The data center, and the role of IT, is changing. Cost pressures, technology changes, and the advent of game-changers like cloud are forcing IT executives to look at how to deliver IT differently. What we’re going to cover today is how Cisco’s Unified Data Center platform can help you evolve your data center from a cost center to a service center.Cisco’s unique unified approach in the data center can help you redefine the economics of your IT operations, so you can spend more of your resources on delivering innovation to your business. With our unified architecture, Cisco can help increase business agility, reduce CapEx and OpEx through financial efficiency, and dramatically simplify your IT operations. To set the stage for how Cisco accomplishes this, I’d like to start by looking at the current state of most IT operations. .
The challenge businesses have in implementing this vision is that a lot of their existing IT – the people and their skill base, the processes they use, even the technology they have implemented, are very silo-based—and not designed to integrate into an automated, on demand model. This is where Cisco provides tremendous value. Our strategy is to help customers evolve away from these silos, and help them evolve their people, processes, and their technologies so that they actually can deliver IT as a service and best take advantage of the trends in the data center. Note that we are NOT saying that you can (or should) fire a bunch of people. If you think back to the PBX to IP telephony transition, staff and processes were able to be redeployed against new initiatives and IT strategies. That is the promise that we believe is the core of what we can deliver.Cisco believes it is important to look an approach that doesn’t look at technologies, processes, and people in isolation. By taking a unified approach and working with technologies that are designed to work together, you are freed to move beyond convergence, enabling a powerful IT-as a service foundation that redefines data center economics and delivers performance, reliability, and business innovation. Unification is the element that will deliver that. We’ve talked about the challenges imposed by siloed technologies when you attempt to converge or virtualize these environments. Many of these server platforms and storage were not designed to work together. This necessitates expensive service engagements to build. Additionally, in order to hide the associated complexity, expensive management software has been deployed to “simplify” infrastructure deployments. This approach just doesn’t work. As you saw in the economics slide earlier, the cost of servers and associated software has skyrocketed. As layers are added, the result is increasing complexity that ultimately makes the architecture brittle and costly. Additional changes force the architecture to become more brittle over time.
Cisco’s data center infrastructure solutions that support Cisco CloudVerse are grouped into three main categories, each offers a selection of products to fit various data center needs. The Cisco Unified Data Center is composed of infrastructure solutions designed for ITaaS and Cloud.This slide provides a brief overview of these categories. It is only an overview. For detailed BDM and TDM information, please visit the Unified Data Center tab on the internal Cisco CloudVerse launch page for presentations, AAG and other information: http://wwwin.cisco.com/marketing/cloud/ These are the solutions that you will sell to support Cisco CloudVerse: Unified Management SolutionsManagement solutions simplify and automate the deployment of IT infrastructure and operate across physical and virtual resources.Unified computing management: Single management interface for hardware and software components and configurationsCisco UCS™ ManagerAutomation and orchestration: Allows policy-based, on-demand provisioning; quickly develop self-service portal and IT service catalog Cisco Intelligent Automation for CloudCisco Intelligent Automation for SAPData center network management: Optimize the overall uptime and reliability of your network to improve business continuityCisco Data Center Network ManagerNetwork services management: Policy-based solution for organizing, provisioning, and deploying network services and resources in cloudCisco Network Services ManagerUnified Fabric SolutionsFlexible network solutions deliver network services to servers, storage, and applications, providing transparent convergence, scalability, and sophisticated intelligence. Solutions include:Cisco multilayer data center switchesCisco Nexus® switchesCisco Catalyst® switchesCisco Fabric ManagerCisco NX-OS SoftwareUnified Computing SolutionsCisco’s next-generation data center system unites computing, network, storage access, and virtualization into a cohesive system designed to reduce total cost of ownership (TCO) and increase business agility. The Cisco Unified Computing System™ (Cisco UCS) is built with:Blade serversRack-mount serversFabric interconnects Virtual interface cards
Bullet1: vMotion moves VMs across physical ports—the network policy must followFrom a network perspective, one would like to have a security policy that is attached to the virtual machine as it moves. Unfortunately, today’s tools only allow for network policy to be attached to the physical server. In fact, VMware has a tool called DRS, or Dynamic Resource Scheduler, that automatically migrates the VM depending on CPU and memory loads. Regardless of the time of day, network administrators need to know what the VMs are doing. What they really need is mobile security policy attached to the VM Bullet2: Impossible to view or apply network policy to locally switched trafficThe second issue with server virtualization is the virtual switch inside the hypervisor that switches packets between virtual machines. It is actually fairly difficult to see which VM is actually talking to other VMs inside the server. Customers are demanding troubleshooting and debugging capabilities inside the server. Bullet3: Need collaboration between network and server adminThere is muddled ownership of the virtual switch. Nowadays, server admins manage the virtual switch, and they need constant communication with their nework administrator to configure the virtual switch. On one hand, Server admins want their network team to configure the virtual network. On the other hand, network admins are demanding network tools to configure the virtual switch and they want visibility down to the virtual machine.Nexus 1000V overcomes these three server virtualization issues, and accelerates datacenter virtualization.
This diagram depicts the key elements from a management standpoint that are required for IT-as-a-Service, regardless of the business applications and IT services delivered – whether it’s for a dev and test environment for your SAP applications team or a production environment for Oracle database hosting. This framework is similar to the architecture for private cloud recommended by analysts firms like Gartner and Forrester. We’re not trying to replicate all of the existing IT management systems (like your existing service desk / ticketing systems and CMDB) that you use to run your legacy data center environments. Instead, this diagram represents the new capabilities necessary for IT-as-a-Service; the mandatory requirements for this new approach include a self-service portal and orchestration, together with policy-based infrastructure resource management.At the top level of the diagram you have the self-service portal, with on-demand provisioning from a catalog of standardized IT options, governance and approvals, as well as tracking the lifecycle of service usage to prevent sprawl and to enable chargeback or showback. This portal can provide users with a unified online “menu” of options for requesting IT services, whether the infrastructure resources are hosted in your own data centers or potentially sourced externally in a hybrid cloud model.From an automation and integration standpoint, you need to combine the portal with an orchestration engine that can provision the requested service and the underlying infrastructure – with policy-based infrastructure resource management and controls across a shared pool of compute, storage, and network resources, whether physical or virtual.And finally, although IT-as-a-Service demands a new approach, it must complement your legacy systems and management tools. So this new management approach needs to integrate with the existing IT environment for operational processes including monitoring and service assurance, configuration management and a CMDB, as well as business processes like user management in your directory systems and financial management - whether you start with a showback model or evolve to pay-per-use billing and chargeback.
With Cisco’s Unified Management for cloud computing, we provide each of these key components – with Cisco Intelligent Automation for Cloud (providing self-service portal, service catalog and orchestration), Cisco Network Services Manager (for policy-based dynamic network provisioning), and Cisco UCS Manager (for policy-based infrastructure provisioning of compute resources, whether physical or virtual).The Cisco Unified Management solution complements our broad ecosystem of partners, including VCE’s Vblock (with EMC storage and VMware) as well as NetApp’s FlexPod architecture – with open APIs to integrate with the most common third party systems and infrastructure vendors in a multi-hypervisor environments – allowing you to preserve and extend the investment in your existing management tools. Our management solutions are designed to enable IT-as-a-Service, for deploying your private cloud and evolving to a hybrid cloud model. And unlike other converged infrastructure systems, you don’t need to rip and replace your existing service management and systems management tools – we’re not trying to replicate those tools, instead we provide you with the flexibility to integrate with those systems.
So, an important question would be to ask—just how much can we change the economics with Cisco Data Center. Can we get to the point where we are spending the majority of our resources and budget on business innovation? The answer is yes—and we expect to see more organizations push the envelope in this area as they continue to implement Cisco’s platform innovation. Here is just one example with which we are especially familiar—Cisco’s own data center. It has long been our practice to use our own technology. So we have been utilizing Cisco Unified Fabric and Unified Computing for a number of years as we moved from a legacy environment to one that was virtualized. In this phase alone, we were able to reduce costs by 37%. Then we began to apply Cisco Unified Management capabilities—and to continue to seek ways of leveraging the entire Unified Data Center platform to streamline and automate processes. In doing so, we were able to deliver almost 40% in additional savings and efficiencies. Beyond cost savings, there were tremendous productivity advances. For instance, in responding to a service request—we went from what used to take 6-8 weeks for what was traditionally a custom solution. As we got into the virtualization phase, we reduced it by more than half—using a manual but more standardized approach, now taking 2-3 weeks. Utilizing the Unified Data Center, however, was what enabled the most dramatic shift. Now, via self-service, a request can be completed in less than 10 minutes. And new capabilities came along with that drastic reduction in time. We gained visibility into the consumption of IT infrastructure services to ‘show back’ and ultimately charge back for the services requested by users – with pricing shared with users to demonstrate the cost and value associated with different options and tiers of service. We believe that this level of transparency and financial accountability will also be critical to businesses like yours.
Partnerships are important in any data center environment. Cisco’s differentiation with our partnerships is the level of integration, validation and testing that we’ve done across a wide range of partners. One of the biggest pain points for customers is ensuring that an application, OS and hypervisor will run effectively on the server platform. Cisco has a broad array of validated solutions across a variety of apps. Same goes for system management, which represents another huge investment by IT. Cisco also has defined what we call ‘ integrated whole offer solutions which utilize pre-packaged Unified Data Center solutions coupled with Cisco services. Whatever option you choose, it will help you obtain the benefits of Cisco Unified Data Center quickly. And customers can use these solutions as a way to expand existing data centers, as well. We also have worked very closely with partners such VCE, HDS and NetApp to build converged infrastructure platforms. These platforms have been designed to eliminateartificially integration (through management layers) and the associated non-recoverable engineering investments that customers need to make. Let’s spend a few minutes introducing those platforms as they’re a key delivery vehicle for a company’s application portfolio.
VCE is a joint venture between Cisco and EMC, along with VMware and Intel, to create pre-packaged, pre-tested infrastructure. This ships as a platform from manufacturing directly to the customer. For customers who are looking for converged infrastructure delivered to them like a product for virtualized infrastructure and cloud services– which provides benefits around simplicity and agility – Vblock provides an ideal solution. Vblock ships in a number of form factors based on the amount of compute and storage required. For the presenter, more information can be found at www.vceportal.com
FlexPod is our joint data center platform with NetApp. Bringing together NetApp storage with Cisco networking and compute, FlexPod supports a wide range of hypervisors (including Red Hat, Microsoft, VMware) and application support. As FlexPod is a reference architecture delivered through our channel ecosystem, it has enormous flexibility in how it can be sized per workload and delivered to the customer. Detailed Cisco Validated Designs tell the channel partner how to build and size a Flexpod so the customer doesn’t have to.
We also have a similar solution with HDS as many customers leverage HDS as their preferred vendor for Tier 1 storage.
There are a number of ways in which IT can build out a data center fabric and leverage fabric-based computing. The first is that they can choose to buy cisco’s best of breed products individually. Many customers will upgrade and refresh products, require new software or features, or leverage their skill sets of build out the initiative they are working on. To help them do that, Cisco has developed a reference architecture called the Virtualized Multi-service Data Center, which is designed to help customers address key technology challenges and build out their infrastructure leveraging Cisco’s best practices. Finally, customers can purchase total solutions that bring together Cisco and our technology ecosystem that feature technologies, services, support and best practices that accelerate and de-risk deployments
Cisco unified data center platform for pervasive financial services