CN201075868Y - Multi spider route device with multipath optical interlinkage parts - Google Patents
Multi spider route device with multipath optical interlinkage parts Download PDFInfo
- Publication number
- CN201075868Y CN201075868Y CNU2007201554908U CN200720155490U CN201075868Y CN 201075868 Y CN201075868 Y CN 201075868Y CN U2007201554908 U CNU2007201554908 U CN U2007201554908U CN 200720155490 U CN200720155490 U CN 200720155490U CN 201075868 Y CN201075868 Y CN 201075868Y
- Authority
- CN
- China
- Prior art keywords
- optical
- nodes
- router
- routing
- chassis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Lifetime
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
技术领域 technical field
本实用新型涉及计算机网络技术,更具体而言,涉及计算机网络之中的多机架路由器。The utility model relates to computer network technology, more specifically, to a multi-rack router in the computer network.
背景技术 Background technique
计算机网络为一组可以交换数据并共享资源的互连的计算机装置的集合。在基于包的网络(如以太网)中,通过将数据分成可变长度的被称为包的块以在这些计算装置之间传递该数据,这些块经由网络单独地从源装置路由到目的装置。该目的装置从包中提取数据并将该数据汇编成其初始形式。A computer network is a collection of interconnected computer devices that can exchange data and share resources. In a packet-based network, such as Ethernet, data is communicated between computing devices by dividing it into variable-length chunks called packets, which are routed individually from source to destination through the network . The destination device extracts the data from the packets and assembles the data into its original form.
被称为路由器的某些装置维护以网络拓扑结构表示的路由选择信息。这些路由器交换路由选择信息以便维持通过网络的可用路由的精确表示。“路由”通常被定义为网络中两个位置之间的路径。在接收到来的数据包时,路由器就检验包中的常被称为“密钥”的信息,以根据路由选择信息来选择适当的下一跃距(next hop)来转发包。Certain devices known as routers maintain routing information in terms of network topology. These routers exchange routing information in order to maintain an accurate representation of available routes through the network. A "route" is generally defined as a path between two locations in a network. When receiving an incoming data packet, the router examines information often called a "key" in the packet to select the appropriate next hop to forward the packet based on the routing information.
通常,服务提供商,诸如在互联网核心中提供网络服务的互联网提供商,一直在努力满足不断增长的带宽需求。一种满足不断增长的带宽需求的方式就是使用“多机架”(“multi-chassis”)路由器。多机架路由器是多个路由节点在其中物理连接并被配置成作为单个路由节点操作的路由器。多机架路由器的一个实例包括:多个线卡机架(line card chassis,简称LCC,其包括一个或多个用于发送和接收包的接口卡(IFC)),以及中央交换控制机架(central switchcontrol chassis,简称SCC,其提供对所述LCC的自顶向下的管理)。这种类型的多机架路由器常常被称为单头多机架路由器,即,所有路由计算都在被指定为路由系统的主机中的单个路由引擎里完成的路由系统。对于网络上的同级路由器来说,多机架路由器显示为单个路由节点。因为多机架路由器结合多个路由装置的资源,所以,这些多机架路由器就具有比单机路由器更高的带宽性能。例如,使用多机架路由器可通过在更少的路由器上合并路由功能来简化和改进服务提供商网络上的路由。Typically, service providers, such as Internet providers that provide network services in the core of the Internet, have struggled to meet ever-increasing bandwidth demands. One way to meet growing bandwidth demands is to use "multi-chassis" routers. A multi-chassis router is a router in which multiple routing nodes are physically connected and configured to operate as a single routing node. An example of a multi-chassis router includes multiple line card chassis (LCCs), which include one or more interface cards (IFCs) for sending and receiving packets, and a central switch control chassis ( central switchcontrol chassis, referred to as SCC, which provides top-down management of the LCC). This type of multi-chassis router is often referred to as a single-head multi-chassis router, ie, a routing system in which all routing calculations are done in a single routing engine in a host computer designated as the routing system. To peer routers on the network, a multi-chassis router appears as a single routing node. Because multi-chassis routers combine the resources of multiple routing devices, these multi-chassis routers have higher bandwidth performance than stand-alone routers. For example, using a multi-chassis router simplifies and improves routing on a service provider network by consolidating routing functionality on fewer routers.
实用新型内容Utility model content
总的来说,本文描述了多机架路由器,其中,通过使用多路光互连部件(multiplexed optical connection)来耦合(couple,连接)多机架路由器中多个路由节点。多级交换结构,诸如3级Clos交换结构,在这些路由节点之间中继包。交换结构的各级可被分布给多机架路由器的单独路由节点,而多路光互连部件在这些节点之间转发包。In general, this paper describes a multi-chassis router in which multiple routing nodes in a multi-chassis router are coupled (coupled) through the use of multiplexed optical connections. A multi-level switch fabric, such as a 3-level Clos switch fabric, relays packets between these routing nodes. The stages of the switch fabric can be distributed to individual routing nodes of the multi-chassis router, while the multi-way optical interconnect forwards packets between these nodes.
例如,多机架路由器可包括多个线卡机架(LCC),它们相互合作以便在网络中作为单个路由器进行操作,而无需包括完全不同的、集中式交换结构。多级交换结构的实施可被分布到LCC,而这些LCC可在光互连部件上使用多路通信来进行通信。另外,一个或多个中央交换节点,诸如中央交换控制机架,可被并入多机架路由器。在任一情形中,使用多路通信都可减少实施交换结构所需的光缆总长度,并可减少在每个LCC上所要求的光缆接口数。其结果是,可更容易地伸缩(scaled)多机架路由器来合并所增数量的路由节点,而无需达到或超过在多机架路由器将配置于其中的环境里的任一物理尺寸的限制。For example, a multi-chassis router may include multiple line card chassis (LCCs) that cooperate to operate as a single router in the network without including a disparate, centralized switching fabric. The implementation of the multi-stage switch fabric can be distributed to LCCs, and these LCCs can communicate using multiplexing over the optical interconnect components. Additionally, one or more central switching nodes, such as a central switching control chassis, may be incorporated into a multi-chassis router. In either case, the use of multiplexing reduces the overall length of fiber optic cables required to implement the switch fabric and reduces the number of fiber optic cable interfaces required on each LCC. As a result, multi-chassis routers can be more easily scaled to incorporate increased numbers of routing nodes without reaching or exceeding any physical size limit in the environment in which the multi-chassis router will be deployed.
在一个实施例中,本实用新型被引入到多机架多机架路由器,该路由器包括:多个在网络中操作为单个路由器的路由节点,以及一个在所述多个路由节点之间转发包的交换结构。该交换结构包括至少一个耦合这些路由节点的多路光互连部件。In one embodiment, the present invention is introduced into a multi-chassis multi-chassis router comprising: a plurality of routing nodes operating as a single router in the network, and a packet forwarder between said plurality of routing nodes the exchange structure. The switch fabric includes at least one multipath optical interconnect coupling the routing nodes.
在另一实施例中,本实用新型被引入到多机架多机架路由器,该路由器包括:多个在网络中作为单个路由器进行操作的N个路由节点,以及一个具有M级的、在所述多个路由节点之间转发包的多级交换结构。多机架路由器还包括N×(M-1)个经由该交换结构来耦合路由节点的数据平面的多路点对点数据互连部件。In another embodiment, the present invention is introduced into a multi-chassis multi-chassis router comprising: a plurality of N routing nodes operating as a single router in the network, and a multi-chassis router with M A multi-level switching structure for forwarding packets between multiple routing nodes. The multi-chassis router also includes N x (M-1) multi-way point-to-point data interconnect components coupling the data planes of the routing nodes via the switch fabric.
在另一个实施例中,本实用新型被引入到用于在多机架路由器中连接多个路由节点的光缆。该光缆包括:用于从所述多个路由节点的第一路由节点中接收光信号的一个光缆输入,以及用于将一部分所述光信号输出到所剩余的路由节点中的每一个的多个光分路器(optical tap)。所述多个光分路器在多个路由节点所剩余的节点中基本等份地分割该光信号的光能。In another embodiment, the invention is incorporated into fiber optic cables for connecting multiple routing nodes in a multi-chassis router. The fiber optic cable comprises: a fiber optic cable input for receiving an optical signal from a first routing node of said plurality of routing nodes, and a plurality of optical cables for outputting a portion of said optical signal to each of the remaining routing nodes Optical splitter (optical tap). The plurality of optical splitters divide the optical energy of the optical signal substantially equally among the remaining nodes of the plurality of routing nodes.
在又一实施例中,本实用新型被引入到用于互连N个网络装置的一组光缆,该组光缆包括N个光缆,其中N是大于或等于2的整数。该N个光缆之中的每一个都包括:用于从所述N个网络装置的第一个中接收光信号的一个输入,以及用于将光信号输出到所述N-1个剩余网络装置的N-1个光分路器。该N-1个光分路器分割光信号以把该光信号的基本等份输出到该N-1个剩余网络装置中。In yet another embodiment, the present invention is incorporated into a set of optical cables for interconnecting N network devices, the set of optical cables includes N optical cables, where N is an integer greater than or equal to 2. Each of the N optical cables includes an input for receiving an optical signal from a first of said N network devices, and for outputting an optical signal to said N-1 remaining network devices N-1 optical splitters. The N-1 optical splitters split the optical signal to output substantially equal portions of the optical signal to the N-1 remaining network devices.
在进一步的实施例中,提出了一种方法,该方法包括:在多机架路由器中的多个路由节点之一处接收包、基于该包中的信息来选择波长(其中,该波长对应于在该多机架路由器中的一个路由节点)、以及把经由具有所选波长的光信号的该包从该多机架路由器中的路由节点之第一路由节点经由具有光互连部件的交换结构传输到路由节点之第二路由节点。In a further embodiment, a method is presented that includes receiving a packet at one of a plurality of routing nodes in a multi-chassis router, selecting a wavelength based on information in the packet (wherein the wavelength corresponds to a routing node in the multi-chassis router), and forwarding the packet via the optical signal with the selected wavelength from a first routing node of the routing nodes in the multi-chassis router via a switch fabric having an optical interconnect transmitted to the second routing node of the routing node.
在又进一步的实施例中,本实用新型被引入到一种网络装置,该装置包括多个转发节点和一组耦合这些转发节点的多路光互连部件。该网络装置在网络上连接其它装置。In yet a further embodiment, the invention is incorporated into a network arrangement comprising a plurality of forwarding nodes and a set of multi-way optical interconnection components coupling the forwarding nodes. The network device connects other devices on the network.
在更进一步的实施例中,本实用新型被引入到多个被耦合到网络上的网络装置,以及一个连接在该网络上的多个网络装置的多机架网络装置。该多机架网络装置包括:在该网络中作为单个装置进行操作的多个节点,以及在所述多个节点之间转发数据平面包的交换结构。该交换结构包括一组耦合这些节点的多路光互连部件。In still further embodiments, the present invention is incorporated into a plurality of network devices coupled to a network, and a multi-chassis network device connected to a plurality of network devices on the network. The multi-chassis network device includes a plurality of nodes operating as a single device in the network, and a switch fabric that forwards data plane packets between the plurality of nodes. The switch fabric includes a set of multiplexed optical interconnects coupling the nodes.
本实用新型的实施例可提供一个或多个的有益效果。例如,所描述的技术提供对多机架路由器(包括在专用机架之中的集中式交换结构)的选择。无需有包含集中式交换结构的专用机架,在多机架路由器中的每个机架也都可包括外部网络接口。所说明的技术允许伸缩多机架路由器而无需限制中央定位的交换结构的带宽容量以及无需限制能在单个中央机架上物理合适的光缆连接器插孔的数量。多路技术在多机架路由器的LCC中合并多个逻辑连接,从而减少电缆连接器插孔的数量和相互连接LCC所需的光缆数量。这就减少了多机架路由器的物理复杂性并增加了可用于诸如外部网络接口等其它用途的物理空间。Embodiments of the present invention may provide one or more beneficial effects. For example, the described technology provides an option for multi-chassis routers that include a centralized switching fabric in a dedicated chassis. Instead of having a dedicated chassis containing a centralized switching fabric, each chassis in a multi-chassis router can also include an external network interface. The described techniques allow scaling of multi-rack routers without limiting the bandwidth capacity of a centrally located switching fabric and without limiting the number of fiber optic cable connector jacks that can physically fit on a single central rack. Multiplexing combines multiple logical connections in the LCCs of a multi-chassis router, thereby reducing the number of cable connector jacks and the number of fiber optic cables required to interconnect the LCCs. This reduces the physical complexity of the multi-chassis router and increases the physical space available for other purposes such as external network interfaces.
在下面的附图和说明书中将描述本实用新型的一个或多个实施例的细节。本实用新型的其他特点、目的、优点将从说明书和附图,以及权利要求书中变得清楚起来。The details of one or more embodiments of the invention are set forth in the accompanying drawings and the description below. Other features, purposes and advantages of the present utility model will become clear from the specification, drawings, and claims.
附图说明 Description of drawings
图1是服务提供商网络之中含有多机架路由器的计算环境的实例框图;1 is an example block diagram of a computing environment including multi-chassis routers in a service provider network;
图2是示出了一种示例性多机架路由器的框图;Figure 2 is a block diagram illustrating an exemplary multi-chassis router;
图3是包括把含有多个通道的多路信号从某一交换结构加载到其它交换结构的光缆的系统的示意图;3 is a schematic diagram of a system including an optical cable carrying a multi-channel signal containing multiple channels from one switch fabric to another switch fabric;
图4是更详细示出了具有一个路由引擎和多个线卡的示例性线卡机架的框图;Figure 4 is a block diagram illustrating in greater detail an exemplary line card shelf having a Routing Engine and multiple line cards;
图5是示出了三级网络的框图;Figure 5 is a block diagram illustrating a three-level network;
图6是包括被配置成等分光输入信号的多个光分路器的光缆的示意图;6 is a schematic diagram of an optical cable including a plurality of optical splitters configured to equally split an optical input signal;
图7是示出了包括在圆形布局中被安排的十六个线卡机架的示例性多机架路由器的框图。7 is a block diagram illustrating an exemplary multi-chassis router including sixteen line card chassis arranged in a circular layout.
具体实施方式 Detailed ways
图1是示出了服务提供商网络6之中含有多机架路由器4的网络环境2的实例的框图。为了示例性的目的,本实用新型的原理根据图1中简化了的网络环境2进行说明,其中,多机架路由器4与边缘路由器5A和5B(“边缘路由器5”)进行通信以提供客户网络8A~8C(“客户网络8”)来对网络6进行访问。多机架路由器4可与边缘路由器5交换路由选择信息以便来保留网络环境2的拓扑结构之准确表示。多机架路由器4可由在服务提供商网络6之中操作为单个节点的多个协作路由部件构成。FIG. 1 is a block diagram illustrating an example of a
虽未示出,但服务提供商网络6可连接由其他提供商所管理的一个或多个网络,并因此可组成如互联网等大规模公共网络基础结构的一部分。进而,客户网络8可视为互联网的边缘网络。服务提供商网络6可在访问互联网的客户网络8中提供计算装置,并可允许客户网络8中的计算装置相互通信。在另一实例中,服务提供商网络6可在互联网的核心中提供网络服务。在上述任一实例中,服务提供商网络6可包括各种网络装置(未示出)而不是多机架路由器4和边缘路由器5,诸如附加的路由器、交换机、服务器或者其它装置。Although not shown, the service provider network 6 may connect to one or more networks managed by other providers, and thus may form part of a large-scale public network infrastructure such as the Internet. Furthermore, the customer network 8 can be regarded as an edge network of the Internet. Service provider network 6 may provide computing devices in customer network 8 with Internet access and may allow computing devices in customer network 8 to communicate with each other. In another example, service provider network 6 may provide network services in the core of the Internet. In any of the above examples, service provider network 6 may include various network devices (not shown) other than
在所示的实例中,边缘路由器5A经由访问链路9A来耦合于客户网络8A,而边缘路由器5B经由访问链路9B和9C分别耦合于客户网络8B和8C。客户网络8可为用于地理上分离的企业站点的网络。客户网络8可包括一个或多个的计算装置(未示出),诸如:个人电脑、便携式电脑、掌上电脑、工作站、服务器、交换机、打印机、客户数据中心或其它装置。图1所示的网络环境2的结构仅仅是示例性的。例如,服务提供商网络6可耦合于任意数量的客户网络8。然而,为了便于描述,在图1中仅示出了客户网络8A~8C。In the example shown, edge router 5A is coupled to
与本实用新型的原理相一致,多机架路由器4包括多个路由节点(未在图1示出),它们物理上被耦合并构造来作为单个路由节点进行操作。即,对于网络环境2的同级边缘路由器5,多机架路由器4显示为单个路由装置。例如,虽然多机架路由器4包括多个路由节点,但从同级边缘路由器5的角度来看,多机架路由器4具有单个网络地址并保留单个同级路由会话以用于保留与每个边缘路由器5的同级路由会话的每个路由协议。Consistent with the principles of the present invention,
如下进一步说明,多机架路由器4的多个路由节点通过使用多路光互连部件在多机架路由器4的数据平面上转发包,即,网络流量。在多机架路由器4的多个路由节点之间的控制面通信也可通过使用多路光互连或者通过其它方式发生。多机架路由器4包括多级交换结构,诸如3级Clos交换结构,其在通过使用多路通信经由光互连部件在这些路由节点之间中继(relay)包。本文所用的术语包指的既是定长又是变长数据单元。在不同的结构中,仅定长数据单元、仅变长数据单元、或者既定长又变长数据单元都可在这些路由节点之间进行中继。As explained further below, the multiple routing nodes of the
在某一示例性结构中,交换结构的各级可以非集中的方式在多机架路由器的单独路由节点中进行分布。例如,多机架路由器可包括多个线卡机架(LCC),其相互协作以便于操作为网络中的单个路由器,而无需包括截然不同的、集中式交换结构。多级交换结构的实现可分布于LCC,而LCC可通过使用多路通信来进行通信。另外,一个或多个中央交换结构节点,诸如交换控制机架(SCC),可并入多机架路由器。在任一情形中,这些路由节点之间的多路通信的使用可提供某些有益效果。例如,多路通信的使用减少了为实现互连节点的交换结构所需的光缆总长度。此外,多路通信可减少每个路由节点上所需的光缆接口的数量。其结果就是,多机架路由器4可更方便进行伸缩来合并增加的路由节点数量,而无需达到或超过多机架路由器将被配置于其中的有关环境方面的任何物理尺寸限制。In an exemplary configuration, the stages of the switch fabric may be distributed among individual routing nodes of the multi-chassis router in a decentralized manner. For example, a multi-chassis router may include multiple line card chassis (LCCs) that cooperate to operate as a single router in the network without including a distinct, centralized switching fabric. The implementation of the multi-stage switch fabric can be distributed among the LCCs, and the LCCs can communicate by using multi-way communication. Additionally, one or more central switch fabric nodes, such as Switch Control Chassis (SCC), may be incorporated into a multi-chassis router. In either case, the use of multiway communication between these routing nodes may provide certain benefits. For example, the use of multiplex communication reduces the overall length of fiber optic cable required to implement a switch fabric interconnecting nodes. Additionally, multiplexing reduces the number of fiber optic interfaces required on each routing node. As a result, the
图2是示出了一种示例性的经由网络在网络装置之间路由数据包的多机架路由器120的框图。多机架路由器120例如可更详细地示出图1的多机架路由器4的实例。FIG. 2 is a block diagram illustrating an
如图2所示,多机架路由器120包括多个操作为网络之中单个节点的合作的路由部件。在该实例中,多机架路由器120包括四个基本相同的LCC 128A~128D(“LCC 128”)。在其它实例中,多机架路由器可包括更多或更少的LCC,并还可包括连接这些LCC的中央路由节点。As shown in FIG. 2,
LCC 128之中的每一个都可用一组线卡134A~134D(“LC134”)进行构造,其中的每一个都包括包转发引擎(PFE)以及一组一个或多个独立接口卡(IFC)(未示出)以用于到来的和离去的网络通信。在该实例中,LCC 128之中每一个都还包括:路由引擎130A~130D(“路由引擎130”)之一,以及用于实施交换结构125A~125D(“交换结构125”)其中的多个部分的电子器件。Each of the LCCs 128 can be constructed with a set of
交换结构125提供在LCC 128之间转发包的多级交换机。如本文所述,交换结构125包括多路光互连部件136,其互连分布于独立的LCC 128的交换结构125A~125D其中的那些部分。在该实例中,多路光互连部件136由互连LCC 128的两组N个光缆构成,其中N表示LCC的数量,即,在此例中,N=4。也就是说,在此例中,每组光缆都包括四个光缆,这四个光缆之一连接于每个LCC128上的多路光输出。在一个实例中,交换结构125为三级交换结构,而每一个LCC 128都包括这三级之中每一个的一部分。多机架路由器120中的第一组光缆将每个LCC 128A的级1都连接到每个LCC的级2。在多机架路由器120中所用的第二组光缆将每个LCC128的级2都连接到每个LCC的级3。如下进一步说明,对于该交换结构的每一级,给定的LCC 128,诸如LCC 128A,可通过使用单个光缆来输出多路通信方式来与其它LCC(如LCC 128B~128D)之中的每一个都进行通信。以这种方式,不是用2N2个光缆,而是仅用2N个光缆就可提供互连多机架路由器120中的N个路由节点(LCC 128)的3级交换结构。在其它实施例中,或多或少的光缆都可用于连接交换结构125的不同部分。Switch fabric 125 provides multiple stages of switches that forward packets between LCCs 128 . As described herein, the switch fabric 125 includes a multi-way
继续用图2的实例,多路光互连部件136总共包括八个光缆。例如,这八个光缆之中每一个都可基本类似于图3中的光互连部件136A。用于每个LCC 128的交换结构125都包括两个多路光输出,即,一个输出是用于从交换结构的第一级到第二级的通信,而另一个输出是用于从第二级到第三级的通信。用于四个LCC 128的八个多路光输出之中的每一个都连接到八个光互连部件136之中的不同一个。LCC 128每个都还有六个输入以从其它LCC 128接收信号。每个光缆都包括三个光分路器,它们将光信号分布到其它LCC 128的输入。在一些实施例中,光缆的光分路器被构造来在连接于该光缆的所有光分路器之中输出基本等份的光信号。在一实施例中,LCC 128通过传输相同光信号的不同波长通道来输出多路通信。发往特定一个LCC 128的波长通道在这一个LCC 128之处被光学隔离,以从用于其它LCC 128的光通道中把相关通道分离。也可使用其它形式的多路技术,诸如时分多路技术(TDM)。Continuing with the example of FIG. 2, the multi-way
路由引擎130A~130D(“路由引擎130”)控制通过多机架路由器120转发的包。单独的光缆137可被用来在路由引擎130之间共享控制面信息。例如,路由引擎可经由光缆137相互进行通信以交换路由选择信息、状态信息、结构数据以及其它信息。例如,该路由选择信息可包括:描述经由该网络的各种路由的路由数据,还有在用于每个路由的网络中指示合适相邻装置的下一跃距数据。路由引擎130更新路由选择信息来准确反映当前的网络拓扑结构。类似于光互连部件136,其用于在LCC 128之间中继数据平面流量,光缆137也可为多路光互联。
路由引擎130还使用路由选择信息来导出转发信息库(forwarding information bases简称FIB)。路由引擎130在每个LCC128之中都安装FIB。用于LCC 128之一的FIB可相同或不同于其它LCC 128的FIB。路由引擎130可经由光缆137进行通信来协调FIB安装。因为光缆137提供专用连接,即从在LCC 128之间由多路光互连部件136所提供的数据包转发连接中分离出来的连接,所以,路由引擎130之中的FIB无需中断执行多机架路由器120的包转发就可进行更新。Routing engine 130 also uses the routing information to derive forwarding information bases (FIB for short). Routing Engine 130 installs a FIB in each LCC 128 . The FIB for one of the LCCs 128 may be the same or different from the FIBs of the other LCCs 128. Routing engine 130 may communicate via
下例示出了多机架路由器120的包转发操作。到来的包首先由例如LC 134B的LC 134的一个IFC从网络中接收,该LC 134将其引入到其PFE之一,后文称为所接收的PFE。所接收的PFE然后就通过使用在LCC上的如路由引擎130B的路由引擎所提供的FIB来确定用于数据包的下一跃距。如果该数据包在与初始接收该包的IFC相同的一个LCC 128上被发往一条离去的链路,所接收的PFE就转发该包到所述离去的链路。以此方式,在已被该网络所接收的相同PFE上发出的包就绕过交换结构125。The following example illustrates the packet forwarding operation of
否则,所接收的PFE将该数据包发送到交换结构125,其中,它被分布到正确的离去的LCC之中,即LCC 128之一。在LCC 128所离去的LCC中,该数据包就被转发到离去的PFE。在一些实施例中,数据包在所接收的PFE之处被分成更小的定长数据单元。然后,这些定长数据单元就可被分别地发送给所述离去的PFE,其中,它们被重新汇编成原始的、更大的数据包。这些更小的定长数据单元并不是每个都沿着所接收的PFE和所述离去的PFE之间的相同路径。这些实施例可提供比在交换结构125上进行转发之前未被分割的更大数据包的实施例对交换结构125更有效的利用。离去的PFE经由某一个LC 134上的IFC之一将数据包输出到适当的下一跃距。因此,由LCC 128之一所接收的、到来的包就可被另一个LCC 128沿着该包的最终目的之路由而发送到下一跃距。以与本实用新型的原理一致的方式进行操作的其它多机架路由器可使用不同的交换和路由机构。Otherwise, the received PFE sends the packet to the switch fabric 125, where it is distributed among the correct outgoing LCCs, namely one of the LCCs 128. In the LCC from which the LCC 128 departs, the packet is forwarded to the departing PFE. In some embodiments, the data packet is divided into smaller fixed-length data units at the received PFE. These fixed-length data units can then be sent individually to the outgoing PFE, where they are reassembled into the original, larger data packets. These smaller fixed-length data units do not each follow the same path between the received PFE and the outgoing PFE. These embodiments may provide more efficient utilization of switch fabric 125 than embodiments in which larger data packets are not fragmented prior to forwarding on switch fabric 125 . The outgoing PFE outputs the packet to the appropriate next hop via one of the IFCs on one of the LCs 134. Thus, an incoming packet received by one of the LCCs 128 may be routed to the next hop by the other LCC 128 along the route of the packet's ultimate destination. Other multi-chassis routers operating in a manner consistent with the principles of the invention may use different switching and routing mechanisms.
多机架路由器120,尤其是LCC 128可包括硬件、固件和/或软件,并可包括处理器、控制单元、离散的硬件电路或者用于执行从计算机可读介质中所提取的指令的其它逻辑电路。这些介质的实例包括:硬盘、闪存、随机存取存储器(RAM)、只读存储器(ROM)、非易失性随机存取存储器(NVRAM)、电可擦除可编程只读存储器(EEPROM)等等。
在多机架路由器120被描述为具有四个节点且每个节点都拥有三级交换结构的一部分的同时,其它实施例也可包括或多或少的节点,和/或具有比位于多于一个节点之上的大约三级的交换结构。在这些实施例之任一个中,成组的光缆可用于在多机架路由器的不同节点之中连接交换结构的不同级。例如,在具有N个节点的多机架路由器中,包括用于N个节点之每一个的某一个光缆的第一组N个光缆可被用于将该交换结构的第一级耦合到第二级。包括用于N个节点之每一个的某一个光缆的第二组N个光缆可被用于将该交换结构的第二级耦合到第三级,从而使得2N个光缆在多机架路由器120的数据平面中执行三级交换结构。N个光缆中的每一个都可包括:用于从N个节点之第一个中接收光信号的单个输入,以及用于将该光信号输出到所剩余的节点之中的N-1个光分路器。扩展这一结构到任何包括M级的交换结构,其中M至少是2,这就提供了M-1组光缆或者更具体来说,总共N×(M-1)个光缆。While
图3是更详细示出了图2一部分的示意图,并示在光互连部件136A上把多路信号240输出到交换结构125B~125D的交换结构125A。光互连部件136A经由光分路器283A~283C(“光分路器283”)将多路信号分布给交换结构125B~125D。FIG. 3 is a schematic diagram illustrating a portion of FIG. 2 in greater detail and shows switch
交换结构125A包括光信号发射器281。光信号发射器281发射含有具备不同波长的多个通道的光信号。例如,光信号发射器281可使用用于每个不同波长的激光。在图3所示的实例中,光信号发射器281能够发射包括高达三个波长的光信号一其对应于每一个交换结构125B~125D。
在多路转换器282中多个波长被物理组合成单个光信号240。从多路转换器282中,光信号240经由光缆连接器237而进入光缆236。光信号240毫无妨碍地穿过光纤239直到光信号240到达光分路器283A。为了允许毫无妨碍的通过,光纤239例如可由具有适合光通信特征的玻璃或塑料制成。Multiple wavelengths are physically combined into a single optical signal 240 in multiplexer 282 . From multiplexer 282 , optical signal 240 enters fiber optic cable 236 via fiber optic cable connector 237 . The optical signal 240 passes through the optical fiber 239 without hindrance until the optical signal 240 reaches the optical splitter 283A. To allow unhindered passage, the optical fiber 239 may be made, for example, of glass or plastic with suitable optical communication characteristics.
光分路器283A从光纤239重新导入光信号240的第一部分241A。光信号240的第一部分241A相同于初始光信号240,除了光信号240的第一部分241A具有比初始光信号240更低的密度之外。光信号240的第一部分241A穿过波长滤波器284A,其过滤出对应于通信通道但不被导入到交换结构125B的波长以隔离含有企图发往交换结构125B的信息的光通道。含有所企图发往交换结构125B的信息的波长可保持相同,从而使滤波器284A总是隔离相同的波长而不管光信号240的内容如何。Optical splitter 283A re-directs first portion 241A of optical signal 240 from optical fiber 239 . First portion 241A of optical signal 240 is identical to original optical signal 240 except that first portion 241A of optical signal 240 has a lower density than initial optical signal 240 . First portion 241A of optical signal 240 passes through wavelength filter 284A, which filters out wavelengths corresponding to communication channels but not directed to switch fabric 125B to isolate optical channels containing information intended for switch fabric 125B. The wavelength containing information intended for switch fabric 125B may remain the same so that filter 284A always blocks the same wavelength regardless of the content of optical signal 240 .
检测器285A检测所滤波的、光信号240的第一部分241A。例如,检测器285A可为:p通道的、固有的(intrinsic)、n通道检测器(PIN检测器),雪崩光电二极管(avalanche photodiode简称APD)或者其它检测器。检测器285A将所滤波的、光信号240的第一部分241A转换成电信号,检测器285A将其与交换结构125B进行通信。Detector 285A detects first portion 241A of filtered optical signal 240 . For example, the detector 285A can be: p-channel, intrinsic, n-channel detector (PIN detector), avalanche photodiode (APD for short), or other detectors. Detector 285A converts filtered first portion 241A of optical signal 240 into an electrical signal, which detector 285A communicates with switch fabric 125B.
在分接点241A之后,光信号240沿着光纤239继续向前直到光信号240到达光分路器283B。光分路器283B使第二部分241B从光信号240转向。第二部分241B由波长滤波器284B进行滤波。类似于波长滤波器284A,波长滤波器284B隔离含有企图发往交换结构125C的信息的通道。一般来说,波长滤波器284B隔离不同于波长滤波器284A和284C的通道。所滤波的第二部分241B由检测器285B进行检测,然后检测器285B把对应的电信号转发到交换结构125C。After the tap point 241A, the optical signal 240 continues along the optical fiber 239 until the optical signal 240 reaches the optical splitter 283B. Optical splitter 283B diverts second portion 241B from optical signal 240 . The second portion 241B is filtered by a wavelength filter 284B. Similar to wavelength filter 284A, wavelength filter 284B isolates channels containing information intended for
在光分路器283B之后,241C部分是光纤239中光信号240所有剩余部分。整个241C部分都由光分接点283C采集并由波长滤波器284C滤波。所滤波的第二部分241C由检测器285C进行检测,然后,检测器285C把对应的电信号转发到交换结构125D。After optical splitter 283B, portion 241C is all remaining portion of optical signal 240 in optical fiber 239 . The entire 241C portion is collected by optical tap 283C and filtered by wavelength filter 284C. Filtered second portion 241C is detected by detector 285C, which then forwards a corresponding electrical signal to switch
在示例性实施例中,光分路器283被构造以基本相等地分割光信号240。在此例中,光分路器283A去除三分之一的光信号240而光分路器283B又去除所剩三分之二光信号240中的一半。这就留下三分之一光信号240给光分路器283C,其全部消耗掉作为241C部分的、所剩余的三分之一光信号240。In an exemplary embodiment, optical splitter 283 is configured to split optical signal 240 substantially equally. In this example, the optical splitter 283A removes one-third of the optical signal 240 and the optical splitter 283B removes half of the remaining two-thirds of the optical signal 240 . This leaves one third of optical signal 240 to optical splitter 283C, which consumes the remaining third of optical signal 240 as part of 241C in its entirety.
滤波器284A~284C以及检测器285A~285C可或为光互连部件136A的一部分或为交换结构125的一部分,或这两者的组合。类似地,多路转换器282既可是光互连部件136A的一部分也可为交换结构125A的一部分,或这两者的组合。Filters 284A-284C and detectors 285A-285C may be either part of optical interconnect 136A or part of switch fabric 125, or a combination of both. Similarly, multiplexer 282 may be part of either optical interconnect 136A or switch
图4是示出了包括线卡机架(LCC)328A的详细视图的示例性多机架路由器320的框图,其表示多机架路由器的一个路由节点。其它路由节点,即,LCC 328B~LCC 328D都通常类似于LCC328A。进一步来说,多机架路由器320可类似或相同于图2的多机架路由器120。为了简洁,有关与多机架路由器120相同的多机架路由器320所描述的细节不在图4中详细说明。4 is a block diagram illustrating an
在此实例中,LCC 328A包括路由引擎330A和四个线卡(LC)334A1~334A4(“LC 334A”)。在LCC 328A中的每个LC 334A都包括包转发引擎(PFE)332A。每个LC 334A都进一步包括一组接口卡(IFC)368A,其提供用于接收包和发送包到外部网络的物理接口。每个LC 334A还都包括LC控制器366A,其根据来自于路由引擎330A的指令而在LC 334A中执行控制功能。In this example,
当LC 334A1上的IFC之一368A1接收到来的数据包时,IFC 368A1就转发所述到来的数据包给PFE 332A1。PFE 332A1就确定所到来的数据包是否具有要求该数据包转发到LCC 328A的IFC之一368A1的目的,或者要求该数据包根据路由引擎330A所提供的FIB转发到在多机架路由器320中的另一IFC。如果所到来的数据包将由LCC 328A的IFC之任一368A1输出,PFE 332A1就转发该数据包到IFC之一个适当368A1。如果不这样的话,PFE 332A1就转发该数据包到交换结构部分325A以经由多路光互连部件而中继到不同的LCC 328。When one of the IFCs 368A 1 on LC 334A 1 receives an incoming data packet, IFC 368A 1 forwards the incoming data packet to PFE 332A 1 . The PFE 332A1 determines whether the incoming packet has a purpose that requires the packet to be forwarded to one of the IFCs 368A1 of the
交换结构部分325A及其驻留在LCC 328B~328D中的类似交换结构部分构成三级交换结构。例如,该三级交换结构可为每级中都包括多个纵横交换机的Clos网络。LCC 328A~328D(LCC 328)中的每一个都包括这三级中每一个的一部分。如交换结构部分325A所示,将从LC 334A1关联的数据包首先被发送到级1交换机372A以传输到级2交换机。级1交换机372A可为纵横交换机或者其它交换机。在其它实施例中,LCC 328A上的级1的一部分可包括一个以上纵横交换机。该交换结构的级1的其它N-1个部分类似地位于LCC 328B~328D。
一旦由级1交换机372A接收,包就被导入到多机架路由器320的LCC 328之一中的交换结构的第二级。例如,该数据包可被导入到级2交换机374A,其位于LCC 328A的交换结构部分325A的内部,在此情形中,该包并不经由多路光通信而被中继到LCC 328之不同的一个。否则,该数据包由发射器381A作为光信号进行加密并由多路转换器382A传输到LCC 328B~328D之一中的级2交换结构部分。控制发射器381A来使用对应于该数据包企图发往的LCC 328B~328D之一上的下游波长滤波器的波长。Once received by stage 1 switch 372A, the packet is directed to the second stage of the switch fabric in one of the LCCs 328 of the
如图4所示,级2交换机374A不仅从交换机372A接收包,而且从位于LCC 328B~328D之上的类似于级1交换机接收包。输入384A~384C(“输入384”)经由光缆接收来自于位于LCC 328B~328D之上的级1部分的包。每个输入384都耦合于不同光缆的光分路器并从LCC 328B~328D中的不同一个接收光信号。光信号在输入384之处进行滤波以隔离对应于企图发往级2交换机374A的数据包的波长。在级2交换机374A之处接收的数据包或是直接转发到级3交换机376A,或是经由发射器381B和多路转换器382B而被中继到位于LCC 328B~328D的级3交换机。As shown in FIG. 4,
输入385A~385C(“输入385”)经由光缆从位于LCC328B-328D的级2交换机接收包。类似于输入384,每个输入385都耦合于不同光缆的光分路器并从LCC 328B~328D中的不同一个接收光信号。这些光信号在输入385处进行滤波以隔离对应于企图发往级3交换机376A的数据包的波长。
级3交换机376A包括连接到在LC 334A上的每个PFE 332A的离散输出(未示出)。级3交换机376A所接收的包对应于该包目的所要求的一组IFC 368A而被导入到PFE 332A。举例来说,如果包被PFE 332A1所接收,则PFE 332A1根据该包目的来转发该包到这一组IFC 368A中的一个。Stage 3 switch 376A includes discrete outputs (not shown) connected to each PFE 332A on LC 334A. Packets received by stage 3 switch 376A are directed to PFE 332A corresponding to the set of IFCs 368A required for the packet's purpose. For example, if a packet is received by PFE 332A 1 , PFE 332A 1 forwards the packet to one of the set of IFCs 368A according to the packet's purpose.
图5是示出了三级交换网络470的逻辑表示的框图。例如,三级网络470可逻辑表示图2的交换结构125。如由虚线425A~425N所表示,网络470的这三个级通过多机架路由器的路由节点(“路由节点425”)进行分布。网络470的这三级包括:由纵横交换机(crossbar switch)472A~472N(统称“交换机472”)构成的级1,由纵横交换机474A~474N(统称“交换机474”)构成的级2,以及由纵横交换机476A~476N(统称“交换机476”)构成的级3。交换机472经由输入478A~478N(统称“输入478”)接收数据包。交换机476经由输出480A~480N(统称“输出480”)中继该数据包。如图5所示,三级网络470的每一级都包括相同数量的纵横交换机。在其它实施例中,这些级可包括不同数量的纵横交换机。例如,级2可包括比级1或级3更多的纵横交换机以减少或消除输入478中的开放输入能被输出480的开放输出所阻碍的这种可能性。在级2中的这些额外的纵横交换机可位于交换结构425或其它地方之中。FIG. 5 is a block diagram showing a logical representation of a three-
为了建立通过网络470从输入478之一到所需的输出480的路径,与所接收的输入478相关的交换机472之一确定可用的级2交换机,其允许路径连接到包括所需输出480的级3交换机476。例如,假设由交换机472A所接收的包被中继到在交换机476A上的输出480之一。交换机472A利用到交换机472A和交换机476A这两者的开放连接来选择任一交换机474。假设交换机472A选择交换机474B。一旦交换机474B接收到数据包,交换机474B就确定到交换机476A的可用路径并转发该数据包到交换机476A。例如,交换机474B可具有多于一个到交换机476A的开放路径。To establish a path through the
如本文所述,在多个级之间的这些连接利用光多路技术,并且源自相同交换机的多个(如,源自交换机472A的N-1个路径)到级2交换机474A-N的路径,表示由相同光互连部件携带的不同波长所定义的N-1个通道。网络470中的每个交换机都可确定可用于包的路径。以此方式,由级1中的交换机472所接收的数据包可穿过将被级3中所需交换机476所接收的、级2中的任一交换机474。As described herein, these connections between stages utilize optical multiplexing, and multiple (e.g., N-1 paths originating from
交换结构被描述为包含三级交换网络的同时,在其它实施例中的交换结构也可包含不同的交换结构。例如,在三级网络中的第二级可被另一个三级网络所替代,从而组成五级网络。还有可能是其它的构造的交换结构。While the switch fabric is described as including a three-level switching network, the switch fabric in other embodiments may also include different switch fabrics. For example, the second level in a three-level network can be replaced by another three-level network, thereby forming a five-level network. Other configured switch fabrics are also possible.
图6是示出了用于具有十六个路由节点(即,N=16)的多机架路由器的单个光缆536的示意图。在此实例中,光缆536具有十五个光分路器592A~592O(“光分路器592”),这对于光缆整体来说是必备的。光分路器592在光缆536上被构造来等分从发射器581和多路转换器582所接收的光信号的光能。光缆536图示成耦合于波长滤波器和检测器组合件584A-584O(“组合件584”)。组合件584隔离含在该光信号中的数据的通道,并转发所隔离的通道到诸如多机架路由器中的节点等网络装置。在此实例中,因为有十五个光分路器592来等分光信号,所以,每个光分路器592都被设计来去除由发射器581传输的初始光信号的整个信号强度的十五分之一。FIG. 6 is a schematic diagram showing a single
实现等分光信号的结构如下。光分路器592A去除其所接收的信号的十五分之一。然而,因为每个所剩余的光分路器592的信号强度都降低了,所以每个后续的光分路器592都去除更大一部分的所剩信号强度。具体来说,每个光分路器592都按公式1去除一定比例的所剩信号强度:The structure for realizing equal division of optical signals is as follows.
P=1/Nr,(公式1)P=1/N r , (Equation 1)
其中,P等于偏向该光分路器的光能之比例,而Nr等于该光缆的剩余分接点的数量。Wherein, P is equal to the proportion of light energy deflected to the optical splitter, and Nr is equal to the number of remaining tap points of the optical cable.
公式1说明了上游光分路器在确定任一光分路器处去除的光信号比例的过程中并不需要被考虑。相反,仅仅重点考虑剩余下游光分路器的个数。这就意味着,在光缆536上的光分路器可从最接近于发射器581的光缆536的末端中去除,而无需干扰剩余的光分路器592的平均的分布。类似地,附加的光分路器可被添加到最接近于发射器581的光缆536的末端,而同时维持在光分路器592和任一新光分路器之间平均的分布。作为实例,被添加到最接近于发射器581的光缆536末端的第一光分路器会需要用光分路器592去除信号强度的十六分之一以具有平均的分布。Formula 1 shows that the upstream optical splitter does not need to be considered in the process of determining the proportion of the optical signal removed at any optical splitter. Instead, only focus on the number of remaining downstream optical splitters. This means that the optical splitter on the
随后,如上例所示,可以更小的子部制造光缆536。这可用于多机架路由器的升级,其中,新的节点被添加到预先存在的系统之中。例如,包括四个节点的多机架路由器可使用仅包括如图6的光分路器592M~592O的三个光分路器的光缆。如果该多机架路由器被扩展到包括八个节点,则要求有具备七个光分路器的光缆。包括如光分路器592I~592L的更多四个光分路器的光缆的部会被添加到光缆的上游侧以生成具有七个光分路器的光缆,从而提供到如光分路器592I~592O的这些光分路器的平均的信号分布。只要光信号强度仍然适合的话,这一技术能用于扩展光缆以包括任意数量的光分路器,而同时维持在该光缆上的所有光分路器之间的光信号的平均分布,从而便于多机架路由器的伸缩。Subsequently, the
图7是示出了包括被安排在圆形布局中的十六个LCC 628A~628P(LCC 628)于其中的多机架路由器640实施例的俯视图。多机架路由器640以基本类似于图2的多机架路由器120的方式进行操作。为了简单起见,有关于与多机架路由器120相同的多机架路由器640的描述细节并不在图7中进行详细讨论。7 is a top view illustrating an embodiment of a
LCC 628利用具有多路光互连部件的三级交换结构。例如,该三级交换结构可类似于图5的三级网络470。该三级交换结构包括多路光互连部件636以用于连接在LCC 628上三级交换结构的不同部分。在此实例中,每个LCC 628都包括两个发射器:一个发射器发射多路光信号以从级1转发数据包到级2,而另一发射器发射多路光信号以从级2转发数据包到级3。每个LCC 628也都包括三十个光信号输入-其一一对应于在其它所有十五个LCC 628上的两个发射器。The LCC 628 utilizes a three-level switch fabric with multiple optical interconnects. For example, the three-level switch fabric may be similar to the three-
每个LCC 628都具有梯形机架,以便LCC 628可轻易放置在类圆形结构之中。如本文所述进行生产的多路光缆可被安排在多机架路由器640的内圆之中,以互连LCC 628的交换结构。LCC 628的梯形形状还可在LCC 628的暴露侧654A~654O上提供相对更大的表面积。暴露侧654A~654O的大的表面积可被用来定位大量的插槽以插入具有物理网络接口的接口卡。LCC 628的梯形形状又限制多机架路由器640的整体接触面积。具体来说,在此实例中,LCC628的梯形形状允许十七个LCC 628以圆形紧紧放置在一起。然而,多机架路由器640仅利用十六个有效的(active)LCC 628。这一小于整圆的结构提供了间隙660,其允许管理员方便例如在维修服务期间可能需要的、对多机架路由器662中心的访问。具有梯形节点的多机架路由器的其它结构也是可能的,例如,多机架路由器可包括两组被分别安排在单独圆形结构之中的且由光缆连接的节点。作为另一实例,多个节点可彼此叠加以构成相邻的圆形结构。Each LCC 628 has a trapezoidal frame so that the LCC 628 can be easily placed in a circular configuration. Multi-lane fiber optic cables produced as described herein may be arranged in the inner circle of the
已经说明了本实用新型的各种实施例。然而,对所述实施例进行的修改仍在本实用新型范围内。例如,在已经参考通过使用波分多路技术来利用多路光互连部件的非集中式多机架路由器进行了说明的同时,本实用新型的实施例也包括单头或多头的多机架路由器。此外,诸如时分多路技术(TDM)的其它多路技术还可用于多机架路由器的交换结构之中。另外,这些技术可用于除了光之外的其它点对点通信介质,假设该点对点通信介质具有基本超过常规铜传导的带宽时延(bandwidth-delay)的产品。术语“带宽时延”指的是连接容量(以每秒位数为单位)乘以其首尾相连的时延(以秒为单位)的产品。其结果,以位(或字节)为单位所测量的数据量等于在任一给定时刻的“空中”数据量,即,已经被传输但未被接收的字节数。光的带宽时延产品例如可由在数百米距离进行传输的10GHz带宽计算出来。这些及其它实施例在所附的权利要求书所述的范围之中。Various embodiments of the invention have been described. However, modifications to the described embodiments are still within the scope of the invention. For example, while the description has been made with reference to a non-centralized multi-chassis router utilizing multiplexed optical interconnect components through the use of wavelength division multiplexing, embodiments of the present invention also include single-headed or multi-headed multi-chassis router. In addition, other multiplexing techniques such as time division multiplexing (TDM) can also be used in the switching fabric of multi-chassis routers. Additionally, these techniques can be used for other point-to-point communication media besides optical, provided that the point-to-point communication medium has a bandwidth-delay product that substantially exceeds the bandwidth-delay of conventional copper conduction. The term "bandwidth latency" refers to the product of the connection capacity (in bits per second) multiplied by its end-to-end latency (in seconds). As a result, the amount of data measured in bits (or bytes) is equal to the amount of data "in the air" at any given moment, ie, the number of bytes that have been transmitted but not received. Optical bandwidth-delay products, for example, can be calculated from a 10 GHz bandwidth transmitted over hundreds of meters. These and other embodiments are within the scope of the following claims.
Claims (14)
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US83925206P | 2006-08-21 | 2006-08-21 | |
| US60/839,252 | 2006-08-21 | ||
| US11/832,342 | 2007-08-01 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201075868Y true CN201075868Y (en) | 2008-06-18 |
Family
ID=39129419
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNU2007201554908U Expired - Lifetime CN201075868Y (en) | 2006-08-21 | 2007-08-21 | Multi spider route device with multipath optical interlinkage parts |
| CN2007101452966A Active CN101132286B (en) | 2006-08-21 | 2007-08-21 | Multi-chassis router with multi-way optical interconnect |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007101452966A Active CN101132286B (en) | 2006-08-21 | 2007-08-21 | Multi-chassis router with multi-way optical interconnect |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN201075868Y (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102158411A (en) * | 2006-08-21 | 2011-08-17 | 丛林网络公司 | Multi-chassis router with multiplexed optical interconnects |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917331B (en) * | 2008-09-11 | 2014-05-07 | 瞻博网络公司 | Systems, methods and devices for data centers |
| US8730954B2 (en) | 2008-09-11 | 2014-05-20 | Juniper Networks, Inc. | Methods and apparatus related to any-to-any connectivity within a data center |
| US8755396B2 (en) | 2008-09-11 | 2014-06-17 | Juniper Networks, Inc. | Methods and apparatus related to flow control within a data center switch fabric |
| US11271871B2 (en) | 2008-09-11 | 2022-03-08 | Juniper Networks, Inc. | Methods and apparatus related to a flexible data center security architecture |
| US9847953B2 (en) | 2008-09-11 | 2017-12-19 | Juniper Networks, Inc. | Methods and apparatus related to virtualization of data center resources |
| US8265071B2 (en) | 2008-09-11 | 2012-09-11 | Juniper Networks, Inc. | Methods and apparatus related to a flexible data center security architecture |
| US8154996B2 (en) * | 2008-09-11 | 2012-04-10 | Juniper Networks, Inc. | Methods and apparatus for flow control associated with multi-staged queues |
| EP2337372B1 (en) | 2009-12-18 | 2012-02-08 | Alcatel Lucent | High capacity switching system |
| US9813252B2 (en) | 2010-03-23 | 2017-11-07 | Juniper Networks, Inc. | Multicasting within a distributed control plane of a switch |
| US9240923B2 (en) | 2010-03-23 | 2016-01-19 | Juniper Networks, Inc. | Methods and apparatus for automatically provisioning resources within a distributed control plane of a switch |
| US9282060B2 (en) | 2010-12-15 | 2016-03-08 | Juniper Networks, Inc. | Methods and apparatus for dynamic resource management within a distributed control plane of a switch |
| CN102356598B (en) | 2011-08-23 | 2013-10-02 | 华为技术有限公司 | A multi-frame cascading device |
| CN102893564B (en) * | 2012-06-21 | 2016-03-09 | 华为技术有限公司 | A kind of router supporting multi-groove |
| WO2020227982A1 (en) * | 2019-05-15 | 2020-11-19 | Alibaba Group Holding Limited | System and method for flexible optical interconnect in data centers |
-
2007
- 2007-08-21 CN CNU2007201554908U patent/CN201075868Y/en not_active Expired - Lifetime
- 2007-08-21 CN CN2007101452966A patent/CN101132286B/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102158411A (en) * | 2006-08-21 | 2011-08-17 | 丛林网络公司 | Multi-chassis router with multiplexed optical interconnects |
| CN102158411B (en) * | 2006-08-21 | 2014-02-05 | 丛林网络公司 | Multi-chassis router with multiplexed optical interconnects |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101132286B (en) | 2012-10-03 |
| CN101132286A (en) | 2008-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102158411B (en) | Multi-chassis router with multiplexed optical interconnects | |
| CN201075868Y (en) | Multi spider route device with multipath optical interlinkage parts | |
| US11070437B2 (en) | Network interconnect as a switch | |
| US8503879B2 (en) | Hybrid optical/electrical switching system for data center networks | |
| AU2015283976B2 (en) | Data center path switch with improved path interconnection architecture | |
| US7406038B1 (en) | System and method for expansion of computer network switching system without disruption thereof | |
| US9332323B2 (en) | Method and apparatus for implementing a multi-dimensional optical circuit switching fabric | |
| EP2721775B1 (en) | Optical architecture and channel plan employing multi-fiber configurations for data center network switching | |
| EP3149905B1 (en) | A trading system | |
| EP3382935B1 (en) | Line card frame, multi-frame cluster router, routing, and message processing | |
| US10735839B2 (en) | Line card chassis, multi-chassis cluster router, and packet processing | |
| KR101324058B1 (en) | High capacity switching system | |
| JP2005521330A (en) | Supervisory channel in optical network systems | |
| JPH11331224A (en) | Wavelength division multiplex optical communication network provided with passive path through in each node | |
| WO2011047715A1 (en) | Optical transport switching node with framer | |
| EP2521326B1 (en) | Run-time scalable switching fabric | |
| US20160269279A1 (en) | Contiguous network for cloud communications | |
| CN1984003B (en) | Distributed communication equipment architectures and techniques | |
| US12520065B2 (en) | Advertising an IP address of loopback interfaces to participating OSPF areas | |
| CN1445956A (en) | Dynamic multiple wavelength grouping ring transmission system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee |
Owner name: JUNIPER NETWORKS INC. Free format text: FORMER NAME: NETSCREEN TECHNOLOGIES INC. |
|
| CP01 | Change in the name or title of a patent holder |
Address after: California, USA Patentee after: Juniper Networks, Inc. Address before: California, USA Patentee before: Jungle network |
|
| CX01 | Expiry of patent term | ||
| CX01 | Expiry of patent term |
Granted publication date: 20080618 |