Back-to-source processing method and apparatus

Abstract

This application provides a back-to-origin processing method, which includes: determining whether the first traffic of the current back-to-origin request is leased line traffic; if the first traffic is determined to be leased line traffic, determining the target leased line and the corresponding target convergence node corresponding to the first traffic; scheduling the first traffic to the target convergence node, so that the target resource can be returned by the target convergence node when it has a cache of the target resource, or the first traffic can be converted into a second traffic of the network segment corresponding to the first central node by the target convergence node when it does not have a cache of the target resource, and then performing back-to-origin processing through a ring network according to the second traffic. The back-to-origin processing method provided by this application allows leased line edge nodes to accurately receive traffic through the leased line data center, and the traffic of the leased line network does not need to be back-to-origin through the public network. This ensures the back-to-origin quality of the leased line edge nodes and reduces the number of scattered nodes in the live broadcast room, thereby reducing the traffic cost incurred during the back-to-origin process.

Description

Technical Field

[0001] This application relates to the field of content delivery network technology, and in particular to a method, apparatus, computer equipment, and storage medium for source retrieval processing. Background Technology

[0002] CDN (Content Delivery Network) live streaming downlink is mainly responsible for distributing streaming audio and video streams. It distributes the live stream from the uplink push point into a tree structure to meet the requests of a large number of users. In this distribution process, edge nodes can perform back-to-origin operations, that is, edge nodes can retrieve the live stream that users need to access from the origin server or secondary origin server in real time.

[0003] As business grows, CDN networks need to continuously expand to cover more users and regions. Furthermore, different businesses and application scenarios have different requirements for CDN networks, making the construction of self-built CDN networks increasingly complex.

[0004] In the construction of self-built CDN networks, there are usually dedicated lines from small operators (such as cable TV and Feixiang) that need to be accessed. In this case, the original dynamic origin routing method that schedules globally cannot accurately route traffic to a specific dedicated line data center. Traffic from small operators can only access the original ring network through the public network for origin routing. However, due to the large number of users on the public network, the origin routing quality of small operators cannot be guaranteed. At the same time, the cost is high because there are many dispersed nodes in the live streaming room. Summary of the Invention

[0005] The purpose of this application is to provide a back-to-origin processing method, apparatus, computer equipment, and storage medium to solve the following technical problems: the existing global dynamic back-to-origin method cannot accurately schedule traffic to a specific dedicated line data center, the traffic back-to-origin of the dedicated line network needs to be processed through the public network, the quality of back-to-origin cannot be guaranteed, and the live broadcast room has many scattered nodes, resulting in high costs.

[0006] One aspect of this application provides a back-to-origin processing method, comprising: determining whether the first traffic of the current back-to-origin request is leased line traffic, the back-to-origin request being initiated by an edge node and used to request a target resource, the edge node including a leased line edge node, the traffic corresponding to the leased line edge node being leased line traffic, and the network segment corresponding to the leased line traffic being a first network segment; if the first traffic is determined to be leased line traffic, determining the target leased line and the corresponding target convergence node corresponding to the first traffic, wherein different leased lines correspond to different convergence nodes in a ring network, the ring network being composed of central nodes of a content delivery network, and the convergence node being a central node in the ring network; scheduling the first traffic to the target convergence node, so that if the target resource is cached by the target convergence node, the target resource is returned, or if the target resource is not cached by the target convergence node, the first traffic is converted from the first network segment to a second network segment corresponding to a first central node by the target convergence node to obtain second traffic, and performing back-to-origin processing through the ring network according to the second traffic, wherein the first central node is the other central nodes in the ring network besides the convergence node.

[0007] Optionally, the step of performing source return through the ring network based on the second traffic includes: if the target resource is obtained through the first central node, the target resource is converted from the second network segment to the first network segment through the first central node and then transmitted to the target convergence node.

[0008] Optionally, the step of performing source backhaul through the ring network based on the second traffic includes: determining that the second traffic belongs to unpopular traffic if the second traffic meets preset conditions; and performing source backhaul in the ring network based on a preset single-line relay if the second traffic is determined to be unpopular traffic.

[0009] Optionally, the method further includes: if it is determined that the second traffic does not meet the preset conditions, determining that the second traffic is not a niche traffic; if it is determined that the second traffic is not a niche traffic, performing source return in the ring network according to a preset multi-line relay.

[0010] Optionally, the method further includes: if it is determined that the first traffic is not dedicated line traffic, scheduling the first traffic to the first central node for back-to-origin.

[0011] Optionally, the method further includes: in the event of an anomaly at the target convergence node, scheduling the first traffic to the first central node for back-to-origin.

[0012] One aspect of this application provides a back-to-origin processing apparatus, comprising: a first determining module, configured to determine whether the first traffic of a current back-to-origin request is leased line traffic, wherein the back-to-origin request is initiated by an edge node and is used to request a target resource, the edge node including a leased line edge node, the traffic corresponding to the leased line edge node is leased line traffic, and the network segment corresponding to the leased line traffic is a first network segment; and a second determining module, configured to, if the first traffic is determined to be leased line traffic, determine the target leased line corresponding to the first traffic and the corresponding target convergence node, wherein different leased lines correspond to different convergence nodes in a ring network, and the ring network is composed of content partitioning. The network consists of central nodes, with the convergence node being a central node in the ring network. A scheduling module is used to schedule the first traffic to the target convergence node, so that if the target resource is cached by the target convergence node, the target resource can be returned; or, if the target resource is not cached, the first traffic can be converted from the first network segment to the second network segment corresponding to the first central node by the target convergence node to obtain second traffic. The second traffic is then used to return to the source through the ring network. The first central node is any other central node in the ring network besides the convergence node.

[0013] Optionally, the source processing device is further configured to: when the target resource is obtained through the first central node, convert the target resource from the second network segment to the first network segment through the first central node and then transmit it to the target convergence node.

[0014] One aspect of this application provides a computer device, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described source retrieval processing method.

[0015] Another aspect of this application provides a computer-readable storage medium storing a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the above-described back-to-source processing method.

[0016] The source-return processing method, apparatus, computer equipment, and storage medium provided in the embodiments of this application have the following advantages:

[0017] By determining whether the first traffic in the current origin pull request is leased line traffic, and if so, identifying the target leased line and target convergence node corresponding to it, the first traffic is scheduled to the target convergence node. If the target resource is cached at the convergence node, it returns the target resource; otherwise, it converts the first traffic into the second traffic corresponding to the first central node. Based on this second traffic, the origin pull is performed through the ring network. This allows leased line traffic to be precisely scheduled to the leased line data center, eliminating the need for leased line edge nodes to access the ring network via the public internet. Instead, they access the convergence node within the ring network via a leased line, ensuring network speed and origin pull quality for the leased line edge nodes. Furthermore, using the convergence node reduces the number of links required for origin pulls, thereby lowering the traffic cost associated with origin pulls. Attached Figure Description

[0018] Figure 1 This refers to the tree structure used in CDN live streaming.

[0019] Figure 2 This is a schematic diagram of a CDN network that does not have convergence nodes built by small operators.

[0020] Figure 3 This is an example diagram of a back-to-origin scenario in a live streaming context;

[0021] Figure 4 A schematic diagram of a CDN network with convergence nodes from small carriers;

[0022] Figure 5 A specific example diagram for building a CDN network with convergence nodes from small carriers;

[0023] Figure 6 The flowchart illustrating the source return processing method of Embodiment 1 of this application is shown in the schematic diagram.

[0024] Figure 7 This is a specific example diagram of the source code processing method;

[0025] Figure 8 for Figure 6 A flowchart of the sub-steps of step S230;

[0026] Figure 9 for Figure 6 Flowchart of the new step;

[0027] Figure 10 This is a flowchart illustrating the source code processing method.

[0028] Figure 11 A block diagram of the source return processing device according to Embodiment 2 of this application is shown schematically;

[0029] Figure 12The schematic diagram illustrates the hardware architecture of the computer device according to Embodiment 3 of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0031] It should be noted that the descriptions involving "first," "second," etc., in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0032] In the description of this application, it should be understood that the numerical labels before the steps do not indicate the order of the steps, but are only used to facilitate the description of this application and to distinguish each step, and therefore should not be construed as a limitation of this application.

[0033] The following is an explanation of the terms used in this application:

[0034] Static source retrieval refers to retrieval to the source via a pre-planned path, without considering other factors.

[0035] Dynamic origin pull refers to the process in CDN or other content distribution systems where, when edge nodes (caching servers) cannot satisfy user requests from their local cache, the system can dynamically select the best data source to make an origin pull request based on various factors such as real-time network conditions, load, and origin server status, and then redistribute the obtained content to the user.

[0036] Small operators refer to operators other than China Telecom, China Mobile, and China Unicom.

[0037] CDN live streaming primarily handles the distribution of streaming audio and video streams. It distributes the live streams from the uplink push points into a tree structure to meet the requests of a large number of users. During this distribution process, edge nodes can perform origin pulls, meaning they retrieve the live streams that users need from the origin server or secondary origin servers in real time. A similar tree structure is shown below. Figure 1 As shown.

[0038] Please refer to Figure 2 This is a schematic diagram of a CDN network without convergence nodes from smaller carriers. In the diagram, 110 represents the origin server, 120 represents the ring network, 121 represents the central nodes within the ring network, 130 represents typical edge nodes, and 140 represents the edge nodes corresponding to smaller carriers. Figure 2 As shown, due to the use of global dynamic origin pull, the edge node 140 corresponding to the small operator, like the general edge node 130, accesses the ring network 120 through the public network for origin pull. Since the edge node 140 corresponding to the small operator needs to share the public network with the public network edge node 130, and there are many users on the public network, the speed is difficult to guarantee, and there are likely to be intermittent jitter problems. The origin pull quality of the edge node corresponding to the small operator cannot be guaranteed, which may cause users to experience stuttering when accessing the live stream.

[0039] Please refer to Figure 3 This is an example diagram of the back-to-origin traffic in a live streaming scenario. As shown in the diagram, the links corresponding to the arc arrows represent the traffic transmission paths back to the origin. It can be seen that the more nodes a live streaming room has, the more links corresponding to the arc arrows there are, and the higher the traffic cost will be.

[0040] Please refer to Figure 4 This diagram illustrates a CDN network with convergence nodes for smaller carriers. 122 represents the convergence node for the smaller carrier. As shown, edge node 140 for the smaller carrier is first scheduled to convergence node 122 in the ring network 120 via static origin pull. Then, it performs origin pull through the ring network 120 using dynamic origin pull logic. Since it doesn't need to share the public network, the network speed and origin pull quality for the edge node for the smaller carrier are guaranteed. Furthermore, since all edge nodes 140 for the smaller carrier can perform origin pulls through convergence node 122, convergence node 122 only needs to obtain one set of resources from origin server 110. When other origin pull requests reach convergence node 122, since it has the corresponding resources, the cache will be hit, and convergence node 122 will directly return the cached resources to edge node 140. This significantly reduces the number of origin pull links and the associated costs.

[0041] Please refer to Figure 5 This diagram illustrates a specific example of a CDN network with convergence nodes from smaller operators. As shown, edge nodes of smaller operators (gd, broadcasting) can access the origin server via convergence nodes in the ring network, and edge nodes of smaller operators (fx, Feixiang) can access the origin server via convergence nodes in the ring network. This ensures the origin server quality for the corresponding edge nodes of smaller operators (gd and fx), reduces the number of backhaul links, and thus reduces the cost of backhauling to the origin server.

[0042] The following will introduce the source return processing scheme of this application through several embodiments.

[0043] Example 1

[0044] Figure 6 The flowchart of the source return processing method of Embodiment 1 of this application is illustrated in the figure. It may include steps S210 to S230, which are described in detail below:

[0045] Step S210: Determine whether the first traffic of the current origin request is leased line traffic. The origin request is initiated by the edge node and is used to request the target resource. The edge node includes the leased line edge node. The traffic corresponding to the leased line edge node is leased line traffic. The network segment corresponding to the leased line traffic is the first network segment.

[0046] The executing entity corresponding to steps S210-S230 can be the scheduling center of the content delivery network. The scheduling center receives origin requests initiated by all edge nodes, including general edge nodes and leased line edge nodes. The scheduling center can determine the network segment of the first traffic. If the network segment of the first traffic belongs to the network segment of a general edge node, then the first traffic is determined to be ordinary traffic, not leased line traffic; if the network segment of the first traffic belongs to the first network segment corresponding to a leased line edge node, then the first traffic is determined to be leased line traffic. Leased line traffic can include several types, and correspondingly, the first network segment can include several types. For example, leased line traffic can include both broadcast and Feixiang leased line traffic, and correspondingly, the first network segment can include the network segment corresponding to broadcast and the network segment corresponding to Feixiang.

[0047] Step S220: If the first traffic is determined to be leased line traffic, determine the target leased line and the target convergence node corresponding to the first traffic. Different leased lines correspond to different convergence nodes in the ring network. The ring network is composed of the central nodes of the content delivery network, and the convergence node is a central node in the ring network.

[0048] A ring network can connect to both edge nodes and the source station. The number of convergence nodes corresponds to the number of leased lines. For example, if there are two leased lines, then there are also two convergence nodes, corresponding to two different leased lines. If the first traffic is determined to be leased line traffic, the target leased line corresponding to the first traffic can be determined based on the network segment corresponding to the first traffic, and then the corresponding target convergence node can be determined based on the target leased line.

[0049] For example, a ring network includes convergence nodes for both broadcasting and data sharing (or similar services). Broadcasting leased lines correspond to their respective convergence nodes, and data sharing leased lines correspond to theirs. The dispatch center can first determine whether the first traffic belongs to either broadcasting or data sharing. If it does, it determines the first traffic is leased line traffic. Further, it determines the corresponding leased line based on whether the network segment corresponding to the first traffic belongs to broadcasting or data sharing. Assuming the network segment corresponding to the first traffic belongs to broadcasting, then the target leased line is determined to be broadcasting, corresponding to the broadcasting convergence node in the ring network.

[0050] Step S230: The first traffic is scheduled to the target convergence node, so that the target resource can be returned by the target convergence node if the target resource is cached, or if the target resource is not cached, the first traffic is converted from the first network segment to the second network segment corresponding to the first central node by the target convergence node to obtain the second traffic, and the second traffic is returned to the source through the ring network. The first central node is the other central nodes in the ring network other than the convergence node.

[0051] After the first traffic is scheduled to the target convergence node, the convergence node can determine whether the cache is hit. If the cache is hit, the target resource is directly returned to the dedicated line edge node that initiated the back-to-origin request. If the cache is not hit, the first traffic is converted from the first network segment to the second network segment corresponding to the first central node to obtain the second traffic. Then, the back-to-origin is carried out through the ring network according to the second traffic, such as obtaining the target resource through the first central node or from the origin station.

[0052] Understandably, after the convergence node obtains the target resource, it will cache the target resource. If other dedicated line edge nodes of the same dedicated line are scheduled to the convergence node for origin retrieval, the target resource will be returned directly by the convergence node because the cache will be hit, without going through the subsequent network segment conversion and the origin retrieval process through the ring network.

[0053] Please refer to Figure 7This diagram illustrates a specific example of the origin pull processing method. As shown, if the first traffic is Feixiang's dedicated line traffic and the network segment corresponding to the first central node is 192, then after scheduling the Feixiang edge node to the Feixiang convergence node (target convergence node) according to the origin pull request, if the Feixiang convergence node has a cache of the target resource, it will hit the cache and directly retrieve the target resource from the cache and return it to the Feixiang edge node; if the Feixiang convergence node does not have a cache of the target resource, then the first traffic of the Feixiang network segment can be converted to the 192 network segment corresponding to the first central node, and then the origin pull can be performed through the ring network. Similarly, if the first traffic is the dedicated line traffic of the broadcasting company, and its corresponding network segment is 103, then after scheduling the broadcasting edge node to the broadcasting convergence node (target convergence node), if the broadcasting convergence node has a cache of the target resource, it will hit the cache and directly obtain the target resource from the cache and return it to the broadcasting edge node; if the broadcasting convergence node does not have a cache of the target resource, then the first traffic of the 103 network segment can be converted to the 192 network segment corresponding to the first central node, and then returned to the source through the ring network.

[0054] In practical applications, taking a dedicated cable TV line as an example, each cable TV room has its own dedicated network. Then, a cable TV room called City A is built in a certain city A. This room is connected to the cable TV network. At the same time, the cable TV room in City A is also on the original ring network. Through this room, the path from any cable TV room to the cable TV room in City A (network segment switching) to the ring network source station can be used for back-to-source communication.

[0055] In an optional embodiment, step S230, which involves returning the target resource to the source via the ring network based on the second traffic, may include: if the target resource is obtained through the first central node, the target resource is converted from the second network segment to the first network segment through the first central node and then transmitted to the target convergence node.

[0056] The target resource is obtained through the first central node, either by hitting its cache or by obtaining the target resource from the origin server. If the target resource is obtained, the first central node converts it from the second network segment to the first network segment and transmits it to the target convergence node. The target convergence node then returns the target resource to the dedicated line edge node corresponding to the first traffic.

[0057] The origin-pull processing method provided in this application determines whether the first traffic of the current origin-pull request is leased line traffic. If the first traffic is determined to be leased line traffic, the target leased line and the target convergence node corresponding to the first traffic are determined. The first traffic is scheduled to the target convergence node. If the target convergence node has the target resource cache, it returns the target resource. If the target resource cache is not available, the first traffic is converted into the second traffic corresponding to the first central node. The origin-pull is then performed through the ring network based on the second traffic. This method can accurately schedule leased line traffic to the leased line data center, so that the leased line edge nodes do not need to access the ring network through the public network for origin-pull, but instead access the convergence node in the ring network through the leased line for origin-pull. This can ensure the network speed and origin-pull quality of the leased line edge nodes. At the same time, performing origin-pull through the convergence node can reduce the number of links for origin-pull, thereby reducing the traffic cost generated by origin-pull.

[0058] In an exemplary embodiment, the back-to-origin processing method of this application embodiment may further include: if it is determined that the first traffic is not dedicated line traffic, the first traffic is scheduled to the first central node for back-to-origin processing.

[0059] By scheduling the first traffic to other central nodes in the ring network (excluding the target convergence node) for back-to-origin when the first traffic is not dedicated line traffic, the original non-dedicated line traffic can be back-to-origin through the original back-to-origin logic.

[0060] In an exemplary embodiment, the back-to-origin processing method of this application embodiment may further include: in the event of an abnormality in the target convergence node, scheduling the first traffic to the first central node for back-to-origin processing.

[0061] By redirecting the first traffic to the first central node for backhaul in the event of an anomaly at the target convergence node, a backup system can be implemented to ensure the return of dedicated line traffic to its source in the event of an anomaly at the target convergence node.

[0062] In an exemplary embodiment, such as Figure 8 As shown, in step S230, the process of returning traffic to the source via the ring network based on the second traffic may include steps S231 to S232:

[0063] Step S231: If the second flow rate meets the preset conditions, determine that the second flow rate belongs to the unpopular flow rate.

[0064] The preset conditions can be set based on factors such as the access frequency of the accessed content, peak traffic, traffic time period, geographical origin of the request corresponding to the traffic, and content type of the accessed content. Specific conditions are not limited here. For example, a preset condition could be that the access frequency of the accessed content is below a certain threshold; if the access frequency of the accessed content corresponding to the second traffic is below this threshold, the second traffic is determined to be infrequent traffic.

[0065] Step S232: If it is determined that the second traffic belongs to unpopular traffic, the source is returned in the ring network according to the preset single-line relay.

[0066] Please continue to refer to this. Figure 7 For example, if the second traffic is the less popular traffic corresponding to Yangzhou, Jiangsu, then the preset single-line relay can be the single-line relay of Yangzhou, Jiangsu in the figure to return to the source.

[0067] In this embodiment, if the second traffic meets the preset conditions, it is determined that the second traffic belongs to unpopular traffic. If the second traffic belongs to unpopular traffic, it is back to the origin in the ring network according to the preset single-line relay. Since there are fewer users corresponding to unpopular traffic, back to the origin through the preset single-line relay can reduce the occupation of CDN network resources while meeting the back to the origin requirements.

[0068] In an exemplary embodiment, such as Figure 9 As shown, the source retrieval processing method in this application embodiment may further include steps S233 to S234:

[0069] Step S233: If it is determined that the second flow does not meet the preset conditions, then the second flow is determined not to be a cold flow.

[0070] Step S234: If it is determined that the second traffic is not a low-traffic traffic, the source is returned in the ring network according to the preset multi-line relay.

[0071] Please continue to refer to this. Figure 7 For example, if the second traffic is traffic from Yangzhou, Jiangsu, which is not considered a niche traffic source, then in a ring network, it can be routed back to the source using a three-line relay.

[0072] Please refer to Figure 10 This is a flowchart illustrating the origin tracing process. As shown, it first determines whether the traffic is dedicated line traffic corresponding to a broadcast or Feixiang node. If not, it proceeds according to the dynamic origin tracing logic (the original origin tracing logic). If so, it first generates a second-hop trunk based on the four-layer tree logic. Next, it determines whether the current origin tracing traffic is infrequent traffic. If not, it selects a multi-line trunk for the third hop and then generates a fourth-hop path to the origin station. If so, it selects a single-line trunk for the third hop and then generates a fourth-hop path to the origin station.

[0073] In this embodiment, if the second traffic does not meet the preset conditions, it is determined that the second traffic is not a niche traffic. If the second traffic is determined to be a niche traffic, it is back to the source in the ring network according to the preset multi-line relay. If the second traffic is not a niche traffic, since there may be a large number of users, the back to the source through the preset multi-line relay can effectively ensure that the back to the source requirement is met.

[0074] Example 2

[0075] Figure 11 The diagram schematically illustrates a source-return processing apparatus 300 according to Embodiment 2 of this application. This source-return processing apparatus 300 can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiments of this application. The program module referred to in the embodiments of this application refers to a series of computer program instruction segments capable of performing a specific function. The following description will specifically introduce the functions of each program module in this embodiment.

[0076] like Figure 11 As shown, the source return processing device 300 may include a first determining module 310, a second determining module 320, and a scheduling module 330.

[0077] The first determining module 310 is used to determine whether the first traffic of the current origin request is dedicated line traffic. The origin request is initiated by an edge node and is used to request the target resource. The edge node includes a dedicated line edge node. The traffic corresponding to the dedicated line edge node is dedicated line traffic. The network segment corresponding to the dedicated line traffic is the first network segment.

[0078] The second determining module 320 is used to determine the target leased line and the target convergence node corresponding to the first traffic when the first traffic is determined to be leased line traffic. Different leased lines correspond to different convergence nodes in the ring network. The ring network is composed of the central nodes of the content delivery network, and the convergence node is a central node in the ring network.

[0079] The scheduling module 330 is used to schedule the first traffic to the target convergence node, so that the target resource can be returned by the target convergence node if the target resource is cached, or if the target resource is not cached, the first traffic can be converted from the first network segment to the second network segment corresponding to the first central node by the target convergence node to obtain the second traffic, and the second traffic can be used to return to the source through the ring network. The first central node is the other central nodes in the ring network other than the convergence node.

[0080] In an exemplary embodiment, the back-to-source processing device 300 is further configured to: when the target resource is obtained through the first central node, convert the target resource from the second network segment to the first network segment through the first central node and then transmit it to the target convergence node.

[0081] In an exemplary embodiment, the source back processing device 300 is further configured to: determine that the second traffic is a low-traffic traffic if the second traffic meets preset conditions; and perform source back processing in the ring network according to a preset single-line relay if the second traffic is determined to be a low-traffic traffic.

[0082] In an exemplary embodiment, the back-to-source processing device 300 is further configured to: determine that the second traffic does not belong to unpopular traffic if it is determined that the second traffic does not meet the preset conditions; and perform back-to-source processing in the ring network according to a preset multi-line relay if it is determined that the second traffic does not belong to unpopular traffic.

[0083] In an exemplary embodiment, the back-to-origin processing device 300 is further configured to: if it is determined that the first traffic is not dedicated line traffic, schedule the first traffic to the first central node for back-to-origin processing.

[0084] In an exemplary embodiment, the back-to-source processing device 300 is further configured to: in the event of an anomaly at the target convergence node, dispatch the first traffic to the first central node for back-to-source processing.

[0085] Example 3

[0086] Figure 12 The diagram schematically illustrates the hardware architecture of a computer device 400 suitable for a back-to-source processing method according to Embodiment 3 of this application. The computer device 400 can be a device capable of automatically performing numerical calculations and / or data processing according to pre-set or stored instructions. For example, it can be a rack server, blade server, tower server, or cabinet server (including standalone servers or server clusters composed of multiple servers), a gateway, etc. Figure 12 As shown, the computer device 400 includes, but is not limited to, a memory 410, a processor 420, and a network interface 430 that can communicate with each other via a system bus. Wherein:

[0087] The memory 410 includes at least one type of computer-readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 410 may be an internal storage module of the computer device 400, such as the hard disk or memory of the computer device 400. In other embodiments, the memory 410 may also be an external storage device of the computer device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the memory 410 may include both the internal storage module and the external storage device of the computer device 400. In this embodiment, the memory 410 is typically used to store the operating system and various application software installed on the computer device 400, such as the program code of the back-to-source processing method. In addition, the memory 410 can also be used to temporarily store various types of data that have been output or will be output.

[0088] In some embodiments, processor 420 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. Processor 420 is typically used to control the overall operation of computer device 400, such as performing control and processing related to data interaction or communication with computer device 400. In this embodiment, processor 420 is used to run program code stored in memory 410 or process data.

[0089] Network interface 430 may include a wireless network interface or a wired network interface, which is typically used to establish a communication link between computer device 400 and other computer devices. For example, network interface 430 is used to connect computer device 400 to an external terminal via a network, establishing a data transmission channel and communication link between computer device 400 and the external terminal. The network may be an intranet, the Internet, Global System for Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, or other wireless or wired networks.

[0090] It should be pointed out that, Figure 12 Only a computer device with components 410-430 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0091] In this embodiment, the back-to-source processing method stored in memory 410 can be further divided into one or more program modules and executed by one or more processors (processor 420 in this embodiment) to complete the embodiment of this application.

[0092] Example 4

[0093] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the back-to-source processing method in the embodiments.

[0094] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device. Of course, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the back-to-source processing method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

[0095] Obviously, those skilled in the art should understand that the modules or steps of the embodiments of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of this application are not limited to any particular combination of hardware and software.

[0096] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A source-following processing method, characterized in that, include: Determine whether the first traffic of the current origin request is leased line traffic. The origin request is initiated by an edge node and is used to request the target resource. The edge node includes a leased line edge node. The traffic corresponding to the leased line edge node is leased line traffic. The network segment corresponding to the leased line traffic is the first network segment. If the first traffic is determined to be dedicated line traffic, the target dedicated line and the target convergence node corresponding to the first traffic are determined. Different dedicated lines correspond to different convergence nodes in the ring network. The ring network is composed of the central nodes of the content delivery network, and the convergence node is a central node in the ring network. The first traffic is scheduled to the target convergence node, so that if the target resource is cached by the target convergence node, the target resource can be returned, or if the target resource is not cached by the target convergence node, the first traffic is converted from the first network segment to the second network segment corresponding to the first central node to obtain the second traffic, and the second traffic is returned to the source through the ring network. The first central node is the other central nodes in the ring network other than the convergence node.

2. The source retrieval processing method according to claim 1, characterized in that, The step of returning to the source via the ring network based on the second traffic includes: If the target resource is obtained through the first central node, the target resource is converted from the second network segment to the first network segment through the first central node and then transmitted to the target convergence node.

3. The source retrieval processing method according to claim 1, characterized in that, The step of returning to the source via the ring network based on the second traffic includes: If the second flow rate meets the preset conditions, it is determined that the second flow rate belongs to the unpopular flow rate. If it is determined that the second traffic is a low-traffic traffic, the source is returned in the ring network according to the preset single-line relay.

4. The source retrieval processing method according to claim 3, characterized in that, The method further includes: If it is determined that the second flow does not meet the preset conditions, it is determined that the second flow does not belong to unpopular flow. If it is determined that the second traffic is not a niche traffic, the source is returned in the ring network according to the preset multi-line relay.

5. The source-following processing method according to any one of claims 1-4, characterized in that, The method further includes: If it is determined that the first traffic is not dedicated line traffic, the first traffic will be scheduled to the first central node for back-to-origin.

6. The source retrieval processing method according to claim 5, characterized in that, The method further includes: In the event of an anomaly at the target convergence node, the first traffic will be redirected to the first central node for back-to-origin processing.

7. A source recovery processing device, characterized in that, include: The first determining module is used to determine whether the first traffic of the current origin request is dedicated line traffic. The origin request is initiated by an edge node and is used to request the target resource. The edge node includes a dedicated line edge node. The traffic corresponding to the dedicated line edge node is dedicated line traffic. The network segment corresponding to the dedicated line traffic is the first network segment. The second determining module is used to determine the target leased line and the target convergence node corresponding to the first traffic when the first traffic is determined to be leased line traffic. Different leased lines correspond to different convergence nodes in the ring network. The ring network is composed of the central nodes of the content delivery network, and the convergence node is a central node in the ring network. The scheduling module is used to schedule the first traffic to the target convergence node, so that the target resource can be returned by the target convergence node if the target resource is cached, or if the target resource is not cached, the first traffic can be converted from the first network segment to the second network segment corresponding to the first central node by the target convergence node to obtain the second traffic, and the second traffic can be used to return to the source through the ring network. The first central node is the other central nodes in the ring network other than the convergence node.

8. The source recovery processing device according to claim 7, characterized in that, The source reversion processing device is also used for: If the target resource is obtained through the first central node, the target resource is converted from the second network segment to the first network segment through the first central node and then transmitted to the target convergence node.

9. A computer device, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the back-to-source processing method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the back-to-source processing method according to any one of claims 1 to 6.

Images