Computing that’s purpose-built for a more energy-efficient, AI-driven future

Just as humans use patterns as mental shortcuts for solving complex problems, AI is about recognizing patterns to distill actionable insights. Now think about how this applies to the data center, where patterns have developed over decades. You have cycles where we use software to solve problems, then hardware innovations enable new software to focus on the next problem. The pendulum swings back and forth repeatedly, with each swing representing a disruptive technology that changes and redefines how we get work done with our developers and with data center infrastructure and operations teams.

AI is clearly the latest pendulum swing and disruptive technology that requires advancements in both hardware and software. GPUs are all the rage today due to the public debut of ChatGPT – but GPUs have been around for a long time. I was a GPU user back in the 1990s because these powerful chips enabled me to play 3D games that required fast processing to calculate things like where all those polygons should be in space, updating visuals fast with each frame.

In technical terms, GPUs can process many parallel floating-point operations faster than standard CPUs and in large part that is their superpower. It’s worth noting that many AI workloads can be optimized to run on a high-performance CPU.  But unlike the CPU, GPUs are free from the responsibility of making all the other subsystems within compute work with each other. Software developers and data scientists can leverage software like CUDA and its development tools to harness the power of GPUs and use all that parallel processing capability to solve some of the world’s most complex problems.

A new way to look at your AI needs

Unlike single, heterogenous infrastructure use cases like virtualization, there are multiple patterns within AI that come with different infrastructure needs in the data center. Organizations can think about AI use cases in terms of three main buckets:

1. Build the model, for large foundational training.

2. Optimize the model, for fine-tuning a pre-trained model with specific data sets.

3. Use the model, for inferencing insights from new data.

The least demanding workloads are optimize and use the model because most of the work can be done in a single box with multiple GPUs. The most intensive, disruptive, and expensive workload is build the model. In general, if you’re looking to train these models at scale you need an environment that can support many GPUs across many servers, networking together for individual GPUs that behave as a single processing unit to solve highly complex problems, faster.

This makes the network critical for training use cases and introduces all kinds of challenges to data center infrastructure and operations, especially if the underlying facility was not built for AI from inception. And most organizations today are not looking to build new data centers.

Therefore, organizations building out their AI data center strategies will have to answer important questions like:

• What AI use cases do you need to support, and based on the business outcomes you need to deliver, where do they fall into the build the model, optimize the model, and use the model buckets?
• Where is the data you need, and where is the best location to enable these use cases to optimize outcomes and minimize the costs?
• Do you need to deliver more power? Are your facilities able to cool these types of workloads with existing methods or do you require new methods like water cooling?
• Finally, what is the impact on your organization’s sustainability goals?

The power of Cisco Compute solutions for AI

As the general manager and senior vice president for Cisco’s compute business, I’m happy to say that Cisco UCS servers are designed for demanding use cases like AI fine-tuning and inferencing, VDI, and many others. With its future-ready, highly modular architecture, Cisco UCS empowers our customers with a blend of high-performance CPUs, optional GPU acceleration, and software-defined automation. This translates to efficient resource allocation for diverse workloads and streamlined management through Cisco Intersight. You can say that with UCS, you get the muscle to power your creativity and the brains to optimize its use for groundbreaking AI use cases.

But Cisco is one player in a wide ecosystem. Technology and solution partners have long been a key to our success, and this is certainly no different in our strategy for AI. This strategy revolves around driving maximum customer value to harness the full long-term potential behind each partnership, which enables us to combine the best of compute and networking with the best tools in AI.

This is the case in our strategic partnerships with NVIDIA, Intel, AMD, Red Hat, and others. One key deliverable has been the steady stream of Cisco Validated Designs (CVDs) that provide pre-configured solution blueprints that simplify integrating AI workloads into existing IT infrastructure. CVDs eliminate the need for our customers to build their AI infrastructure from scratch. This translates to faster deployment times and reduced risks associated with complex infrastructure configurations and deployments.

Another key pillar of our AI computing strategy is offering customers a diversity of solution options that include standalone blade and rack-based servers, converged infrastructure, and hyperconverged infrastructure (HCI). These options enable customers to address a variety of use cases and deployment domains throughout their hybrid multicloud environments – from centralized data centers to edge end points. Here are just a couple of examples:

• Converged infrastructures with partners like NetApp and Pure Storage offer a strong foundation for the full lifecycle of AI development from training AI models to day-to-day operations of AI workloads in production environments. For highly demanding AI use cases like scientific research or complex financial simulations, our converged infrastructures can be customized and upgraded to provide the scalability and flexibility needed to handle these computationally intensive workloads efficiently.
• We also offer an HCI option through our strategic partnership with Nutanix that is well-suited for hybrid and multi-cloud environments through the cloud-native designs of Nutanix solutions. This allows our customers to seamlessly extend their AI workloads across on-premises infrastructure and public cloud resources, for optimal performance and cost efficiency. This solution is also ideal for edge deployments, where real-time data processing is crucial.

AI Infrastructure with sustainability in mind 

Cisco’s engineering teams are focused on embedding energy management, software and hardware sustainability, and business model transformation into everything we do. Together with energy optimization, these new innovations will have the potential to help more customers accelerate their sustainability goals.

Working in tandem with engineering teams across Cisco, Denise Lee leads Cisco’s Engineering Sustainability Office with a mission to deliver more sustainable products and solutions to our customers and partners. With electricity usage from data centers, AI, and the cryptocurrency sector potentially doubling by 2026, according to a recent International Energy Agency report, we are at a pivotal moment where AI, data centers, and energy efficiency must come together. AI data center ecosystems must be designed with sustainability in mind. Denise outlined the systems design thinking that highlights the opportunities for data center energy efficiency across performance, cooling, and power in her recent blog, Reimagine Your Data Center for Responsible AI Deployments.

Recognition for Cisco’s efforts have already begun. Cisco’s UCS X-series has received the Sustainable Product of the Year by SEAL Awards and an Energy Star rating from the U.S. Environmental Protection Agency. And Cisco continues to focus on critical features in our portfolio through agreement on product sustainability requirements to address the demands on data centers in the years ahead.

Look ahead to Cisco Live

We are just a couple of months away from Cisco Live US, our premier customer event and showcase for the many different and exciting innovations from Cisco and our technology and solution partners. We will be sharing many exciting Cisco Compute solutions for AI and other uses cases. Our Sustainability Zone will feature a virtual tour through a modernized Cisco data center where you can learn about Cisco compute technologies and their sustainability benefits. I’ll share more details in my next blog closer to the event.

Source: cisco.com

Continue reading

Experience Eco-Friendly Data Center Efficiency with Cisco’s Unified Computing System (UCS)

In the highly dynamic and ever-evolving world of enterprise computing, data centers serve as the backbones of operations, driving the need for powerful, scalable, and energy-efficient server solutions. As businesses continuously strive to refine their IT ecosystems, recognizing and capitalizing on data center energy-saving attributes and design innovations is essential for fostering sustainable development and maximizing operational efficiency and effectiveness.

Cisco’s Unified Computing System (UCS) stands at the forefront of this technological landscape, offering a comprehensive portfolio of server options tailored to meet the most diverse of requirements. Each component of the UCS family, including the B-Series, C-Series, HyperFlex, and X-Series, is designed with energy efficiency in mind, delivering performance while mitigating energy use. Energy efficiency is a major consideration, starting from the beginning of the planning and design phases of these technologies and products all the way through into each update.

The UCS Blade Servers and Chassis (B-Series) provide a harmonious blend of integration and dense computing power, while the UCS Rack-Mount Servers (C-Series) offer versatility and incremental scalability. These offerings are complemented by Cisco’s UCS HyperFlex Systems, the next-generation of hyper-converged infrastructure that brings compute, storage, and networking into a cohesive, highly efficient platform. Furthermore, the UCS X-Series takes flexibility and efficiency to new heights with its modular, future-proof architecture.

Cisco UCS B-Series Blade Chassis and Servers

The Cisco UCS B-Series Blade Chassis and Servers offer several features and design elements that contribute to greater energy efficiency compared to traditional blade server chassis. The following components and functions of UCS contribute to this efficiency:

1. Unified Design: Cisco UCS incorporates a unified system that integrates computing, networking, storage access, and virtualization resources into a single, cohesive architecture. This integration reduces the number of physical components needed, leading to lower power consumption compared to traditional setups where these elements are usually separate and require additional power.

2. Power Management: UCS includes sophisticated power management capabilities at both the hardware and software levels. This enables dynamic power allocation based on workload demands, allowing unused resources to be powered down or put into a low-power state. By adjusting power usage according to actual requirements, the wasting of energy is minimized.

3. Efficient Cooling: The blade servers and chassis are designed to optimize airflow and cooling efficiency. This reduces the need for excessive cooling, which can be a significant contributor to energy consumption in data centers. By efficiently managing airflow and cooling, Cisco UCS helps minimize the overall energy required for server operation.

4. Higher Density: UCS Blade Series Chassis typically support higher server densities compared to traditional blade server chassis. By consolidating more computing power into a smaller physical footprint, organizations can achieve greater efficiency in terms of space utilization, power consumption, and cooling requirements.

5. Virtualization Support: Cisco UCS is designed to work seamlessly with virtualization technologies such as VMware, Microsoft Hyper-V, and others. Virtualization allows for better utilization of server resources by running multiple virtual machines (VMs) on a single physical server. This consolidation reduces the total number of servers needed, thereby lowering energy consumption across the data center.

6. Power capping and monitoring: UCS provides features for power capping and monitoring, allowing administrators to set maximum power limits for individual servers or groups of servers. This helps prevent power spikes and ensures that power usage remains within predefined thresholds, thus optimizing energy efficiency.

7. Efficient Hardware Components: UCS incorporates energy-efficient hardware components such as processors, memory modules, and power supplies. These components are designed to deliver high performance while minimizing power consumption, contributing to overall energy efficiency.

Cisco UCS Blade Series Chassis and Servers facilitate greater energy efficiency through a combination of unified design, power management capabilities, efficient cooling, higher physical density, support for virtualization, and the use of energy-efficient hardware components. By leveraging these features, organizations can reduce their overall energy consumption and operational costs in the data center.

Cisco UCS C-Series Rack Servers

Cisco UCS C-Series Rack Servers are standalone servers that tend to be more flexible in terms of deployment and may be easier to cool individually. They are often more efficient in environments where fewer servers are required or when full utilization of a blade chassis is not possible. In such cases, deploying a few rack servers can be more energy-efficient than powering a partially empty blade chassis.

The Cisco UCS Rack Servers, like the Blade Series, have been designed with energy efficiency in mind. The following aspects contribute to the energy efficiency of UCS Rack Servers:

1. Modular Design: UCS Rack Servers are built with a modular design that allows for easy expansion and servicing. This means that components can be added or replaced as needed without unnecessary wasting resources.

2. Component Efficiency: Like the Blade Series, UCS Rack Servers use high-efficiency power supplies, voltage regulators, and cooling fans. These components are chosen for their ability to deliver performance while minimizing energy consumption.

3. Thermal Design: The physical design of the UCS Rack Servers helps to optimize airflow, which can reduce the need for excessive cooling. Proper thermal management ensures that the servers maintain an optimal operating temperature, which contributes to energy savings.

4. Advanced CPUs: UCS Rack Servers are equipped with the latest processors that offer a balance between performance and power usage. These CPUs often include features that reduce power consumption when full performance is not required.

5. Energy Star Certification: Many UCS Rack Servers are Energy Star certified, meaning they meet strict energy efficiency guidelines set by the U.S. Environmental Protection Agency.

6. Management Software: Cisco’s management software allows for detailed monitoring and control of power usage across UCS Rack Servers. This software can help identify underutilized resources and optimize power settings based on the workload.

Cisco UCS Rack Servers are designed with energy efficiency as a core principle. They feature a modular design that enables easy expansion and servicing, high-efficiency components such as power supplies and cooling fans, and processors that balance performance with power consumption. The thermal design of these rack servers optimizes airflow, contributing to reduced cooling needs.

Additionally, many UCS Rack Servers have earned Energy Star certification, indicating compliance with stringent energy efficiency guidelines. Management software further enhances energy savings by allowing detailed monitoring and control over power usage, ensuring that resources are optimized according to workload demands. These factors make UCS Rack Servers a suitable choice for data centers focused on minimizing energy consumption while maintaining high performance.

Cisco UCS S-Series Storage Servers

The Cisco UCS S-Series servers are engineered to offer high-density storage solutions with scalability, which leads to considerable energy efficiency benefits when compared to the UCS B-Series blade servers and C-Series rack servers. The B-Series focuses on optimizing compute density and network integration in a blade server form factor, while the C-Series provides versatile rack-mount server solutions. In contrast, the S-Series emphasizes storage density and capacity.

Each series has its unique design optimizations; however, the S-Series can often consolidate storage and compute resources more effectively, potentially reducing the overall energy footprint by minimizing the need for additional servers and standalone storage units. This consolidation is a key factor in achieving greater energy efficiency within data centers.

The UCS S-Series servers incorporate the following features that contribute to energy efficiency:

1. Efficient Hardware Components: Similar to other Cisco UCS servers, the UCS S-Series servers utilize energy-efficient hardware components such as processors, memory modules, and power supplies. These components are designed to provide high performance while minimizing power consumption, thereby improving energy efficiency.
2. Scalability and Flexibility: S-Series servers are highly scalable and offer flexible configurations to meet diverse workload requirements. This scalability allows engineers to right-size their infrastructure and avoid over-provisioning, which often leads to wasteful energy consumption.
3. Storage Optimization: UCS S-Series servers are optimized for storage-intensive workloads by offering high-density storage options within a compact form factor. With consolidated storage resources via fewer physical devices, organizations can reduce power consumption associated with managing and powering multiple storage systems.
4. Power Management Features: S-Series servers incorporate power management features similar to other UCS servers, allowing administrators to monitor and control power usage at both the server and chassis levels. These features enable organizations to optimize power consumption based on workload demands, reducing energy waste.
5. Unified Management: UCS S-Series servers are part of the Cisco Unified Computing System, which provides unified management capabilities for the entire infrastructure, including compute, storage, and networking components. This centralized management approach helps administrators efficiently monitor and optimize energy usage across the data center.

Cisco UCS HyperFlex HX-Series Servers

The Cisco HyperFlex HX-Series represents a fully integrated and hyperconverged infrastructure system that combines computing, storage, and networking into a simplified, scalable, and high-performance architecture designed to handle a wide array of workloads and applications.

When it comes to energy efficiency, the HyperFlex HX-Series stands out by further consolidating data center functions and streamlining resource management compared to the traditional UCS B-Series, C-Series, and S-Series. Unlike the B-Series blade servers which prioritize compute density, the C-Series rack servers which offer flexibility, or the S-Series storage servers which focus on high-density storage, the HX-Series incorporates all of these aspects into a cohesive unit. By doing so, it reduces the need for separate storage and compute layers, leading to potentially lower power and cooling requirements.

The integration inherent in hyperconverged infrastructure, such as the HX-Series, often results in higher efficiency and a smaller energy footprint as it reduces the number of physical components required, maximizes resource utilization, and optimizes workload distribution; all of this contributes to a more energy-conscious data center environment.

The HyperFlex can contribute to energy efficiency in the following ways:

1. Consolidation of Resources: HyperFlex integrates compute, storage, and networking resources into a single platform, eliminating the need for separate hardware components such as standalone servers, storage arrays, and networking switches. By consolidating these resources, organizations can reduce overall power consumption when compared to traditional infrastructure setups that require separate instances of these components.
2. Efficient Hardware Components: HyperFlex HX-Series Servers are designed to incorporate energy-efficient hardware components such as processors, memory modules, and power supplies. These components are optimized for performance, per watt, helping to minimize power consumption while delivering the necessary robust compute and storage capabilities.
3. Dynamic Resource Allocation: HyperFlex platforms often include features for dynamic resource allocation and optimization. This may include technologies such as VMware Distributed Resource Scheduler (DRS) or Cisco Intersight Workload Optimizer, which intelligently distribute workloads across the infrastructure to maximize resource utilization and minimize energy waste.
4. Software-Defined Storage Efficiency: HyperFlex utilizes software-defined storage (SDS) technology, which allows for more efficient use of storage resources compared to traditional storage solutions. Features such as deduplication, compression, and thin provisioning help to reduce the overall storage footprint, resulting in lower power consumption associated with storage devices.
5. Integrated Management and Automation: HyperFlex platforms typically include centralized management and automation capabilities that enable administrators to efficiently monitor and control the entire infrastructure from a single interface. This combined integration management approach can streamline operations, optimize resource usage, and identify opportunities for energy saving.
6. Scalability and Right-Sizing: HyperFlex allows organizations to scale resources incrementally by adding additional server nodes to the cluster as needed. This scalability enables organizations to custom fit their infrastructure and avoid over-provisioning, which can lead to unnecessary energy consumption.
7. Efficient Cooling Design: HyperFlex systems are designed with extreme consideration for efficient cooling to maintain optimal operating temperatures for the hardware components. By optimizing airflow and cooling mechanisms within the infrastructure, HyperFlex helps minimize energy consumption associated with cooling systems.

Cisco UCS X-Series Modular System

The Cisco UCS X-Series is a versatile and innovative computing platform that elevates the concept of a modular system to new heights, offering a flexible, future-ready solution for the modern data center. It stands apart from the traditional UCS B-Series blade servers, C-Series rack servers, S-Series storage servers, and even the integrated HyperFlex HX-Series hyperconverged systems, in that it provides a unique blend of adaptability and scalability. The X-Series is designed with a composable infrastructure that allows dynamic reconfiguration of computing, storage, and I/O resources to match specific workload requirements.

In terms of energy efficiency, the UCS X-Series is engineered to streamline power usage by dynamically adapting to the demands of various applications. It achieves this through a technology that allows components to be powered on and off independently, which can lead to significant energy savings compared to the always-on nature of B-Series and C-Series servers. While the S-Series servers are optimized for high-density storage, the X-Series can reduce the need for separate high-capacity storage systems by incorporating storage elements directly into its composable framework. Furthermore, compared to the HyperFlex HX-Series, the UCS X-Series may offer even more granular control over resource allocation, potentially leading to even better energy management and waste reduction.

The UCS X-Series platform aims to set a new standard for sustainability by optimizing power consumption across diverse workloads, minimizing the environmental impact, and lowering the total cost of ownership (TCO) through improved energy efficiency. By intelligently consolidating and optimizing resources, the X-Series promises, and has proven to be, a forward-looking solution that responds to the growing need for eco-friendly and cost-effective data center operations.

The Cisco UCS X-Series can contribute to energy efficiency in the following ways:

1. Integrated Architecture: Cisco UCS X-Series combines compute, storage, and networking into a unified system, reducing the need for seperate components. This consolidation leads to lower overall energy consumption compared to traditional data center architectures.
2. Energy-Efficient Components: The UCS X-Series is built with the latest energy-efficient technologies; CPUs, memory modules, and power supplies in the X-Series are selected for their performance-to-power consumption ratio, ensuring that energy use is optimized without sacrificing performance.
3. Intelligent Workload Placement: Cisco UCS X-Series can utilize Cisco Intersight and other intelligent resource management tools to distribute workloads intelligently and efficiently across available resources, optimizing power usage and reducing unnecessary energy expenditure.
4. Software-Defined Storage Benefits: The X-Series can leverage software-defined storage which often includes features like deduplication, compression, and thin provisioning to make storage operations more efficient and reduce the energy needed for data storage.
5. Automated Management: With Cisco Intersight, the X-Series provides automated management and orchestration across the infrastructure, helping to streamline operations, reduce manual intervention, and cut down on energy usage through improved allocation of resources.
6. Scalable Infrastructure: The modular design of the UCS X-Series allows for easy scalability, thus allowing organizations to add resources only as needed. This helps prevent over-provisioning and the energy costs associated with idle equipment.
7. Optimized Cooling: The X-Series chassis is designed with cooling efficiency in mind, using advanced airflow management and heat sinks to keep components at optimal temperatures. This reduces the amount of energy needed for cooling infrastructure.

Mindful energy consumption without compromise

Cisco’s UCS offers a robust and diverse suite of server solutions, each engineered to address the specific demands of modern-day data centers with a sharp focus on energy efficiency. The UCS B-Series and C-Series each bring distinct advantages in terms of integration, computing density, and flexible scalability, while the S-Series specializes in high-density storage capabilities. The HyperFlex HX-Series advances the convergence of compute, storage, and networking, streamlining data center operations and energy consumption. Finally, the UCS X-Series represents the pinnacle of modularity and future-proof design, delivering unparalleled flexibility to dynamically meet the shifting demands of enterprise workloads.

Across this entire portfolio, from the B-Series to the X-Series, Cisco has infused an ethos of sustainability, incorporating energy-efficient hardware, advanced power management, and intelligent cooling designs. By optimizing the use of resources, embracing virtualization, and enabling scalable, granular infrastructure deployments, Cisco’s UCS platforms are not just powerful computing solutions but are also catalysts for energy-conscious, cost-effective, and environmentally responsible data center operations.

For organizations navigating the complexities of digital transformation while balancing operational efficiency with the goal of sustainability, the Cisco UCS lineup stands ready to deliver performance that powers growth without compromising on our commitment to a greener future.

Continue reading

Cisco Intersight Gets a New Look

New User Interface Signals Milestone for Hybrid Cloud Operations Platform

Cisco Intersight, Cisco’s hybrid cloud operations platform, passed a major milestone with the recent release of its new user interface (UI). The UI introduces Cisco’s new branding for its Cloud Networking and Computing software portfolio, brings Nexus Cloud (Cisco’s cloud-managed platform for networking) into the Intersight platform, and improves readability and task findability.

Consistent User Experience

“One of our priorities for the software-as-a-service offerings in Cisco’s Networking and Computing portfolio is to provide a consistent and familiar user experience, no matter which product someone’s using,” said Jeff New, Cisco Intersight Product Manager. Intersight is the first platform to introduce Cisco’s common UI that will be rolled out across its data center computing, networking, and security solutions to provide a more consistent experience for customers.

Cloud Networking, Newest Intersight Platform Service

Intersight’s new UI also introduces cloud-managed networking as the platform’s newest IT operations service. This signals the next step in the platform’s vision to simplify IT operations through a cloud operations model that extends the principles of the cloud to the entire cloud/network IT stack. Nexus Cloud will debut as a service on Cisco Intersight following its current tech preview.

Intersight users can select the IT operations functions they need to perform using the multi-service selector

To easily access Intersight’s services, the new UI introduces a multi-service selector. From the selector, users can choose:

◉ Infrastructure Service – visualize, control, and automate Cisco UCS, HyperFlex, and third-party computing devices

◉ Cloud Orchestrator – automate workflows with a drag-and-drop designer to accelerate delivery of apps and infrastructure

◉ Workload Optimizer – ensure applications get resources when and where needed, at the lowest cost

Nexus Cloud – deploy, manage, and operate your Cisco Nexus networks from the cloud

◉ My Dashboard – personalize a multi-service dashboard using widgets for capabilities across the services on the Intersight platform

◉ System – Claim devices, licensing, identity access management, and other account settings

Intersight users will have access to the functions they have licensed and their corresponding permissions. Once users are in a specific service, they’ll find capabilities in a familiar way.

Command Palette – Get to Actions and Information Quickly

Intersight is a comprehensive solution for hybrid cloud operations with a robust feature set. Intersight users have asked for a faster way to find specific objects in their environments as well as the actions they want to take.

To do this, we’ve introduced the Command Palette. Based on a simple search approach, users can input what they want to do and select from the search results. (“Command K” for Mac users and “Control K” for PC users.) The command palette shows suggestions based on your current context and items you’ve used recently.

Users who took part in the tech preview of the new UI report being pleased with the shortcut to specific tasks they want to execute. This lets them launch operations and begin working in fewer clicks.

Cisco Intersight users can find actions fast using the Command Palette.

Users can find actions fast using the Command Palette

The new UI also improves readability. The classic Intersight UI presented information in a dense way with heavy text on a single screen. In the new UI, users will find that readability is improved with more relevant information on individual screens and more space that allows users to focus on what’s most important.

One UI, Multiple Benefits

“The new UI is more than an improved look and feel,” said New. “The release of the new UI marks the next significant milestone on our vision to deliver a flexible hybrid cloud operations platform to help customers simplify IT operations. Cloud networking joins the suite of Intersight services, with more to come. And through the common UI, we’re lowering the learning curve for customers of Cisco software so it’s easier to get up and running.”

Source: cisco.com

Continue reading

Cisco UCS Unified Fabric now 100Gb end-to-end for X-Series

Since 2009, Cisco UCS Unified Fabric has been one of the key differentiators between UCS servers and the rest of the industry. Unified Fabric is the combination of data, storage, and management traffic on a single cable. This greatly simplifies your server and networking infrastructure and provides both CapEx (adapters, cables, switches) and OpEx (warranty, power & cooling, management) savings. Cisco’s unified fabric is a single cable that connects the UCS X-Series chassis to the fabric Interconnects

Read More: 700-150: Introduction to Cisco Sales (ICS)

In a redundant deployment, you reduce the number of cables and switches 5:2 – two switches/cables for data and storage and one for management.

12+ years ago, Cisco UCS first shipped with 10Gb when the rest of the industry’s standard was 1Gb. In March, we announced we were leapfrogging the industry again by making 100Gb standard for UCS X-Series vs. 25Gb for other vendors.

The Cisco UCS X-Series Unified Fabric consists of three components: VICs, IFMs, and 6500 Series Fabric Interconnects.

Cisco UCS Virtual Interface Card (VIC) 15000 Series

VICs (Virtual Interface Cards) are more than a NIC or an ordinary converged network adapter (CNA – Ethernet + storage). Other vendors offer NICs or CNAs, but none offer the full functionality of a VIC. The two key differentiators are the inclusion of management traffic and the number of virtual adapter interfaces.

Cisco UCS servers are configured via policies and templates. The VIC receives the configuration from Cisco Intersight and is pushed to the server. This removes the need for a server management network.

Virtual adapter interfaces come in two flavors – data and storage. These virtual adapter interfaces extend the network fabric directly to both servers and virtual machines via end-to-end network virtualization so that a single connectivity mechanism can be used to connect both physical and virtual servers with the same level of visibility and control. Each can have their own quality service, guaranteeing bandwidth and QoS thus providing optimal user experience. Cisco VICs supports more virtual adapter interfaces than any other NIC or CNA giving you the ability to tune and shape traffic to every application.

I’ll leave it to the data sheet to call out all the hardware features like low latency and kernel bypass for performance optimizations among others.

Cisco UCS VIC 15231 mLOM, 2×100 Gbps

Cisco UCS 9108 100G Intelligent Fabric Module (IFM)

An IFM is the connection point between the X9508 Chassis (and servers) and the Fabric Interconnect – either the 6400 or 6500 series. Our 2nd gen IFM ups the speed from 25Gb to 100Gb. Like its predecessor, each IFM has eight ports, and they are always deployed in redundant pairs. The amount of bandwidth is determined by the number of ports used. If you are looking to future proof but don’t need the full 800Gb per IFM, you just use fewer ports. As your needs increase, just use the remaining ports. 

Cisco UCS 9108 100G Intelligent Fabric Module

Cisco UCS 6536 Fabric Interconnect

The 36 port Cisco UCS 6536 Fabric Interconnect supports Cisco UCS X-Series, UCS B-Series, and UCS C-Series servers. It offers line-rate, low-latency, lossless 1/10/25/40/100 Gigabit Ethernet, Fibre Channel, NVMe over Fabric (NVMe/FC, NVMe/TCP, NVMe over ROCEv2), and Fibre Channel over Ethernet (FCoE) functions. The total switching capacity is 7.42 Tbps.

Of the 36 ports, the FI has 32 40/100-Gb Ethernet and 4 unified ports that support 40/100-Gb Ethernet ports or 16 Fibre Channel ports after breakout at 8/16/32-Gb FC speeds. The switch also supports two ports at 1-Gb speed using QSA, and all 36 ports can breakout for 10- or 25-Gb Ethernet connectivity and support FCoE.

Cisco UCS 6536 Fabric Interconnect

Putting Unified Fabric all together

The adage is a picture is worth 1,000 words. To save you reading 1k words, here is a diagram showing Cisco Unified Fabric and the entire UCS portfolio.

Click on me to make full size!

What can 5th Gen Unified Fabric do for you?

Unified Fabric will simplify your infrastructure and save you money. The architecture means there are few components to procure, install, power, and maintain. Less money spent upfront and less time and money spent over their life. This will increase your business agility and allow you to focus on adding value to your business vs. keeping the lights on.

Then add in the performance benefits that 100Gb line rate, low latency end-to-end solution provides for your applications and user experience. You will have increased the reliability, efficiency, and scalability of the network.

Source: cisco.com

Continue reading

Expanding workloads for UCS X-Series with UCS X-Fabric Technology

First, we increased the amount of storage – going from two drives on a B-Series to six drives on a X-Series. Now we are adding GPUs to X-Series that were previously only available in rack servers.

How does it work?

The VIC (Virtual Interface Card) on the server node connects to the UCS X9416 X-Fabric Module. The X-Fabric Module connects to the UCS X440p PCIe node with the GPUs. This elegant, easily upgradable, cable-free solution is only possible on a mid-plane, free chassis design like UCS X-Series.

Cisco UCS X9416 X-Fabric Module

The first UCS X-Fabric Technology module is PCIe Gen 4 expansion for the UCS X210c M6 Compute Node. The two X9416 X-Fabric Modules expand the PCIe bus from the server to the UCS X440p PCIe Node. No cables, no fuss, no muss.

Cisco UCS X440p PCIe Node

More and more applications can benefit from accelerators like GPUs. Ranging from AI/ML to the stalwart VDI, adding one or more GPUs to a server can greatly improve the user experience and application performance.

The Cisco UCS X440p PCIe Node allows you to add up to four GPUs to a Cisco UCS X210c Compute Node in conjunction with the UCS X9416 X-Fabric Module.

Different workloads require different types of GPUs. Cisco initially supports:

◉ Up to two Nvidia A100 Tensor Core GPUs

◉ Up to two Nvidia A16 GPUs

◉ Up to two Nvidia A40 GPUs

◉ Up to four Nvidia T4 Tensor Core GPUs

The modular design of UCS X-Series allows you to decouple the CPU / GPU refresh cycles. GPU suppliers like Nvidia, AMD, and Intel release their products at a different cadence than CPUs. If your application performance is sensitive to GPU performance, being able to simply slide in an UCS X440p PCIe node with the latest GPUs allows you extend the investment of all the other solution components (chassis, servers, IFMs, & PSUs) providing a better overall TCO.

Cisco Intersight

Management has always been a UCS superpower. Being able to manage every component for X-Series in a single app is paramount. From inventory to firmware updates, you manage all the UCS X-Fabric Technology components with the same process you manage the server and Intelligent Fabric Modules.

Run any app

Your requirements for modern, accelerated workloads shouldn’t dictate your server form factor. They should seamlessly integrate into a system that also runs all your traditional applications from core infrastructure, to database, to VSI. A single system, managed from the cloud, spanning all your workloads not only simplifies your environment, but will allow you to focus on business needs, not figuring out what unique hardware is needed for a specific application.

Source: cisco.com

Continue reading

Cisco UCS and Cisco MDS

Better together

At a concert, few years ago, the director spoke to the audience and said something that resonated in my mind for long time. His words went like this: the value of the ensemble is greater than the sum of the value of the individual musicians. The meaning was clear. He wanted to illustrate the significance of playing together, as an orchestra, rather than a group of individual sound musicians.

The same concept comes to my mind when I think of the combination of Cisco UCS, and Cisco MDS 9000 storage networking. You can use them independently, or connected to other products. But the combination of Cisco UCS and Cisco MDS delivers unique benefits that exceed the sum of the individual products. The pseudo-mathematical formula 1+1=3 can well express the concept. Alternatively, another way to describe it is the prosaic expression “better together”.

Cisco UCS + Cisco MDS synergy: 1+1=3

The joint adoption of Cisco UCS compute systems and Cisco MDS 9000 Series of storage networking switches provides a significant benefit to the enterprise. Over the years, I have collected information from the many customer opportunities I have been directly involved in. When reflecting on that, I identified a list of synergies and benefits coming from the joint adoption of Cisco UCS with Cisco MDS 9000. I also discovered those benefits can be grouped into three main categories: advanced design options, easier management and better support.

Key advantages

◉ Multiprotocol flexibility allows organizations to deploy Fibre Channel and FCIP on a single chassis and more easily benefit from the advantages of both technologies. Support for SCSI, NVMe and FICON protocols is also available. Moreover, you have the advantage to be fully covered under a Cisco verified solution.

◉ VSANs can logically segregate storage traffic and create multi-tenancy, and they are supported in the Fibre Channel fabric and within Cisco UCS. This capability is only available from Cisco.

◉ VSAN trunking allows the use of the same link for carrying traffic from multiple VSANs, reducing the need for multiple links while segregating traffic. This is a unique Cisco capability.

◉ F-port PortChannels provide link aggregation of multiple Cisco UCS to Cisco MDS 9000 physical links into a single logical channel, as well as fault tolerance and uniform traffic load balancing. This capability is only available from Cisco.

◉ NVMe/FC can boost application performance by reducing latency and minimizing CPU usage for data transfer activities. You also have the advantage to be fully covered under a Cisco verified solution.

◉ Common Operating System and management tools ease network implementation, maintenance, and troubleshooting by relying on the same skill set across SAN, LAN, and computing environments. This is a unique Cisco capability.

◉ Cisco UCS visibility from Nexus Dashboard Fabric Controller allows a single view for all networking elements in a Cisco data center architecture, including Cisco UCS fabric interconnects and server vNICs and vHBAs. This capability is only available from Cisco.

◉ Cisco Intersight integration covering both compute and storage networking provides lifecycle management of Cisco UCS servers, as well as Cisco Nexus 9000 and Cisco MDS 9000 products. This is a unique Cisco capability.

◉ Cisco Intersight Cloud Orchestrator can be used to automate different technology domains with an easy-to-use and low-code workflow designer, enabling IT operations teams to move at the speed of the business. This is a unique Cisco capability.

◉ Smart Zoning reduces the need to implement and maintain large zone databases and eases management and implementation tasks. You also have the advantage to be fully covered under a Cisco verified solution.

◉ Assured interoperability and feature compatibility, avoiding tedious compatibility matrix verification and deployment delays. This capability is only available from Cisco.

◉ Organizations can interact with a single vendor when troubleshooting problems across computing and networking environments. This is a unique Cisco capability.

◉ A variety of support models are available across data center solutions to efficiently manage and coordinate partners to resolve problems. This capability is only available from Cisco.

Key business benefits

When we consider the business implications of the advantages listed above, we can discover that Cisco UCS plus Cisco MDS 9000 integrated solution delivers:

◉ Operational savings from hassle-free firmware upgrades, solution automation with Cisco Intersight and operational simplification with smart zoning

◉ Increased uptime with Cisco support and a single pane of glass for unified visibility, combined with deep traffic analysis and proactive troubleshooting

◉ Application performance improvements from uniform traffic load balancing on uplinks and NVMe/FC end-to-end support, all combined with congestion prevention with MDS 9000 DIRL software.

In short, the Cisco MDS 9000 Series provides superior performance, high availability, and intelligent storage networking for Cisco UCS environments in small, medium and large organizations.

Source: cisco.com

Continue reading

FlashStack Data Protection with Veeam: A New Cisco Validated Design

Delivering an optimal user experience for business-critical applications is a non-negotiable element for successful businesses. Architecting infrastructure that meets application and SLA requirements is vital to delivering the superior performance on which great user experiences rest. Today, this infrastructure is often built with the latest compute technology, high-performance flash storage arrays, and enterprise networking. Combining modern data protection and infrastructure is also key to availability, because pairing data protection with the right backup infrastructure can help an organization respond to its unique demands.

Unfortunately, deploying on-premises infrastructure can be complex, time consuming and costly. This is where converged infrastructure from FlashStack comes in. Built in partnership by Cisco and Pure Storage, FlashStack offers everything a modern infrastructure platform needs—more simplicity, more flexibility, and more speed. FlashStack delivers cloudlike experiences and economics to your data center through easy adoption, unified management, and fewer siloes.

FlashStack Data Protection with Veeam

Now, Cisco and Pure Storage have partnered with Veeam—a consistent Leader in the Gartner Magic Quadrant for Data Center and Recovery Solutions—to build a Cisco Validated Design (CVD) that provides a complete set of data protection options for FlashStack. These options use Pure FlashArray//C, Cisco UCS C240 AFF Rack Server or UCS S3260 Storage Server, and Veeam software. FlashStack with Veeam Data Protection provides an end-to-end solution that includes backup and archive to on-premises and public clouds.

These new CVDs offer three target architectures, depending on restore requirements, backup throughput, storage efficiency and capacity, as shown in Figure 1.

FlashStack with Veeam data protection combines two solutions required to deliver optimal user experiences:

Converged infrastructure meets modern data protection

Figure 1  FlashStack backup environment with three potential backup targets

FlashStack provides pre-integrated, pre-validated converged infrastructure that combines compute, network and storage—as I mentioned earlier—into a platform designed for business-critical applications and a wide variety of workloads. This platform delivers maximum performance, increased flexibility, and rapid scalability. And it enables rapid, confident deployment as well as reducing the management overhead consumed by patches and updates.

 Modern infrastructure also needs modern data protection, and Veeam’s data protection platform integrates backup and replication with advanced monitoring analytics and intelligent automation. This platform works with FlashStack to deliver performance and features to help ensure that your data and applications are available while also unlocking the power of backup data.

Depending on your requirements, you can choose from several infrastructure platforms on which to run your data protection environment:

FlashArray//C: fast restores with storage efficiency (dedupe and compression)

Veeam, with FlashArray//C from Pure Storage and Cisco UCS C220 M5 servers, delivers maximum flash-based performance that can handle multiple workloads, while paired with Pure Storage data efficiency features. This solution offers storage capacity without compromise, along with flash-based performance at close to disk economics. It targets multiple workloads and large scale deployments such as:

◉ All-QLC flash storage for cost-effective, capacity-oriented workloads

◉ Advanced data services and technologies for guaranteed data efficiency

◉ Scale-up, scale-out architecture to meet the capacity expansion requirements of data-intensive workloads

◉ Non-disruptive, Evergreen architecture that eliminates risky, complex, and costly upgrades

C240 AFF: fast restores and high backup throughput

Veeam, with Cisco UCS C240 M5 all-flash storage servers, delivers the performance and flexibility needed to run and support virtually any workload, while meeting the requirements of a sophisticated data protection environment.  It features:

◉ Architectural and compute flexibility

◉ Multiple workload capacity

◉ Best-in-class backup and restore performance

◉ Scale-out capability

S3260: Dense platform with optimal restores and high backup throughput

Veeam, with Cisco UCS S3260 M5 storage servers, delivers superior performance with massive scale-up capability and disk economics. This solution includes Cisco Intersight or UCS Manager to reduce cost of ownership, simplify management, and deliver consistent policy-based deployments and scalability.

This dense storage platform, combined with FlashStack and Veeam, offers massive storage capacity and high backup throughput for multiple workloads. You can run Veeam components such as Proxy, Console and Repository on a single compute and storage platform with the ability to scale both compute and storage through Veeam scale-out backup repositories

You can deploy a scale-out backup storage platform on a cluster of Cisco UCS S3260 storage servers, providing an S3 archive target for the Veeam cloud tier. This tier features scale-out backup repository architecture, which makes it possible to move older backup files to more cost-effective cloud or on-premises object storage. Archiving backup in the cloud tier can result in up to 10X savings on long-term data retention costs and help you align with compliance requirements by storing data as long as needed.

Power and data protect your business-critical applications

Organizations are upgrading their infrastructure to accelerate innovation, increase agility, and reduce complexity while enabling rapid scalability. FlashStack brings the latest in compute, network, and storage components together in a single, pre-validated architecture that speeds time to deployment, reduces overall IT costs and deployment risk, and is tailored for specific workloads.If you’re an existing FlashStack customer or use other backup solutions, check out the following links to learn more about how this Cisco Validated Design can power and protect your applications and help you consistently deliver optimal user experiences for the applications that contribute to your success.

Continue reading

VDI Rapid Deploy – Enable Remote Work Fast!

Life as we all knew it changed in early 2020. Not only our personal lives, but our professional lives as well. Working from outside the office for most of us was a one-off, requiring our boss’s approval to do it for a day or two. Lots of organizations didn’t allow working remotely at all. Others had established remote work policies and had deployed the tools to enable it for a portion of their workforce.

When we were all suddenly thrown into the situation where we ALL had to work remotely, no one was prepared. The pandemic created demand for remote work that was unprecedented, unexpected, and impossible to support with existing infrastructures. Demands for collaboration tools like Cisco WebEx and Cisco WebEx Teams skyrocketed. Demands for secure access to corporate networks went through the roof. Cisco AnyConnect secure VPN services, Cisco DUO two factor authentication and Cisco Umbrella secure DNS service filled the secure access requirements.

We’ve now come to find that those foundational tools don’t provide the full remote work experience that you and I need as we transition into long-term remote work. We need access to all our applications and all our data. And it’s critical that the applications and data be in the same physical location for acceptable performance.

Enter Virtual Desktop Infrastructure, or “VDI” for short. VDI has been around for a long time, as far back as the mid-80s. The technology is continuously evolving and improving. It’s considered a mainstream, virtually risk-free technology for supporting secure remote work. VDI is deployed at scales of 100,000 users or more at some of the largest organizations on the planet. It is also deployed at scales as low as 400 users, thanks to the economics of hyperconvergence.

VDI brings some very key benefits for remote work to organizations and end users:

Two of the challenges for bringing a VDI environment online in the past in your environment has been complexity and time to deploy. There is typically a fair amount of evaluation, analysis and planning that goes into a deployment upfront. Depending on the organization, that phase can take weeks or even several months depending on size. Then there’s the hardware design phase to support the VDI environment. Bills of Materials are built, considered, modified and finally settled on. By the time the design and infrastructure are settled on, the purchase order is cut, the equipment is delivered and installed, another month or so has gone by. At this point we usually start the VDI deployment.

The typical planning and hardware design phase take too long for the environment we are operating in. Recognizing this, in March 2020, the Cisco VDI and Graphic Solutions team created a program called Quick Ship. The intent was to pre-engineer Cisco UCS converged infrastructure and Cisco HyperFlex hyperconverged infrastructure options that could support a specified number of specific Microsoft Windows 10 virtual machines. Here is the Windows 10 Virtual Machine configuration the pre-engineered bundles support:

By using a target user Windows 10 VM configuration and the engineered Quick Ship UCS and HyperFlex bundles, we were able to eliminate the typical planning and hardware design phases.

That brought us to the VDI deployment phase. What we realized is that the deployment of the VDI system was a challenge for many customers.

Enter Rapid Deploy. We launched Rapid Deploy on August 24th to replace the Quick Ship program and address the deployment challenge. Rapid Deploy is built on the same tenants of eliminating the upfront planning and hardware design phases. What we added were offers from Cisco Customer Experience (CX,) formerly known as Cisco Advanced Services.

Rapid Deploy includes optional deployment service offers from Cisco CX for Citrix Apps and Desktops or VMware Horizon target user Windows 10 virtual desktops in increments of 500 or 1000 users. By utilizing the optional Cisco CX services offered in Rapid Deploy, a customer could go from their hardware and software order to a minimum 500 seat VDI environment in as little as a month.

We currently have 15 Rapid Deploy offers in our ordering tool that Cisco sellers and Cisco Partner sellers can leverage to build greenfield environments or add capacity to existing VDI environments. The offers can be created in less than five minutes by leveraging the solution identifier (SID) as the quote template. They can be customized to add more memory or NVIDIA GPUs.

Now customers can build out a highly performant, pre-engineered Cisco HyperFlex hyperconverged infrastructure or a Cisco UCS converged infrastructure and deploy the VDI infrastructure and virtual desktops in an amazingly short time!

Continue reading