WO2017088789A1 - 线卡框、多框集群路由器、及报文处理 - Google Patents

线卡框、多框集群路由器、及报文处理 Download PDF

Info

Publication number
WO2017088789A1
WO2017088789A1 PCT/CN2016/107053 CN2016107053W WO2017088789A1 WO 2017088789 A1 WO2017088789 A1 WO 2017088789A1 CN 2016107053 W CN2016107053 W CN 2016107053W WO 2017088789 A1 WO2017088789 A1 WO 2017088789A1
Authority
WO
WIPO (PCT)
Prior art keywords
line card
unit
optical
card frame
frame
Prior art date
Application number
PCT/CN2016/107053
Other languages
English (en)
French (fr)
Inventor
杨武
Original Assignee
新华三技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 新华三技术有限公司 filed Critical 新华三技术有限公司
Priority to EP16868012.2A priority Critical patent/EP3382965B1/en
Priority to US15/778,458 priority patent/US10735839B2/en
Priority to JP2018543419A priority patent/JP6605747B2/ja
Publication of WO2017088789A1 publication Critical patent/WO2017088789A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/10—Packet switching elements characterised by the switching fabric construction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
    • H04Q11/0062—Network aspects
    • H04Q11/0071—Provisions for the electrical-optical layer interface
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04J—MULTIPLEX COMMUNICATION
    • H04J14/00—Optical multiplex systems
    • H04J14/02—Wavelength-division multiplex systems
    • H04J14/0227—Operation, administration, maintenance or provisioning [OAMP] of WDM networks, e.g. media access, routing or wavelength allocation
    • H04J14/0254—Optical medium access
    • H04J14/0267—Optical signaling or routing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/15—Interconnection of switching modules
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/15—Interconnection of switching modules
    • H04L49/1553—Interconnection of ATM switching modules, e.g. ATM switching fabrics
    • H04L49/1561—Distribute and route fabrics, e.g. Batcher-Banyan
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q1/00—Details of selecting apparatus or arrangements
    • H04Q1/02—Constructional details
    • H04Q1/04—Frames or mounting racks for selector switches; Accessories therefor, e.g. frame cover
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q1/00—Details of selecting apparatus or arrangements
    • H04Q1/18—Electrical details
    • H04Q1/30—Signalling arrangements; Manipulation of signalling currents
    • H04Q1/50—Conversion between different kinds of signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
    • H04Q11/0005—Switch and router aspects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
    • H04Q11/0062—Network aspects
    • H04Q11/0066—Provisions for optical burst or packet networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H04Q11/04—Selecting arrangements for multiplex systems for time-division multiplexing
    • H04Q11/06—Time-space-time switching
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/25—Routing or path finding in a switch fabric

Definitions

  • a router is a network infrastructure device that operates on the third layer of the Open Systems Interconnection Protocol model, that is, a packet switching device at the network layer, which has the capability of connecting different network types and can select a message transmission path.
  • Open Systems Interconnection Protocol model that is, a packet switching device at the network layer, which has the capability of connecting different network types and can select a message transmission path.
  • FIG. 1 is a side view and a front view of a line card frame of a router according to an embodiment of the present application
  • FIG. 2 is a functional block diagram of a multi-chassis cluster router according to an embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a connection relationship of a line card frame according to an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram of a connection relationship between a line card unit and a photoelectric conversion unit according to an embodiment of the present application
  • FIG. 5 is a schematic diagram of a connection relationship of an optical interface unit according to an embodiment of the present disclosure
  • FIG. 6 is a schematic structural diagram of an internal structure of an optical connector according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic diagram of an internal structure of an optical connector and a cluster interface according to an embodiment of the present disclosure
  • FIG. 8 is a schematic diagram of a connection relationship between a line card unit and a photoelectric conversion unit according to an embodiment of the present application
  • FIG. 9 is a schematic diagram of a 4 ⁇ 4 multi-core optical fiber cross-connection between an on-board optical component module and an optical connector according to an embodiment of the present application;
  • FIG. 10 is a functional block diagram of a switching unit of a central switching frame according to an embodiment of the present disclosure.
  • FIG. 11 is a flowchart of packet forwarding processing in a multi-chassis cluster system according to an embodiment of the present disclosure.
  • the router has many parameters.
  • the number of slots is the maximum number of line card units (or service processing units) that the router can provide.
  • the interface capacity is the maximum number of ports that the router can provide.
  • the interface capacity the number of line card units ⁇
  • the switching capacity is a technical indicator of the capacity of the switching network, and refers to the maximum throughput of the switching network.
  • the switching capacity, the number of slots, and the interface capacity of the core node router cannot meet the requirements, especially when the deployment is completed, the requirement is not met, and the operator hopes that the router of the core node can be elastically expandable.
  • the switching capacity and interface capacity can be expanded by multiple router devices, so that a multi-chassis cluster router emerges.
  • Multi-chassis clustering refers to the use of cascading technology to interconnect existing single-chassis routers to form a new multi-chassis cluster system, which is extended in terms of switching capacity, number of slots, and interface capacity.
  • Multi-chassis cluster routers usually consist of a central switch chassis, a line card chassis, and interconnect fibers. In a multi-chassis cluster router, packet exchange between the line card frame and the line card frame is implemented through a central switching frame.
  • FIG. 1 is a side view and a front view of a line card frame of a router according to an embodiment of the present application.
  • the cluster router line card frame provided by the embodiment of the present application adopts a three-level structure of “main control unit 104 / line card unit 101 + photoelectric conversion unit 107 + fan unit 105 ”, wherein multiple units of the same function Parallel to each other, the space they occupy is at the same level.
  • each line card unit 101 or main control unit 104 occupies a first stage slot
  • each photoelectric conversion unit 107 occupies a second stage slot
  • the fan unit 105 occupies a level 3 slot.
  • the classification of the slots is only for distinguishing the various portions of the laminated structure, and does not limit the present application.
  • the line card unit 101 and the photoelectric conversion unit 107 are electrically connected without a backplane, so that the switching capacity, the slot density, and the interface density of the single-line card frame can be improved without changing the height of the router chassis.
  • the air inlet hole is provided on the panel of the main control unit/line card unit, and the cold air enters from the air inlet hole, and the hot air can be formed through the main control unit/line card unit and the photoelectric conversion unit in sequence, and then passed through The fan unit is discharged.
  • the non-backplane orthogonal electrical connection means that the single board and the single board (the line card unit and the switching unit) are directly connected through the connector without the connection of the printed circuit board, and the single board and the single board
  • the angle between the two is 90 degrees or 270 degrees; it is different from the traditional backplane connection and the backplane orthogonal connection.
  • the switching unit of the line card frame cannot provide the cascaded fiber interface on the panel, that is, the line card frame cannot be cascaded to the central switch frame through the switching unit; With the improvement of forwarding performance, large-capacity switching and photoelectric conversion functions are simultaneously realized in the slot of the switching unit, and engineering practice is more difficult. Therefore, the embodiment of the present application provides a corresponding new multi-frame cluster router.
  • FIG. 2 is a functional block diagram of a multi-chassis cluster router according to an embodiment of the present application.
  • the multi-chassis cluster router is composed of a line card frame 100, a central switching frame 300, and a line card frame 200.
  • the line card frame 100 and the central switching frame 300 are connected by an optical fiber 400, and the central switching frame 300 and the line card frame are connected.
  • 200 is connected by fiber 500.
  • the line card frame 100 includes a plurality of line card units 101 and a plurality of photoelectric conversion units 107; similarly, the line card frame 200 includes a plurality of line card units 201 and a plurality of photoelectric conversion units 207.
  • the backplane unit is removed in the line card frame 100, and the switching unit is replaced with the photoelectric conversion unit 107, and the photoelectric conversion unit 107 occupies the slot where the original switching unit is located.
  • the backplane unit is removed within the line card frame 200, and the switching unit is replaced with the photoelectric conversion unit 207.
  • the line card frame 100 adopts a 3-stage slot structure, each line card unit 101 occupies a first-stage slot, each photoelectric conversion unit 107 occupies a second-stage slot, and the fan unit 105 occupies a third-stage slot;
  • the card unit 101 and the photoelectric conversion unit 107 are electrically connected without a backplane.
  • the multi-chassis cluster router since the switching capacity of the multi-chassis cluster router is very large, the multi-chassis cluster router still adopts a multi-stage switching architecture, but the first, second, and third levels are all selected. It is implemented by the switching unit 301 of the central switching frame 300.
  • the line card frames 100 and 200 do not implement the first and third level routing, and the routing between the different line card units in the line card frames 100 and 200 is also implemented by the central switching frame 300.
  • FIG. 3 is a schematic structural diagram of a connection relationship of a line card frame according to an embodiment of the present disclosure. As shown in FIG. 3, in order to adapt to the electromechanical structure of FIG. 1, the embodiment of the present application improves the connection relationship of the line card frame as follows:
  • the part of the line card unit slot in the line card frame is changed to the fiber interface unit slot, that is, the cluster of the router is realized by sacrificing part of the line card unit slot; the fiber interface unit 106 is connected to the photoelectric conversion unit 107 through the optical connector 1062.
  • the optical connector 1062 is smaller than the electrical connection.
  • the device 1013 is thus capable of achieving higher density, and the fiber interface unit 106 occupies less slot space; in addition, the electrical connector 1013 and the optical connector 1062 can be easily replaced without the backplane connection so that the chassis is not changed.
  • the photoelectric conversion unit 107 has an on-board optical component module 1071 for realizing mutual conversion of optical signals and electrical signals.
  • the onboard optical component module 1071 has an electrical signal interface and an optical signal interface.
  • the electrical signal interface of the onboard optical component module 1071 is connected to the line card unit 101 through the electrical connector 1013, and the optical signal interface of the onboard optical component module 1071 is passed through the optical fiber 1063.
  • the optical connector 1062 is coupled to the fiber optic interface unit 106.
  • the fiber optic interface unit 106 then connects the optical signal on the optical connector 1062 to the cluster interface 1061 on the router panel via the optical fiber 1064, through the series of connections, from the message processing module 1012.
  • the signal eventually reaches the cluster interface 1061.
  • the cluster interface 1061 of the line card frame is connected to the switching unit of the central switching frame or to the cluster interface of another line card frame.
  • the signal of the cluster interface 1061 may be all or part of the message processing unit 1012 from within the line card frame.
  • the line card unit 101 includes a message processing module 1012.
  • each of the cluster interface 1061 and all the message processing modules 1012 in the line card frame have The signal transmission channel; and/or each message processing module 1012 in the line card frame has a signal transmission channel with all the cluster interfaces 1061 of the line card frame.
  • the signal transmission channel means that the signal can be transmitted in the medium from the starting end to the destination end, and the medium includes not limited to the message processing module, the printed circuit board, the electrical connector, the switch chip module, and the photoelectric conversion. Modules, optical fibers, optical connectors, etc.
  • the signals of each cluster interface 1061 are averaged from all message processing modules 1012 of all line card units 101 of the line card frame 100.
  • the cluster interface is used to implement the cascading between the frames of the router, that is, the cluster of the router is realized by sacrificing the slot of the part of the line card unit; and the level between the line card frame and the central switching frame is implemented in the case of the central switching frame. Union.
  • the optical connector 1062 supports the insertion and removal of the optical fiber interface unit 106, and also supports the insertion and removal of the photoelectric conversion unit 107.
  • the electrical connector 1013 supports the insertion and removal of the line card unit 101, and also supports the insertion and removal of the photoelectric conversion unit 107.
  • the signal driving circuit is added to the electrical signal transmission path of the onboard optical module module 1071 to the line card unit 101.
  • the optical connector 1062 may include a plurality of sub-interfaces, each of which provides a multi-core fiber optic interconnection.
  • the cluster interface 1061 may include a plurality of sub-interfaces, each of which provides a multi-core optical fiber interconnection.
  • FIG. 4 is a schematic diagram of a connection relationship between a line card unit and a photoelectric conversion unit according to an embodiment of the present application.
  • each packet processing module 1012 has a link connection with all the photoelectric conversion units 107 in the line card frame in which the message processing module 1012 is located, thereby achieving an even distribution of the connection signals of each message processing module 1012. All the photoelectric conversion units 107 in the line card frame where the message processing module 1012 is located.
  • the connection load of the message processing module 1012 is shared to all of the photoelectric conversion units 107, so that the system has redundancy, and when one photoelectric conversion unit 107 fails, the non-blocking line speed forwarding can still be guaranteed.
  • each line card unit 101 provides three message processing modules 1012, each message processing module.
  • 1012 has 36 Lanes (36 receiving and 36 transmitting) signals to the photoelectric conversion unit 107
  • each photoelectric conversion unit 107 provides three optical connectors 1062
  • each optical connector 1062 provides six sub-interfaces
  • each photoelectric conversion unit 107 There are a total of 18 onboard optical component modules 1071.
  • Each onboard optical component module 1071 converts 12Lanes (12 transmit and 12 receive) signals into 24-core optical signals
  • each fiber optic interface unit 106 provides 12 cluster interfaces 1061.
  • Each cluster interface 1061 provides three sub-interfaces.
  • the message processing module 1012 and the six photoelectric conversion units 107 are connected by a link, so that the 36Lanes signal of the message processing module 1012 is evenly distributed to the six photoelectric conversion units 107, and each photoelectric conversion unit 107 is obtained.
  • the onboard optical module virtual unit 1072, each onboard optical module virtual unit .1072 obtains 1Lanes of each message processing module 1012, that is, 36Lanes of each onboard optical module virtual unit 1072 from 36 message processing modules 1012, That is, each message processing module 1012 provides a 1 Lane signal to an onboard optical module virtual unit 1072.
  • Each onboard optical module virtual unit 1072 includes three onboard optical component modules 1071, such that each onboard optical module virtual unit 1072 converts 36Lanes electrical signals into 72 core optical signals and is then coupled to optical connectors 1062, each The optical connector 1062 provides six sub-interfaces 1063, each of which provides a 24-core multimode fiber.
  • the 72-core multimode fiber signals of the three sub-interfaces 1063 are from an on-board optical module virtual unit 1072, so these signals average from the 1 signal signal of each of the 36 message processing modules of the 12 line card units.
  • FIG. 5 is a schematic diagram of a connection relationship of an optical interface unit according to an embodiment of the present disclosure.
  • each cluster interface 1061 provides a 72-core multimode optical interface (ie, three 24-core sub-interfaces) connected to three sub-interfaces of the optical connector 1062.
  • the 72-core optical fiber signal of the cluster interface 1061 The 36 Lanes signal averages 36 message processing modules 1012 from the 12 line card units 101.
  • FIG. 6 is a schematic diagram of the internal structure of an optical connector according to an embodiment of the present application.
  • the optical connector 1062 includes a plurality of sub-interfaces 1063, each of which provides a multi-core fiber connection.
  • the connection density of the optical signal can be increased, and on the other hand, the engineering practice difficulty of the optical connector can be reduced.
  • the optical connector 1062 can protect the optical fiber head, that is, protect the sub-interface optical connector and the optical fiber from damage during the plugging and unplugging process.
  • the cluster interface 1061 adopts multiple sub-interfaces to increase the connection density of the optical signals and reduce the engineering practice difficulty of the sub-interface optical connection.
  • the number of the line card frame and the central switch frame fiber can be simplified, and the engineering wiring is easier to implement.
  • a higher density fiber optic connector and a multi-core branch cable are employed.
  • the sub-interface 1063 of the optical connector 1062 is a 72-core optical interface
  • the sub-interface of the cluster interface 1061a is 24 cores
  • the sub-interface of the cluster interface 1061b is 72 cores.
  • an embodiment of the present application provides a solution for implementing the optical connector 1062 and the onboard optical component module 1071 by optical fiber cross-connection.
  • the optical signal is connected between.
  • the onboard optical component module 1071 is disposed in the vicinity of the corresponding electrical connector 1013, thereby improving the complicated layout and connection layer through the printed circuit board. The number is large, the transmission distance is long, and the electrical signal quality is poor.
  • FIG. 8 is a schematic diagram of a connection relationship between a line card unit and a photoelectric conversion unit according to an embodiment of the present application.
  • the optical cross-connect unit 1073 realizes optical signal interconnection of the on-board optical component module 1071 to the optical connector 1062, and finally realizes that the 72-core optical signal (36Lanes signal) of the cluster interface is averaged from 36 message processing. Module.
  • the optical cross-connect unit 1073 can be implemented by a multi-core branch fiber or an optical backplane (Shuffle).
  • the basic principle is the same, and all are optical fiber connections, but the physical mediums are different.
  • FIG. 9 is a schematic diagram of a 4 ⁇ 4 multi-core optical fiber cross-connection between an on-board optical component module and an optical connector according to an embodiment of the present application.
  • the optical signals from the different onboard optical component modules are connected to different optical connectors or sub-interfaces of the optical connectors through fiber optic patch cords.
  • the fiber jumper refers to the change of the interface between the inbound direction and the outbound direction through the connection relationship inside the optical fiber, or the change of the interface signal line sequence.
  • the four optical fibers from the on-board optical module 1 are connected to the optical connector 1, the optical connector 2, the optical connector 3, and the optical connector 4, respectively.
  • the multi-chassis cluster router also employs a multi-stage switching architecture.
  • the embodiment of the present invention provides a multi-chassis cluster router, which includes a central switching frame and a line card frame.
  • the central switching frame and the line card frame are interconnected by optical fibers, and the line card frame described above is used.
  • the central switching frame implements routing between different line card units in the same line card frame, and routing between different line card frames.
  • the multi-chassis cluster router provided by the embodiment of the present application includes a first type of routing unit and a second type of routing unit; wherein the second type of routing unit is connected to the cluster interface and the first type of routing unit To realize the routing from the cluster interface in the same line card frame to the first type of routing unit or from the first type of routing unit to the cluster interface; the first type of routing unit is connected to the second type of routing unit to achieve no The routing of the second type of routing unit between the line card frames.
  • FIG. 10 is a functional block diagram of a switching unit of a central switching frame according to an embodiment of the present disclosure.
  • an exchange unit 301 provided in accordance with an embodiment of the present application includes a second level routing unit 3011, a first level routing unit 3012, and a third level routing unit 3012.
  • the first-stage routing unit 3012 and the third-level routing unit 3012 are completely identical in connection relationship and function, except that the first-level routing unit is in the direction of the entry, and the third-level selection is in the exit direction.
  • the road unit is not divided into the following, and is collectively referred to as the second type of routing unit.
  • the second-level routing unit 3011 becomes the first type of routing unit.
  • Each of the first and third-level routing units 3012 is connected to each of the cluster interface 1061 and the plurality of second-level routing units 3011, and implements from the cluster interface 1061 to the second-level routing unit 3011 or from the first The routing of the secondary routing unit 3011 to the cluster interface 1061.
  • the second-stage routing unit 3011 connects the plurality of first- and third-level routing units 3012 to implement routing between different first- and third-level routing units 3012.
  • the embodiment of the invention further provides a packet processing method, which adopts the multi-chassis cluster router described above, and includes the following steps:
  • the line card unit of the ingress line card frame performs packet inbound processing, and sends the message to the photoelectric conversion unit of the ingress line card frame;
  • the photoelectric conversion unit converts an electrical signal into an optical signal, and transmits the optical signal to a central switching frame;
  • the central switch box exchanges packets, and the inbound interface converts the optical signal into an electrical signal, and searches for the destination line card frame according to the packet header, and the outbound interface converts the electrical signal into an optical signal, and transmits the optical signal to the destination line card frame;
  • the photoelectric conversion unit of the destination line card frame converts the optical signal into an electrical signal, and transmits the electrical signal to the destination line card unit;
  • the destination line card unit performs packet outbound processing and sends the message.
  • FIG. 11 is a flowchart of packet forwarding processing in a multi-chassis cluster system according to an embodiment of the present disclosure.
  • a packet processing process provided by another embodiment of the present application includes:
  • Step S1201 The line card unit 101 of the entry line card frame 100 performs packet inbound processing, including Packet parsing, traffic classification, caching, traffic management, table lookup forwarding, message slicing, and headers are then sent to the opto-electronic conversion unit.
  • packet inbound processing including Packet parsing, traffic classification, caching, traffic management, table lookup forwarding, message slicing, and headers are then sent to the opto-electronic conversion unit.
  • Step S1202 The photoelectric conversion unit 107 performs a process of converting an electrical signal into an optical signal: sequentially passing the onboard optical component module, the optical connector, the cluster interface and the optical fiber between the optical fibers, the optical fiber 400, and then transmitting the optical signal to the central switch. Block 300.
  • Step S1203 The central switching frame 300 performs packet exchange: the inbound interface converts the optical signal into an electrical signal, searches the destination line card frame 200 according to the packet header, and the outbound interface converts the electrical signal into an optical signal, and sends the signal to the destination line card frame 200. .
  • Step S1204 The photoelectric conversion unit 207 of the destination line card frame 200 converts the optical signal into an electrical signal: sequentially passes through the optical fiber 500, the cluster interface of the destination line card frame, the optical connector, the onboard optical component module, and the optical fiber between them.
  • the line card unit 201 is sent to the destination line card unit 201, wherein the line card unit corresponding to the destination network is the destination line card unit.
  • Step S1205 The line card unit that receives the electrical signal, that is, the destination line card unit, performs packet outgoing direction processing: packet reassembly, service quality assurance (traffic management, queue scheduling, etc.), link layer information addition, and transmission. Message.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请公开了一种线卡框，所述线卡框内包括线卡单元、光电转换单元以及光纤接口单元；光电转换单元中具有板载光组件模块，用于实现光信号和电信号的相互转换；板载光组件模块的电信号接口通过电连接器连接到线卡单元，板载光组件模块的光信号接口通过光连接器连接到光纤接口单元；光纤接口单元通过光纤将光信号连接到路由器面板上的集群接口，所述集群接口用于实现路由器的不同框之间的级联。本申请还公开了多框集群路由器及报文处理方法。

Description

线卡框、多框集群路由器、及报文处理
发明背景
路由器是工作在开放系统互连协议模型的第三层的网络基础设备，即网络层的分组交换设备，具有连接不同网络类型的能力，并能够选择报文传输路径。随着互联网的飞速发展，对作为网络基础设备的路由器提出进一步的要求；很多情况下，核心节点路由器的交换容量、槽位数量和接口容量不能满足需求。
附图简要说明
图1为本申请实施例提供的路由器的线卡框的侧视图与前视图；
图2为本申请实施例提供的多框集群路由器功能框图；
图3为本申请实施例提供的线卡框的连接关系结构示意图；
图4为本申请实施例提供的线卡单元与光电转换单元的连接关系示意图；
图5为本申请实施例提供的光接口单元连接关系示意图；
图6为本申请实施例提供的光连接器内部结构示意图；
图7为本申请实施例提供的光连接器和集群接口的内部结构示意图；
图8为本申请实施例提供的线卡单元与光电转换单元连接关系示意图；
图9为本申请实施例提供的板载光组件模块与光连接器之间的4×4多芯光纤交叉互连示意图；
图10为本申请实施例提供的中央交换框的交换单元功能框图；
图11为本申请实施例提供的多框集群系统报文转发处理流程图。
实施本申请的方式
为使本申请技术方案的技术原理、特点以及技术效果更加清楚，以下结合具体实施例对本申请技术方案进行详细阐述。
路由器有许多参数，例如，槽位数量是路由器最大可提供的线卡单元(或称业务处理单元)的数量；接口容量是路由器最大可以提供某种端口的数量，接口容量＝线卡单元数量×每个线卡单元的端口数量；交换容量是交换网能力的技术指标，指交换网最大的吞吐能力。在核心节点路由器的交换容量、槽位数量和接口容量不能满足需求的情况下，尤其可能是在刚刚部署完成即不满足需求，运营商希望核心节点的路由器能够弹性可扩充。在一台路由器设备不能满足的情况下，可以通过多台路由器设备扩充交换容量和接口容量，这样，多框集群路由器应运而生。
多框集群是指利用级联技术将原有的单机框路由器互连，组成一个新的多框集群系统，在交换容量、槽位数量和接口容量上进行扩展。多框集群路由器通常由中央交换框、线卡框和互连光纤组成。在多框集群路由器中，线卡框与线卡框之间的报文交换通过中央交换框实现。
图1为本申请实施例提供的路由器的线卡框的侧视图与前视图。请参见图1，本申请实施例提供的集群路由器线卡框采用“主控单元104/线卡单元101+光电转换单元107+风扇单元105”的三级结构，其中，相同功能的多个单元彼此平行，它们所占据的空间位于同一级。如图1所示，每一个线卡单元101或主控单元104占据一个第1级槽位，每一个光电转换单元107占据一个第2级槽位，风扇单元105占据第3级槽位。此处，槽位的分级只是用于区分层叠结构的各部分，并不限制本申请。
线卡单元101与光电转换单元107之间采用无背板正交电连接，这样，可以在不改变路由器机箱高度的情况下，提高了单线卡框的交换容量、槽位密度和接口密度，而且支持前后风道。在本申请实施例中，在主控单元/线卡单元的面板上提供进风孔，冷风从进风孔进入，可以依次穿过主控单元/线卡单元、光电转换单元形成热风，然后通过风扇单元排出。所述无背板正交电连接，是指单板与单板(线卡单元与交换单元)之间通过连接器直接连接，而无需印制电路板实现的连接，且单板与单板之间的角度为90度或270度；区别于传统的背板连接、背板正交连接。
若采用传统的线卡框硬件结构，通常线卡框的交换单元无法在面板上提供级联的光纤接口，即线卡框将无法通过交换单元级联到中央交换框；另外，随着交换容量和转发性能的提升，在交换单元槽位上同时实现大容量的交换和光电转换功能，工程实践难度加大。因此，本申请实施例提供了相应的新的多框集群路由器。
图2为本申请实施例提供的多框集群路由器功能框图。请参见图2，多框集群路由器由线卡框100、中央交换框300和线卡框200组成，线卡框100与中央交换框300之间通过光纤400连接，中央交换框300与线卡框200之间通过光纤500连接。线卡框100内包括多个线卡单元101和多个光电转换单元107；类似地，线卡框200内包括多个线卡单元201和多个光电转换单元207。与传统的集群路由器线卡框相比，线卡框100内移除了背板单元，并将交换单元替换为光电转换单元107，光电转换单元107占据原先交换单元所在的槽位。同理，线卡框200内移除了背板单元，并将交换单元替换为光电转换单元207。线卡框100采用3级槽位结构，每一个线卡单元101占据一个第1级槽位，每一个光电转换单元107占据一个第2级槽位，风扇单元105占据第3级槽位；线卡单元101与光电转换单元107之间采用无背板正交电连接。
在本申请实施例提供的多框集群路由器线卡框结构中，由于多框集群路由器的交换容量非常巨大，多框集群路由器还是采用多级交换架构，但第1、2、3级选路都是由中央交换框300的交换单元301实现。线卡框100和200不实现第1、3级选路，线卡框100和200内不同线卡单元之间的选路也由中央交换框300实现。
图3为本申请实施例提供的线卡框的连接关系结构示意图。如图3所示，为了适应图1的机电结构，本申请实施例对于线卡框连接关系做出如下改进：
将线卡框中的一部分线卡单元槽位更改为光纤接口单元槽位，即通过牺牲部分线卡单元槽位实现路由器的集群；光纤接口单元106通过光连接器1062连接光电转换单元107。通常情况下，光连接器1062的体积小于电连接 器1013，因此能够实现更高密度，光纤接口单元106仅占用较少的槽位空间；此外，无背板连接使得机框不变更的情况下很容易更换电连接器1013和光连接器1062。
光电转换单元107中具有板载光组件模块1071，用于实现光信号和电信号的相互转换。板载光组件模块1071具有电信号接口与光信号接口，板载光组件模块1071的电信号接口通过电连接器1013连接到线卡单元101，板载光组件模块1071的光信号接口通过光纤1063和光连接器1062连接到光纤接口单元106，光纤接口单元106通过光纤1064再将光连接器1062上的光信号连接到路由器面板上的集群接口1061，通过上述一系列连接，来自报文处理模块1012的信号最终到达集群接口1061。然后，线卡框的集群接口1061连接到中央交换框的交换单元，或者连接到另一个线卡框的集群接口。
集群接口1061的信号可以是来自本线卡框内的全部或部分报文处理单元1012。
线卡单元101包括报文处理模块1012；为了使线卡单元的报文处理模块的信号能够到达集群接口，进一步的，每个集群接口1061与本线卡框内的所有报文处理模块1012具有信号传输通道；和/或，本线卡框内的每个报文处理模块1012与本线卡框的所有集群接口1061具有信号传输通道。所述具有信号传输通道，指的是信号可以在介质中传输，从起始端达到目的端，所述介质包括不限于报文处理模块、印制板电路、电连接器、交换芯片模块、光电转换模块、光纤、光连接器等。
根据本申请实施例，每个集群接口1061的信号平均来自线卡框100的所有线卡单元101的所有报文处理模块1012。集群接口用于实现路由器的各框之间的级联，即通过牺牲部分线卡单元槽位实现路由器的集群；在有中央交换框的情况下，实现线卡框与中央交换框之间的级联。
根据本申请实施例，光连接器1062支持光纤接口单元106的插拔，也支持光电转换单元107的插拔。
根据本申请实施例，电连接器1013支持线卡单元101的插拔，也支持光电转换单元107的插拔。
根据本申请实施例，在传输距离较远的情况下，在板载光组件模块1071到线卡单元101的电信号传输通路上，增加信号驱动电路。
根据本申请实施例，光连接器1062可以包括多个子接口，每个子接口提供多芯光纤互连。
根据本申请实施例，集群接口1061可以包括多个子接口，每个子接口提供多芯光纤互连。
图4为本申请实施例提供的线卡单元与光电转换单元的连接关系示意图。请参考图4，每个报文处理模块1012与该报文处理模块1012所在的线卡框内的所有光电转换单元107具备链路连接，从而实现每个报文处理模块1012的连接信号平均分配到该报文处理模块1012所在的线卡框内的所有光电转换单元107。这样，报文处理模块1012的连接负载分担到所有的光电转换单元107，使系统具有冗余，当一个光电转换单元107故障时，仍然能够保证无阻塞线速转发。
为了便于进一步理解本申请实施例提供的线卡单元101与光电转换单元107连接关系，以下通过具体示例进行说明。假设在一个线卡框中共有12个线卡单元101、6个光电转换单元107、3个光纤接口单元106，每个线卡单元101提供3个报文处理模块1012，每个报文处理模块1012共有36Lanes(36个接收和36个发送)信号到光电转换单元107，每个光电转换单元107提供3个光连接器1062，每个光连接器1062提供6个子接口，每个光电转换单元107共有18个板载光组件模块1071，每个板载光组件模块1071将12Lanes(12个发送和12个接收)信号转换为24芯光信号，每个光纤接口单元106提供12个集群接口1061，每个集群接口1061提供3个子接口。
如图4所示，报文处理模块1012与6个光电转换单元107具备链路连接，从而实现报文处理模块1012的36Lanes信号平均分配到6个光电转换单元107，每个光电转换单元107得到6Lanes；将18个板载光组件模块1071分成6个 板载光模块虚拟单元1072，每个板载光模块虚拟单元.1072得到每个报文处理模块1012的1Lanes，即每个板载光模块虚拟单元1072的36Lanes来自36个报文处理模块1012，即每个报文处理模块1012分别提供1Lane信号给一个板载光模块虚拟单元1072。
每个板载光模块虚拟单元1072包括3个板载光组件模块1071，因此每个板载光模块虚拟单元1072将36Lanes的电信号转换为72芯光信号后连接到光连接器1062，每个光连接器1062提供6个子接口1063，每个子接口1063提供24芯多模光纤。3个子接口1063的72芯多模光纤信号来自一个板载光模块虚拟单元1072，所以这些信号平均来自12个线卡单元的36个报文处理模块各1Lane信号。
图5为本申请实施例提供的光接口单元连接关系示意图。请参考图5，每个集群接口1061提供72芯多模光接口(即3个24芯子接口)连接到光连接器1062的3个子接口，综上所述，集群接口1061的72芯光纤信号(即36Lanes信号)平均来自12个线卡单元101的36个报文处理模块1012。
图6为本申请实施例提供的光连接器内部结构示意图。请参考图6，光连接器1062包括多个子接口1063，每个子接口1063提供多芯光纤连接。通过使用多个子接口，一方面可以提高光信号的连接密度，另一方面又可以降低光连接器的工程实践难度。插拔光纤接口单元106和光电转换单元107时，光连接器1062能够保护光纤头部，即在插拔过程中保护子接口光连接器和光纤不受损坏。
集群接口1061采用多个子接口也可以提高光信号的连接密度，降低子接口光连接的工程实践难度；另外一方面还可以简化线卡框与中央交换框光纤的数量，工程布线更容易实现。
根据本申请实施例，采用更高密度的光纤连接器和多芯分支光纤(Breakout Cable)。如图7所示，假设光连接器1062的子接口1063为72芯的光接口，集群接口1061a的子接口为24芯，集群接口1061b的子接口为72芯。
对于光连接器1062与板载光组件模块1071之间的光连接的具体实现方式，本申请的实施例提供了一种解决方案，通过光纤交叉连接实现光连接器1062与板载光组件模块1071之间的光信号连接。根据本申请一个实施例，在光电转换单元107的印制电路板上，将板载光组件模块1071就近布置到相应的电连接器1013附近，从而改善了通过印制电路板连接布局复杂、层数较多、传输距离远、电气信号质量差的特点。
图8为本申请实施例提供的线卡单元与光电转换单元连接关系示意图。请参考图8，光交叉互连单元1073实现板载光组件模块1071到光连接器1062的光信号互连，最终实现集群接口的72芯光信号(36Lanes信号)还是平均来自36个报文处理模块。
光交叉互连单元1073可以通过多芯分支光纤或光背板(Shuffle)实现，其基本原理都是相同的，都是光纤的连接，只是承载的物理介质不同。
图9为本申请实施例提供的板载光组件模块与光连接器之间的4×4多芯光纤交叉互连示意图。请参考图9，来自不同的板载光组件模块的光信号通过光纤跳线的模式连接到不同的光连接器或光连接器的子接口。光纤跳线是指通过光纤内部的连接关系，实现入方向与出方向接口的改变，或接口信号线序的改变。例如，来自板载光组件模块1的四根光纤分别连接到光连接器1、光连接器2、光连接器3和光连接器4。
本申请的各个实施例中，多框集群路由器还是采用多级交换架构。
本申请实施例提供一种多框集群路由器，包括中央交换框以及线卡框，中央交换框与线卡框之间通过光纤互连，采用上述所述的线卡框。
所述中央交换框实现同一线卡框内不同线卡单元之间的选路，以及不同线卡框之间的选路。
进一步的，本申请实施例提供的多框集群路由器，中央交换框包括第一类选路单元和第二类选路单元；其中，第二类选路单元连接集群接口和第一类选路单元，实现从同一线卡框内集群接口到第一类选路单元或者从第一类选路单元到集群接口的选路；第一类选路单元连接第二类选路单元，实现不 同线卡框之间的第二类选路单元的选路。
图10为本申请实施例提供的中央交换框的交换单元功能框图。请参考图10，跟据本申请一个实施例中提供的交换单元301包括了第二级选路单元3011、第一级选路单元3012和第三级选路单元3012。其中，第一级选路单元3012和第三级选路单元3012在连接关系和功能上完全一致，只是在入口方向上的是第一级选路单元，在出口方向上的是第三级选路单元，故以下不作区分，统称为第二类选路单元，相对应地，第二级选路单元3011成为第一类选路单元。每个第一、三级选路单元3012连接线卡框100中的每一个集群接口1061和多个第二级选路单元3011，实现从集群接口1061到第二级选路单元3011或者从第二级选路单元3011到集群接口1061的选路。第二级选路单元3011连接多个第一、三级选路单元3012，实现不同的第一、三级选路单元3012之间的选路。
本发明实施例还提供了一种报文处理方法，该方法采用上述所述的多框集群路由器，包括如下步骤：
入口线卡框的线卡单元进行报文入方向处理，将报文发送到入口线卡框的光电转换单元；
所述光电转换单元将电信号转换为光信号，将光信号传输至中央交换框；
中央交换框进行报文交换，入接口将光信号转化为电信号，根据报文头查找目的线卡框，出接口将电信号转换为光信号，将光信号传输至目的线卡框；
目的线卡框的光电转换单元将光信号转换为电信号，将电信号传输至目的线卡单元；
目的线卡单元执行报文出方向处理，发送所述报文。
图11为本申请实施例提供的多框集群系统报文转发处理流程图。请参考图11，基于图2和图3的所述的多框集群路由器，本申请的另一实施例提供的报文处理流程包括：
步骤S1201：入口线卡框100的线卡单元101进行报文入方向处理，包括 报文解析、流分类、缓存、流量管理、查表转发、报文切片和贴头，然后将报文发送到光电转换单元。
步骤S1202：光电转换单元107执行电信号转换为光信号的过程：依次通过板载光组件模块、光连接器、、集群接口及其之间的光纤、光纤400，然后将光信号发送到中央交换框300。
步骤S1203：中央交换框300进行报文交换：入接口将光信号转化为电信号，根据报文头查找目的线卡框200，出接口将电信号转换为光信号，发送到目的线卡框200。
步骤S1204：目的线卡框200的光电转换单元207将光信号转换为电信号：依次通过光纤500、目的线卡框的集群接口、光连接器、板载光组件模块及其之间的光纤，发送到目的线卡单元201，其中，目的网络对应的线卡单元为目的线卡单元。
步骤S1205：接收到所述电信号的线卡单元即所述目的线卡单元执行报文出方向处理：报文重组、服务质量保证(流量管理、队列调度等)、链路层信息添加，发送报文。
应当理解，虽然本说明书是按照各个实施方式描述的，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施方式中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请的保护范围，凡在本申请技术方案的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。

Claims (10)

  1. 一种线卡框，其特征在于，所述线卡框内包括线卡单元、光电转换单元以及光纤接口单元；
    光电转换单元中具有板载光组件模块，用于实现光信号和电信号的相互转换；板载光组件模块的电信号接口通过电连接器连接到线卡单元，板载光组件模块的光信号接口通过光连接器连接到光纤接口单元；
    光纤接口单元通过光纤将光信号连接到路由器面板上的集群接口，所述集群接口用于实现路由器的不同框之间的级联。
  2. 根据权利要求1所述的线卡框，其特征在于，
    所述线卡单元包括报文处理模块；
    每个集群接口与本线卡框内的所有报文处理模块具有信号传输通道；和/或，
    本线卡框内的每个报文处理模块，与本线卡框的所有集群接口具有信号传输通道。
  3. 根据权利要求2所述的线卡框，其特征在于，每个集群接口与本线卡框内的所有光电转换单元具有信号传输通道；和/或，
    本线卡框内的每个报文处理模块，与本线卡框内的所有光电转换单元具有信号传输通道。
  4. 根据权利要求1所述的线卡框，其特征在于，线卡框内还包括风扇单元；所述线卡框采用3级槽位结构，每一个线卡单元或光纤接口单元占据一个第1级槽位，每一个光电转换单元占据一个第2级槽位，风扇单元占据第3级槽位；线卡单元与光电转换单元之间采用无背板正交电连接，光纤接口单元与光电转换单元之间采用光连接。
  5. 根据权利要求1所述的线卡框，其特征在于，在板载光组件模块到线卡单元的电信号传输通路上，还包括信号驱动电路。
  6. 根据权利要求1所述的线卡框，其特征在于，所述光电转换单元进一步包括光交叉互连模块；
    通过光交叉互连模块实现光连接器与板载光组件模块之间的光信号连接。
  7. 根据权利要求5所述的线卡框，其特征在于，光交叉互连模块为多芯分支光纤或光背板。
  8. 一种多框集群路由器，包括中央交换框以及线卡框，中央交换框与线卡框之间通过光纤互连，其特征在于，所述线卡框为如权利要求1至7任一所述的线卡框；
    所述中央交换框实现同一线卡框内不同线卡单元之间的选路，以及不同线卡框之间的选路。
  9. 根据权利要求8所述的多框集群路由器，其特征在于，中央交换框包括第一类选路单元和第二类选路单元；其中，第二类选路单元连接集群接口和第一类选路单元，实现从同一线卡框内集群接口到第一类选路单元或者从第一类选路单元到集群接口的选路；第一类选路单元连接第二类选路单元，实现不同线卡框之间的第二类选路单元的选路。
  10. 一种报文处理方法，其特征在于，该方法采用如权利要求9所述的多框集群路由器，包括如下步骤：
    入口线卡框的线卡单元进行报文入方向处理，将报文发送到入口线卡框的光电转换单元；
    所述光电转换单元将电信号转换为光信号，将光信号传输至中央交换框；
    中央交换框进行报文交换，入接口将光信号转化为电信号，根据报文头查找目的线卡框，出接口将电信号转换为光信号，将光信号传输至目的线卡框；
    目的线卡框的光电转换单元将光信号转换为电信号，将电信号传输至目的线卡单元；
    目的线卡单元执行报文出方向处理，发送所述报文。
PCT/CN2016/107053 2015-11-24 2016-11-24 线卡框、多框集群路由器、及报文处理 WO2017088789A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP16868012.2A EP3382965B1 (en) 2015-11-24 2016-11-24 Line card frame, multi-frame cluster router, and message processing
US15/778,458 US10735839B2 (en) 2015-11-24 2016-11-24 Line card chassis, multi-chassis cluster router, and packet processing
JP2018543419A JP6605747B2 (ja) 2015-11-24 2016-11-24 ラインカードシャーシ、マルチシャーシクラスタルータおよびパケット処理

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510823203.5 2015-11-24
CN201510823203.5A CN106789753B (zh) 2015-11-24 2015-11-24 一种线卡框、多框集群路由器、及报文处理方法

Publications (1)

Publication Number Publication Date
WO2017088789A1 true WO2017088789A1 (zh) 2017-06-01

Family

ID=58763950

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/107053 WO2017088789A1 (zh) 2015-11-24 2016-11-24 线卡框、多框集群路由器、及报文处理

Country Status (5)

Country Link
US (1) US10735839B2 (zh)
EP (1) EP3382965B1 (zh)
JP (1) JP6605747B2 (zh)
CN (1) CN106789753B (zh)
WO (1) WO2017088789A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106789753B (zh) * 2015-11-24 2020-06-26 新华三技术有限公司 一种线卡框、多框集群路由器、及报文处理方法
CN106789679B (zh) * 2015-11-24 2020-02-21 新华三技术有限公司 一种线卡框、多框集群路由器、选路及报文处理方法
GB2561974B (en) * 2017-03-23 2022-05-04 Rockley Photonics Ltd Leaf switch module and optoelectronic switch
CN107239427B (zh) 2017-06-09 2020-12-01 华为技术有限公司 连接装置、网板连接系统和通信设备
CN107426635A (zh) * 2017-06-29 2017-12-01 北京华为数字技术有限公司 一种光互联系统
WO2019099602A1 (en) * 2017-11-20 2019-05-23 Corning Research & Development Corporation Optical interconnect assemblies and associated systems for large-scale spine and leaf topologies
CN111865837B (zh) * 2018-04-03 2024-04-12 华为技术有限公司 数据通信系统和方法
CN109861745B (zh) * 2019-01-02 2021-05-07 新华三技术有限公司 一种故障处理方法和集群路由器
CN110046128A (zh) * 2019-02-28 2019-07-23 西南电子技术研究所（中国电子科技集团公司第十研究所） 高速光纤互连背板

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7720061B1 (en) * 2006-08-18 2010-05-18 Juniper Networks, Inc. Distributed solution for managing periodic communications in a multi-chassis routing system
CN102326358A (zh) * 2008-10-29 2012-01-18 华为技术有限公司 一种集群系统扩容方法、装置及集群系统
CN102726058A (zh) * 2011-11-25 2012-10-10 华为技术有限公司 多框集群的光网络交换节点、光突发同步方法及线路框

Family Cites Families (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07307962A (ja) * 1994-03-17 1995-11-21 Fujitsu Ltd 回路基板の実装構造
US6647208B1 (en) * 1999-03-18 2003-11-11 Massachusetts Institute Of Technology Hybrid electronic/optical switch system
US6934471B1 (en) * 1999-06-03 2005-08-23 Avici Systems, Inc. Photonic switch using time-slot interchange
US7013084B2 (en) 2001-02-28 2006-03-14 Lambda Opticalsystems Corporation Multi-tiered control architecture for adaptive optical networks, and methods and apparatus therefor
US7110394B1 (en) 2001-06-25 2006-09-19 Sanera Systems, Inc. Packet switching apparatus including cascade ports and method for switching packets
US7106729B1 (en) 2001-10-29 2006-09-12 Ciena Corporation Switching control mechanism based upon the logical partitioning of a switch element
US6694083B2 (en) 2001-11-14 2004-02-17 Harris Corporation Device including a fiber optic cable harness and associated methods
GB0208797D0 (en) * 2002-04-17 2002-05-29 Univ Cambridge Tech IP-Capable switch
US20050089027A1 (en) * 2002-06-18 2005-04-28 Colton John R. Intelligent optical data switching system
US6796716B1 (en) * 2002-07-01 2004-09-28 Nortel Networks, Ltd. Network device containing an optical module having optical and electrical connections facing one direction
JP4623010B2 (ja) * 2004-11-18 2011-02-02 日本電気株式会社 スイッチ装置、スイッチ方法及びスイッチ制御用プログラム
JP4553768B2 (ja) 2005-03-29 2010-09-29 富士通株式会社 光パケットスイッチシステム
US8050559B2 (en) 2006-08-21 2011-11-01 Juniper Networks, Inc. Multi-chassis router with multiplexed optical interconnects
JP5012232B2 (ja) * 2007-06-08 2012-08-29 富士通株式会社 光スイッチ装置
CN101098238B (zh) 2007-06-29 2010-12-22 华为技术有限公司 一种数据通信系统、交换网板及方法
WO2009105281A2 (en) * 2008-02-22 2009-08-27 Opvista Incorporated Spectrally efficient parallel optical wdm channels for long-haul man and wan optical networks
CN101296186B (zh) 2008-06-13 2010-12-22 杭州华三通信技术有限公司 一种路由交换设备、方法和交换线卡板
CN101631081B (zh) 2009-08-12 2011-06-08 华为技术有限公司 一种多级交换网
CN102217252B (zh) * 2009-08-14 2013-10-09 华为技术有限公司 集群设备的通信系统
CN101895398B (zh) 2010-07-15 2012-07-25 华为技术有限公司 数据通信方法和装置
CN101917337B (zh) * 2010-08-09 2015-06-03 中兴通讯股份有限公司 路由器集群中板间互联的装置及方法
US8982905B2 (en) 2011-05-16 2015-03-17 International Business Machines Corporation Fabric interconnect for distributed fabric architecture
EP2670082A4 (en) 2011-08-23 2014-02-19 Huawei Tech Co Ltd MULTI-CHASSIS CASCADE DEVICE
US9042229B2 (en) 2011-10-06 2015-05-26 International Business Machines Corporation Partitioning a network switch into multiple switching domains
US9116313B2 (en) * 2012-04-11 2015-08-25 Cisco Technology, Inc. Silicon photonics structures with pluggable light sources
CN102907054B (zh) 2012-08-03 2014-06-25 华为技术有限公司 一种数据交换方法、装置及系统
CN103067795B (zh) * 2013-01-05 2016-03-30 北京华为数字技术有限公司 多框集群系统、中央交换框及实现数据交换的方法
US9020356B2 (en) 2013-02-07 2015-04-28 Verizon Patent And Licensing Inc. Polarization multiplexed short distance connection
CN104641593B (zh) 2013-03-01 2018-02-13 华为技术有限公司 网板和通信设备
US9544667B2 (en) * 2013-10-14 2017-01-10 Nec Corporation Burst switching system using optical cross-connect as switch fabric
US9258255B2 (en) * 2014-04-11 2016-02-09 Cisco Technology, Inc. Hierarchical programming of dual-stack switches in a network environment
CN106789679B (zh) * 2015-11-24 2020-02-21 新华三技术有限公司 一种线卡框、多框集群路由器、选路及报文处理方法
CN106789753B (zh) * 2015-11-24 2020-06-26 新华三技术有限公司 一种线卡框、多框集群路由器、及报文处理方法
US9967048B1 (en) * 2016-10-14 2018-05-08 Juniper Networks, Inc. Optical transceiver with external laser source

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7720061B1 (en) * 2006-08-18 2010-05-18 Juniper Networks, Inc. Distributed solution for managing periodic communications in a multi-chassis routing system
CN102326358A (zh) * 2008-10-29 2012-01-18 华为技术有限公司 一种集群系统扩容方法、装置及集群系统
CN102726058A (zh) * 2011-11-25 2012-10-10 华为技术有限公司 多框集群的光网络交换节点、光突发同步方法及线路框

Also Published As

Publication number Publication date
JP2018533331A (ja) 2018-11-08
US20190253777A1 (en) 2019-08-15
EP3382965A4 (en) 2018-11-21
JP6605747B2 (ja) 2019-11-13
EP3382965B1 (en) 2023-08-23
US10735839B2 (en) 2020-08-04
CN106789753B (zh) 2020-06-26
EP3382965A1 (en) 2018-10-03
CN106789753A (zh) 2017-05-31

Similar Documents

Publication Publication Date Title
WO2017088789A1 (zh) 线卡框、多框集群路由器、及报文处理
WO2017088781A1 (zh) 线卡框、多框集群路由器、选路及报文处理
US11671330B2 (en) Network interconnect as a switch
US8842688B2 (en) Reducing cabling complexity in large-scale networks
JP6434533B2 (ja) Ｐｉｃスイッチを使用するスケーラブルなフォトニックパケットアーキテクチャのための装置および方法
CN106954102B (zh) 一种光背板子架装置
US20150312657A1 (en) Data Center Network and Method for Deploying the Data Center Network
US20080279094A1 (en) Switching System And Method For Improving Switching Bandwidth
WO2009015574A1 (fr) Trame d'échange, routeur de mise en grappes
US11102110B2 (en) Data center network (DCN) architecture and communication
WO2017143940A1 (zh) 一种交换方法及交换系统
WO2015154511A1 (zh) 光信号的交叉系统、交叉处理方法及装置
CN110337838B (zh) 突破性的模块系统
WO2021159936A1 (zh) 连接结构及设备安装方法
US20150355690A1 (en) Communication apparatus
CN208782834U (zh) 一种用于多主机管理的交换机
CN214101389U (zh) 互联系统和互联模块
EP3097700B1 (en) Packet switch using physical layer fiber pathways
WO2021228204A1 (zh) 一种电子设备
CN108768897B (zh) 端口扩展设备和堆叠系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16868012

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2018543419

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016868012

Country of ref document: EP