White Paper Intel® I/O Acceleration Technology

White Paper 
Intel® I/O Acceleration 
Technology

White Paper Intel® I/O Acceleration Technology

Accelerating High-Speed Networking with Intel® I/O Acceleration Technology The emergence of multi-Gigabit Ethernet allows data centers to adapt to the increasing bandwidth requirements of enterprise IT. To take full advantage of this network capacity, data center managers must consider the impact of high- traffic volume on server resources. A compelling way of efficiently ...translating high bandwidth into increased throughput and enhanced quality of service is to take advantage of Intel® I/O Acceleration Technology (Intel® I/OAT), now available in the new Dual-Core and Quad-Core Intel® Xeon® processor-based server platforms. Intel I/OAT moves data more efficiently through these servers for fast, scalable, and reliable networking. Additionally, it provides network acceleration that scales seamlessly across multiple Ethernet ports, while providing a safe and flexible choice for IT managers due to its tight integration into popular operating systems. White Paper Accelerating High-Speed Networking with Intel® I/O Acceleration Technology Introduction Business success is becoming increasingly dependent on the rapid transfer, processing, compilation, and storage of data. To improve data transfers to and from applications, IT managers are investing in new networking and storage infrastructure to achieve higher performance. However, network I/O bottlenecks have emerged as the key IT challenge in realizing full value from server investments. Until recently, the real nature and extent of I/O bottlenecks was not thoroughly understood. Most network issues could be resolved with faster servers, higher bandwidth network interface cards (NICs), and various networking techniques such as network segmentation. However, the volume of network traffic begun to outpace server capacity to manage that data. This increase in network traffic is due to the confluence of a variety of market trends. These trends include: • Convergence of data fabrics to Ethernet • Server consolidation and virtualization, which is increasing server port densities and maximizing per-port bandwidth requirements • Clusters and grids—rather than large servers—are becoming the leading way of creating high-performance computing resources • Increased adoption of enterprise audio and video resources (VOIP, video conferencing) and real-time data acquisition are contributing to network congestion • Increased adoption of network-attached storage, versus direct- attach storage, to meet enterprise back-up and recovery needs • Deployment of high-density blade servers to accommodate enterprise-computing requirements The increased reliance on networked data and networked compute resources results in a need to manage an ever-increasing data load. This increased load threatens to outpace server-processing capabilities, as demonstrated by the marginal gains from traditional performance enhancements (for example, increasing network bandwidth and adding servers). As a result, IT managers are now asking, “After investing in a 10X improvement in network bandwidth, why aren’t we seeing comparable improvements in application response time and reliability?” To answer this question, Intel research and development teams evaluated the entire server architecture to identify the I/O bottlenecks and determine their nature and impact on network performance. Out of this investigation came a new technology † called Intel® I/O Acceleration Technology (Intel® I/OAT). This white paper discusses the platform-wide I/O bottlenecks found through Intel research and how Intel I/OAT resolves those issues for accelerating high-speed Read the full White Paper Intel® I/O Acceleration Technology.

Videos relacionados