Introduction
The Cisco Unified Computing System (Cisco UCS) is a revolutionary computing architecture designed for IT innovation and business acceleration. It enables fast IT by combining computing, networking, and storage infrastructure with management and virtualization capabilities to offer exceptional speed, simplicity, and scalability. This unique Cisco architecture provides pools of policy-based composable infrastructure that customers can optimize for traditional workloads, data analytics, and cloud-native applications, all within a common operating environment with open APIs for broad interoperability and automation. Cisco UCS has redefined computing to enhance application performance and scalability, simplify infrastructure management, reduce costs, and accelerate IT delivery to the business.
The digital business transformation is upon us, and it is creating new demands on IT organizations:
- Scalable operations: The main issue for IT organizations is managing infrastructure at scale and being able to match resources to application requirements—yet manage all of the various types of infrastructure in a simple, holistic fashion. Furthermore, the IT organization’s clients—line-of-business managers, application developers, and DevOps teams—are asserting increasing influence over the adoption, purchase, and deployment of technology. IT organizations saddled with ponderous management tools are hard-pressed to compete with the fluidity of self-service, hybrid cloud environments that their clients can purchase on their own if the IT organization doesn’t keep pace.
- IT agility: Everyone is now distributed, including IT teams. New operational models must also foster collaboration to support distributed IT expertise. Hence, they need an operating model that allows them to deploy, manage, and optimize apps and infrastructure regardless of where it is located–public, managed, edge, private cloud, and public cloud environments—all while maintaining compliance with best practices, business and governmental regulations, and data sovereignty requirements.
- Application growth and diversity: Modern applications are becoming less monolithic and more like organic entities that grow and shrink through modular, distributed microservices. This reduces dependence on traditional IT infrastructure and places new demands on IT organizations regarding the large number of endpoints to manage and the flexible infrastructure needed to support them. With agile development and DevOps deployment approaches becoming the norm, developers, and administrators demand the capability to program their own infrastructure. This is necessary to roll out new applications and updates to existing ones quickly.
- Velocity: Everything keeps moving faster – there are more apps and more diversity. That is why new solutions and delivery models are needed to keep up and accelerate the journey to a hybrid cloud.
Single Unified System
The straightforward solution to today’s infrastructure challenges is Cisco UCS. It’s not a collection of servers. It’s a fully self-aware, self-integrating system. The system is flexible, agile, and adaptable, and the portfolio of products supported by Cisco UCS includes blade, rack, modular, multinode, and storage-intensive servers. There is a fundamental difference between the vendors that sell servers and Cisco UCS. Servers arose as more powerful PC, taking many of their attributes, including the time-consuming, manual, error-prone configuration of I/O, network, and storage subsystems. Traditional servers are monolithic, complex to deploy, and even more complex to adapt to new workload demands.
In contrast, Cisco UCS is a single unified system, with fundamental attributes that transformed the industry:
- 100 percent programmable: From the very beginning, Cisco UCS was designed with the entire state of each server—identity, configuration, and connectivity—abstracted into software. This makes our system fully composable: adaptable through software to meet the varying requirements ranging from modern cloud-native workloads to traditional monolithic business applications. With a completely programmable system, you can give your clients the level of control they need to manage their workloads. The Cisco Intersight cloud operations platform gives you complete role- and policy-based control over all your resources regardless of where they reside. Fine-grained infrastructure management can be handled in Agile development and DevOps shops with scripting languages that provide access to the Cisco UCS unified application programming interface (API).
- Fabric centric: Cisco UCS was designed to blend all of the system’s I/O traffic into a single shared active-active network that carries all modes of communication from servers to the outside world. Low-latency, high-bandwidth network fabric is a shared resource so networking can be allocated to interfaces based on policies rather than physical interface configuration and hardwired-wired cabling. The result is that you can provision and balance resources to meet your workload needs easily.
- Analytics powered: What if your infrastructure talked directly with your support organization? The recommendation engine built into the Cisco Intersight software integrates with the Cisco Technical Assistance Center (TAC) to help you easily detect problems and initiate support requests. As the Cisco Intersight recommendation engine gains intelligence, our vision is for it to provide suggestions and recommendations for you to optimize your configurations to gain the most from your investment.
- Endpoint aware: Cisco UCS was developed in the virtualization era, where the norm was multiple independent workloads running on the same server. Today the number of workloads has become practically unimaginable as containerized environments place hundreds of workloads in a single virtual machine. Whether you run virtualized, containerized, or bare-metal workloads, all I/O is virtualized. This gives you the capability to support a massive number of endpoints but with a level of control equivalent to each endpoint having its own dedicated (but virtual) cable to the outside world. This gives you the scale of virtualized, with the workload isolation and security of the physical world.
- Intent based: Intersight software helps you to more precisely align your infrastructure with the needs of your business and respond in real time to optimize application performance. It enables administrators to automate configurations or tasks based on specific requirements that are tied to business objectives and application performance. Rather than having to be concerned with every detail of system configuration, intent-based management enables you to describe what you want to accomplish, with the cloud-based automation we provide translating your intent into action. Once your applications are up and running, you can use the Intersight Workload Optimizer (IWO) to provide correlated insight into your application components and the resources they use for real-time adjustments that help ensure application performance.
Stateless Compute
The service profile decouples a server identity and configuration from the hardware, which gives you the maximum amount of flexibility and control. It allows you to override the identity values that are on the server at the time of association and use the resource pools and policies set up in Cisco UCS Manager to automate some administration tasks.
You can disassociate this service profile from one server and then associate it with another server. This re-association can be done manually or through an automated server pool policy. The burned-in settings, such as a universally unique identifier (UUID) and MAC address, on the new server, are overwritten with the configuration in the service profile. As a result, the change in server is transparent to your network. You do not need to reconfigure any component or application on your network to begin using the new server.
Service profile allows you to take advantage of and manage system resources through resource pools and policies, such as the following:
- Virtualized identity information, including pools of MAC addresses, world wide name (WWN) addresses, and UUIDs
- Ethernet and Fibre Channel adapter profile policies
- Firmware package policies
- Operating system boot order policies
Unless the service profile contains power management policies, a server pool qualification policy, or another policy that requires a specific hardware configuration, the profile can be used for any type of server in the Cisco UCS instance.
You can associate these service profiles with either a rack-mount server or a blade server. The ability to migrate the service profile depends upon whether you choose to restrict migration of the service profile.
With a service profile template, you can quickly create several service profiles with the same basic parameters, such as the number of network interface cards (vNICs) and virtual host bus adapters (vHBAs), and with identity information drawn from the same pools.
Unified Fabric
Cisco UCS Fabric Interconnects provide a single point of connectivity and management for a system. Deployed as an active-active pair, the system’s fabric interconnects integrate all components into a single, highly available connectivity domain. The fabric interconnects manage all I/O efficiently and securely at a single point, resulting in deterministic I/O latency regardless of a server or virtual machine’s topological location in the system. Cisco Fabric Interconnects support low-latency, line-rate, lossless Ethernet, and Fibre Channel over Ethernet (FCoE) connectivity.
The Cisco UCS network fabric is implemented with an end-to-end architecture that uses Cisco Unified Fabric and Cisco Fabric Extender (FEX) Technology to connect every Cisco UCS component with a single network and a single network layer. The result is a single, large, virtual blade server chassis that can accommodate both blade and rack servers and connect any two entities, physical or virtual, with a single network hop.
Cisco UCS Fabric Interconnects deployed in a traditional Cisco UCS fabric can be used for traditional connectivity to a two-tier network using a core and aggregation network topology or a spine-and-leaf topology. Cisco UCS Fabric Interconnects deployed in a traditional Cisco UCS fabric. SANs and upstream enterprise switches connect to the fabric interconnects, and the embedded Cisco UCS Manager provides management for the stateless fabric. Cisco Fabric Extenders can be simultaneously connected to Cisco UCS Fabric Interconnects, providing a convenient transition to newer generation fabrics without requiring upgrades for infrastructure that doesn’t need the additional bandwidth.
A single network layer brings the unified fabric to every blade chassis and server rack. FEX Technology reduces three network layers to one, eliminating hypervisor switches and blade-chassis-resident switches and replacing them with a single point of management and connectivity. In Cisco UCS, low-cost, low-power, and zero-management Cisco UCS and Cisco Nexus fabric extenders pass all traffic from servers and virtual machines to the system’s fabric interconnects. This approach reduces infrastructure cost for each server and interconnects servers with a single hop, in contrast to the multiple hops and higher latency inherent in traditional environments. The combination of the system’s fabric interconnects, fabric extenders, and Cisco UCS virtual interface cards (VICs) establishes a centrally managed yet physically distributed system that can contain both blade and rack servers.
Cisco VICs directly connect the network to physical rack and blade servers and virtual machines. Static PCI Express (PCIe) interfaces are configured on demand to adapt servers to meet the best-practice needs of any operating system or hypervisor, providing the network interface card (NICs) and host bus adapters (HBAs) they need without requiring any special driver software. Dynamic interfaces are configured and attached to virtual machines, giving them direct access to the network. After they are attached, a virtual machine’s network interfaces migrate from server to server along with the virtual machine, simplifying virtual network management and providing air-gap security to virtual environments. Every network link has the same security as if it were a physical cable.
Within a Cisco UCS instance, every interface on a Cisco VIC (or on a third-party converged network adapter [CNA]) is terminated at a virtual interface within the fabric interconnect. Virtual interfaces are not permanently bound to a specific physical interface on the fabric interconnect. Simply by changing the virtual-to-physical mapping in the fabric interconnect, you can move vNICs from server to server. Terminating every connection at a virtual interface allows physical and virtual machines to be treated equivalently, with the same visibility and control as a physical network. This approach securely isolates each link and subjects each link to quality of service (QoS) controls as if the traffic were traversing its own physical cable.