WO2023001020A1 - 基于正交架构的业务板卡启动方法、业务板卡及正交设备 - Google Patents

基于正交架构的业务板卡启动方法、业务板卡及正交设备 Download PDF

Info

Publication number
WO2023001020A1
WO2023001020A1 PCT/CN2022/105086 CN2022105086W WO2023001020A1 WO 2023001020 A1 WO2023001020 A1 WO 2023001020A1 CN 2022105086 W CN2022105086 W CN 2022105086W WO 2023001020 A1 WO2023001020 A1 WO 2023001020A1
Authority
WO
WIPO (PCT)
Prior art keywords
service
processing unit
service processing
unit
control unit
Prior art date
Application number
PCT/CN2022/105086
Other languages
English (en)
French (fr)
Inventor
付国辉
谢永恒
万月亮
Original Assignee
北京锐安科技有限公司
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 北京锐安科技有限公司 filed Critical 北京锐安科技有限公司
Publication of WO2023001020A1 publication Critical patent/WO2023001020A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/4401—Bootstrapping
    • G06F9/4405—Initialisation of multiprocessor systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/4401—Bootstrapping
    • G06F9/4416—Network booting; Remote initial program loading [RIPL]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/4401—Bootstrapping
    • G06F9/4418—Suspend and resume; Hibernate and awake

Definitions

  • the present application relates to the communication field, for example, to a method for starting a service board based on an orthogonal architecture, a service board and an orthogonal device.
  • a network device based on an orthogonal architecture can be equipped with multiple control boards, multiple service boards and multiple switching boards. Among them, the business board and the switching board are directly connected, and the data in the business board can directly reach the switching board, which greatly reduces transmission loss, not only improves the transmission efficiency of data exchange, but also provides greater switching capacity and processing Scalability.
  • the embodiment of the present application provides a method for starting a business board based on an orthogonal architecture, a business board and an orthogonal device, so as to solve the problem of controlling the central processing unit (Central Processing Unit) by setting different target physical addresses for each business processing unit.
  • Unit, CPU Central Processing Unit
  • Unit, CPU has the problem of Internet Protocol (Internet Protocol, IP) conflict when making upper-layer application calls, so as to achieve the effect of improving the throughput of network equipment and being easy to manage.
  • IP Internet Protocol
  • the embodiment of the present application provides a method for starting a service board based on an orthogonal architecture.
  • the service board includes: a control unit, a plurality of service processing units, and a coding unit; the method includes:
  • the encoding unit assigns a different encoding to each of the service processing units after the service board is powered on;
  • Each of the business processing units determines the target physical address of the business processing unit according to the assigned code, and modifies the initial physical address of the business processing unit to the target physical address;
  • the control unit controls the startup of the corresponding service processing unit through each target physical address.
  • the embodiment of the present application also provides a service board based on an orthogonal architecture, including: a control unit, a plurality of service processing units, and a coding unit, and the plurality of service processing units are connected to the control unit and the coding unit respectively.
  • the encoding unit is electrically connected;
  • the encoding unit is configured to assign a different encoding to each of the service processing units after the service board is powered on;
  • Each of the business processing units is configured to determine the target physical address of the business processing unit according to the assigned code, and modify the initial physical address of the business processing unit to the target physical address;
  • the control unit is configured to control the startup of the corresponding service processing unit through each of the target physical addresses.
  • the embodiment of the present application further provides an orthogonal device, including the service board based on the orthogonal architecture as described in the second aspect.
  • FIG. 1 is a schematic structural diagram of an orthogonal device provided in an embodiment of the present application.
  • FIG. 2 is a flow chart of a method for starting a service board based on an orthogonal architecture provided in Embodiment 1 of the present application;
  • FIG. 3 is a schematic structural diagram of a service board based on an orthogonal architecture provided in an embodiment of the present application
  • FIG. 4 is a flow chart of a method for starting a service board application DP startup module based on an orthogonal architecture provided in Embodiment 2 of the present application;
  • FIG. 5 is a flow chart of a delay waiting method for connecting a service processing unit provided in Embodiment 3 of the present application;
  • FIG. 6 is a flow chart of a method for calling a loading module for loading provided in Embodiment 4 of the present application.
  • FIG. 1 is a schematic structural diagram of an orthogonal device provided by an embodiment of the present application.
  • the orthogonal device adopts an orthogonal architecture, and the orthogonal architecture adopts the direct connection between the service board and the switching board, so the data can directly reach the switching board, greatly reducing transmission loss, improving switching transmission efficiency, and providing greater switching capacity and processing
  • Expansion capabilities provide a cost-effective, highly modular, compatible, and scalable hardware architecture for next-generation converged communications and data network applications, helping telecom equipment manufacturers meet the growing data transmission requirements of operators.
  • the control board communicates with external and business boards to complete the normal functions of one or more modules in the system.
  • the control board accepts the settings of the device from the external system and saves the configuration information in the control board. Locally, it is loaded when the control board is started and the device is set according to the configuration information.
  • the business board realizes business processing functions such as detection and forwarding of network data packets.
  • the service processing function is implemented by a service processing unit, which may also be called a network processing unit. In this application, one service board can be equipped with multiple service processing units as required.
  • the control CPU in the service board is responsible for management functions such as identification, configuration and loading of service processing programs of the service processing units in the service board.
  • the orthogonal architecture can flexibly install several service boards to meet the performance requirements of different application scenarios and solve the space limitation of the control board.
  • Figure 1 shows an example of 2 control boards, 8 service boards and 6 switching boards, and the orthogonal architecture in this application is not limited thereto.
  • FIG. 2 is a flow chart of a method for starting a service board based on an orthogonal architecture provided in Embodiment 1 of the present application. This embodiment is applicable to the case where a network operator sets multiple service processing units in one service board.
  • the method can be performed by a service board based on an orthogonal architecture, and includes the following steps:
  • the encoding unit assigns a different encoding to each service processing unit after the service board is powered on.
  • FIG. 3 is a schematic structural diagram of a service board based on an orthogonal architecture provided by an embodiment of the present application.
  • the coding unit may be a complex programmable logic device (Complex Programmable Logic Device, CPLD).
  • CPLD Complex Programmable Logic Device
  • the service board uses the general-purpose input/output (GPIO) logic level of the coding unit to set the slot coding (pre-coding) of the business processing unit, that is, through the GPIO logic Levels to assign different codes to each business unit.
  • the logic level here is preset, that is, each business processing unit has a unique corresponding logic level.
  • Each service processing unit determines the target physical address of the service processing unit according to the assigned code, and modifies the initial physical address of the service processing unit to the target physical address.
  • the target physical address includes an Internet Protocol IP address and a Media Access Control MAC address.
  • each business processing unit After each business processing unit receives the slot code, it uses a preset algorithm to calculate the slot code to obtain the unit ChipID value of the business processing unit. For example, different slot codes can be directly used as different ChipID values , you can also do one-to-one mapping in other ways.
  • the business board itself has a fixed and unique IP address, so the ChipID value of each business processing unit can be incorporated into the IP address of the business board to which it belongs to obtain the IP address of each business processing unit, and then obtain the respective MAC address.
  • the control unit controls the startup of the corresponding service processing unit through each target physical address.
  • control unit controls the corresponding service processing unit to download and execute the data plane service program through each target physical address, so as to start each service processing unit.
  • the control unit can identify each service processing unit based on the IP address of each service processing unit, judge whether the service processing unit is in place, and load the application program to the service processing unit.
  • the control unit in the service board can effectively identify each service processing unit, and then realize the startup of each service processing unit.
  • the types of each service processing unit on the same service board can be different.
  • the advantage of this setting is that the service boards of the same type can be identical, which is easy for production management, and the slots in the service boards can be installed or unloaded with different business processing units according to requirements, and the control unit can automatically identify whether the business processing unit is In place and its kind, convenient and flexible.
  • the control unit After the service processing unit is assigned the target physical address, the control unit starts the data plane (DataPlane, DP) start module.
  • DataPlane data plane
  • the main function of the DP startup module is to enable the control unit to establish communication with the service processing unit, download the file of the DP service program to the service processing unit and execute it.
  • the DP business program is pre-stored in the file system of the control unit.
  • Fig. 4 is a flow chart of a method for starting a service board application DP start-up module based on an orthogonal architecture provided in Embodiment 2 of the present application.
  • This embodiment modifies S130 in Embodiment 1, and details the service board A method for starting with a DP startup module.
  • a method for starting a DP startup module based on an orthogonal architecture-based service card application includes the following steps:
  • the log file is used to record the relevant operations performed by the control unit. If there is a current log file, the DP startup module will first back up the current log file for subsequent retrieval; if there is no current log file, it will save the current log file Date and debug information are output to log files.
  • the DP startup module obtains the IP address of each business processing unit and the IP address of the control unit for subsequent identification and communication between the control unit and the business processing unit.
  • the DP startup module copies the DP service program to the server directory.
  • the DP service program is stored in the built-in memory of the control unit, and the DP startup module copies the DP service program to the server directory of the control unit, and then loads the DP service program in the server directory into the service processing unit, so that the business processing
  • the unit implements related functions.
  • the DP starting module connects the control unit to a single service processing unit through the IP address of each service processing unit.
  • the DP startup module calls the loading module to load the DP business program in the server directory into the business processing unit, and the loading module can load the data in the control unit to the business processing unit according to the IP addresses of the control unit and the business processing unit middle.
  • the control unit is provided with a verification module, which is used to check whether the DP business program is successfully loaded into the business processing unit, and executes S450 based on the inspection result that the DP business program is not successfully loaded into the business processing unit; Process the checking result in the unit, and execute S470.
  • a verification module which is used to check whether the DP business program is successfully loaded into the business processing unit, and executes S450 based on the inspection result that the DP business program is not successfully loaded into the business processing unit; Process the checking result in the unit, and execute S470.
  • DP service programs can be loaded to each service processing unit.
  • the service board further includes a switch unit, and the control unit is electrically connected to each service processing unit through the switch unit.
  • the control unit sends the DP service program to the service processing unit, and the service processing unit sends the target physical address to the control unit through the switching unit.
  • the service board may further include a bridge, after the service board is started, the control unit performs control plane (ControlPlane, CP) management on each service processing unit through the bridge, that is to say , the bridge slice can be used to transmit other control signals to the service processing unit.
  • the bridge chip can be set as a high-speed Peripheral Component Interconnect Express (PCIE) bus.
  • PCIE Peripheral Component Interconnect Express
  • the control unit determines the interface identification (IP) of the target service processing unit based on the code (ChipID) assigned to the target service processing unit, and sends the target
  • the service processing unit performs CP management. That is, as shown in FIG. 3 , the bridge slice has two interfaces facing the service processing unit, respectively connecting the left and right service processing units.
  • CP management may include at least one of power management, reset operation, and configuration information distribution. For example, when the bridge slice adopts the PCIE bus, the control unit sends a reset command to each service processing unit through different PCIE numbers, so that each service processing unit returns to factory settings.
  • the advantage of this setting is that by distinguishing the types of information transmitted by the bridge slice and the switching unit, the information transmission is more orderly.
  • FIG. 5 is a flow chart of a delay waiting method for connecting a service processing unit provided in Embodiment 3 of the present application. The method can be executed by the DP startup module of the control unit. As shown in Figure 5, a kind of delayed waiting method for connecting the service processing unit represented by S440 in Figure 4 includes the following steps:
  • the relevant instructions for connecting the service processing unit are stored in the control unit, and the DP start module invokes the instruction and establishes a connection with the service processing unit by obtaining the IP of the service processing unit.
  • the DP startup module finds that the control unit has not established a normal connection with the service processing unit, the DP startup module sleeps temporarily at this time, and the sleep time can be preset, for example, it can be 1 second.
  • a counting module may be set in the DP starting module to count the times of dormancy during the process of establishing a connection with the service processing unit.
  • the DP startup module can pre-set the threshold number of times.
  • the business processing unit still fails after multiple connections, it can store the date and failure information in the log and end the process to prevent infinite loop connection actions. That is to say, based on the judgment result that the sleep times are greater than the threshold number of times, execute S550; based on the judgment result that the sleep times are not greater than the threshold number of times, execute S510.
  • the technical solution of this embodiment solves the problem of program stagnation if the control unit fails to connect to the business processing unit normally by setting the dormancy and dormancy times for the DP startup module, and achieves the effect of improving the operation stability of the DP startup module.
  • FIG. 6 is a flow chart of a method for calling a loading module for loading provided in Embodiment 4 of the present application. This method can start the loading module in the module by the DP of the control unit implement. As shown in Figure 6, a method for calling a loading module for loading represented by S450 in Figure 4 includes the following steps. It should be noted that the method for loading in this embodiment has two implementation bodies, namely the loading module and Business processing unit:
  • the business processing unit has established a connection with the control unit, and in S610, the loading module invokes the relevant program stored in the control unit to lock a certain business processing unit that has established a connection, so as to prepare for subsequent downloading to the business processing unit Load the DP business program.
  • the loading module executes the operation of loading the DP service program into the service processing unit, and then judges whether the loading has been completed, and executes S630 based on the judgment result of the loading completion; and executes S610 based on the judgment result of the unloading completion.
  • the business processing unit After the DP business program is loaded into the business processing unit, the business processing unit installs the DP business program and grants the business program relevant permissions for subsequent use of the program.
  • the business processing unit executes the business program, and judges whether the execution result is correct, and executes S630 based on the judgment result that the execution result is not correct; and ends the loading method based on the judgment result that the execution result is correct.
  • the technical solution of this embodiment solves the problem that the loaded DP business program may not be used normally by confirming the loading and execution status of the DP business program, and achieves the effect of improving the operation stability of the DP startup module.
  • Fig. 3 is a schematic diagram of a service board based on an orthogonal architecture in the present application, the service board includes a control unit, a plurality of service processing units and a coding unit, and the plurality of service processing units are respectively connected to the control unit It is electrically connected with the coding unit.
  • the service board may further include a bridge or a switching unit.
  • the service board is started by the method described in the above embodiment.
  • the coding unit is configured to assign different codes to each of the business processing units after the service board is powered on; each of the business processing units is configured to Determine the target physical address of the business processing unit, and modify the initial physical address of the business processing unit to the target physical address; the control unit is configured to control the corresponding business processing unit through each of the target physical addresses start up.
  • the technical solution of this embodiment solves the problem of single function of the service board by setting multiple service processing units on a single service board of orthogonal architecture, and achieves the effect of improving the functional diversity of a single service board.
  • Fig. 1 is a schematic diagram of an orthogonal device in the present application, and the orthogonal device includes the service board based on the orthogonal architecture described in Embodiment 5.
  • the technical solution of this embodiment solves the problem that the functions of the orthogonal equipment are not rich by setting multiple business processing units on a single business board with an orthogonal architecture, and achieves the improvement of the functional diversity of a single business board, thereby improving Effects of Orthogonal Device Functional Diversity.
  • Non-volatile memory can include read-only memory (Read Only Memory, ROM), programmable ROM (Programmable ROM, PROM), electrically programmable ROM (Electrically Programmable ROM, EPROM), electrically erasable programmable ROM (Electrically Erasable Programmable, EEPROM) or flash memory. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory.
  • RAM is available in many forms, such as Static RAM (Static RAM, SRAM), Dynamic RAM (Dynamic RAM, DRAM), Synchronous DRAM (Synchnonous DRAM, SDRAM), Double Data Rate SDRAM (Double Data Rate SDRAM, DDR SDRAM), enhanced SDRAM (Enhanced SDRAM, ESDRAM), synchronous link DRAM (Synchnonous Link DRAM, SLDRAM), memory bus direct RAM (Rambus Direct RAM, RDRAM), direct memory bus dynamic RAM (Direct Rambus Dynamic RAM, DRDRAM), and memory bus dynamic RAM (Rambus Dynamic RAM, RDRAM), etc.

Abstract

本申请实施例公开了一种基于正交架构的业务板卡启动方法，所述业务板卡包括：控制单元、多个业务处理单元和编码单元；所述方法包括：所述编码单元在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；每个所述业务处理单元根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；所述控制单元通过每个所述目标物理地址控制对应的业务处理单元的启动。

Description

基于正交架构的业务板卡启动方法、业务板卡及正交设备
本公开要求在2021年7月21日提交中国专利局、申请号为202110827081.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域，例如涉及一种基于正交架构的业务板卡启动方法、业务板卡及正交设备。
背景技术
随着云计算、云存储、音视频下载、流媒体等业务兴起，网络通信数据流量与日俱增，对网络的业务承载能力和处理能力的要求也越来越高，因此，基于正交架构的网络设备应运而生。基于正交架构的网络设备可配备多块控制板卡，多块业务板卡以及多块交换板卡。其中，业务板卡和交换板卡直接对接，业务板卡中的数据可直接到达交换板卡，大幅降低传输损耗，不仅提高了数据交换的传输效率，同时也提供了更大的交换容量和处理扩展能力。
但是，相关技术中基于正交架构的网络设备仍无法满足网络的业务承载能力和处理能力的要求。
发明内容
本申请实施例提供了一种基于正交架构的业务板卡启动方法、业务板卡及正交设备，以通过对每个业务处理单元设置不同的目标物理地址，解决控制中央处理器(Central Processing Unit，CPU)在进行上层应用程序调用时出现互联网协议(Internet Protocol，IP)冲突的问题，达到提高网络设备吞吐量且易于管理的效果。
第一方面，本申请实施例提供了一种基于正交架构的业务板卡启动方法，所述业务板卡包括：控制单元、多个业务处理单元和编码单元；所述方法包括：
所述编码单元在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；
每个所述业务处理单元根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；
所述控制单元通过每个所述目标物理地址控制对应的业务处理单元的启动。
第二方面，本申请实施例还提供了一种基于正交架构的业务板卡，包括：控制单元、多个业务处理单元和编码单元，所述多个业务处理单元分别与所述控制单元和所述编码单元电连接；
所述编码单元被设置为在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；
每个所述业务处理单元被设置为根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；
所述控制单元被设置为通过每个所述目标物理地址控制对应的业务处理单元的启动。
第三方面，本申请实施例还提供了一种正交设备，包括如第二方面所述的基于正交架构的业务板卡。
附图说明
图1为本申请实施例提供的一种正交设备的结构示意图；
图2为本申请实施例一提供的一种基于正交架构的业务板卡启动方法的流程图；
图3为本申请实施例提供的一种基于正交架构的业务板卡的结构示意图；
图4为本申请实施例二提供的一种基于正交架构的业务板卡应用DP启动模块的启动方法的流程图；
图5为本申请实施例三提供的一种连接业务处理单元的延时等待方法的流程图；
图6为本申请实施例四提供的一种调用加载模块进行加载的方法的流程图。
具体实施方式
下面结合附图和实施例对本申请实施例作说明。可以理解的是，此处所描述的实施例仅仅用于解释本申请实施例。另外还需要说明的是，为了便于描述， 附图中仅示出了与本申请实施例相关的部分而非全部结构。
图1为本申请实施例提供的一种正交设备的结构示意图。该正交设备采用正交架构，正交架构采用业务板卡和交换板卡直接对接，因此数据可直接到达交换板卡，大幅降低传输损耗，提高交换传输效率，同时提供更大交换容量和处理扩展能力，为下一代融合通信及数据网络应用提供了高性价比、高模块化、兼容性强、可扩展好的硬件架构，有助于电信设备制造商满足运营商日益增长的数据传输要求。
控制板卡作为控制平面的核心，与外部和业务板卡进行业务通信，完成系统内一个或多个模块的正常功能，控制板卡接受外部系统对设备的设置，将配置信息保存在控制板卡本地，在控制板卡启动时加载并且按照配置信息对设备进行设置。业务板卡实现网络数据包的检测、转发等业务处理的功能。业务处理功能由业务处理单元实现，业务处理单元也可以被称为网络处理单元。在本申请中，一个业务板卡可以根据需要安装多个业务处理单元。业务板卡内的控制CPU负责本业务板卡内的业务处理单元的识别、配置和加载业务处理程序等管理功能。正交架构可以灵活的安装若干块业务板卡，以适应不同应用场景的性能需求，并且解决了控制板卡的空间限制。
图1中示出了2个控制板卡、8个业务板卡和6个交换板卡的示例，本申请中的正交架构不限于此。
实施例一
图2为本申请实施例一提供的一种基于正交架构的业务板卡启动方法的流程图，本实施例可适用于网络运营商在一个业务板卡中设置多个业务处理单元的情况，该方法可以由一种基于正交架构的业务板卡来执行，包括如下步骤：
S110、编码单元在业务板卡上电后为每个业务处理单元分配不同的编码。
图3为本申请实施例提供的一种基于正交架构的业务板卡的结构示意图，图中以2个业务处理单元(网络处理单元)为例，事实上业务处理单元的数量可以大于2。编码单元可以是复杂可编程逻辑器件(Complex Programmable Logic Device，CPLD)。业务板卡上电启动时，业务板卡使用编码单元的通用输入/输出(General-Purpose Input/Output，GPIO)逻辑电平来设置业务处理单元的槽 位编码(预编码)，即通过GPIO逻辑电平来为每个业务单元分配不同的编码，这里的逻辑电平是预先设定好的，即每个业务处理单元有唯一对应的逻辑电平。
S120、每个业务处理单元根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为目标物理地址。
可选的，目标物理地址包括互联网协议IP地址和媒体访问控制MAC地址。
每个业务处理单元接收到槽位编码之后，使用预设算法对槽位编码进行计算，从而得出本业务处理单元的单元ChipID值，例如，可以将不同的槽位编码直接作为不同的ChipID值，也可以做其他方式的一一映射。业务板卡本身具有固定且唯一的IP地址，因此可以将每个业务处理单元的ChipID值并入所属的业务板卡的IP地址，得到每个业务处理单元的IP地址，进而得到业务处理单元各自的MAC地址。
S130、控制单元通过每个目标物理地址控制对应的业务处理单元的启动。
可选的，控制单元通过每个目标物理地址控制对应的业务处理单元下载并执行数据面业务程序，以实现每个业务处理单元的启动。
控制单元可以基于每个业务处理单元的IP地址对每个业务处理单元分别进行识别，并判断业务处理单元是否在位，以及向业务处理单元加载应用程序。
本实施例的技术方案，通过在一个业务板卡上设置多个业务处理单元，通过多个业务处理单元来处理网络中的数据，从而提高了业务板卡对网络的业务承载能力和处理能力；同时，由于多个业务处理单元配置了不同的目标物理地址，使得业务板卡中的控制单元能够有效识别出每个业务处理单元，进而实现对每个业务处理单元的启动。
可选的，同一业务板卡上的每个业务处理单元类型可以不同。这样设置的好处在于同一种类的业务板卡可以完全相同，易于生产管理，而业务板卡内的槽位可以根据需求安装或空载不同的业务处理单元，控制单元通过软件自动识别业务处理单元是否在位及其种类，方便灵活。
实施例二
业务处理单元分配到目标物理地址后，控制单元启动数据面(DataPlane， DP)启动模块。如图2所示，DP启动模块的主要功能是使能控制单元与业务处理单元建立通信，将DP业务程序的文件下载到业务处理单元并执行。DP业务程序预先存储在控制单元的文件系统中。
图4为本申请实施例二提供的一种基于正交架构的业务板卡应用DP启动模块的启动方法的流程图，本实施例对实施例一中的S130进行改动，详述了业务板卡应用DP启动模块进行启动的方法。如图4所示，一种基于正交架构的业务板卡应用DP启动模块的启动方法包括如下步骤：
S410、判断日志文件是否存在。
日志文件用于记录控制单元进行过的相关操作，若存在当前日志文件，DP启动模块则先对当前日志文件进行备份，以备后续调取；若不存在当前日志文件，则将本次操作的日期和调试信息输出到日志文件中。
S420、获取控制单元与每个业务处理单元的IP地址。
由于之前已经为每个业务处理单元分配了IP地址，因此DP启动模块获取每个业务处理单元的IP地址和控制单元的IP地址，用于后续控制单元与业务处理单元进行识别和通信。
S430、DP启动模块将DP业务程序拷贝到服务器目录。
DP业务程序存储在控制单元的内设存储器中，DP启动模块将DP业务程序拷贝到控制单元的服务器目录中，之后会将服务器目录中的DP业务程序加载到业务处理单元中，以使业务处理单元实现相关功能。
S440、连接业务处理单元。
DP启动模块通过每个业务处理单元的IP地址，使得控制单元连接到单个业务处理单元。
S450、调用加载模块进行加载。
DP启动模块调用加载模块，从而将服务器目录中的DP业务程序加载到该业务处理单元中，加载模块可以根据控制单元和业务处理单元的IP地址，将控制单元中的数据加载到该业务处理单元中。
S460、调用校验模块进行校验。
控制单元设置有校验模块，用于检查DP业务程序是否成功加载到业务处理 单元中，基于DP业务程序未成功加载到业务处理单元中的检查结果，执行S450；基于DP业务程序成功加载到业务处理单元中的检查结果，执行S470。
S470、判断业务处理单元是否全部加载完毕，基于业务处理单元全部加载完毕的判断结果，结束该业务程序的加载流程；基于业务处理单元未全部加载完毕的判断结果，执行S440。
S470、判断业务处理单元是否全部加载完毕。
基于业务处理单元全部加载完毕的判断结果，结束该DP业务程序加载过程；基于业务处理单元未全部加载完毕的判断结果，返回至锁定业务处理单元，以对下一个业务处理单元进行处理。
可选的，可以对每个业务处理单元加载不同的DP业务程序。
本实施例的技术方案，通过对具有不同的目标物理地址的每个业务处理单元加载DP业务程序，解决了业务板卡功能单一的问题，达到了提高单个业务板卡功能多样性的效果。
如图3所示，可选的，所述业务板卡还包括交换单元，控制单元通过所述交换单元与每个业务处理单元电连接。本申请实施例中控制单元向业务处理单元发送DP业务程序，业务处理单元向控制单元发送目标物理地址均可以通过交换单元。
可选的，所述业务板卡还可以包括桥片，在所述业务板卡启动后，控制单元通过所述桥片对每个业务处理单元进行控制面(ControlPlane，CP)管理，也就是说，桥片可用于向业务处理单元传输其他控制信号。桥片可以设置为高速外设组件互连(Peripheral Component Interconnect Express，PCIE)式总线。控制单元作为桥片的主设备，所有业务处理单元作为桥片的从设备挂载在桥片下。
控制单元基于目标业务处理单元分配到的编码(ChipID)，确定所述目标业务处理单元的接口标识(IP)，并通过所述桥片中的与所述接口标识对应的接口，对所述目标业务处理单元进行CP管理。即如图3所示，桥片面向业务处理单元共两个接口，分别连接左右两个业务处理单元。可选的，CP管理可以包括电源管理、复位操作以及配置信息下发中的至少一种。例如，在桥片采用PCIE总线的情况下，控制单元通过不同的PCIE号向每个业务处理单元发送复位命令，使每个业务处理单元回到出厂设置。
这样设置的好处在于，通过区分桥片与交换单元传输的信息类型，使得信息传输更加有序。
实施例三
本实施例对实施例二中的S440进行改动，图5为本申请实施例三提供的一种连接业务处理单元的延时等待方法的流程图，该方法可以由控制单元的DP启动模块执行。如图5所示，图4中S440所表示的一种连接业务处理单元的延时等待方法包括如下步骤：
S510、调用命令连接业务处理单元。
在控制单元中存储用于连接业务处理单元的相关指令，DP启动模块调用指令并通过获得业务处理单元的IP从而与业务处理单元建立连接。
S520、判断是否正常连接。
判断当前的业务处理单元是否与控制单元建立正常的连接，基于当前的业务处理单元未与控制单元建立正常的连接的判断结果，执行S530；基于当前的业务处理单元与控制单元建立正常的连接的判断结果，执行S560。
S530、休眠，并计算休眠次数。
由于DP启动模块发现控制单元与业务处理单元没有建立正常的连接，此时DP启动模块暂时休眠，休眠时间可以预先设定，例如，可以为1秒。DP启动模块中可以设置计数模块，对与该业务处理单元建立连接的过程中的休眠次数进行计数。
S540、判断休眠次数是否大于阈值次数。
DP启动模块可以预先设置阈值次数，当多次连接业务处理单元之后仍然失败，则可以将日期和失败信息存储到日志中之后结束进程，以防止无限次循环连接动作。也就是说，基于休眠次数大于阈值次数的判断结果，执行S550；基于休眠次数不大于阈值次数的判断结果，执行S510。
S550、输出日期和失败信息到日志文件。
S560、输出日期和调试信息到日志文件。
本实施例的技术方案，通过对DP启动模块设置休眠和休眠次数，解决了若控制单元不能正常连接业务处理单元导致程序停滞的问题，达到了提高DP启动模块运行稳定性的效果。
实施例四
本实施例对实施例二中的S450进行改动，图6为本申请实施例四提供的一种调用加载模块进行加载的方法的流程图，该方法可以由控制单元的DP启动模块中的加载模块执行。如图6所示，图4中S450所表示的一种调用加载模块进行加载的方法包括如下步骤，需要注意的是，本实施例中进行加载的方法具有两个实施主体，分别是加载模块和业务处理单元：
S610、调用命令登录到业务处理单元。
在S440中，业务处理单元已经与控制单元建立了连接，在S610中，加载模块调用控制单元中存储的相关程序，来锁定已经建立连接的某个业务处理单元，以备后续向该业务处理单元加载DP业务程序。
S620、将DP业务程序加载到业务处理单元。
加载模块执行将DP业务程序加载到业务处理单元的操作，之后判断加载是否已经完成，基于加载完成的判断结果，执行S630；基于未加载完成的判断结果，执行S610。
S630、增加业务可执行权限。
当DP业务程序加载到业务处理单元之后，业务处理单元对该DP业务程序进行安装，给予该业务程序相关权限，以便后续使用该程序。
S640、执行业务程序。
业务处理单元执行业务程序，并判断执行结果是否正确，基于执行结果不是正确的判断结果，执行S630；基于执行结果是正确的判断结果，结束该进行加载的方法。
本实施例的技术方案，通过对DP业务程序的加载情况和执行情况进行确认，解决了加载的DP业务程序可能无法正常使用的问题，达到了提高DP启动模块运行稳定性的效果。
实施例五
图3是本申请中的一种基于正交架构的业务板卡的示意图，该业务板卡包括控制单元、多个业务处理单元和编码单元，所述多个业务处理单元分别与所述控制单元和编码单元电连接。可选的，所述业务板卡还可以包括桥片或交换单元。
所述业务板卡通过上述实施例所述的方法进行启动。
在一实施例中，所述编码单元被设置为在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；每个所述业务处理单元被设置为根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；所述控制单元被设置为通过每个所述目标物理地址控制对应的业务处理单元的启动。
本实施例的技术方案，通过在单个正交架构的业务板卡上设置多个业务处理单元，解决了业务板卡功能单一的问题，达到了提高单个业务板卡的功能多样性的效果。
实施例六
图1是本申请中一种正交设备的示意图，该正交设备中包括实施例五中所述的基于正交架构的业务板卡。
本实施例的技术方案，通过在单个正交架构的业务板卡上设置多个业务处理单元，解决了正交设备功能不丰富的问题，达到了提高单个业务板卡的功能多样性，从而提高正交设备功能多样性的效果。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述方法的实施例的流程。可选的，本申请所提供的上述实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储 器。非易失性存储器可包括只读存储器(Read Only Memory，ROM)、可编程ROM(Programmable ROM，PROM)、电可编程ROM(Electrically Programmable ROM，EPROM)、电可擦除可编程ROM(Electrically Erasable Programmable，EEPROM)或闪存。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(Static RAM，SRAM)、动态RAM(Dynamic RAM，DRAM)、同步DRAM(Synchnonous DRAM，SDRAM)、双数据率SDRAM(Double Data Rate SDRAM，DDRSDRAM)、增强型SDRAM(Enhanced SDRAM，ESDRAM)、同步链路DRAM(Synchnonous Link DRAM，SLDRAM)、存储器总线直接RAM(Rambus Direct RAM，RDRAM)、直接存储器总线动态RAM(Direct Rambus Dynamic RAM，DRDRAM)、以及存储器总线动态RAM(Rambus Dynamic RAM，RDRAM)等。

Claims (10)

  1. 一种基于正交架构的业务板卡启动方法，其中，所述业务板卡包括：控制单元、多个业务处理单元和编码单元；所述方法包括：
    所述编码单元在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；
    每个所述业务处理单元根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；
    所述控制单元通过每个所述目标物理地址控制对应的业务处理单元的启动。
  2. 根据权利要求1所述的方法，其中，所述目标物理地址包括互联网协议IP地址和媒体访问控制MAC地址。
  3. 根据权利要求1所述的方法，其中，所述控制单元通过每个所述目标物理地址控制对应的业务处理单元的启动，包括：
    控制单元通过每个所述目标物理地址控制对应的业务处理单元下载并执行数据面业务程序，以实现每个所述业务处理单元的启动。
  4. 根据权利要求3所述的方法，其中，所述业务板卡还包括：交换单元，控制单元通过所述交换单元与每个所述业务处理单元电连接。
  5. 根据权利要求1至4中任一项所述的方法，其中，所述业务板卡还包括：桥片；所述方法还包括：
    在所述业务板卡启动后，控制单元通过所述桥片对每个所述业务处理单元进行控制面管理。
  6. 根据权利要求5所述的方法，其中，所述控制单元通过所述桥片对每个所述业务处理单元进行控制面管理，包括：
    控制单元基于目标业务处理单元分配到的编码，确定所述目标业务处理单 元的接口标识，并通过所述桥片中的与所述接口标识对应的接口，对所述目标业务处理单元进行控制面管理。
  7. 根据权利要求5所述的方法，其中，所述控制面管理包括电源管理、复位操作以及配置信息下发中的至少一种。
  8. 根据权利要求1至4中任一项所述的方法，其中，每个所述业务处理单元的类型不同。
  9. 一种基于正交架构的业务板卡，包括：控制单元、多个业务处理单元和编码单元，所述多个业务处理单元分别与所述控制单元和所述编码单元电连接；
    所述编码单元被设置为在所述业务板卡上电后为每个所述业务处理单元分配不同的编码；
    每个所述业务处理单元被设置为根据分配到的编码确定本业务处理单元的目标物理地址，并将本业务处理单元的初始物理地址修改为所述目标物理地址；
    所述控制单元被设置为通过每个所述目标物理地址控制对应的业务处理单元的启动。
  10. 一种正交设备，包括如权利要求9所述的基于正交架构的业务板卡。
PCT/CN2022/105086 2021-07-21 2022-07-12 基于正交架构的业务板卡启动方法、业务板卡及正交设备 WO2023001020A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110827081.2 2021-07-21
CN202110827081.2A CN113568669A (zh) 2021-07-21 2021-07-21 基于正交架构的业务板卡启动方法、业务板卡及正交设备

Publications (1)

Publication Number Publication Date
WO2023001020A1 true WO2023001020A1 (zh) 2023-01-26

Family

ID=78166035

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/105086 WO2023001020A1 (zh) 2021-07-21 2022-07-12 基于正交架构的业务板卡启动方法、业务板卡及正交设备

Country Status (2)

Country Link
CN (1) CN113568669A (zh)
WO (1) WO2023001020A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113568669A (zh) * 2021-07-21 2021-10-29 北京锐安科技有限公司 基于正交架构的业务板卡启动方法、业务板卡及正交设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101707636A (zh) * 2009-11-20 2010-05-12 中兴通讯股份有限公司 用于基站bbu单板的ip地址分配方法及装置
CN102726025A (zh) * 2011-11-29 2012-10-10 华为技术有限公司 一种业务包的安装方法和相关装置
CN103442095A (zh) * 2013-08-16 2013-12-11 京信通信系统（中国）有限公司 单板上子卡地址的获取方法和系统
CN103634145A (zh) * 2013-11-25 2014-03-12 山东超越数控电子有限公司 一种实现云设备中交换机独立管理和集中管理的方法
US9825902B1 (en) * 2015-04-22 2017-11-21 Cisco Technology, Inc. Route advertisement for native hardware-based virtual IP address (“VIP”) on layer 2/layer 3 switch
CN113568669A (zh) * 2021-07-21 2021-10-29 北京锐安科技有限公司 基于正交架构的业务板卡启动方法、业务板卡及正交设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130329606A1 (en) * 2012-06-11 2013-12-12 James O. Jones Physical address correlation for network traffic tracking
CN105657080A (zh) * 2016-03-09 2016-06-08 浙江安正科技股份有限公司 一种ip地址配置方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101707636A (zh) * 2009-11-20 2010-05-12 中兴通讯股份有限公司 用于基站bbu单板的ip地址分配方法及装置
CN102726025A (zh) * 2011-11-29 2012-10-10 华为技术有限公司 一种业务包的安装方法和相关装置
CN103442095A (zh) * 2013-08-16 2013-12-11 京信通信系统（中国）有限公司 单板上子卡地址的获取方法和系统
CN103634145A (zh) * 2013-11-25 2014-03-12 山东超越数控电子有限公司 一种实现云设备中交换机独立管理和集中管理的方法
US9825902B1 (en) * 2015-04-22 2017-11-21 Cisco Technology, Inc. Route advertisement for native hardware-based virtual IP address (“VIP”) on layer 2/layer 3 switch
CN113568669A (zh) * 2021-07-21 2021-10-29 北京锐安科技有限公司 基于正交架构的业务板卡启动方法、业务板卡及正交设备

Also Published As

Publication number Publication date
CN113568669A (zh) 2021-10-29

Similar Documents

Publication Publication Date Title
US10063470B2 (en) Data center network system based on software-defined network and packet forwarding method, address resolution method, routing controller thereof
US8862865B2 (en) Rebooting infiniband clusters
US8769040B2 (en) Service providing system, a virtual machine server, a service providing method, and a program thereof
US7657260B2 (en) Method of providing data redundancy for home location register
US11394607B2 (en) Method and system for network configuration
WO2016184175A1 (zh) 数据库处理方法及装置
US20190245914A1 (en) Method and device for processing persistent connection establishment request
US10083098B1 (en) Network function virtualization (NFV) virtual network function (VNF) crash recovery
WO2009097776A1 (zh) 一种实现业务升级的系统、装置及方法
US11403319B2 (en) High-availability network device database synchronization
CN110995617B (zh) 基于mqtt的数据报送方法、装置、计算机设备和存储介质
EP3316555A1 (en) Mac address synchronization method, device and system
WO2023001020A1 (zh) 基于正交架构的业务板卡启动方法、业务板卡及正交设备
CN111597061A (zh) 一种客户端或服务端进行远程过程调用方法及装置
CN102726025B (zh) 一种业务包的安装方法和相关装置
CN107948063B (zh) 一种建立聚合链路的方法和接入设备
WO2020252724A1 (zh) 日志处理方法、设备及计算机可读存储介质
CN109120680B (zh) 一种控制系统、方法及相关设备
WO2013189069A1 (zh) 负荷分担方法及装置、单板
CN114553693B (zh) 网关升级方法及装置
WO2017048698A1 (en) Efficient hardware trust verification in data communication systems that comprise network interface cards, central processing units, and data memory buffers
WO2021120754A1 (zh) 一种指令写入方法、装置及网络设备
US8108736B2 (en) Multi-partition computer system, failure handling method and program therefor
CN112073499A (zh) 一种多机型云物理服务器的动态服务方法
CN1798413A (zh) 一种远端维护通道的建立方法

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: 22845185

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE