核心路由器中业务引擎交换吞吐量研究

本文给出了核心路由器中业务引擎吞吐量分析的一般模型,并应用此模型研究了实际设计的用于OC-48c接口的业务引擎.由此得出:当采用GigaStream交换芯片时,每路CSIX(Common Switch Interface)接口至少需用4路HSSL(High Speed Serial Link)链路;在CSIX接口处形成CFrame帧时需要对IP包最后一个信元按照实际大小形成CFrame帧,才能保证交换网络与CSIX接口处线速转发所有长度的IP包.最后,本文给出了业务引擎吞吐量和IP包存储之间的一般性关系,该关系可用于指导核心路由器交换网络的设计.     

A distributed scheduling architecture for scalable packet switches

The continuous growth in the demand for diversified quality-of-service (QoS) guarantees in broadband networks introduces new challenges in the design of packet switches that scale to large switching capacities. Packet scheduling is the most critical function involved in the provision of individual bandwidth and delay guarantees to the switched flows. Most of the scheduling techniques proposed so far assume the presence in the switch of a single contention point, residing in front of the outgoing links. Such an assumption is not consistent with the highly distributed nature of many popular architectures for scalable switches, which typically have multiple contention points, located in both ingress and egress port cards, as well as in the switching fabric. We define a distributed multilayered scheduler (DMS) to provide differentiated QoS guarantees to individual end-to-end flows in packet switches with multiple contention points. Our scheduling architecture is simple to implement, since it keeps per-flow scheduling confined within the port cards, and is suitable to support guaranteed and best-effort traffic in a wide range of QoS frameworks in both IP and ATM networks     

无建立无状态QoS路由

本文提出了无建立无状态QoS路由的概念,并认证了实现无状态QoS路由的关键在于:(1)如何将应用的QoS要求嵌入IP分组头中;(2)如何有效地设计路由器的分组转发策略.本文结合特定的路由算法,提出了多种新颖的无建立无状态QoS路由具体实现方案.本文提出的无状态QoS路由方案最大限度地利用了目前IP网络中采用的"尽力传送"路由表风格,具有良好的可扩展性、鲁棒性、简单性和有效性.     

下一代网络--多协议标记交换MPLS思想剖析

多协议标记交换MPLS通过在传统的IP包里加入标记，使原来依赖于IP头标分析的路由转发转变为依赖于标记的转发，这不仅可以大大地提高IP包的转发速度，更可使传统IP网络具有QoS能力。本文深入分析了标记转发的思想．并指出了MPLS实现其优点所用的机制与原理。     

宽带综合IP网的MPLS技术及其应用

多协议标记交换（MPLS）技术是综合利用网络第二层交换技术的有效性和第三层IP路由的灵活性等优点而产生的多层交换技术。通过在传统的IP包里加入标记，使路由转发依赖于标记，大大地提高IP包的转发速度，同时可使传统IP网络具有服务质量（QoS）能力。现主要分析MPLS体系结构，指出MPLS的一些应用。     

Demonstration of the highly reliable Hikari router network based on a newly developed disjoint path selection scheme

Integration of multiprotocol label switching functions and multiprotocol lambda switching functions can enhance the throughput of IP networks and remove bottlenecks that are derived from electrical packet processing. To enhance the packet forwarding capability, NTT proposed a photonic MPLS concept that includes MP/spl lambda/S, and demonstrated IP, MPLS, and photonic MPLS integrated router systems called the photonic MPLS router. This router system is now called the Hikari router. The word Hikari is Japanese meaning beam, light, lightwave, optical, photonic, and sunshine. The amount of IP data traffic has grown remarkably. Massive IP routers and flexible route control mechanisms are now required to cope with the increased amount of traffic. The Hikari router can offer two solutions utilizing photonic switching technologies, and photonic network operation and management technologies. The first solution is utilizing photonic switching technologies realized using optical-switch-based crossconnect systems. The other solution is realized using the MPLS and MP/spl lambda/S signaling protocol and photonic network protection functions. In this article we report on the implementation of the Hikari router systems, propose a newly developed disjoint path selection scheme for generalized MPLS networks with shared risk link group constraints, and demonstrate the signaling protocol and network protection functions. The demonstration system achieves a distributed optical path set-up/tear-down protocol with an extended constraint-based routing label distribution protocol. Fast self-healing through automatic protection switching and a new restoration scheme are also implemented. These functions are successfully implemented, and the performance is verified on a demonstration network. The protection switching scheme achieves protection in less than 20 ms, and the optical path restoration scheme achieves restoration in less than 500 ms.     

Routing with a clue

We suggest a new simple forwarding technique to speed up IP destination address lookup. The technique is a natural extension of IP, requires 5 bits in the IP header (IPv4, 7 in IPv6), and performs IP lookup nearly as fast as IP/Tag switching but with a smaller memory requirement and a much simpler protocol. The basic idea is that each router adds a "clue" to each packet, telling its downstream router where it ended the IP lookup. Since the forwarding tables of neighboring routers are similar, the clue either directly determines the best prefix match for the downstream router, or provides the downstream router with a good point to start its IP lookup. The new scheme thus prevents repeated computations and distributes the lookup process across the routers along the packet path. Each router starts the lookup computation at the point its upstream neighbor has finished. Furthermore, the new scheme is easily assimilated into heterogeneous IP networks, does not require routers coordination, and requires no setup time. Even a flow of one packet enjoys the benefits of the scheme without any additional overhead. The speedup we achieve is about 10 times faster than current standard techniques. In a sense, this paper shows that the current routers employed in the Internet are clue-less; namely, it is possible to speed up the IP lookup by an order of magnitude without any major changes to the existing protocols     

Internetworking based on cell switch router-architecture andprotocol overview

This paper describes an internetworking architecture and related protocol overview based on routers that have asynchronous transfer mode (ATM) cell switching capability in addition to conventional Internet protocol (IP) packet forwarding. The proposed architecture can provide high-throughput and low-latency switched paths for individual application flows or a group of application flows while retaining current router-based internetworking architecture. The proposed router is able to establish the switched path based on the characteristics of flows, e.g., arrival of a data packet with specific upper layer protocols or arrival of more than a certain amount of data packets in a predetermined period, as well as by the reception of an IP-layer resource reservation request, such as resource reservation protocol (RSVP). One important feature that is provided by the proposed router is interoperability with the emerging ATM network platform specified by the ATM Forum and the telecommunications sector of the International Telecommunications Union (ITU-T). The proposed routers can be interconnected with each other over the point-to-point synchronous optical network link as well as over the ATM network platform, which provides permanent virtual channel, virtual path, or switched virtual channel (SVC) services. That enables network carriers to provide Internet/intranet services as well as others, such as telephony, ATM/time division multiplexing leased line, or native ATM SVC services     

SEAL2: An SDN‐enabled all‐Layer2 packet forwarding network architecture for multitenant datacenter networks

This paper presents the design and development of a new network virtualization scheme to support multitenant datacenter networking (MT‐DCN) based on software‐defined networking (SDN) technologies. Effective multitenancy supports are essential and challenging for datacenter networking designs. In this study, we propose a new network virtualization architecture framework for efficient packet forwarding in MT‐DCN. Traditionally, an internet host uses IP addresses for both host identification and location information, which causes mobile IP problems whenever the host is moved from one IP subnet to another. Unfortunately, virtual machine (VM) mobility is inevitable for cloud computing in datacenters for reasons such as server consolidation and network traffic flow optimization. To solve the problems, we decouple VM identification and location information with two independent values neither by IP addresses. We redefine the semantics of Ethernet MAC address to embed tenant ID information to the MAC address field without violating its original functionality. We also replace traditional Layer2/Layer3 two‐stage routing schemes (MAC/IP) with an all‐Layer2 packet forwarding mechanism that combines MAC addresses (for VM identification and forwarding in local server groups under an edge switch gateway) and multiprotocol label switching (MPLS) labels (for packet transportation between edge switch gateways across the core label switching network connecting all the edge gateways). To accommodate conventional IP packet architecture in a multitenant environment, SDN (OpenFlow) technology is used to handle all this complex network traffics. We verified the design concepts by a simple system prototype in which all the major system components were implemented. Based on the prototype system, we evaluated packet forwarding efficiency under the proposed network architecture and compared it with conventional IP subnet routing approaches. We also evaluated the incurred packet processing overhead caused by each of the packet routing components.     

基于IXDP2401的转发件间数据包处理信息传输方法的研究

IETF ForCES工作组提出了一种开放可编程的IP路由器体系结构,由转发件（FE）和控制件（CE）组成.在这种结构的路由器中有多个转发件,数据包可能由非本地FE转发.针对这类数据包的处理,定义了一种数据格式用于实现FE间数据包处理信息的传输,主要携带数据包的转发信息和重组信息,以提高数据包的处理效率,并完成正常的转发工作.最后,给出了其基于IXDP2401的实现方法.     

An IP transport and routing architecture for next-generationsatellite networks

Over the past several years, a number of new satellite systems have been proposed to provide high-speed Internet and multimedia services to businesses and home users. These proposals have been driven by the desire of network operators to reach end users that do not have cost effective access to other alternatives such as fiber, DSL, and cable, and by the availability of new spectrum (Ka-band) for use by new satellite services. The proposed systems generally employ multiple high-power spot beams, an onboard fast packet switch, and a demand-assigned multiple access scheme to provision IP-based services. In this article we concentrate on a geosynchronous satellite system where packet transport and switching within the satellite system are based on ATM. We describe an IP/ATM interworking and IP routing architecture that is driven by three main requirements: (1) the ability to support ATM SVCs between hundreds of thousands of satellite terminals by a single ATM switch located onboard; (2) a scalable IP routing architecture that does not result in large volumes of routing traffic to be transported over the satellite; and (3) the ability to segment the satellite terminals for routing and administrative control by ISPs and enterprise networks     

A novel IP with MPLS over WDM-based broad-band wavelength switchedIP network

This paper presents a new technology for constructing IP over photonic systems. An IP with multiprotocol label switching (MPLS) over wavelength division multiplexing (WDM)-based broad-band IP network architecture and protocol is proposed and analyzed in this paper, which supports variable-length IP-like optical packet label switching and optical virtual path routing. This system tries to merge into one layer the functionalities of the wavelength switching, SONET mux/demux, and IP routing, and is sometimes known as the concept of optical MPLS. The label banding, forwarding/switching process, and node architecture of the proposed network are discussed and studied. A unique as well as important function of a lambda/label edge router (LER) is a flow assembly device that can encompass MPLS' forward equivalence classes, label stacking, and label switching path aggregation function. At the same time, a particular function of the core label switching router is wavelength merging. A fiber delay line is used to delay the data stream in order to process the label information and resolve contention. Transmission bit error rate measurements of the baseband data stream and back-to-back is also demonstrated to show its feasibility     

基于IP突发信源模型数据包的定量计算研究

本文以IP突发信源on/off模型的单IP业务源的数据包生成特性分析为基础,以队列缓冲配置和IP数据包丢失率、排队时延的计算为主要研究对象,通过对多业务源排队系统的IP数据包排队时延进行深入的综合分析,得出了一些新的QoS定量计算解析式,这些解析式可用于计算IP交换路由器QoS参数.     

MPLS-Linux体系结构及交换路由性能分析

本文详细介绍了MPLS-Linux的体系结构、核心数据结构、标签交换过程和QoS运行等实现技术，通过对MPLS-Linux组成的交换路由系统进行性能测试和分析，发现：在链路轻载或预留带宽的情况下，交换路由系统对数据流的服务质量优于传统路由系统；只有综合应用策略路由、数据报分类调度和标签交换才能实现Internet环境下对端到端服务质量的控制。     

高速高性能的下一代选路与交换技术

网络演变和发展与选路和交换技术密切相关。文章综述了适应未来网络发展的高速、高性能的选路与交换技术,包括快速选路与转发、ATM交换的新进展和新应用、IP/ATM集成交换、新传送模式、开放式控制以及光分组交换技术。     

High-Performance Hybrid-Switching Optical Router for IP over WDM Integration

Because pure electrical routers with their bandwidth limitations can hardly keep up with the tremendous traffic growth in the Internet, optical routers based on various optical switching techniques including optical wavelength switching (OWS), optical burst switching (OBS), and optical packet switching (OPS) have been suggested to cope with this problem. However, because OBS and OPS are both in their early experimental phase and OWS only provides coarse granularity switching, a hybrid-switching optical router with combined OWS and electrical packet switching is a necessity in order to accommodate the entire multi-granularity traffic with multi-service requirements in a cost-effective manner. Its coordination capability of optical circuit switching and electrical packet switching enables efficient/intelligent usage of network resources. In this paper, we first review research and developments of such IP routers employing optical switching/interconnection techniques and examine how these techniques can be used inside routers to scale node capacity and to improve optical Internet performance. We also present and study the performance of a terabit optical router with an optical-electrical hybrid-switching fabric. The node architecture is based on the idea of IP over WDM integration with Generalized Multi-Protocol Label Switching (GMPLS). The network-level performance evaluations show that the proposed hybrid-switching optical router is a cost-effective solution for building the next generation GMPLS-based multi-granularity optical Internet.     

多平面ATM交换网络结构及其性能分析

本文提出一种新的多平面ＡＴＭ交换网络结构。该结构比单平面结构有更好的性能,并且在网络平扩容和冗余备份等方面均具有优良的特性。通过采用虚拟队列和概率母函数的方法,分析了在随机均匀业务模型下该交换网络缓存器的平均队长、平均信元时延和交换网络最大吞吐率等性能参数的封闭表达式,计算机仿真结果表明了分析结果具有很高的精确度。该分析方法不需复杂的叠代算法,在交换机的工程设计中同时也具有重要的实际意义。     

High-performance optical-label switching packet routers and smart edge routers for the next-generation Internet

This paper discusses the architecture, protocol, analysis, and experimentation of optical packet switching routers incorporating optical-label switching (OLS) technologies and electronic edge routers with traffic shaping capabilities. The core optical router incorporates all-optical switching with contention resolution in wavelength, time, and space domains. It is also capable of accommodating traffic of any protocol and format, and supports packet, flow, burst, and circuit traffic. The edge router is designed to achieve traffic shaping with consideration for quality of service and priority based class-of-service. Simulation results show packet loss rates below 0.3% at load 0.7 and jitter values below 18 /spl mu/s. The traffic shaping reduces the packet loss rate by a factor of /spl sim/5 while adding negligible additional latency. The OLS core routers and the electronic edge routers are constructed including the field-programmable-gate-arrays incorporating the wavelength-aware forwarding and contention resolution algorithms. The experiment shows optical-label-based packet switching with a packet loss rate near 0.2%.     

A novel architecture of optical code label processing in parallel designed for all optical routing system

A novel architecture of optical code label routing is designed based on optical code division multiplexing techniques, which performs the data packet forwarding and processing in parallel with a way of making the label and payload encoded and decoded separately. It uses optical polarity characteristics to realize the separation of the label and payload, employs fiber Bragg grating to encode/decode the label and payload so as to process them in parallel, and makes the forwarding and routing process realized in the optical domain. In the core router, the separation of the label and payload guarantees that the switch processing only includes the short label code recognition, without processing the payload. The payload recognition is carried out in the edge router. Thus, the router can simplify the processing of encoding and decoding in the core router, accelerating the switching, and increase the throughput greatly. Moreover, the novel routing scheme not only supports the varying of data packets, transparent transmission, fine granularity switching, and so on, but also is suitable for the aggregation of data service. It is attractive for the future development of all optical routing.