Fabric-based computing: Bridging data center silos
Sumit Mukhija, National Sales Manager,Datacentre, Cisco India and SAARC
As organizations increasingly rely on IT to help enable, and even change, their business strategies, they need their IT infrastructure to be more powerful, agile, and cost effective than ever. Today's enterprises require continual system availability, demand ubiquitous access, and expect rapid and fluid responses to their ever-changing business needs.
To provide these functions, enterprise data centers are challenged to get more use out of existing resources and operate quickly, with increased agility. They must improve asset utilization to reduce or defer capital expenses, reduce power and cooling consumption to cut costs and align with green business practices. They must make data and resources available in real time to provide flexibility and alignment with current and future business needs.
To meet these challenges, organizations must build a single network-based data center infrastructure that unifies traditional server, storage, and network operations to more efficiently support evolving business applications. Based on industry standards like FCoE, Fabric based computing is a concept which helps companies to introduce a "wire once" deployment model. With this computing model, configuration may change, but without requiring the companies to install new components.
Fabric computing is the principle driving state-of-the-art next generation data centers and networks. All resources are linked together in a common architecture that can be virtualized. In other words, the compute and storage platform is architecturally 'unified' with the network and the virtualization platform, making no distinction between the network and the edge devices connected to it.
Fabric computing eliminates manual integration, in favor of an integrated architecture, thereby breaking down the silos of compute, storage, and network resources. It helps to design next-generation architecture for enterprise servers having powerful server capabilities and advanced networking features on a single server structure. Resources are no longer tied to a single machine and the distinction between network and computer is erased by linking thousands of processors and storage devices into a single system.
An architecture based on the premise of 'one application, one server' helps to transform the data center's traditional separate infrastructures into pools of virtualized storage, computing, and I/O resources. This allows customers to directly address the cost inefficiencies and service inflexibly that are inherent in many current data centers. A cross-data center orchestration strategy helps to mitigate the complexity of virtualized environments and develop the capability of the data center to sense and respond to changing business needs.
Advantages of a Unified fabric:
Fabric computing combines powerful server capabilities and advanced networking into a single fabric that creates reconfigurable, scalable pools of interconnected computing, network, communications, and storage resources. Such a unified data center network fabric has the operational characteristics to concurrently handle LAN, SAN, and server clustering traffic.
Consolidating the multiple networks in the data center into a single network will promote significant reductions in capital and operating expenses. Just as important, giving every server in the data center consistent and ubiquitous I/O capabilities will markedly improve the service capabilities, flexibility, and resilience of the data center.
The unified data center fabric helps organizations align IT assets with their business priorities and deliver tangible benefits. It provides consolidation and higher utilization of previously separate resources, reducing the number of server I/O adapters and cables by as much as 50 percent and lowering power and cooling costs by up to 30 percent through the elimination of unnecessary switching infrastructure. The simplified infrastructure will also lower operational expenses related to management and operations.
While transitioning to a unified fabric, customers do not have to compromise on architectural, management, or operational best practices in either Ethernet or Fiber Channel networks or invest in extensive staff training, rewrite network architecture plans and operating procedures associated with architectural makeover.
Unified fabric architecture supports virtual machine server clusters, enabling applications to move across the network while maintaining their provisioned network services, such as security policy, quality of service (QoS), and overall performance. As a result, IT managers can easily move applications based on factors such as CPU utilization and thermal loads. Rapid provisioning of a dynamic and flexible application infrastructure is enabled by the combination of server virtualization and the virtual machine optimized services.
Data center infrastructure based on the unified fabric is engineered with specific hardware and operating systems to deliver component- and system-level operational continuity. In addition to offering component-level protection, this can have a significant positive effect on a customer's business continuance capabilities. Virtual machine optimized services ensure that applications are quickly and transparently moved to a new infrastructure in response to challenges such as hardware failure or unexpectedly high application use. In a recovery scenario, the simplified infrastructure and consistent I/O capabilities facilitate service recovery.
Enterprises' growing dependence on IT for business advantage invariably manifests itself as growth in the server infrastructure that supports these new business systems. The Unified fabric delivers a server access networking solution that addresses the challenges of a sprawling, inefficient, inflexible infrastructure and the resulting spiraling TCO, while improving the feasibility and applicability of related strategies such as server virtualization.
What the future holds:
Fabric based computing helps enable a 'wire once' deployment model where changing configurations no longer means installing new components or re-cabling existing ones. This helps to reduce cost by eliminating the need for a parallel set of components to support multiple data transmission protocols. Along with the reduction in these infrastructure components on the server side, a similar reduction on the network edge is possible, further reducing costs.
Offering flexibility and taking advantage of the role that the network plays in addressing key aspects of security, scalability and interoperability, fabric based computing will help both public and private cloud management, going forward. For the same carbon footprint, such data center architecture can deliver up to four times the compute capacity and up to four times the bandwidth capacity.