WO2019052299A1

WO2019052299A1 - Sdn switch, and application and management method for sdn switch

Info

Publication number: WO2019052299A1
Application number: PCT/CN2018/100570
Authority: WO
Inventors: 梁向锋
Original assignee: 通鼎互联信息股份有限公司
Priority date: 2017-09-15
Filing date: 2018-08-15
Publication date: 2019-03-21
Also published as: CN107682281B; CN107682281A

Abstract

Proposed are an SDN switch, and an application and management method for an SDN switcher. The switch comprises: an access card, a switching card, a service card and a control card, wherein the switching card is provided with a physical switching network; the service card is provided with a network processor and a cache memory module; and the control card is provided with an SDN controller. The cache memory module comprises: a cache unit, a main control unit and a redirection unit, wherein the cache unit is used for downloading and caching; the main control unit is used for the centralized management of the entire system; and the redirection unit is used for access redirection. A caching space of the cache memory module further comprises at least one of or a combination of the following: a memory component of a network processor in the service card, a storage component of a processor of the switching card, a storage component of a processor of the control card, and a storage component of a processor of the access card. The present invention improves the efficiency of responding to a request of a client, reduces the processing pressure of a server during the distribution of application contents, and improves the service processing capability of a server.

Description

一种SDN交换机和SDN交换机的应用管理方法Application management method of SDN switch and SDN switch

技术领域Technical field

本申请涉及数据通信技术领域，具体而言，涉及一种SDN交换机和一种SDN交换机的应用管理方法。The present application relates to the field of data communication technologies, and in particular, to an SDN switch and an application management method of an SDN switch.

背景技术Background technique

在互联网和移动应用高速发展的今天，用户已经越来越不满足常规的对互联网的浏览、查询、电子邮件等应用，而希望在线影音视频、高速下载、移动终端业务等应用方面拥有更好的用户体验。With the rapid development of the Internet and mobile applications, users have become less and less satisfied with the traditional Internet browsing, query, email and other applications, and hope that online video and video, high-speed download, mobile terminal services and other applications have better user experience.

为了缓解网络设备的出口带宽面临的巨大压力，现有技术中，除了扩展带宽、控制流量以外，还采用部署高速缓存加速***的方式来实现Web下载、在线影音、P2P下载、移动APP等应用的自动缓存加速功能，从而降低同种业务请求对出口带宽的反复消耗，为用户带来本地化的上网服务体验，同时大幅节约出口带宽资源。但部署高速缓存加速***的方法存在有如下的问题：In order to alleviate the huge pressure on the export bandwidth of network devices, in addition to expanding bandwidth and controlling traffic, the prior art also adopts a method of deploying a cache acceleration system to implement applications such as web downloading, online video and audio, P2P downloading, and mobile APP. The automatic cache acceleration function reduces the repeated consumption of the same bandwidth for the same type of service request, and provides the user with a localized Internet service experience, while greatly reducing the export bandwidth resources. However, there are the following problems with the method of deploying a cache acceleration system:

最常见的增加高速缓存加速***的方法是构建分布式服务器集群，如图1所示，服务器集群是由多台服务器1、路由器2、交换机3构建的网络，服务器1用作客户机4的应用缓存服务器，网络访问缓存服务器。The most common way to increase the cache acceleration system is to build a distributed server cluster. As shown in Figure 1, the server cluster is a network built by multiple servers 1, routers 2, and switches 3. Server 1 is used as a client 4 application. Cache server, network access cache server.

采用分布式集群管理方式，可以通过增加应用服务器1的数量，可以减轻由于多用户并发访问对服务器带来的压力，但是这样会显著地增加服务器1的配置成本和运行维护的成本。By adopting the distributed cluster management mode, the number of application servers 1 can be increased, and the pressure on the server due to concurrent access by multiple users can be alleviated, but this can significantly increase the configuration cost and operation and maintenance cost of the server 1.

此种缓存加速***通过利用标准中定义的302状态码将客户端的请求临时引流到本地缓存加速***，从而将***内缓存单元的数据加速分发给客户端，避免客户端通过网络出口向源网站低速获取并挤占出口带宽，依赖于在网络出口处增加新的服务器集群，将用户访问流量引向加速服务器，从而减轻出口网络带宽压力，在一定程度上加速用户访问应用体验。The cache acceleration system temporarily transfers the client's request to the local cache acceleration system by using the 302 status code defined in the standard, thereby accelerating the data of the cache unit in the system to the client, and preventing the client from slowing down to the source website through the network exit. Acquiring and squeezing the egress bandwidth depends on adding a new server cluster at the network egress and directing user access traffic to the acceleration server, thereby reducing the pressure on the egress network bandwidth and, to a certain extent, accelerating user access to the application experience.

由于此种加速方式，只是将远端的应用内容取回到本地服务器上，降低了用户访问时网络上的延时，一旦出现多用户并发访问的情况，服务器的处理能力和网络转发能力依然是瓶颈，同样会出现用户访问拥塞，服务器响应不及时的问题，尤其在应对在线视频，网络直播应用时，这种缓存加速方法同样会力不从心，无法实现高效率和高并发。Because of this acceleration method, only the remote application content is retrieved back to the local server, which reduces the delay on the network when the user accesses. In the case of multi-user concurrent access, the processing capability and network forwarding capability of the server are still Bottlenecks, there will also be problems with user access congestion, server response is not timely, especially in response to online video, webcast applications, this cache acceleration method will also be unable to achieve high efficiency and high concurrency.

申请内容Application content

本申请旨在至少解决现有技术或相关技术中存在的技术问题之一。The present application is intended to address at least one of the technical problems existing in the related art or related art.

为此，本申请的第一方面在于提出了一种SDN交换机。To this end, the first aspect of the present application is to propose an SDN switch.

本申请的第二方面在于提出了一种SDN交换机的应用管理方法。A second aspect of the present application is to propose an application management method for an SDN switch.

为实现上述目的，根据本申请的第一方面提出了一种SDN交换机，包括：接入卡，用于通信网络中数据流量的接收与发送；交换卡，用于将接入卡接收的通信流量分发到各个业务卡，交换卡设置有物理交换网络；业务卡用于分析处理通信流量内容以及流量解析，业务卡设置有网络处理器和高速缓存内存模块；控制卡，用于控制和管理整个SDN交换机的工作状态，控制卡设置有SDN控制器；高速缓存内存模块包括：缓存单元、主控单元及重定向单元，缓存单元用于下载缓存，主控单元用于整个***的集中管理，重定向单元用于访问重定向；其中，高速缓存内存模块的缓存空间还包括以下至少一个或其组合：业务卡中的网络处理器的内存部件、交换卡的处理器的存储部件、控制卡的处理器的存储部件、接入卡的处理器的存储部件。To achieve the above object, according to a first aspect of the present application, an SDN switch is provided, comprising: an access card for receiving and transmitting data traffic in a communication network; and a switching card for receiving communication traffic of the access card Distributed to each service card, the switch card is provided with a physical switching network; the service card is used to analyze and process the traffic content and traffic resolution, the service card is provided with a network processor and a cache memory module; the control card is used to control and manage the entire SDN The working state of the switch, the control card is provided with an SDN controller; the cache memory module includes: a cache unit, a main control unit and a redirection unit, the cache unit is used for downloading the cache, and the main control unit is used for centralized management and redirection of the entire system. The unit is used for access redirection; wherein the cache space of the cache memory module further comprises at least one of the following or a combination thereof: a memory component of the network processor in the service card, a storage component of the processor of the switch card, and a processor of the control card Storage component, storage component of the processor of the access card.

本申请提供的SDN交换机，具有较大的存储空间的高速缓存内存模块，高速缓存内存模块不仅可以利用自身具备的存储空间，当存储容量过大时，还可以利用接入卡、交换卡、业务卡和控制卡内处理器的存储空间，进而进一步地提高了整体交换机的存储空间，可以满足应用文件的缓存需求；通过SDN交换机***中的网络处理器的高速缓存内存模块来缓存应用，充分应用网络处理器多达4K的处理线程，并行分发应用内容到达各自的请求客户端，从而提高响应客户端请求的效率，减轻服务器分发应用内容时的处理压力，提高服务器的业务处理能力，同时解决了应用缓存和高速并行转发的问题。The SDN switch provided by the present application has a cache memory module with a large storage space, and the cache memory module can not only utilize the storage space provided by itself, but also can utilize the access card, the exchange card, and the service when the storage capacity is too large. The storage space of the processor in the card and the control card further improves the storage space of the overall switch, and can meet the cache requirement of the application file; cache the application through the cache memory module of the network processor in the SDN switch system, and fully apply The network processor has up to 4K processing threads, and distributes the application content in parallel to reach the respective request clients, thereby improving the efficiency of responding to the client request, reducing the processing pressure when the server distributes the application content, improving the server's business processing capability, and solving the problem. Application caching and high-speed parallel forwarding issues.

相关技术中，针对大型网吧应用和在线视频直播等网络负载较重的情况，在客户机向服务器请求较大文件时，比如几GB的大小应用，如果有多个用户同时请求该文件，则服务器需要同时处理多个下载请求，而服务器的网络处理能力一般有限，应付数据转发的压力较大，响应其他应用的请求就会延迟，造成用户体验较差。本申请提供的SDN交换机，通过设置高速缓存内存模块，可以解决服务器响应客户端请求效率低的问题，提高服务器支持多用户访问请求的能力，提升用户访问体验，降低服务器的运行负载，利用SDN交换机***中网络处理器的应用识别，高速缓存，并行转发能力，解决目前应用缓存***请求响应速度慢的问题。In the related art, for a large network load such as a large Internet cafe application and an online video live broadcast, when a client requests a large file from a server, such as a size of several GB, if multiple users request the file at the same time, the server Multiple download requests need to be processed at the same time, and the network processing capacity of the server is generally limited, and the pressure for data forwarding is large, and requests for responding to other applications are delayed, resulting in poor user experience. The SDN switch provided by the present application can solve the problem that the server responds to the client request with low efficiency by setting the cache memory module, improve the server's ability to support multiple user access requests, improve the user access experience, reduce the running load of the server, and utilize the SDN switch. The application identification, cache, and parallel forwarding capabilities of the network processor in the system solve the problem that the response speed of the current application cache system is slow.

根据本申请的上述实施例的SDN交换机，还可以具有以下技术特征：According to the SDN switch of the above embodiment of the present application, the following technical features may also be provided:

在上述技术方案中，优选地，高速缓存内存模块采用数据报文的方式缓存应用文件，并可以为缓存应用文件创建文件描述信息。In the above technical solution, preferably, the cache memory module caches the application file by using a data packet, and may create file description information for the cache application file.

在该技术方案中，高速缓存内存模块采用数据报文的方式缓存应用文件，并可以为缓存的应用文件创建文件描述信息，用户设备请求相应的应用时，SDN交换机可以通过搜索该高速缓存内存模块的缓存空间的方式直接得到所需的应用文件，并可以通过更新SDN交换机的内存中数据的控制信息，通过并行转发引擎转发的应用文件到相应的用户设备。In the technical solution, the cache memory module caches the application file by using a data packet, and can create a file description information for the cached application file. When the user equipment requests the corresponding application, the SDN switch can search the cache memory module. The way of the cache space directly obtains the required application files, and can update the application files forwarded by the parallel forwarding engine to the corresponding user equipment by updating the control information of the in-memory data of the SDN switch.

在上述技术方案中，优选地，高速缓存内存模块的单一节点的高速内存的最大内存量大于等于96GB；SDN交换机可以安装的节点数量大于等于12个；高速缓存内存模块的网络接口带宽为4.8Tbps。In the above technical solution, preferably, the maximum memory capacity of the single node of the cache memory module is greater than or equal to 96 GB; the number of nodes that the SDN switch can be installed is greater than or equal to 12; and the network interface bandwidth of the cache memory module is 4.8 Tbps. .

在该技术方案中，SDN交换机的单一节点的高速内存最高可达96GB以上，而在一个SDN交换机的机架设备里面往往可以最少安装12个节点，因此，单一设备的最大缓存容量可达1.1TB以上，整个***可以实现48K硬件线程同时处理应用缓存和网络转发，基本上可以满足绝大多数应用文件的缓存需求。进一步地，SDN交换机***最大的网络接口带宽为4.8Tbps，SDN交换机***网络超强的并发处理能力，使得该***在处理多用户并发访问时轻松自如，多达48K的处理线程，可以同时处理带宽4.8Tbps的业务流量，不会出现由于网络转发能力而造成的网络拥塞问题。In this technical solution, the high-speed memory of a single node of an SDN switch can be up to 96 GB or more, and a minimum of 12 nodes can be installed in a rack device of an SDN switch. Therefore, the maximum buffer capacity of a single device can reach 1.1 TB. In the above, the entire system can realize 48K hardware threads to process application cache and network forwarding at the same time, which can basically satisfy the cache requirement of most application files. Further, the maximum network interface bandwidth of the SDN switch system is 4.8 Tbps, and the SDN switch system network has superior concurrent processing capability, so that the system can easily handle multiple users concurrent access, and up to 48K processing threads can simultaneously process bandwidth. The traffic of 4.8 Tbps does not cause network congestion caused by network forwarding capability.

根据本申请的第二方面提出了一种SDN交换机的应用管理方法，用于如上述任一技术方案所述的SDN交换机，SDN交换机与用户设备通过网络服务器进行交互，应用管理方法包括：接收用户设备发送的请求报文；解析请求报文，并获取请求报文中对应的应用信息；根据应用信息查询SDN交换机的应用缓存数据库中是否存在对应的应用信息；当存在对应的应用信息时，根据应用信息在所述应用缓存数据库中的存储位置，启动所述请求报文的重定向操作；当不存在对应的应用信息时，则执行网络服务器的响应请求流程，并缓存应用信息。According to the second aspect of the present application, an application management method for an SDN switch is provided, which is used for an SDN switch according to any one of the foregoing technical solutions. The SDN switch interacts with the user equipment through a network server, and the application management method includes: receiving a user. The request packet sent by the device; parsing the request packet, and obtaining the corresponding application information in the request packet; querying whether the corresponding application information exists in the application cache database of the SDN switch according to the application information; when there is corresponding application information, according to The storage location of the application information in the application cache database starts the redirection operation of the request message; when there is no corresponding application information, the response request process of the network server is executed, and the application information is cached.

本申请提供的SDN交换机的应用管理方法，接收用户设备发送请求报文，并对的请求报文进行解析以获取用户设备请求的应用信息，根据得到的应用信息在应用缓存数据库中进行查找，如果交换机的数据库中已存在该应用信息，则直接响应用户设备的请求；如果交换机的数据库中没有该应用信息，则通过网络服务器下载该应用，并缓存至交换机的数据库。通过本申请提供的SDN交换机的应用管理方法，可以解决服务器响应客户端请求效率低的问题，提高服务器支持多用户访问请求的能力，提升用户访问体验，降低服务器的运行负载，利用SDN交换机***中网络处理器的应用识别，高速缓存，并行转发能力，解决目前应用缓存***请求响应速度慢的问题。The application management method of the SDN switch provided by the application, the receiving user equipment sends a request message, parses the request message to obtain the application information requested by the user equipment, and searches in the application cache database according to the obtained application information, if If the application information exists in the database of the switch, it directly responds to the request of the user equipment; if the application information is not in the database of the switch, the application is downloaded through the network server and cached to the database of the switch. The application management method of the SDN switch provided by the application can solve the problem that the server responds to the client request with low efficiency, improve the server's ability to support multiple user access requests, improve the user access experience, and reduce the running load of the server, and utilize the SDN switch system. The network processor's application identification, cache, and parallel forwarding capabilities solve the problem of slow response response of the current application cache system.

具体地，用户设备通过SDN交换机向网络服务器发出下载应用请求时，其中，用户设备可以是浏览器、下载客户端、P2P客户端等，网络服务器可以是HTTP服务器、CDN服务器、P2P服务器、P2P客户端等，SDN交换机可实现应用的缓存加速，执行加速用户应用访问速度的控制程序，加速用户应用访问速度的控制程序可以运行于SDN交换机的控制卡处理器上，也可以运行在通过各个板卡之间的竞争选举出来的交换卡处理器上。该控制程序可深度解析用户设备发送的请求报文和网络服务器的响应数据，利用SDN交换机中业务卡上的网络处理器4K线程资源，使其工作在特有的ZOL(Zero Overhead Linux)模式下，并发处理数据报文的解析与转发任务。Specifically, the user equipment sends a download application request to the network server through the SDN switch, where the user equipment may be a browser, a download client, a P2P client, etc., and the network server may be an HTTP server, a CDN server, a P2P server, or a P2P client. The SDN switch can implement the cache acceleration of the application, execute the control program for accelerating the access speed of the user application, and the control program for accelerating the access speed of the user application can be run on the control card processor of the SDN switch, or can be run through each board. The competition between the elections is on the exchange card processor. The control program can deeply parse the request message sent by the user equipment and the response data of the network server, and use the network processor 4K thread resource on the service card in the SDN switch to work in the unique ZOL (Zero Overhead Linux) mode. Concurrent processing of data packet parsing and forwarding tasks.

在上述技术方案中，优选地，当存在对应的所述应用信息时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作的步骤，具体包括：根据所述应用信息在应用缓存数据库中的存储位置，发送重定向请求至用户设备；接收重定向请求的响应报文，根据响应报文中的应用信息，将应用缓存数据库中保存的对应的应用信息发送至用户设备。In the above technical solution, preferably, when the corresponding application information is present, the step of initiating a redirection operation of the request message according to the storage location of the application information in the application cache database, specifically: according to the application information Sending a redirection request to the user equipment in the storage location of the application cache database; receiving the response message of the redirection request, and sending the corresponding application information saved in the application cache database to the user equipment according to the application information in the response packet .

在上述技术方案中，优选地，当应用缓存数据库存在对应的应用信息时，还包括：判断应用信息是否为可用；当应用信息可用时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作；当应用信息不可用时，则执行网络服务器的响应请求流程，并缓存应用信息。In the above technical solution, preferably, when the application cache information has corresponding application information, the method further includes: determining whether the application information is available; and when the application information is available, starting the request according to the storage location of the application information in the application cache database. The redirection operation of the message; when the application information is not available, the response request process of the web server is executed, and the application information is cached.

在上述技术方案中，优选地，当应用缓存数据库存在对应的应用信息时，还包括：判断应用信息的置信度是否大于预设阈值；当置信度大于等于预设阈值时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作；当置信度小于所述预设阈值时，则执行网络服务器的响应请求流程，并缓存应用信息。In the above technical solution, preferably, when the application cache information has corresponding application information, the method further includes: determining whether the confidence of the application information is greater than a preset threshold; and when the confidence is greater than or equal to the preset threshold, applying the application according to the application information The storage location in the cache database is used to initiate a redirect operation of the request packet. When the confidence level is less than the preset threshold, the response request process of the network server is executed, and the application information is cached.

在上述技术方案中，优选地，当不存在对应的应用信息时，则执行网络服务器的响应请求流程，并缓存应用信息的步骤，具体包括：获取应用信息对应的资源占用信息；判断资源占用信息的资源占用值是否达到热点阈值；当资源占用值达到热点阈值时，启动请求报文的响应操作，并下载应用信息对应的应用至应用缓存数据库；当资源占用值未达到热点阈值时，启动网络服务器响应请求报文。In the above technical solution, preferably, when there is no corresponding application information, the step of executing the response request process of the network server and caching the application information includes: acquiring resource occupation information corresponding to the application information; and determining resource occupation information Whether the resource occupancy value reaches the hotspot threshold; when the resource occupancy value reaches the hotspot threshold, the response operation of the request message is started, and the application corresponding to the application information is downloaded to the application cache database; when the resource occupancy value does not reach the hotspot threshold, the network is started. The server responds to the request message.

在上述技术方案中，优选地，解析所述请求报文的步骤，具体包括：当请求报文中包括地址信息时，对地址信息进行归一化处理，获取处理后地址信息。In the above technical solution, the step of parsing the request message specifically includes: when the request message includes the address information, normalizing the address information to obtain the processed address information.

在上述技术方案中，优选地，还包括：向网络服务器发送与应用信息对应的异步更新请求；获取并缓存更新后的应用信息。In the above technical solution, preferably, the method further includes: sending an asynchronous update request corresponding to the application information to the network server; acquiring and buffering the updated application information.

在上述技术方案中，优选地，请求报文为所述用户设备所需的数据及数据的请求点。In the above technical solution, preferably, the request message is a request point of data and data required by the user equipment.

在上述技术方案中，优选地，请求点包括以下至少一种，用户设备请求观看视频的起始时间点、用户设备请求观看视频时间点相对于整个视频文件初始点的时间点，或者是请求观看视频字节在整个视频文件中的具体字节位置。In the above technical solution, preferably, the request point includes at least one of the following, a starting time point at which the user equipment requests to watch the video, a time point at which the user equipment requests to watch the video time point relative to the initial point of the entire video file, or a request to view The specific byte position of the video byte in the entire video file.

本申请的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本申请的实践了解到。Additional aspects and advantages of the present invention will be set forth in part in the description which follows.

附图说明DRAWINGS

本申请的上述和/或附加的方面和优点从结合下面附图对实施例的描述中将变得明显和容易理解，其中：The above and/or additional aspects and advantages of the present application will become apparent and readily understood from

图1示出了相关中构建分布式服务器集群的示意图；Figure 1 shows a schematic diagram of building a distributed server cluster in relation to;

图2示出了本申请一个实施例的SDN交换机的应用管理方法的示意图；2 is a schematic diagram of an application management method of an SDN switch according to an embodiment of the present application;

图3示出了本申请再一个实施例的SDN交换机的应用管理方法的流程图；FIG. 3 is a flowchart of an application management method of an SDN switch according to still another embodiment of the present application;

图4示出了本申请一个实施例一种应用缓存加速方法的流程图；FIG. 4 is a flowchart of an application cache acceleration method according to an embodiment of the present application;

图5示出了本申请一个实施例一种在线视频访问的缓存加速方法的流程图。FIG. 5 is a flowchart of a cache acceleration method for online video access according to an embodiment of the present application.

其中，图1中附图标记与部件名称之间的对应关系为：Wherein, the correspondence between the reference numerals and the component names in FIG. 1 is:

1服务器、2路由器、3交换机，4客户机；1 server, 2 routers, 3 switches, 4 clients;

图2中附图标记与部件名称之间的对应关系为：The correspondence between the reference numerals in Figure 2 and the part names is:

10用户设备，20SDN交换机，30网络服务器。10 user equipment, 20SDN switch, 30 network server.

具体实施方式Detailed ways

为了能够更清楚地理解本申请的上述目的、特征和优点，下面结合附图和具体实施方式对本申请进行进一步的详细描述。需要说明的是，在不冲突的情况下，本申请的实施例及实施例中的特征可以相互组合。The above objects, features and advantages of the present application will be more clearly understood from the following description of the appended claims. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

在下面的描述中阐述了很多具体细节以便于充分理解本申请，但是，本申请还可以采用其他不同于在此描述的其他方式来实施，因此，本申请的保护范围并不受下面公开的具体实施例的限制。In the following description, numerous specific details are set forth in order to facilitate a full understanding of the application. However, the present application may also be practiced in other different ways than those described herein. Therefore, the scope of the present application is not limited by the specifics disclosed below. Limitations of the embodiments.

根据本申请的第一方面的实施例提出了一种SDN交换机20，包括：接入卡，用于通信网络中数据流量的接收与发送；交换卡，用于将接入卡接收的通信流量分发到各个业务卡，交换卡设置有物理交换网络；业务卡用于分析处理通信流量内容以及流量解析，业务卡设置有网络处理器和高速缓存内存模块；控制卡，用于控制和管理整个SDN交换机20的工作状态，控制卡设置有SDN控制器；高速缓存内存模块包括：缓存单元、主控单元及重定向单元，缓存单元用于下载缓存，主控单元用于整个***的集中管理，重定向单元用于访问重定向；其中，高速缓存内存模块的缓存空间还包括以下至少一个或其组合：业务卡中的网络处理器的内存部件、交换卡的处理器的存储部件、控制卡的处理器的存储部件、接入卡的处理器的存储部件。According to an embodiment of the first aspect of the present application, an SDN switch 20 is provided, comprising: an access card for receiving and transmitting data traffic in a communication network; and a switching card for distributing communication traffic received by the access card To each service card, the switch card is provided with a physical switching network; the service card is used for analyzing and processing the traffic content and the traffic analysis, the service card is provided with a network processor and a cache memory module; and the control card is used for controlling and managing the entire SDN switch. 20 working state, the control card is provided with an SDN controller; the cache memory module comprises: a cache unit, a main control unit and a redirection unit, the cache unit is used for downloading the cache, and the main control unit is used for centralized management and redirection of the entire system. The unit is used for access redirection; wherein the cache space of the cache memory module further comprises at least one of the following or a combination thereof: a memory component of the network processor in the service card, a storage component of the processor of the switch card, and a processor of the control card Storage component, storage component of the processor of the access card.

本申请提供的SDN交换机20，具有较大的存储空间的高速缓存内存模块，高速缓存内存模块不仅可以利用自身具备的存储空间，当存储容量过大时，还可以利用接入卡、交换卡、业务卡和控制卡内处理器的存储空间，进而进一步地提高了整体交换机的存储空间，可以满足应用文件的缓存需求；通过SDN交换机20***中的网络处理器的高速缓存内存模块来缓存应用，充分应用网络处理器多达4K的处理线程，并行分发应用内容到达各自的请求客户端，从而提高响应客户端请求的效率，减轻服务器分发应用内容时的处理压力，提高服务器的业务处理能力，同时解决了应用缓存和高速并行转发的问题。The SDN switch 20 provided by the present application has a cache memory module with a large storage space, and the cache memory module can not only utilize the storage space provided by itself, but also can utilize the access card and the exchange card when the storage capacity is too large. The storage space of the processor in the service card and the control card further improves the storage space of the overall switch, and can meet the cache requirement of the application file; the cache memory module of the network processor in the SDN switch 20 system caches the application, Fully apply the processing thread of the network processor up to 4K, and distribute the application content in parallel to reach the respective request client, thereby improving the efficiency of responding to the client request, reducing the processing pressure when the server distributes the application content, and improving the server's business processing capability. Solved the problem of application caching and high-speed parallel forwarding.

相关技术中，针对大型网吧应用和在线视频直播等网络负载较重的情况，在客户机向服务器请求较大文件时，比如几GB的大小应用，如果有多个用户同时请求该文件，则服务器需要同时处理多个下载请求，而服务器的网络处理能力一般有限，应付数据转发的压力较大，响应其他应用的请求就会延迟，造成用户体验较差。本申请提供的SDN交换机20，通过设置高速缓存内存模块，可以解决服务器响应客户端请求效率低的问题，提高服务器支持多用户访问请求的能力，提升用户访问体验，降低服务器的运行负载，利用SDN交换机20***中网络处理器的应用识别，高速缓存，并行转发能力，解决目前应用缓存***请求响应速度慢的问题。In the related art, for a large network load such as a large Internet cafe application and an online video live broadcast, when a client requests a large file from a server, such as a size of several GB, if multiple users request the file at the same time, the server Multiple download requests need to be processed at the same time, and the network processing capacity of the server is generally limited, and the pressure for data forwarding is large, and requests for responding to other applications are delayed, resulting in poor user experience. The SDN switch 20 provided by the present application can solve the problem that the server responds to the client request with low efficiency by setting the cache memory module, improve the server's ability to support multiple user access requests, improve the user access experience, reduce the server running load, and utilize SDN. The application identification, cache, and parallel forwarding capability of the network processor in the system of the switch 20 solves the problem that the response speed of the current application cache system is slow.

具体实施例中，SDN交换机20的高速缓存内存模块的缓存空间，可以由业务卡中的网络处理器的高速内存部件组成，如业务卡上的网络处理器的多个内存控制器，以及DDR3，DDR4系列的内存组件，这些高速内存部件往往具有高达1Tbps的访问带宽和1333Mhz的时钟速度，可以充分满足保存应用文件的缓存需求。进一步地，当业务需求量较大时，交换卡、控制卡和接入卡的处理器的存储部件也可以作为高速缓存内存模块的一部分。In a specific embodiment, the cache space of the cache memory module of the SDN switch 20 may be composed of a high-speed memory component of the network processor in the service card, such as multiple memory controllers of the network processor on the service card, and DDR3. DDR4 series of memory components, these high-speed memory components often have access bandwidth of up to 1Tbps and clock speed of 1333Mhz, which can fully meet the cache requirements of saving application files. Further, when the amount of business demand is large, the storage components of the processor of the switch card, the control card, and the access card may also be part of the cache memory module.

在本申请的一个实施例中，优选地，高速缓存内存模块采用数据报文的方式缓存应用文件，并可以为缓存应用文件创建文件描述信息。In an embodiment of the present application, preferably, the cache memory module caches the application file by means of data packets, and may create file description information for the cache application file.

在该实施例中，高速缓存内存模块采用数据报文的方式缓存应用文件，并可以为缓存的应用文件创建文件描述信息，用户设备10请求相应的应用时，SDN交换机20可以通过搜索该高速缓存内存模块的缓存空间的方式直接得到所需的应用文件，并可以通过更新SDN交换机20的内存中数据的控制信息，通过并行转发引擎转发的应用文件到相应的用户设备10。In this embodiment, the cache memory module caches the application file by means of data packets, and can create file description information for the cached application file. When the user equipment 10 requests the corresponding application, the SDN switch 20 can search the cache. The cache space of the memory module directly obtains the required application file, and can update the application file forwarded by the parallel forwarding engine to the corresponding user equipment 10 by updating the control information of the in-memory data of the SDN switch 20.

在本申请的一个实施例中，优选地，高速缓存内存模块的单一节点的高速内存的最大内存量大于等于96GB；SDN交换机20可以安装的节点数量大于等于12个；高速缓存内存模块的网络接口带宽为4.8Tbps。In an embodiment of the present application, preferably, the maximum memory capacity of the single node of the cache memory module is greater than or equal to 96 GB; the number of nodes that the SDN switch 20 can be installed is greater than or equal to 12; the network interface of the cache memory module The bandwidth is 4.8 Tbps.

在该实施例中，SDN交换机20的单一节点的高速内存最高可达96GB以上，而在一个SDN交换机20的机架设备里面往往可以最少安装12个节点，因此，单一设备的最大缓存容量可达1.1TB以上，整个***可以实现48K硬件线程同时处理应用缓存和网络转发，基本上可以满足绝大多数应用文件的缓存需求。进一步地，SDN交换机20***最大的网络接口带宽为4.8Tbps，SDN交换机20***网络超强的并发处理能力，使得该***在处理多用户并发访问时轻松自如，多达48K的处理线程，可以同时处理带宽4.8Tbps的业务流量，不会出现由于网络转发能力而造成的网络拥塞问题。In this embodiment, the single node of the SDN switch 20 has a high-speed memory of up to 96 GB or more, and in a rack device of an SDN switch 20, a minimum of 12 nodes can be installed. Therefore, the maximum buffer capacity of a single device can be reached. Above 1.1TB, the entire system can realize 48K hardware threads to process application cache and network forwarding at the same time, which can basically meet the cache requirements of most application files. Further, the maximum network interface bandwidth of the SDN switch 20 system is 4.8 Tbps, and the SDN switch 20 system network has strong concurrent processing capability, so that the system can easily handle multi-user concurrent access, and up to 48K processing threads can simultaneously When processing traffic with a bandwidth of 4.8 Tbps, there is no network congestion caused by network forwarding capability.

根据本申请的第二方面实施例提出了一种SDN交换机20的应用管理方法，用于如上述任一技术方案所述的SDN交换机20，如图2所示，SDN交换机20与用户设备10通过网络服务器30进行交互，通信***包括网络服务器30，SDN交换机20，用户设备10。其中，网络服务器30为网站服务器，是指驻留于因特网上某种类型计算机的程序，能够响应Internet上运行在其他计算机中的浏览器的访问请求，并向浏览器等Web客户端提供文档；SDN交换机20为具有应用管理功能的网络通信设备，可以加速用户设备10访问网络服务器30的速度，即代理网络用户设备10获取网络信息，具体用于管理网页组件和回应网页浏览器的请求，以及缓存网站的网页；SDN交换机20可以是后续实施例中描述的任一种可能的实现形式，具有应用管理功能的SDN交换机20可以同时处理多个网页的访问请求、以及一个网页的多个访问请求。用户设备10可以是个人电脑、平板电脑、数字助理、笔记本和手机等终端设备，例如是可以向用户提供语音和/或数据连通性的设备，具有无线连接功能的手持式设备。用户设备10可以有多个，该用户设备10安装了浏览器，例如QQ浏览器、优视科技浏览器和百度浏览器或360浏览器等，具体浏览器的类型不作限定。According to the second aspect of the present application, an application management method of the SDN switch 20 is provided for the SDN switch 20 as described in any one of the foregoing technical solutions. As shown in FIG. 2, the SDN switch 20 and the user equipment 10 pass The network server 30 interacts, and the communication system includes a network server 30, an SDN switch 20, and a user equipment 10. The web server 30 is a web server, and refers to a program of a certain type of computer residing on the Internet, capable of responding to an access request of a browser running on another computer on the Internet, and providing a document to a web client such as a browser; The SDN switch 20 is a network communication device with an application management function, which can speed up the access of the user device 10 to the network server 30, that is, the proxy network user device 10 acquires network information, specifically for managing webpage components and responding to requests of the web browser, and Cache the webpage of the website; the SDN switch 20 may be any possible implementation form described in the following embodiments, and the SDN switch 20 with the application management function can simultaneously process access requests of multiple web pages and multiple access requests of one webpage. . The user device 10 may be a terminal device such as a personal computer, a tablet computer, a digital assistant, a notebook, and a mobile phone, for example, a device that can provide voice and/or data connectivity to a user, and a handheld device with wireless connectivity. There may be a plurality of user devices 10, and the user device 10 is installed with a browser, such as a QQ browser, a Vision browser, a Baidu browser, or a 360 browser. The type of the specific browser is not limited.

如图3所示，本申请一个实施例的应用管理方法的流程图：As shown in FIG. 3, a flowchart of an application management method according to an embodiment of the present application:

步骤102，接收用户设备10发送的请求报文；Step 102: Receive a request message sent by the user equipment 10;

步骤104，解析请求报文，并获取请求报文中对应的应用信息；Step 104: Parse the request packet, and obtain corresponding application information in the request packet.

步骤106，根据应用信息查询SDN交换机20的应用缓存数据库中是否存在对应的应用信息；Step 106: Query, according to the application information, whether the corresponding application information exists in the application cache database of the SDN switch 20;

步骤108，当存在对应的应用信息时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作；Step 108: When there is corresponding application information, start a redirection operation of the request message according to the storage location of the application information in the application cache database;

步骤110，当不存在对应的应用信息时，则执行网络服务器30的响应请求流程，并缓存应用信息。Step 110: When there is no corresponding application information, the response request process of the network server 30 is executed, and the application information is cached.

如图2和图3所示，本申请提供的SDN交换机20的应用管理方法，接收用户设备10发送请求报文，并对的请求报文进行解析以获取用户设备10请求的应用信息，根据得到的应用信息在应用缓存数据库中进行查找，如果交换机的数据库中已存在该应用信息，则直接响应用户设备10的请求；如果交换机的数据库中没有该应用信息，则通过网络服务器30下载该应用，并缓存至交换机的数据库。通过本申请提供的SDN交换机20的应用管理方法，可以解决服务器响应客户端请求效率低的问题，提高服务器支持多用户访问请求的能力，提升用户访问体验，降低服务器的运行负载，利用SDN交换机20***中网络处理器的应用识别，高速缓存，并行转发能力，解决目前应用缓存***请求响应速度慢的问题。As shown in FIG. 2 and FIG. 3, the application management method of the SDN switch 20 provided by the present application receives the request packet from the user equipment 10, and parses the request packet to obtain the application information requested by the user equipment 10. The application information is searched in the application cache database. If the application information already exists in the database of the switch, it directly responds to the request of the user equipment 10; if the application information is not in the database of the switch, the application is downloaded through the network server 30, And cached to the database of the switch. Through the application management method of the SDN switch 20 provided by the present application, the problem that the server responds to the client request with low efficiency can be solved, the server can support the multi-user access request, the user access experience is improved, and the running load of the server is reduced, and the SDN switch 20 is utilized. The application identification, cache, and parallel forwarding capabilities of the network processor in the system solve the problem that the response speed of the current application cache system is slow.

具体地，用户设备10通过SDN交换机20向网络服务器30发出下载应用请求时，其中，用户设备10可以是浏览器、下载客户端、P2P客户端等，网络服务器30可以是HTTP服务器、CDN服务器、P2P服务器、P2P客户端等，SDN交换机20可实现应用的缓存加速，执行加速用户应用访问速度的控制程序，加速用户应用访问速度的控制程序可以运行于SDN交换机20的控制卡处理器上，也可以运行在通过各个板卡之间的竞争选举出来的交换卡处理器上。该控制程序可深度解析用户设备10发送的请求报文和网络服务器30的响应数据，利用SDN交换机20中业务卡上的网络处理器4K线程资源，使其工作在特有的ZOL(Zero Overhead Linux)模式下，并发处理数据报文的解析与转发任务。Specifically, the user equipment 10 sends a download application request to the network server 30 through the SDN switch 20, where the user equipment 10 can be a browser, a download client, a P2P client, etc., and the network server 30 can be an HTTP server, a CDN server, or the like. The P2P server, the P2P client, and the like, the SDN switch 20 can implement the cache acceleration of the application, execute a control program for accelerating the access speed of the user application, and the control program for accelerating the access speed of the user application can be run on the control card processor of the SDN switch 20, It can run on a switch card processor that is elected through competition between the various boards. The control program can deeply parse the request message sent by the user equipment 10 and the response data of the network server 30, and utilize the network processor 4K thread resources on the service card in the SDN switch 20 to work in the unique ZOL (Zero Overhead Linux). In the mode, the parsing and forwarding tasks of data packets are processed concurrently.

具体实施例中，SDN交换机20的应用管理方法依赖于接入卡与交换卡来实现数据流量的接收与发送，单一节点可以处理400Gbps带宽的网络流量。交换卡根据配置可将接收到的流量平均分配到业务卡的网络处理器上，使其发挥出最大的处理能力。进一步地，充分利用业务卡上的网络处理器，来深度解析用户设备10发送的请求报文，得到每个用户设备101发出报文的会话信息，并可进一步分析请求信息中所承载的应用信息，最大可以支持40M的用户并发请求。进一步地，应用信息可按照hash方式来存储在***的高速内存中，该程序对上述解析出来的应用信息进行hash运算，依据计算结果来查询所请求的信息是否已存在于缓存数据库中。In a specific embodiment, the application management method of the SDN switch 20 relies on an access card and a switch card to implement data traffic reception and transmission, and a single node can process network traffic of 400 Gbps bandwidth. The switch card is configured to distribute the received traffic evenly across the network processor of the service card to maximize its processing power. Further, the network processor on the service card is fully utilized to deeply parse the request message sent by the user equipment 10, and the session information sent by each user equipment 101 is obtained, and the application information carried in the request information may be further analyzed. The maximum can support 40M users concurrent requests. Further, the application information may be stored in the high-speed memory of the system according to a hash manner, and the program performs a hash operation on the parsed application information, and queries whether the requested information already exists in the cache database according to the calculation result.

在本申请的一个实施例中，优选地，当存在对应的所述应用信息时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作的步骤，具体包括：根据所述应用信息在应用缓存数据库中的存储位置，发送重定向请求至用户设备10；接收重定向请求的响应报文，根据响应报文中的应用信息，将应用缓存数据库中保存的对应的应用信息发送至用户设备10。In an embodiment of the present application, preferably, when there is corresponding application information, the step of initiating a redirection operation of the request message according to the storage location of the application information in the application cache database, specifically includes: The application information is stored in the application cache database, and the redirection request is sent to the user equipment 10; the response message of the redirection request is received, and the corresponding application information stored in the cache database is applied according to the application information in the response message. Sent to user device 10.

在该实施例中，用户设备10和网络服务器30之间采用HTTP协议的302重定向机制实现数据流的转接控制。通过解析用户设备10浏览器发出的http请求，根据查询命中结果发送302重定向URL到用户设备101浏览器；用户设备10浏览器按重定向URL向SDN交换机20控制程序重新发起HTTP请求；控制程序接收HTTP请求，直接响应请求，并将应用缓存数据转发给该请求的用户设备10。In this embodiment, the user equipment 10 and the network server 30 implement the transfer control of the data flow by using the 302 redirection mechanism of the HTTP protocol. By parsing the http request sent by the browser of the user equipment 10, sending a 302 redirect URL to the user equipment 101 browser according to the query hit result; the user equipment 10 browser re-initiates the HTTP request to the SDN switch 20 control program according to the redirect URL; the control program The HTTP request is received, the request is directly responded, and the application cache data is forwarded to the requesting user device 10.

在本申请的一个实施例中，优选地，当应用缓存数据库存在对应的应用信息时，还包括：判断应用信息是否为可用；当应用信息可用时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作；当应用信息不可用时，则执行网络服务器30的响应请求流程，并缓存应用信息。In an embodiment of the present application, preferably, when the application cache database has corresponding application information, the method further includes: determining whether the application information is available; and when the application information is available, storing the location in the application cache database according to the application information. The redirection operation of the request message is initiated; when the application information is not available, the response request process of the web server 30 is executed, and the application information is cached.

在本申请的一个实施例中，优选地，当应用缓存数据库存在对应的应用信息时，还包括：判断应用信息的置信度是否大于预设阈值；当置信度大于等于预设阈值时，根据应用信息在应用缓存数据库中的存储位置，启动请求报文的重定向操作；当置信度小于所述预设阈值时，则执行网络服务器30的响应请求流程，并缓存应用信息。In an embodiment of the present application, preferably, when the application cache information has corresponding application information, the method further includes: determining whether the confidence of the application information is greater than a preset threshold; and when the confidence is greater than or equal to the preset threshold, according to the application The storage location of the information in the application cache database initiates a redirect operation of the request message; when the confidence level is less than the preset threshold, the response request process of the network server 30 is executed, and the application information is cached.

在本申请的一个实施例中，优选地，当不存在对应的应用信息时，则执行网络服务器30的响应请求流程，并缓存应用信息的步骤，具体包括：获取应用信息对应的资源占用信息；判断资源占用信息的资源占用值是否达到热点阈值；当资源占用值达到热点阈值时，启动请求报文的响应操作，并下载应用信息对应的应用至应用缓存数据库；当资源占用值未达到热点阈值时，启动网络服务器30响应请求报文。In an embodiment of the present application, preferably, when there is no corresponding application information, the step of executing the response request process of the network server 30 and caching the application information includes: acquiring resource occupation information corresponding to the application information; Determining whether the resource occupancy value of the resource occupation information reaches the hotspot threshold; when the resource occupancy value reaches the hotspot threshold, the response operation of the request message is started, and the application corresponding to the application information is downloaded to the application cache database; when the resource occupancy value does not reach the hotspot threshold When the network server 30 is started, it responds to the request message.

在该实施例中，通过判断网络服务器30上该请求资源是否已达到热点资源的阀值，如果达到阀值时，程序将该资源下载到***缓存中，该缓存可以是业务卡上网络处理器的高速内存，也可以是由其他控制卡和交换卡中没有被***利用的内存。若没有达到预设的阈值，程序则不去执行缓存步骤和重定向步骤，由网络服务器30直接响应用户设备10发出的应用请求。In this embodiment, by determining whether the requested resource on the network server 30 has reached the threshold of the hotspot resource, if the threshold is reached, the program downloads the resource into the system cache, which may be a network processor on the service card. The high-speed memory can also be used by other control cards and switch cards that are not utilized by the system. If the preset threshold is not reached, the program does not perform the caching step and the redirection step, and the web server 30 directly responds to the application request sent by the user device 10.

图4示出了本申请一个实施例提供了一种应用缓存加速的方法，能够提高用户设备10加载网页的速度，该实施例的流程如图4所示：FIG. 4 illustrates an embodiment of the present application, which provides a method for applying cache acceleration, which can improve the speed at which the user equipment 10 loads a webpage. The flow of this embodiment is as shown in FIG. 4:

步骤202，接收用户设备10发送的请求报文，请求报文中包括地址信息；Step 202: Receive a request message sent by the user equipment 10, where the request message includes address information.

步骤204，对地址信息进行归一化处理，获取处理后地址信息；Step 204: Perform normalization processing on the address information to obtain the processed address information.

步骤206，根据处理后地址信息，在缓存数据库中查找处理后地址信息相对应的缓存网页；Step 206: Search, according to the processed address information, a cached webpage corresponding to the processed address information in the cache database;

步骤208，根据处理后地址信息查找到的缓存网页参数判断该缓存网页是否为可用缓存网页；Step 208: Determine, according to the cached webpage parameter found by the processed address information, whether the cached webpage is an available cached webpage;

步骤210，当该缓存网页为可用缓存网页时，将目标缓存网页返回给所述用户设备10； Step 210, when the cached webpage is an available cached webpage, returning the target cached webpage to the user equipment 10;

步骤212，当该缓存网页不是可用缓存网页时，根据处理后地址信息向网络服务器30获取对应的当前网页，并将当前网页发送给用户设备10。Step 212: When the cached webpage is not a cached webpage, obtain the corresponding current webpage from the web server 30 according to the processed address information, and send the current webpage to the user equipment 10.

在该实施例中，通过接收到携带地址信息的访问请求后，对该地址信息进行归一化处理，以去除与用户相关的信息，从而增加获取到目标缓存网页的概率，然后使用归一化后的地址信息从数据库中获取目标缓存网页，并在根据缓存网页参数确定所述目标缓存网页为可用缓存网页时，将所述目标缓存网页返回给所述用户设备10，使得用户设备10快速加载目标缓存网页。In this embodiment, after receiving the access request carrying the address information, the address information is normalized to remove information related to the user, thereby increasing the probability of acquiring the target cached webpage, and then using normalization. After the address information is obtained from the database, the target cached webpage is obtained from the database, and when the target cached webpage is determined to be a cached webpage according to the cached webpage parameter, the target cached webpage is returned to the user equipment 10, so that the user equipment 10 is quickly loaded. Target cache page.

进一步地，该地址信息是指从一个网页指向一个目标的连接关系，所指向的目标可以是另一个网页，也可以是相同网页上的不同位置，还可以是图片、电子邮件地址、文件、甚至是应用程序。该地址信息可以是统一资源定位符(英文全称：Uniform Resource Locator，英文简称：URL)、链接等唯一标识网页、能够跳转至对应的网页的信息，具体本文不作限定。URL是与因特网相连的机器上的任何可访问对象的一个指针，URL包含模式(或称协议)、服务器名称(或IP地址)、路径和文件名。Further, the address information refers to a connection relationship from a webpage to a target, and the target pointed to may be another webpage, or may be a different location on the same webpage, or may be a picture, an email address, a file, or even Is the application. The address information may be a uniform resource locator (English name: Uniform Resource Locator, English abbreviation: URL), a link, and the like, which can uniquely identify a webpage, and can jump to the corresponding webpage, which is not limited herein. A URL is a pointer to any accessible object on a machine connected to the Internet. The URL contains the pattern (or protocol), server name (or IP address), path, and file name.

具体实施例中，用户设备10UE1和UE2都安装了QQ浏览器，UE1使用QQ浏览器向SDN交换机20发送访问腾讯新闻网的访问请求，SDN交换机20则根据访问请求中的URL1从腾讯新闻网抓取与该URL1对应的网页1，并缓存至共享存储，随后，UE2使用QQ浏览器向SDN交换机20发送访问腾讯新闻网的访问请求，代理服务器先对访问请求中的URL2进行归一化处理，即去除URL2中与UE2的用户相关的信息(例如设备类型、订阅标识、用户身份标识等)，由于URL1和URL2的区别主要在于携带的与用户相关的信息不同，而实际所请求的都是腾讯新闻网的网络地址，如果不进行归一化处理，直接使用URL2在共享存储中查找缓存的网页的话，可能无法匹配到该网页，而使用归一化后的URL2在共享存储中查找，则可以提高匹配到网页的概率，提高了查找网页的速率。In the specific embodiment, the user equipments 10UE1 and UE2 both have a QQ browser installed, and the UE1 sends an access request to the SDN switch 20 to access the Tencent news network by using the QQ browser, and the SDN switch 20 grabs the Tencent news network according to the URL1 in the access request. Taking the webpage 1 corresponding to the URL1 and buffering it to the shared storage, then the UE2 sends an access request to the SDN switch 20 to access the Tencent news network by using the QQ browser, and the proxy server first normalizes the URL2 in the access request. That is, the information related to the user of the UE2 in the URL2 (such as the device type, the subscription identifier, the user identity, and the like) is removed. The difference between the URL1 and the URL2 is mainly because the information related to the user is different, and the actual request is Tencent. If the network address of the news network is not normalized, if you use URL2 to find the cached webpage in the shared storage, you may not be able to match the webpage. If you use the normalized URL2 to search in the shared storage, you can Improve the probability of matching to a web page and increase the rate at which web pages are found.

进一步地，缓存网页参数可以包括缓存网页的原始响应、缓存网页的置信度、缓存网页的更新时间及缓存网页的有效时长等中的至少一项。Further, the cache webpage parameter may include at least one of an original response of the cached webpage, a confidence level of the cached webpage, an update time of the cached webpage, and an effective duration of the cached webpage.

具体实施例中，缓存网页参数为缓存网页的置信度，SDN交换机20可以根据目标缓存网页的置信度确定目标缓存网页为可用缓存网页，具体为：判断目标缓存网页的置信度是否大于预设阈值，若大于预设阈值，则确定目标缓存网页为可用缓存网页，将目标缓存网页发送给用户设备10。In a specific embodiment, the cached webpage parameter is a confidence level of the cached webpage, and the SDN switch 20 can determine that the target cached webpage is an available cached webpage according to the confidence level of the target cached webpage, specifically: determining whether the confidence level of the target cached webpage is greater than a preset threshold. If the threshold is greater than the preset threshold, the target cache webpage is determined to be an available cache webpage, and the target cache webpage is sent to the user equipment 10.

反之，若无法通过上述地址信息从数据库中获取到对应的目标缓存网页，则SDN交换机20使用用户设备10发送的地址信息从地址信息链接到的网站抓取对应的网页；或者，虽然SDN交换机202通过上述地址信息从数据库中获取到对应的目标缓存网页，但数据路中缓存的目标缓存网页的置信度小于预设阈值，表明当前该地址信息对应的最新网页与数据库中缓存的目标缓存网页相差较大，则SDN交换机20需要使用用户设备10发送的地址信息从地址信息链接到的网站抓取对应的网页，然后发送给用户设备10。On the other hand, if the corresponding target cache webpage cannot be obtained from the database through the above address information, the SDN switch 20 uses the address information sent by the user equipment 10 to fetch the corresponding webpage from the website to which the address information is linked; or, although the SDN switch 202 The corresponding target cached webpage is obtained from the database by using the above address information, but the confidence of the target cached webpage cached in the data path is less than a preset threshold, indicating that the latest webpage corresponding to the current address information is different from the cached target cached webpage in the database. If the address is larger, the SDN switch 20 needs to use the address information sent by the user equipment 10 to fetch the corresponding webpage from the website to which the address information is linked, and then send the corresponding webpage to the user equipment 10.

在本申请的一个实施例中，优选地，还包括：向网络服务器30发送与应用信息对应的异步更新请求；获取并缓存更新后的应用信息。In an embodiment of the present application, preferably, the method further includes: sending an asynchronous update request corresponding to the application information to the network server 30; acquiring and buffering the updated application information.

具体实施例中，SDN交换机20周期性的、或不定时的向网络服务器30请求异步更新或近似缓存，具体包括：In an embodiment, the SDN switch 20 requests asynchronous or approximate caching to the network server 30 periodically or irregularly, including:

SDN交换机20在将目标缓存资源返回给用户设备10之后，SDN交换机20向目标缓存网页所属的网站发送携带未归一化的地址信息的异步更新请求；异步更新请求用于向网站请求获取未归一化的地址信息对应的当前网页，以及用于更新目标缓存网页的访问量和更新网站的访问量，即通过异步更新可以避免目标缓存网页的真实访问量减少，使网站端与SDN交换机20端的数据同步，从而保证网站的真实访问量的可靠性；SDN交换机20根据获取的当前网页异步更新数据库中缓存的目标缓存网页。具体的，SDN交换机20根据获取的当前网页异步更新数据库中缓存的所述目标缓存网页时，SDN交换机20通过对比当前网页与数据库中缓存的目标缓存网页，以计算目标缓存网页对当前网页的置信度，置信度用于判断所述当前网页是否为可缓存；在确定所述当前网页为可缓存后，则根据当前网页对数据库中缓存的目标缓存网页进行近似缓存，以使数据库中缓存的目标缓存网页异步更新。After the SDN switch 20 returns the target cache resource to the user equipment 10, the SDN switch 20 sends an asynchronous update request carrying the unnormalized address information to the website to which the target cache page belongs; the asynchronous update request is used to request the website to obtain the unreturned request. The current webpage corresponding to the address information, and the amount of visits for updating the target cached webpage and the amount of visits of the updated website, that is, the asynchronous update can avoid the real traffic of the target cached webpage, and the website end and the SDN switch 20 end The data is synchronized to ensure the reliability of the real traffic of the website; the SDN switch 20 asynchronously updates the cached target cached pages in the database according to the obtained current webpage. Specifically, when the SDN switch 20 asynchronously updates the target cached webpage cached in the database according to the obtained current webpage, the SDN switch 20 compares the current webpage with the cached webpage cached in the database to calculate the confidence of the target cached webpage to the current webpage. Degree, the confidence is used to determine whether the current webpage is cacheable; after determining that the current webpage is cacheable, the target cached webpage cached in the database is approximate cached according to the current webpage, so as to cache the target in the database. Cache webpages are updated asynchronously.

具体实施例中，在异步请求更新流程中，SDN交换机20可根据从网站获取的最新网页(即所述当前网页)的包头所包含的字段信息来重新计算目标缓存网页的置信度，具体的计算过程主要包括以下几种情况：In a specific embodiment, in the asynchronous request update process, the SDN switch 20 may recalculate the confidence of the target cached webpage according to the field information included in the header of the latest webpage (ie, the current webpage) obtained from the website, and the specific calculation The process mainly includes the following situations:

一、若当前网页的包头中包含指示不对当前网页进行缓存的第一类标识，则SDN交换机20将置信度置0，其中，第一类标识至少包括以下之一：缓存控制cachecontrol字段设置为不缓存、网页参数pragma字段设置为不缓存、或cookies等，该cachecontrol字段也还可以包括其他能够标识不缓存的字段，或者第一类标识采用其它类似的字段去标识不缓存，具体本文不作限定。例如，在使用cache-control字段标识不缓存时，cache-control字段的取值至少包括以下之一：私有缓存(private)字段、不缓存(no-cache)字段、不存储(no-store)字段、强制重新生效(must-revalidate)字段、代理重新生效(proxy-revalidate)字段、缓存时长字段(max-age＝0)，即只要cache-control字段的取值包括这几个中的至少一个时，则表明不可以对网页缓存，那么需要将当前的置信度置0，在后续的访问请求中重新计算置信度。If the header of the current webpage includes the first type of identifier indicating that the current webpage is not cached, the SDN switch 20 sets the confidence level to 0. The first type of identifier includes at least one of the following: the cache control cachecontrol field is set to no. The cache, the webpage parameter pragma field is set to not cache, or the cookies, and the cache control field may also include other fields that can identify the non-cache, or the first type of identifier uses other similar fields to identify the cache, which is not limited herein. For example, when the cache-control field is used to identify that the cache is not cached, the value of the cache-control field includes at least one of the following: a private cache (private) field, a non-cache (no-cache) field, and a non-store (no-store) field. , mandatory-revalidation (must-revalidate) field, proxy-revalidation (proxy-revalidate) field, cache duration field (max-age=0), that is, as long as the value of the cache-control field includes at least one of these , indicating that the web page cannot be cached, then the current confidence level needs to be set to 0, and the confidence level is recalculated in subsequent access requests.

二、若当前网页的包头中包含指示对当前网页进行缓存的第二类标识，则SDN交换机20增加所述置信度。2. If the header of the current web page includes a second type of identifier indicating that the current web page is cached, the SDN switch 20 increases the confidence level.

SDN交换机20可以对包含第二类标识的目标缓存网页的置信度增加A1，A1为正整数，A1的取值可以根据网站的类别、网站设计、或用户需求等来设定，具体本文不作限定。例如，在使用所述cache-control字段标识可缓存时，所述第二类标识至少包括以下之一：cache-control字段的取值设置为缓存时长大于0、缓存期满(expire)字段置为未到期、或目标缓存网页的消息摘要值与当前网页的md5相同。即只要cache-control字段的取值包括这几个中的n个时，则表明可以对网页缓存，那么对当前的置信度增加n*A1。例如，cache-control字段的取值只包括expire字段设置为未到期时，置信度增加20；cache-control字段的取值包括expire字段设置为未到期、以及目标缓存网页的md5与当前网页的md5相同时，置信度增加40，其他同理，不作赘述。可以理解的是，针对cache-control字段的不同取值，置信度的取值可以预先定义，具体的取值不作限定。The SDN switch 20 can increase the confidence of the target cached webpage including the second type of identifiers by A1, and A1 is a positive integer. The value of A1 can be set according to the category of the website, website design, or user requirements, etc., which is not limited herein. . For example, when the cache-control field is used to identify the cacheable, the second type identifier includes at least one of the following: the value of the cache-control field is set to a cache duration greater than 0, and the cache expiration field is set to The message digest value of the unexpired or target cached web page is the same as the md5 of the current web page. That is, as long as the value of the cache-control field includes n of these, it indicates that the webpage can be cached, and then the current confidence is increased by n*A1. For example, the value of the cache-control field only includes when the expire field is set to unexpired, and the confidence is increased by 20; the value of the cache-control field includes the expire field set to not expired, and the md5 of the target cache page and the current webpage. When the md5 is the same, the confidence level is increased by 40. Others are similar and will not be described. It can be understood that, for different values of the cache-control field, the value of the confidence can be predefined, and the specific value is not limited.

三、若目标缓存网页与当前网页的差异内容的长度小于预设的字节数，则SDN交换机20增加置信度。3. If the length of the difference content between the target cache webpage and the current webpage is less than the preset number of bytes, the SDN switch 20 increases the confidence level.

SDN交换机20在一段时间内，可能会接收到多个用户设备10的访问请求，也可能接收到同一个用户设备10的多次访问请求，则SDN交换机20对接收到的多个用户设备10的访问请求进行校验，和/或对接收到的同一个用户设备10的多次访问请求进行校验，可见，可以通过对访问请求进行校验来执行置信度的计算，用户设备10发送的地址信息中包括目标域名信息，故通过校验访问请求计算置信度的具体过程为：The SDN switch 20 may receive the access request of multiple user equipments 10 or may receive multiple access requests of the same user equipment 10 for a period of time, and then the SDN switch 20 receives the received multiple user equipments 10 The access request is verified, and/or the received multiple access requests of the same user equipment 10 are verified. It can be seen that the calculation of the confidence can be performed by verifying the access request, and the address sent by the user equipment 10 The information includes the target domain name information, so the specific process of calculating the confidence by verifying the access request is:

针对每一次访问请求，SDN交换机20都可以根据域名信息与字节数的对应关系，确定与目标域名信息对应的目标字节数。当目标缓存网页与当前网页的差异数据的长度小于目标字节数时，则SDN交换机20对目标缓存网页的置信度增加A2，A2为正整数。For each access request, the SDN switch 20 can determine the number of target bytes corresponding to the target domain name information according to the correspondence between the domain name information and the number of bytes. When the length of the difference data between the target cache webpage and the current webpage is less than the target number of bytes, the confidence of the SDN switch 20 to the target cached webpage is increased by A2, and A2 is a positive integer.

可以理解的是，由于每个网站都定义自身特定的域名，根据网站的域名信息便可以唯一识别所请求的网站，SDN交换机20可以预先为每个网站定义：所请求访问的网页的最新网页的内容长度相较于数据库中缓存的目标缓存网页，其内容长度的变化在一定范围内时，可以对置信度增加A2。可选的，对于不同的域名信息对应的网站，可以设置对置信度增加不同或相同的数值，具体本文不作限定，网站的置信度的取值也不作限定。例如，针对腾讯新闻网，可以设置3字节数，即在当前请求访问的所述当前网页与目标缓存网页相比，内容变化的长度为3个字节时，置信度增加5，又例如，对于新浪网，可以设置20个字节，具体的置信度可以增加5或者其他数值。It can be understood that since each website defines its own specific domain name, the requested website can be uniquely identified according to the domain name information of the website, and the SDN switch 20 can define in advance for each website: the latest webpage of the requested webpage. When the content length is smaller than the target cached webpage cached in the database, the content length can be increased within a certain range, and the confidence can be increased by A2. Optionally, for the website corresponding to different domain name information, the value of the confidence level may be set to be different or the same, which is not limited in this document, and the value of the website's confidence is not limited. For example, for Tencent News Network, a 3-byte number can be set, that is, when the current webpage currently requested to be accessed is 3 bytes longer than the target cache webpage, the confidence is increased by 5, for example, For Sina.com, you can set 20 bytes, and the specific confidence can be increased by 5 or other values.

针对上述三种情况，SDN交换机20可以针对每一次访问请求进行置信度的计算，以刷新目标缓存网页的置信度，由于目标缓存网页的置信度不断变化，故SDN交换机20对于在目标缓存网页的置信度小于预设阈值之前接收到用户设备10的访问请求，都需要从网站获取地址信息对应的当前网页，然后返回给发送访问请求的用户设备10。当在目标缓存网页的置信度达到预设阈值后，则标记目标缓存网页为可用，并且，SDN交换机20对于在目标缓存网页的置信度达到预设阈值后所接收到用户设备10的访问请求，可以直接将数据库中缓存的目标缓存网页返回给发送访问请求的用户设备10，不需要再从网站去抓取与所述地址信息对应的网页了。For the above three cases, the SDN switch 20 can perform a confidence calculation for each access request to refresh the confidence of the target cached webpage. Since the confidence of the target cached webpage is constantly changing, the SDN switch 20 is for the target cached webpage. If the access request of the user equipment 10 is received before the confidence level is less than the preset threshold, the current webpage corresponding to the address information needs to be obtained from the website, and then returned to the user equipment 10 that sends the access request. After the confidence level of the target cache webpage reaches a preset threshold, the marked target cache webpage is available, and the SDN switch 20 receives the access request of the user equipment 10 after the confidence level of the target cached webpage reaches a preset threshold. The target cache webpage cached in the database can be directly returned to the user equipment 10 that sends the access request, and the webpage corresponding to the address information does not need to be fetched from the website.

图5示出了本申请再一个实施例提供了一种在线视频访问的缓存加速方法，能够提高用户设备10加载视频的速度，加速方法的流程图如图5所示：FIG. 5 shows another embodiment of the present application, which provides a cache acceleration method for online video access, which can improve the speed at which the user equipment 10 loads video. The flowchart of the acceleration method is shown in FIG. 5:

步骤302，接收用户设备10发送的第一请求信息，第一请求信息指示用户设备10所需的视频数据及视频数据的请求点；Step 302: Receive first request information sent by the user equipment 10, where the first request information indicates a request point of video data and video data required by the user equipment 10;

步骤304，根据第一请求信息，在缓存数据库中查找是否存在对应的视频数据；Step 304: Search, according to the first request information, whether there is corresponding video data in the cache database.

步骤306，当存在对应的视频数据时，根据请求点确定视频数据的起始观看位置； Step 306, when there is corresponding video data, determining a starting viewing position of the video data according to the request point;

步骤308，当不存在存在对应的视频数据时，向网络服务器30请求下载该未缓存的视频数据，并发送至用户设备10； Step 308, when there is no corresponding video data, the network server 30 is requested to download the uncached video data, and sent to the user equipment 10;

步骤310，当不存在对应的视频数据时，多个用户设备10发送同一第一请求信息时，判断多个用户设备10对应的请求点是否达到预设热点阈值；Step 310: When there is no corresponding video data, when the multiple user equipments 10 send the same first request information, determine whether the request points corresponding to the multiple user equipments 10 reach the preset hotspot threshold;

步骤312，根据预设热点阀值从多个用户设备10的第一请求信息指示的该相同数据的请求点中选择一个请求点发送。Step 312: Select a request point to send from the request points of the same data indicated by the first request information of the plurality of user equipments 10 according to the preset hotspot threshold.

具体实施例中，请求点包括以下至少一种，用户设备10请求观看视频的起始时间点、用户设备10请求观看视频时间点相对于整个视频文件初始点的时间点，或者是请求观看视频字节在整个视频文件中的具体字节位置。In a specific embodiment, the request point includes at least one of the following, a start time point at which the user equipment 10 requests to watch the video, a time point when the user equipment 10 requests to watch the video time point relative to the initial point of the entire video file, or a request to watch the video word. The specific byte position of the section in the entire video file.

若SDN交换机20接收了用户设备10中设备A，B，C，D，E分别发送的第一请求信息，每个第一请求信息中分别指示设备A，B，C，D，E所请求的视频数据及该视频数据的请求点。即设备A发送的第一请求信息指示设备A所请求的视频数据及该视频数据的请求点，设备B发送的第一请求信息指示设备B所请求的视频数据及该视频数据的请求点，设备C发送的第一请求信息指示设备C所请求的视频数据及该视频数据的请求点，设备D发送的第一请求信息指示设备D所请求的视频数据及该视频数据的请求点，设备E发送的第一请求信息指示设备E所请求的视频数据及该视频数据的请求点。其中，请求点表示用户设备10需要观看该视频数据的起始位置如果设备A、B、C请求的视频数据相同，比如均为电影M，并且设备A，B，C请求的该视频数据是不同请求点。设备D、E请求的视频数据为X以外的其他视频数据，设备D、E请求的视频数据及对应的请求点可以相同或者不同。If the SDN switch 20 receives the first request information sent by the devices A, B, C, D, and E in the user equipment 10, each of the first request information respectively indicates the requests of the devices A, B, C, D, and E. Video data and the request point of the video data. That is, the first request information sent by the device A indicates the video data requested by the device A and the request point of the video data, and the first request information sent by the device B indicates the video data requested by the device B and the request point of the video data, and the device The first request information sent by C indicates the video data requested by the device C and the request point of the video data, and the first request information sent by the device D indicates the video data requested by the device D and the request point of the video data, and the device E sends the request point. The first request information indicates the video data requested by the device E and the request point of the video data. The request point indicates that the user equipment 10 needs to view the starting position of the video data. If the video data requested by the devices A, B, and C is the same, for example, all are the movie M, and the video data requested by the devices A, B, and C is different. Request point. The video data requested by the devices D and E is other video data than X, and the video data requested by the devices D and E and the corresponding request points may be the same or different.

进一步的，如果设备A，B，C不是从整个视频文件M的起始点请求观看，即不是从头开始观看视频文件，那么设备A，B，C发送的请求信息中存在指示设备A，B，C请求的该视频数据的不同请求点的字段。其中，请求点可以为用户设备10请求观看视频时间点相对于整个视频文件初始点的时间点，或者是请求观看视频字节在整个视频文件中的具体字节位置等。如，HTTP(Hypertext Transport Protocol,超文本传送协议)请求消息中，起始行的参数部分会用start＝x(or begin＝x)来指明本条请求的请求点，其中，x为请求点，可以表示时间，如x＝32，表示起始观看时间是第32秒；也可以表示具体字节数，如1204，表示起始观看位置是第1204字节处等Further, if the devices A, B, and C do not request viewing from the starting point of the entire video file M, that is, instead of viewing the video file from the beginning, the pointing device A, B, and C are present in the request information sent by the devices A, B, and C. The field of the different request points for the requested video data. The request point may be a time point at which the user equipment 10 requests to watch the video time point relative to the initial point of the entire video file, or a specific byte position requesting to watch the video byte in the entire video file. For example, in the HTTP (Hypertext Transport Protocol) request message, the parameter part of the start line will use start=x(or begin=x) to indicate the request point of this request, where x is the request point, Indicates the time, such as x=32, indicating that the initial viewing time is the 32nd second; it can also represent the specific number of bytes, such as 1204, indicating that the starting viewing position is the 1204th byte, etc.

若确定发送第一请求信息多个用户设备10中的至少两个用户设备10发送的第一请求信息指示的数据相同且该数据未缓存在SDN交换机20上，则在落入每个预设窗口内的请求点中选择一个请求点。If it is determined that the data indicated by the first request information sent by the at least two user equipments 10 of the plurality of user equipments 10 transmitting the first request information is the same and the data is not cached on the SDN switch 20, then each preset window is dropped. Select one of the request points within the request point.

若SDN交换机20收到的多个用户设备10的第一请求信息指示的是已缓存在所述SDN交换机20缓存单元上的数据，则可以从用户设备10请求的请求点开始向每个用户设备10送该用户设备10请求的数据。若某个或某些用户设备10请求的是未缓存在所述SDN交换机20缓存单元上的数据，则SDN交换机20向网络服务器30请求该未缓存的数据，接收数据后再向相应的用户设备10发送。If the first request information of the plurality of user equipments 10 received by the SDN switch 20 indicates the data that has been cached on the cache unit of the SDN switch 20, the request point from the user equipment 10 may be started to each user equipment. 10 sends the data requested by the user equipment 10. If one or some of the user equipments 10 request data that is not cached on the cache unit of the SDN switch 20, the SDN switch 20 requests the uncached data from the network server 30, and then receives the data and then sends the data to the corresponding user equipment. 10 sent.

若SDN交换机20收到多个用户设备10中的至少两个用户设备10对同一未缓存的数据进行请求，若对接收到的这段视频数据的各个请求点都单独进行请求和转发，则需要占用较大的上游网络流量，所以可以利用预设热点阀值对至少两个用户设备10所需的相同或不同的请求点进行选择，如根据预设热点阀值从至少两个用户设备10的第一请求信息指示的该相同数据的请求点中选择一个请求点发送，从而减少重复发送，降低对上游网络带宽的消耗。If the SDN switch 20 receives at least two user equipments 10 of the plurality of user equipments 10 to request the same uncached data, if each request point of the received video data is separately requested and forwarded, A large upstream network traffic is occupied, so that the same or different request points required by at least two user equipments 10 can be selected by using a preset hotspot threshold, such as from at least two user equipments 10 according to a preset hotspot threshold. A request point is selected from the request points of the same data indicated by the first request information, thereby reducing repeated transmission and reducing consumption of bandwidth of the upstream network.

进一步地，预设热点阀值大小可以根据时间设定，如预设热点阀值为6秒，此时SDN交换机20同时收到用户设备10中设备A，B，C对SDN交换机20缓存中未缓存的同一个文件M进行请求的第一请求信息，设备A，B，C请求的文件M记作“file-abc”。以HTTP请求消息为例，假设设备A，B，C的请求最大时间间隔在6秒之内，则说明达到了预设热点阀值，SDN交换机20将会向网络服务器30发送该资源的下载请求。Further, the preset hotspot threshold value may be set according to time. For example, the preset hotspot threshold is 6 seconds. At this time, the SDN switch 20 simultaneously receives the devices A, B, and C in the user equipment 10 and does not cache the SDN switch 20. The cached same file M makes the requested first request information, and the file M requested by the device A, B, C is denoted as "file-abc". Taking the HTTP request message as an example, if the maximum time interval of the requests of the devices A, B, and C is within 6 seconds, it indicates that the preset hotspot threshold is reached, and the SDN switch 20 will send a download request for the resource to the network server 30. .

SDN交换机20向源服务器发送第二请求信息，第二请求信息指示所述未缓存的数据及所述选择的请求点。The SDN switch 20 sends second request information to the source server, the second request information indicating the uncached data and the selected request point.

SDN交换机20向网络服务器30发送指示所述选择的请求点的第二请求信息，如SDN交换机20在收到设备A，B，C对SDN交换机20未缓存的同一个文件记作“file-abc”的请求后，选择了设备A和设备B的请求点，SDN交换机20向网络服务器30发送该文件的第二请求信息。因此，SDN交换机20就可以将网络服务器30发送的数据，如视频数据、音频数据等根据用户设备10请求的请求点所对应的位置，分别向同一预设热点阀值内的用户设备10发送，这样上游网络带宽消耗降低的同时，满足了用户观看需求。The SDN switch 20 sends the second request information indicating the selected request point to the network server 30. For example, the SDN switch 20 receives the same file that the device SDN switch 20 does not cache on the receiving device A, B, and C as "file-abc". After the request, the request points of device A and device B are selected, and the SDN switch 20 transmits the second request information of the file to the network server 30. Therefore, the SDN switch 20 can send the data sent by the network server 30, such as video data and audio data, to the user equipment 10 in the same preset hotspot threshold according to the location corresponding to the request point requested by the user equipment 10, In this way, the bandwidth consumption of the upstream network is reduced, and the user's viewing demand is satisfied.

SDN交换机20能够做到用户设备10和网络服务器30端都无感知的完成视频缓存加速，即无需修改用户设备10端配置和网络服务器30端的配置，也不用在用户设备10安装插件或者改变用户浏览网站的访问习惯，就能完成***的加速功能。重定向采用了HTTP协议中定义的标准协议族。HTTP协议中的状态码是用以表示网页服务器HTTP响应状态的3位数字。The SDN switch 20 can complete the video buffer acceleration without the user equipment 10 and the network server 30, so that the user equipment 10 end configuration and the network server 30 end configuration need not be modified, and the user equipment 10 does not need to install the plug-in or change the user browsing. The accessibility of the website can complete the acceleration function of the system. The redirection uses the standard protocol family defined in the HTTP protocol. The status code in the HTTP protocol is a 3-digit number used to indicate the HTTP response status of the web server.

SDN交换机20通过利用标准中定义的302状态码将用户设备10的请求临时引流到SDN交换机20缓存加速***，从而将***内缓存单元的数据加速分发给用户设备10，避免用户设备10端通过网络出口向源网站低速获取并挤占出口带宽。The SDN switch 20 temporarily deports the request of the user equipment 10 to the SDN switch 20 cache acceleration system by using the 302 status code defined in the standard, thereby accelerating the data of the cache unit in the system to the user equipment 10, and avoiding the user equipment 10 through the network. The export acquires and squeezes the export bandwidth at a low speed to the source website.

以上所述仅为本申请的优选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above description is only the preferred embodiment of the present application, and is not intended to limit the present application, and various changes and modifications may be made to the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application are intended to be included within the scope of the present application.

Claims

一种SDN交换机，其特征在于，包括：An SDN switch, comprising:

接入卡，用于通信网络中数据流量的接收与发送；An access card for receiving and transmitting data traffic in a communication network;

交换卡，用于将接入卡接收的通信流量分发到各个业务卡，所述交换卡设置有物理交换网络；a switching card, configured to distribute communication traffic received by the access card to each service card, where the switch card is provided with a physical switching network;

所述业务卡用于分析处理通信流量内容以及流量解析，所述业务卡设置有网络处理器和高速缓存内存模块；The service card is configured to analyze and process communication traffic content and traffic resolution, and the service card is provided with a network processor and a cache memory module;

控制卡，用于控制和管理整个所述SDN交换机的工作状态，所述控制卡设置有SDN控制器；a control card, configured to control and manage an operating state of the entire SDN switch, where the control card is provided with an SDN controller;

所述高速缓存内存模块包括：缓存单元、主控单元及重定向单元，所述缓存单元用于下载缓存，所述主控单元用于整个***的集中管理，所述重定向单元用于访问重定向；The cache memory module includes: a cache unit, a main control unit, and a redirection unit, the cache unit is configured to download a cache, the main control unit is used for centralized management of the entire system, and the redirection unit is used for accessing heavy Orientation

其中，所述高速缓存内存模块的缓存空间还包括以下至少一个或其组合：所述业务卡中的所述网络处理器的内存部件、所述交换卡的处理器的存储部件、所述控制卡的处理器的存储部件、所述接入卡的处理器的存储部件。The cache space of the cache memory module further includes at least one of or a combination thereof: a memory component of the network processor in the service card, a storage component of a processor of the switch card, and the control card a storage component of the processor, a storage component of the processor of the access card.
根据权利要求1所述的SDN交换机，其特征在于，The SDN switch of claim 1 wherein:

所述高速缓存内存模块采用数据报文的方式缓存应用文件，并可以为所述缓存应用文件创建文件描述信息。The cache memory module caches an application file by using a data packet, and can create file description information for the cache application file.
根据权利要求1或2所述的SDN交换机，其特征在于，The SDN switch according to claim 1 or 2, characterized in that

所述高速缓存内存模块的单一节点的高速内存的最大内存量大于等于96GB；The maximum amount of high-speed memory of a single node of the cache memory module is greater than or equal to 96 GB;

所述SDN交换机可以安装的节点数量大于等于12个；The number of nodes that the SDN switch can be installed is greater than or equal to 12;

所述高速缓存内存模块的网络接口带宽为4.8Tbps。The network interface bandwidth of the cache memory module is 4.8 Tbps.
一种SDN交换机的应用管理方法，用于如权利要求1至3中任一项所述的SDN交换机，所述SDN交换机与用户设备通过网络服务器进行交互，其特征在于，所述应用管理方法包括：An application management method for an SDN switch, for the SDN switch according to any one of claims 1 to 3, wherein the SDN switch interacts with a user equipment through a network server, wherein the application management method comprises :

接收所述用户设备发送的请求报文；Receiving a request message sent by the user equipment;

解析所述请求报文，并获取所述请求报文中对应的应用信息；Parsing the request packet, and acquiring corresponding application information in the request packet;

根据所述应用信息查询所述SDN交换机的应用缓存数据库中是否存在对应的所述应用信息；Querying, according to the application information, whether the corresponding application information exists in an application cache database of the SDN switch;

当存在对应的所述应用信息时，根据所述应用信息在所述应用缓存数据库中的存储位置，启动所述请求报文的重定向操作；When the corresponding application information is present, the redirection operation of the request message is started according to the storage location of the application information in the application cache database;

当不存在对应的所述应用信息时，则执行所述网络服务器的响应请求流程，并缓存所述应用信息。When the corresponding application information does not exist, the response request process of the network server is executed, and the application information is cached.
根据权利要求4所述的SDN交换机的应用管理方法，其特征在于，所述当存在对应的所述应用信息时，根据所述应用信息在所述应用缓存数据库中的存储位置，启动所述请求报文的重定向操作的步骤，具体包括：The application management method of the SDN switch according to claim 4, wherein when the corresponding application information exists, the request is started according to the storage location of the application information in the application cache database. The steps of the packet redirection operation include:

根据所述应用信息在所述应用缓存数据库中的存储位置，发送重定向请求至所述用户设备；Sending a redirect request to the user equipment according to the storage location of the application information in the application cache database;

接收所述重定向请求的响应报文，根据所述响应报文中的应用信息，将所述应用缓存数据库中保存的对应的应用信息发送至用户设备。Receiving the response message of the redirection request, and sending the corresponding application information saved in the application cache database to the user equipment according to the application information in the response message.
根据权利要求5所述的SDN交换机的应用管理方法，其特征在于，当所述应用缓存数据库存在对应的所述应用信息时，还包括：The application management method of the SDN switch according to claim 5, wherein when the application cache database has the corresponding application information, the method further includes:

判断所述应用信息是否为可用；Determining whether the application information is available;

当所述应用信息可用时，根据所述应用信息在所述应用缓存数据库中的存储位置，启动所述请求报文的重定向操作；When the application information is available, the redirection operation of the request message is started according to the storage location of the application information in the application cache database;

当所述应用信息不可用时，则执行所述网络服务器的响应请求流程，并缓存所述应用信息。When the application information is unavailable, the response request process of the network server is executed, and the application information is cached.
根据权利要求5所述的SDN交换机的应用管理方法，其特征在于，当所述应用缓存数据库存在对应的所述应用信息时，还包括：The application management method of the SDN switch according to claim 5, wherein when the application cache database has the corresponding application information, the method further includes:

判断所述应用信息的置信度是否大于预设阈值；Determining whether the confidence of the application information is greater than a preset threshold;

当所述置信度大于等于所述预设阈值时，根据所述应用信息在所述应用缓存数据库中的存储位置，启动所述请求报文的重定向操作；When the confidence level is greater than or equal to the preset threshold, the redirection operation of the request message is started according to the storage location of the application information in the application cache database;

当所述置信度小于所述预设阈值时，则执行所述网络服务器的响应请求流程，并缓存所述应用信息。When the confidence is less than the preset threshold, the response request process of the network server is executed, and the application information is cached.
根据权利要求4至7中任一项所述的SDN交换机的应用管理方法，其特征在于，所述当不存在对应的所述应用信息时，则执行所述网络服务器的响应请求流程，并缓存所述应用信息的步骤，具体包括：The application management method of the SDN switch according to any one of claims 4 to 7, wherein when the corresponding application information does not exist, the response request flow of the network server is executed, and the cache is cached. The step of applying the information specifically includes:

获取所述应用信息对应的资源占用信息；Obtaining resource occupation information corresponding to the application information;

判断所述资源占用信息的资源占用值是否达到热点阈值；Determining whether the resource occupancy value of the resource occupation information reaches a hotspot threshold;

当所述资源占用值达到所述热点阈值时，启动所述请求报文的响应操作，并下载所述应用信息对应的应用至所述应用缓存数据库；And when the resource occupancy value reaches the hotspot threshold, the response operation of the request message is started, and the application corresponding to the application information is downloaded to the application cache database;

当所述资源占用值未达到所述热点阈值时，启动所述网络服务器响应所述请求报文。And when the resource occupancy value does not reach the hotspot threshold, the network server is started to respond to the request message.
根据权利要求4至7中任一项所述的SDN交换机的应用管理方法，其特征在于，所述解析所述请求报文的步骤，具体包括：The application management method of the SDN switch according to any one of claims 4 to 7, wherein the step of parsing the request packet specifically includes:

当所述请求报文中包括地址信息时，对所述地址信息进行归一化处理，获取处理后地址信息。When the request message includes the address information, the address information is normalized to obtain the processed address information.
根据权利要求4至7中任一项所述的SDN交换机的应用管理方法，其特征在于，还包括：The application management method of the SDN switch according to any one of claims 4 to 7, further comprising:

向所述网络服务器发送与所述应用信息对应的异步更新请求；Sending an asynchronous update request corresponding to the application information to the network server;

获取并缓存更新后的应用信息。Get and cache updated app information.
根据权利要求4至7中任一项所述的SDN交换机的应用管理方法，其特征在于，The application management method of an SDN switch according to any one of claims 4 to 7, characterized in that

所述请求报文为所述用户设备所需的数据及数据的请求点。The request message is a request point for data and data required by the user equipment.
根据权利要求11所述的SDN交换机的应用管理方法，其特征在于，所述请求点包括以下至少一种，所述用户设备请求观看视频的起始时间点、所述用户设备请求观看视频时间点相对于整个视频文件初始点的时间点，或者是请求观看视频字节在整个视频文件中的具体字节位置。The application management method of the SDN switch according to claim 11, wherein the request point includes at least one of the following, a start time point at which the user equipment requests to watch a video, and a time point at which the user equipment requests to watch a video. Relative to the point in time of the initial point of the entire video file, or the specific byte position of the video file requested to view the entire video file.