’s provide prescriptive design guidance around how to build solutions with specific outcomes (performance) as documented through a testing/documentation discipline that Cisco’s been doing for years. You’ll find our repository of desktop virtualization CVD’s here.
So now let’s talk about the CVD itself. Our principal author is Ramesh Guduru – he’s a Virtualization Systems Engineer in Cisco’s Data Center Business Group and has extensive experience in Horizon View, virtualization infrastructure and management, Cisco UCS and storage. Ramesh assembled a test platform based on the setup shown in Figure 1.
Figure 1: Cisco CVD Validation Platform
As you can see the core pillars of the solution are:
Key things we wanted to expose/profile in this effort included:
- More with less – more powerful processors and faster memory
- System footprint for delivering 2,000 Horizon View desktops, while still retaining room to expand as demand increases
- Leverage more economical processors – ex: a 57% lower list price for the Intel E5-2680 v2 10-core processors vs. top bin processors tested in the past = lower server cost = lower per desktop CAPEX
- Hosting density leadership (# desktops per compute blade)
- End user experience as exercised using LoginVSI with medium workload with Flash
- Boot-up and login performance (simulating the Monday-morning boot storm dilemma all VDI implementations face and daily login storms)·
From a design perspective we also wanted to ensure our system provided:
- Full n+1 fault tolerance across the stack
- Fully virtualized platform, inclusive of the virtual desktops, as well as the infrastructure componentry like vCenter, AD, SQL servers etc.
I’ll leave it to you the explore the methodology Ramesh followed for the CVD, but let me point to a couple interesting things gained from this effort:
- With our B200 M3 blade, we increased our desktop workload capacity (across the system) by 30% compared with full-width blades used in prior analyses
- We collapsed the footprint from 30 RU down to just 12 RU.
- The combined effect of the selected CPU (Intel Ivy Bridge), high-bandwidth, low-latency unified fabric, and our VIC 1240 converged networking adapter yielded exceptional user experience at under 1.75 sec at full load.
- The EMC VNX5600 provided outstanding storage performance for both file and block, using EMC Fast Cache technology.
- VMware Horizon View 5.3 with Sparse Virtual Disk gave us better disk performance and disk space efficiency.
And as for the 16 minute thing?
- That’s how long it took for the full population of 2,000 virtual desktops to get booted and ready to login (under 16 minutes). And in an additional 14 we had all of them running user workload with no sign of exhausting the system.
Get the details by digging into the CVD posted here
Tags: EMC, horizon view, UCS, vdi, VMware, vspex