Flow control within a high-performance, scalable, and drop-free data center switching fabric

Abstract

Embodiments of the present invention relate to flow control within a high-performance, scalable, and call-drop-free data center switching fabric. Describe a high-performance, scalable, and call-drop-free data center switching fabric and infrastructure. Data center switching fabrics can utilize low-cost, off-the-shelf packet-based switching components such as IP over Ethernet (IPoE) and overlay forwarding technologies rather than proprietary switching fabrics. In one example, a host network accelerator (HNA) is positioned between servers (eg, virtual machines or dedicated servers) in a data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNA is a hardware device that embeds a virtual router on one or more integrated circuits, where the virtual router is configured to extend one or more virtual networks to virtual machines and use an overlay network to seamlessly transfer packets through a switch fabric. In other words, the HNA provides a seamless hardware-based interface to the overlay technology used to communicate packet flows through the data center's core switching network.

Description

[0001] Cross References to Applications [0002] This application claims the benefit of U.S. Provisional Application No. 61 / 973,045, filed March 31, 2014, the entire contents of which are hereby incorporated by reference. technical field [0003] The present invention relates to computer networks, and more particularly to data centers providing virtual networks. Background technique [0004] In a typical cloud-based data center, a large collection of interconnected servers provides computing and / or storage capacity for executing various applications. For example, a data center may include a facility that hosts applications and services for subscribers, such as customers of the data center. A data center may, for example, host all infrastructure equipment, such as networking and storage systems, redundant power supplies, and environmental controls. In most data centers, clusters of storage systems and application servers are interconnected via a high-speed switching fabric...

AI Technical Summary

Problems solved by technology

Proprietary switching fabrics can provide high performance, but can sometimes be more expensive, and in some cases can provide a single point of failure for the network

Off-the-shelf packet-based switching components can be cheaper, but can result in lossy, non-deterministic behavior

Images