Link reconstruction method and system

Abstract

The invention provides a link reconstruction method and system, and aims to avoid the condition of poor user experience caused by link establishment failure among content distribution network nodes and link failure in a transmission process. The method comprises the following steps: obtaining detection results of each node and each source station, wherein the detection results at least comprise index data representing node transmission performance; according to the detection result, determining a plurality of transmission paths in which intermediate nodes are not repeated and back source nodes are the same; the plurality of transmission paths comprise a first number of initial paths and a second number of alternative paths, and the back-to-source node is a previous hop node of the source station; and according to the priority order of the plurality of transmission paths, establishing a first number of transmission paths for data transmission, the first number of transmission paths including initial paths and / or the alternative paths, and the priority of the initial paths being greater than the priority of the alternative paths.

Description

Technical Field

[0001] The present disclosure relates to the technical field of content distribution networks, and in particular to a link reconstruction method and system. Background Art

[0002] Application acceleration products are transport layer acceleration products. Relying on the high-quality nodes and lines of the Content Delivery Network (CDN) platform, through core technologies such as intelligent scheduling and transmission optimization, they provide performance optimization services for various applications based on the TCP / UDP protocol, and can effectively solve problems such as jitter and congestion of public network links.

[0003] As one of the important components of application acceleration products, the application acceleration gateway can realize fast data transmission based on the intelligent routing issued by the dynamic path proxy service agent. In order to further improve the transmission efficiency and reliability, multiple transmission technologies can be used to establish multiple paths from the user side to the source station, so that data packets can be transmitted simultaneously through multiple paths.

[0004] However, in actual applications, due to network fluctuations, node failures, etc., multi-channel transmission may result in failures in establishing connections between CDN nodes and link failures during transmission, which will affect user experience. However, no effective solutions have been proposed in the relevant technologies for these situations. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the present disclosure provides a link reconstruction method and system. The technical solution of the present disclosure is as follows: According to a first aspect of an embodiment of the present disclosure, a link reestablishment method is provided, including: Acquire detection results for each node and each source station, wherein the detection results at least include indicator data characterizing node transmission performance; According to the detection result, multiple transmission paths with no duplication of intermediate nodes and the same back-to-source node are determined; the multiple transmission paths include a first number of initial paths and a second number of alternative paths, and the back-to-source node is a previous hop node of the source station; According to the priority order of the multiple transmission paths, a first number of transmission paths are established for data transmission, the first number of transmission paths including an initial path and / or the alternative path, the priority of the initial path is greater than the priority of the alternative path.

[0006] Optionally, establishing a first number of transmission paths for data transmission according to the priority order of the plurality of transmission paths includes: By establishing connections between nodes, each initial path is established for data transmission; or, In the case where the initial path fails to be established, determining a third number of the initial paths that failed to be established; Rebuilding the candidate paths in sequence until the number of the successfully established candidate paths meets the third number; Performing data transmission by establishing the successfully established initial path and the third number of the candidate paths; Wherein, when the second number of candidate paths are all reconstructed and the number of the successfully established candidate paths does not meet the third number, data transmission is performed through the successfully established initial path and the successfully established candidate paths.

[0007] Optionally, establishing a first number of transmission paths for data transmission according to the priority order of the plurality of transmission paths includes: Splitting the target data for data transmission according to a first quantity to obtain a first quantity of sub-data; The sub-data are respectively transmitted through the first number of transmission paths.

[0008] Optionally, it also includes: Cache the sub-data in a cache area; Transmitting the sub-data respectively through the first number of transmission paths; comprising: determining a first timeout period; Determine whether each of the sub-data in the buffer area receives a confirmation message within a first timeout period; In the case that the sub-data has not received a confirmation message, confirming that a link failure occurs in a transmission path corresponding to the sub-data for which the confirmation message has not been received; Reconstructing the candidate paths in sequence to obtain a target candidate path corresponding to the transmission path with link failure; The sub-data corresponding to the transmission path of the link failure is determined from the buffer area, and the sub-data is transmitted through the target alternative path.

[0009] Optionally, after confirming that a link failure occurs in a transmission path corresponding to the sub-data for which the confirmation message has not been received, the method further includes: At a back-to-source node of the transmission path, triggering an abnormal session of the transmission path; Determining a second timeout period of the abnormal session; The transmitting the sub-data through the target candidate path includes: If the target candidate path is successfully established within the second timeout period, the sub-data is transmitted through the target candidate path.

[0010] Optionally, transmitting the sub-data respectively through the first number of transmission paths includes: Determine respectively whether each of the sub-data is greater than a minimum compression requirement; In the case where the sub-data is larger than the minimum compression requirement, the sub-data is compressed, and a compression identifier is added to the protocol header of the compressed sub-data; the compression identifier is used to indicate that: the data is compressed data, so that the end node decompresses the compressed sub-data based on the compression identifier; the end node is determined by the transmission direction of the transmission path; the transmission direction includes uplink transmission or downlink transmission; The compressed sub-data with compression identifiers added thereto are transmitted respectively through the first number of transmission paths.

[0011] Optionally, transmitting the sub-data respectively through the first number of transmission paths includes: Determine the previous hop node of the source node in each transmission path respectively; In each of the previous hop nodes, the content of the target option is set according to the session identifier of the target data; wherein the content of the target option is used to identify the association of each connection corresponding to the target data; the connection is a connection between each node in the transmission path; The associated sub-data transmitted through each transmission path are distributed to a server of the same back-source node, so that the sub-data of each transmission path are processed through the same process of the server.

[0012] Optionally, detection results for each node and each source station are obtained; including: Perform periodic detection on each node and each source station to obtain detection results; After calculating, weighting and smoothing the network jitter of the detection results, the detection weight of each node is determined; the detection weight represents: the priority of the node in determining the transmission path; Adding the detection weight to the detection result to obtain the detection result carrying the detection weight; According to the detection result, multiple transmission paths with no duplication of intermediate nodes and the same back-to-source nodes are determined, including: According to the detection result carrying the detection weight, a plurality of transmission paths with no duplication of intermediate nodes and the same back-to-source nodes are determined.

[0013] According to a second aspect of an embodiment of the present disclosure, a link reconstruction system is provided, including: An acquisition module, used to acquire detection results of each node and each source station, wherein the detection results at least include indicator data characterizing the transmission performance of the node; A determination module, configured to determine, based on the detection result, a plurality of transmission paths having non-repeated intermediate nodes and the same back-to-source node; the plurality of transmission paths comprising a first number of initial paths and a second number of alternative paths, and the back-to-source node being a previous hop node of the source station; An establishing module is used to establish a first number of transmission paths for data transmission according to the priority order of the multiple transmission paths, wherein the first number of transmission paths includes an initial path and / or the alternative path, and the priority of the initial path is greater than the priority of the alternative path.

[0014] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the link reconstruction method described in the first aspect are implemented.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the link reconstruction method described in the first aspect are implemented.

[0016] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the link reconstruction method described in the first aspect are implemented.

[0017] According to the detection results, the present invention determines multiple transmission paths with no duplication of intermediate nodes and the same back-to-source nodes, thus avoiding potential bottlenecks caused by node duplication. In the event of failure to establish the initial path or a link failure, an alternative path can be used for data transmission, which can dynamically allocate traffic, avoid overloading a single node or path, and effectively relieve pressure on the source station. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the description of the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a schematic diagram of the steps of a link reconstruction method shown in an embodiment of the present disclosure; Figure 2is a schematic diagram showing a transmission path reconstruction caused by a failure of establishing a connection between nodes according to an embodiment of the present disclosure; Figure 3 is a schematic diagram showing a transmission path reconstruction due to a link failure in an embodiment of the present disclosure; Figure 4 is a block diagram of a link reconstruction system shown in an embodiment of the present disclosure; Figure 5 It is a schematic diagram of an electronic device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0021] The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0022] For ease of understanding, the professional terms involved in the present disclosure are first explained.

[0023] Dynamic Path Proxy Service (Dynamic Agent): For customers who use dynamic acceleration, it provides periodic detection of CDN nodes and customer origins, obtains detection results, and calculates, EWMA (Exponentially Weighted Moving-Average) weights, and smoothes network jitter to obtain the final detection weight, which is then reported to the Central Path Calculation Service (CCS) for intelligent routing decisions. Dynamic Agent provides dynamic acceleration intelligent routing detection services for application acceleration products, and acts as a bridge between CCS and application acceleration gateways, responsible for receiving and setting dynamic paths.

[0024] CCS: Responsible for performing comprehensive calculations on the node and source quality data reported by the dynamic agent to obtain the optimal path back to the source, and then sending the optimal path data to the application acceleration gateway through the dynamic agent.

[0025] Application acceleration gateway: receives customer requests, accelerates dynamic resources according to customer configuration, and provides functions such as multi-channel transmission and data compression. Based on the optimal return path issued by the dynamic agent, it ensures that the request is forwarded normally within the CDN node, ultimately achieving the fastest and most stable return to the source.

[0026] In actual applications, due to network fluctuations, node failures and other reasons, multi-channel transmission may result in failure to establish connections between CDN nodes and link failures during transmission.

[0027] When there is a problem of failure to establish connections between CDN nodes, users will immediately experience slower access speeds, delayed page loading, or even inaccessibility, leading to a higher bounce rate. At the same time, since CDN nodes are unavailable, user requests are directly redirected to the source site, which will suddenly increase the traffic pressure on the source site, thereby affecting the stability and response speed of the source site, which will directly affect user experience and business operations.

[0028] In the event of a link failure during transmission, data that has not yet been sent will be transferred from the transmission path with the link failure to the remaining available paths for transmission, which will increase the burden on the CDN node and reduce the processing capacity and response speed of the CDN node. Excessive burden may cause the computing resources and network bandwidth of the CDN node to reach the limit or even be exhausted. It is also more likely to fail or crash under high load, which directly affects the stability and reliability of the service. This will cause the user to partially load the page or video buffering errors, which still seriously affects the user experience.

[0029] In order to solve the above technical problems, the present disclosure proposes a link reconstruction method, which can effectively alleviate the impact on user experience when a transmission path error occurs in a multi-path scenario.

[0030] Figure 1 FIG. 1 is a schematic diagram of the steps of a link reconstruction method shown in an embodiment of the present disclosure. Figure 1 As shown, the method may specifically include the following steps: Step S11: Acquire detection results for each node and each source station, wherein the detection results at least include indicator data characterizing node transmission performance.

[0031] Start the dynamic agent and regularly detect each CDN node and origin server. Collect the detection results, which mainly include indicator data that characterize the node transmission performance, such as packet loss rate, latency, bandwidth, etc.

[0032] Step S12: according to the detection result, determine multiple transmission paths with no repeated intermediate nodes and the same back-to-source node; the multiple transmission paths include a first number of initial paths and a second number of alternative paths, and the back-to-source node is the previous hop node of the source station.

[0033] The detection results are reported to CCS. Based on the detection results, CCS obtains multiple transmission paths with no duplication of intermediate nodes and the same back-to-source nodes. Multiple transmission paths are the optimal transmission paths determined based on the detection results and after analyzing the transmission efficiency between nodes.

[0034] Each transmission path includes a user end, an edge node, an intermediate node, a back-to-source node, and a source station, wherein the intermediate nodes of each transmission path are different from each other, and each transmission path includes one or more intermediate nodes.

[0035] Users initiate requests through devices such as computers, mobile phones and other user terminals; the edge node, as part of the CDN, is responsible for receiving user requests; after the intermediate node receives the request from the edge node, it forwards the request to the back-to-source node; the back-to-source node is usually a node pointing to the content source. After receiving the request, the back-to-source node will obtain the required content from the source station and return it to the edge node; the source station is the server that stores the original content.

[0036] The multiple transmission paths include an initial path and an alternative path. The initial path is a transmission path that is initially determined to be enabled, and the alternative path is a transmission path that is enabled when an error occurs in the initial path.

[0037] According to the network load, it can be determined how many transmission paths to use for parallel transmission in a multi-channel transmission scenario, that is, the first number. Therefore, when CCS determines the optimal path, it is necessary to determine the first number of initial paths, and in order to ensure that the system can perform data transmission stably even when an error occurs in the initial path, a second number of alternative paths can be configured. The first number and the second number can be equal. When the first number and the second number are consistent, it can be ensured that if an error occurs in each initial path, then the same number of alternative paths can be used to perform the same data transmission task, which can effectively avoid the problem of data loading failure due to errors in the transmission path.

[0038] The transmission path obtained by CCS is sent to the edge node through the dynamic Agent.

[0039] Step S13: according to the priority order of the plurality of transmission paths, establish a first number of transmission paths for data transmission, the first number of transmission paths including an initial path and / or the alternative path, the priority of the initial path being greater than the priority of the alternative path.

[0040] After receiving the transmission path sent by the dynamic agent, the edge node establishes the transmission path and transmits data through the successfully established transmission path.

[0041] Since the initial path is the transmission path that is determined to be enabled at the beginning, the priority of the initial path is higher than that of the alternative path when establishing the transmission path.

[0042] When the first number of transmission paths need to be used for data transmission, the initial paths and the alternative paths are established in sequence according to the priority order, so that the first number of transmission paths are successfully established. If all the initial paths are successfully established, that is, the first number of initial paths are successfully established, the need for the first number of transmission paths is met, and the alternative paths are not established at this time. If the establishment of an initial path fails, the alternative paths are rebuilt so that the first number of transmission paths are used for data transmission.

[0043] In order to ensure that in a multi-channel transmission scenario, there are a first number of transmission paths for transmitting target data, after the transmission paths are successfully established, it is necessary to constantly confirm whether there is a link failure in the transmission paths. When a link failure occurs in a transmission path, an alternative path needs to be established so that there are always the first number of transmission paths for multi-channel transmission of target data. In a specific implementation, if the first number of initial paths are successfully established, if a link failure occurs in an initial path during data transmission using the initial paths, then each alternative link is rebuilt in turn, and the successfully established alternative path is used for data transmission.

[0044] When the successfully reconstructed alternative links meet the current transmission requirements, the remaining alternative paths that have not been established will not be reconstructed. The remaining alternative paths are used to prepare for possible subsequent transmission errors. If transmission errors still occur in the future, these remaining alternative paths will be reconstructed in turn.

[0045] Using the embodiments of the present disclosure, based on the detection results, the method can determine multiple transmission paths with no duplication of intermediate nodes and the same return source nodes, which not only ensures the diverse transmission of data, but also improves the transmission efficiency and stability of the overall network by avoiding the reuse of intermediate nodes. By obtaining the detection results of each node and each source station, detailed indicator data on the node transmission performance can be collected, providing a solid foundation for subsequent path selection and optimization. The multiple transmission paths include a first number of initial paths and a second number of alternative paths, so that the system can quickly switch to the alternative path when a problem occurs in the initial path, thereby ensuring the continuity and stability of data transmission. The situation of link failure is taken into account, and corresponding countermeasures are provided. When a link failure occurs in the transmission path, the system can quickly rebuild the alternative path to ensure the continuity of data transmission.

[0046] In an optional embodiment, the method further includes: the initial path and the alternative path are established only once.

[0047] The initial path and the alternative path are established only once. If a transmission path fails to be established or a link failure occurs during data transmission, this transmission path will not be considered in subsequent data transmission tasks.

[0048] For example, CCS sends initial path 1, initial path 2, initial path 3 and alternative links 1, alternative link 2 and alternative link 3, and establishes three initial paths. Initial path 1 and initial path 2 are successfully established, but initial path 3 fails to be established. In order to ensure that there are three transmission paths for data transmission, alternative link 1, alternative link 2 and alternative link 3 are rebuilt in sequence. Alternative link 1 fails to be established, but alternative link 2 is successfully established. At this time, alternative link 3 is not rebuilt. Initial path 1, initial path 2 and alternative link 2 are used for data transmission. During data transmission, a link failure occurs in initial path 1, and alternative link 3 is rebuilt without considering alternative link 1 and initial path 3.

[0049] By adopting the embodiments of the present disclosure, by limiting the number of times the initial path and the alternative path are established to once, the system can avoid unnecessary repeated establishment processes, thereby saving a large amount of computing resources and time.

[0050] Among them, in an optional embodiment, the detection results of each node and each source station are obtained; including: periodically detecting each node and each source station to obtain the detection results; determining the detection weight of each node after calculating, weighting and smoothing the network jitter on the detection results; the detection weight represents: the priority of the node being selected in the process of determining the transmission path; adding the detection weight to the detection result to obtain the detection result carrying the detection weight; according to the detection result, determining to obtain multiple transmission paths with no repeated intermediate nodes and the same return source nodes, including: according to the detection result carrying the detection weight, determining to obtain multiple transmission paths with no repeated intermediate nodes and the same return source nodes.

[0051] Dynamic Agent provides periodic detection of CDN nodes and customer origins to obtain detection results. The detection period can be adjusted according to the speed of network changes and the stability of transmission requirements.

[0052] The detection results include but are not limited to packet loss rate, delay, bandwidth utilization, and other indicators that can represent the system transmission performance. The collected detection data can be calculated to obtain the performance indicators of each node, such as average packet loss rate, average delay, etc.

[0053] After the detection results are collected, the detection results can be processed by calculation, EWMA weighting, network jitter smoothing, etc. Specifically, the performance indicators of each node are weighted and summed to obtain the comprehensive performance score of the node, and the volatility and instability of network performance are considered, and the smoothing algorithm is used to process the comprehensive performance score to reduce the impact of short-term fluctuations on path selection.

[0054] The smoothed comprehensive performance score can be used as the detection weight of the node, which reflects the priority of the node when determining the transmission path.

[0055] Based on the detection weight of each node, a path search algorithm can be used to search for multiple possible transmission paths between the node and the source station. The performance of multiple possible transmission paths can be evaluated, including the total delay of the path, the total bandwidth utilization, etc., to obtain the performance evaluation results of the path.

[0056] Then, based on the performance evaluation results of the path and the current transmission requirements, multiple transmission paths with no duplication of intermediate nodes and the same return source nodes are selected from multiple possible transmission paths to meet the needs of multi-path transmission. The selected multiple transmission paths are the optimal transmission paths in the current transmission scenario.

[0057] By adopting the embodiments of the present disclosure, the system can obtain network status information in real time by periodically detecting each node and each source station, providing reliable data support for subsequent path selection. After calculating, weighting and smoothing the network jitter of the detection results, the system can more accurately evaluate the performance of each node and determine their priority in the transmission path selection. By considering the detection weight of the node, the system can avoid assigning data transmission tasks to nodes with poor performance, thereby optimizing the utilization of network resources.

[0058] Among them, in an optional embodiment, according to the priority order of the multiple transmission paths, a first number of transmission paths are established for data transmission, including: establishing each initial path for data transmission by establishing connections between nodes; or, in the event that the initial path fails to be established, determining a third number of the initial paths that failed to be established; rebuilding the alternative paths in sequence until the number of successfully established alternative paths meets the third number; data transmission is performed through the successfully established initial paths and the third number of alternative paths; wherein, when the second number of alternative paths are all reconstructed and the number of successfully established alternative paths does not meet the third number, data transmission is performed through the successfully established initial paths and the successfully established alternative paths.

[0059] The transmission paths are established in a priority order of first establishing the initial path and then establishing the candidate paths, so that there are a first number of transmission paths that are successfully established.

[0060] In the process of establishing transmission paths, there are two situations: one is that all initial paths are successfully established, and the other is that some initial paths fail to be established and alternative paths need to be established to meet the goal of successfully establishing the first number of transmission paths.

[0061] Any transmission path is established by establishing connections between nodes. The edge node establishes connections with the intermediate nodes of each transmission path based on the received transmission path, and then the intermediate node establishes connections with the back-to-source node, and the back-to-source node establishes connections with the source station. In the event of a connection failure in any connection link of the transmission path, the transmission path is judged to have failed to be established. For example, when the edge node is abnormally connected to the next-hop parent node, the transmission path is judged to have failed to be established; when the non-edge node fails to connect to the next-hop parent node, the transmission path is also judged to have failed to be established.

[0062] In the first stage, a first number of initial paths are established to determine whether each initial path is successfully established. If the first number of initial paths are successfully established, the second stage is not entered, and each successfully established initial path is used for data transmission. If an initial path fails to be established, it is determined that the number of currently successfully established initial paths does not meet the first number requirement, and an alternative path needs to be established to meet the requirement of using the first number of transmission paths for multi-path transmission.

[0063] In the second stage, the third number of initial paths that failed to be established is determined, so as to judge that the third number of transmission paths is still short of the requirement of using the first number of transmission paths for multi-path transmission. The alternative paths are rebuilt in sequence until the number of successfully established alternative paths meets the third number, and then the establishment of the alternative paths is stopped. The meaning of rebuilding each alternative path in sequence is that the establishment of the next alternative path will not begin until the establishment of an alternative path fails. In a specific implementation, if the establishment of the Nth transmission path fails, then the N+1th transmission path is rebuilt for the Nth transmission path, and if the establishment of the N+1th transmission path fails, then the N+2th transmission path is rebuilt until all alternative paths are attempted to be rebuilt, and the reconstruction operation of the alternative paths is stopped, or in the process of sequential reconstruction of the alternative paths, an alternative path is successfully established, and the reconstruction operation of the alternative paths is also stopped.

[0064] When the third number of candidate paths are successfully established, the initial path successfully established in the first phase and the third number of candidate paths are used for data transmission, so as to meet the requirement of using the first number of transmission paths for multiplexing the current target data.

[0065] Each transmission path is established only once. If any transmission path fails to be established, it will not be considered in the subsequent transmission path establishment. The present disclosure will not rebuild the transmission path that failed to be established before. That is, there are three states for the status of the transmission path: successful establishment, failed establishment, and unestablished. When considering the establishment of a transmission path, only the transmission path with the status of unestablished is established.

[0066] Therefore, there is a situation that the second number of candidate paths are rebuilt in sequence, but the number of successfully established candidate paths still does not meet the third number requirement, resulting in the number of transmission paths that can currently perform data transmission not meeting the first number requirement, and the transmission paths that can currently perform data transmission include the initial paths that are successfully established in the first stage and the candidate paths that are successfully established in the second stage. In this case, the path that currently does not meet the first number requirement is used for data transmission.

[0067] By adopting the embodiments of the present disclosure, by giving priority to establishing the initial path and establishing alternative paths in sequence when necessary, it is possible to ensure that as many transmission paths as possible are effectively utilized. By establishing multiple transmission paths (including initial paths and alternative paths), when some paths fail to be established, the remaining transmission paths can still be established, thereby maintaining the continuity of data transmission and improving the fault tolerance and reliability of data transmission. By rebuilding other available alternative paths with the same return source node, node resources can be fully utilized, the overall bandwidth utilization efficiency can be improved, high node load can be avoided, direct return to the source due to node failure can be reduced, the pressure on the source station can be reduced, and the stability and response speed of the source station can be improved.

[0068] Among them, in an optional embodiment, according to the priority order of the multiple transmission paths, a first number of transmission paths are established for data transmission, including: splitting the target data for data transmission according to the first number to obtain a first number of sub-data; and transmitting the sub-data respectively through the first number of transmission paths.

[0069] Determine the target data that needs to be currently transmitted, and perform multiplexing on the target data. Determine the number of transmission paths that are currently successfully established, that is, the first number. Divide the target data according to the first number to obtain a first number of sub-data, where the sub-data is in the form of data blocks, and each sub-data is transmitted through a transmission path, that is, the transmission path and the sub-data are in a one-to-one relationship, and the sub-data transmitted by each transmission path are different, and each transmission path needs to transmit the sub-data.

[0070] By adopting the embodiments of the present disclosure, by splitting the target data into multiple sub-data and transmitting them through different transmission paths, network bandwidth and transmission resources can be fully utilized, thereby accelerating the overall data transmission speed. Parallel transmission of multiple transmission paths means that even if a path fails or is congested, other paths can still continue to transmit data, thereby improving the fault tolerance and reliability of data transmission. For large data transmission tasks, splitting them into multiple sub-data and transmitting them through multiple paths can more effectively manage the transmission process and avoid overload and bottleneck problems of a single path.

[0071] Among them, in an optional embodiment, the sub-data are transmitted separately through the first number of transmission paths, including: separately determining whether each of the sub-data is greater than the minimum compression requirement; when the sub-data is greater than the minimum compression requirement, compressing the sub-data and adding a compression identifier to the protocol header of the compressed sub-data; the compression identifier is used to characterize: the data is compressed data, so that the end node decompresses the compressed sub-data based on the compression identifier; the end node is determined by the transmission direction of the transmission path; the transmission direction includes uplink transmission or downlink transmission; and the compressed sub-data with the compression identifier added are transmitted separately through the first number of transmission paths.

[0072] After the target data is split according to the first number and the first number of sub-data is obtained, the size of each sub-data needs to be determined, and the oversized sub-data is compressed to improve the efficiency of data transmission. The split sub-data have their own corresponding serial numbers, which are used to restore each sub-data to the correct target data. The sub-data are spliced ​​in sequence according to the serial numbers to ensure that each sub-data is in the correct position.

[0073] The minimum compression requirement is set based on historical experience or the current system load. The minimum compression requirement means that when the size of a data is larger than the minimum compression requirement, the data needs to be compressed.

[0074] The transmission direction of the transmission path includes uplink transmission or downlink transmission, where uplink transmission means from the client to the server, and downlink transmission means from the server to the client. When performing uplink transmission or downlink transmission, the end node is different, the end node of uplink transmission is the source node, and the end node of downlink transmission is the edge node.

[0075] Perform compression judgment on each sub-data separately, determine the size relationship between the sub-data and the minimum compression requirement, and when there is sub-data that is larger than the minimum compression requirement, compress the sub-data, and add a compression mark to the compressed sub-data. The compression mark is added to the protocol header. If a data has a compression mark, it indicates that the data is obtained through compression. If the data needs to be processed, it is necessary to first decompress the data to obtain the original data of the data, and then process the original data. Specifically, at the end node, after receiving the data transmitted by the previous intermediate node, such as receiving the sub-data, the end node needs to identify whether the data carries a compression mark; if the data carries a compression mark, the end node needs to decompress the data to obtain the decompressed data, and perform subsequent processing on the decompressed data, such as transmission and parsing; if the data does not carry a compression mark, the received sub-data is directly used for subsequent processing.

[0076] When the sub-data is not larger than the minimum compression requirement, the transmission path is used to directly transmit the sub-data. When the sub-data is larger than the minimum compression requirement, the sub-data is compressed to obtain compressed sub-data, which is then transmitted using the transmission path.

[0077] By using the embodiments of the present disclosure, by judging whether the sub-data is larger than the minimum compression requirement and compressing the sub-data that is larger than the requirement, the amount of data to be transmitted can be significantly reduced. Since the compressed data occupies less network bandwidth, the data transmission speed is accelerated. In the case of parallel transmission of multiple transmission paths, compressed data can more effectively utilize the bandwidth of each node and improve the transmission efficiency of the overall network.

[0078] In order to ensure that each sub-data corresponding to the target data can be processed uniformly, it is also necessary to set the association of each connection corresponding to the target data to ensure that the associated transmission paths can transmit the respectively processed data to the same location.

[0079] Among them, in an optional embodiment, the sub-data are transmitted respectively through the first number of transmission paths, including: determining the previous hop node of the source node in each of the transmission paths respectively; in each of the previous hop nodes, setting the content of the target option according to the session identifier of the target data; wherein, the content of the target option is set to identify the association of each connection corresponding to the target data; the connection is the connection between each node in the transmission path; distributing the associated sub-data transmitted through each transmission path to the server of the same source node; and processing the sub-data of each of the transmission paths through the same process of the server.

[0080] The target option can be a tcp option.

[0081] In each transmission path, the previous hop node of the source node is determined, and in the previous hop node, the content of the target option is set according to the session identifier of the corresponding target data. This makes it possible for the connections for multiplexing the target data to be associated with each other. In addition, the association of each transmission path needs to be transmitted to the LVS (Linux Virtual Server) and the kernel of the source node.

[0082] LVS is used to ensure that when all associated transmission paths are connected to the back-to-source node, each sub-data in the transmission path will be distributed to the same RS (Real Server), avoiding request switching between different servers and improving service stability and response speed; the back-to-source node kernel is used to ensure that all associated transmission path sub-data will be distributed to the same worker process of the back-to-source node for processing.

[0083] After receiving the sub-data corresponding to each transmission path of the target data, the back-to-source node determines whether each sub-data has a compression mark. If the sub-data has a compression mark, the sub-data is first decompressed to obtain the original uncompressed sub-data, and the uncompressed sub-data are spliced ​​according to the sequence number when they were split, and then forwarded to the source station.

[0084] By adopting the embodiments of the present disclosure, multiple connections can be effectively identified and associated to ensure that data packets can be correctly classified into corresponding sessions in a multi-channel transmission scenario. If a link fails, the system can use the content of the set target option to quickly identify and switch to other available links, ensuring the continuity and stability of the data flow and enhancing the system's fault recovery capabilities.

[0085] When using the first number of transmission paths to perform multi-channel transmission of target data, link failures may occur in some transmission paths. The following is a solution used by the present disclosure to solve this problem. The solution can address the problem of link failures during multi-channel transmission, which leads to a decrease in transmission speed or even transmission failure, traffic waste and resource consumption. The edge node caches data. If the edge node finds that a link failure has occurred in the transmission path, a transmission path to the same source node is re-established, and the data is distributed to the newly created transmission path for transmission. This can better cope with node failures and significantly improve transmission efficiency.

[0086] Among them, in an optional embodiment, it also includes: caching the sub-data in a cache area; transmitting the sub-paths respectively through the first number of transmission paths; including: determining a first timeout period; determining whether each of the sub-data in the cache area has received a confirmation message within the first timeout period; in the event that the sub-data has not received a confirmation message, confirming that a link failure has occurred in the transmission path corresponding to the sub-data that has not received the confirmation message; rebuilding the alternative paths in turn to obtain the target alternative paths corresponding to the transmission path with the link failure; determining the sub-data corresponding to the transmission path with the link failure from the cache area, and transmitting the sub-data through the target alternative path.

[0087] When the edge node transmits the sub-data of the target data through the transmission path, it caches the sent sub-data and caches it in the cache area.

[0088] The edge node needs to confirm whether each sub-data in the buffer area is successfully transmitted through the transmission path based on the received confirmation message. A first timeout is set for receiving the confirmation message. The confirmation message can be an ACK message (Acknowledgment). When the sender sends a data packet to the receiver, the receiver will send an ACK message back to the sender after successfully receiving the data to confirm that the data has been successfully received.

[0089] For a sub-data, if its corresponding confirmation message is received within the first time, it is determined that the transmission path corresponding to the sub-data successfully transmits the sub-data. For a sub-data, if its corresponding confirmation message is not received within the first timeout period, it means that the transmission path corresponding to the sub-data has not successfully transmitted the sub-data and a link failure occurs in the transmission path.

[0090] In order to deal with the problem of link failure in the transmission path, when a link failure occurs in a transmission path, the edge node initiates link reconstruction and re-establishes a transmission path to the same source node, that is, rebuilds the alternative path so that it can transmit the sub-data that needs to be transmitted on the transmission path with link failure.

[0091] In the case of a link failure on any transmission path, a fourth number of the transmission paths where the link failure occurs is determined, and alternative paths that have not been established are rebuilt in sequence until there are successfully established alternative paths that meet the fourth number, and in the case of the fourth number of alternative paths being successfully established, the alternative paths are no longer rebuilt. Sub-data corresponding to the transmission paths with each link failure are confirmed in the buffer area, and the sub-data are transmitted using the alternative paths corresponding to the transmission paths with the link failure.

[0092] During the transmission of the sub-data on the alternative path, it is still determined whether a link failure occurs on the alternative path. If a link failure occurs on the alternative path, the edge node reconstructs the alternative path that has not been established to resume the transmission of the sub-data.

[0093] If a transmission path has a link failure, but there is currently no established alternative path that can be rebuilt, that is, the alternative path corresponding to the transmission path for restoring transmission cannot be rebuilt at present, the transmission path that does not currently have a link failure can be used to transmit the sub-data corresponding to the transmission path that has a link failure.

[0094] In a specific example, there are N existing transmission paths for transmitting target data. When it is determined that a certain transmission path, such as the Nth path, has a link failure, the edge node initiates link reconstruction, re-establishes an N+1th path to the same source node, and transfers the sub-data corresponding to the Nth path to the newly created N+1th path for transmission, thereby ensuring that the target data is transmitted simultaneously using N transmission paths, thereby improving transmission efficiency. In addition, if a link failure also occurs on the N+1th path, then the N+2th path is rebuilt, and the sub-data of the N+1th path is transmitted through the N+2th path. During the transmission process, it is determined whether the N+2th path has a link failure. If a link failure still occurs during the transmission of the sub-data after all alternative links are rebuilt, the sub-data is transmitted using a transmission path that does not currently have a link failure.

[0095] If the sub-data corresponding to the transmission path of the link failure has no compression mark and exceeds the minimum compression requirement, it needs to be compressed and then transmitted using the re-established transmission path.

[0096] By adopting the embodiments of the present disclosure, by caching the sub-data in the cache area, the system can retain a copy of the data during the data transmission process, and even if a problem occurs during the transmission process, the data can be retrieved from the cache, thereby improving the reliability of data transmission. By setting a first timeout period and checking whether a confirmation message is received, the system can promptly detect link failures that may occur during data transmission. Once a failure is detected, the system can respond quickly and restore data transmission by rebuilding an alternative path, thereby ensuring data integrity and continuity of transmission. After confirming the link failure, the system can extract the sub-data that was not successfully transmitted from the cache area and retransmit it through the rebuilt alternative path, ensuring that the data can be successfully transmitted to the destination even in the most unfavorable circumstances.

[0097] In the event of a link anomaly on the transmission path, it is necessary not only to rebuild the transmission path at the edge node, but also to cooperate with the source node in rebuilding the transmission path. The following are the operations that the source node will perform in the scenario of rebuilding the transmission path.

[0098] Among them, in an optional embodiment, after confirming that a link failure occurs in the transmission path corresponding to the sub-data for which a confirmation message has not been received, it also includes: triggering an abnormal session of the transmission path at the source node of the transmission path; determining a second timeout period of the abnormal session; transmitting the sub-data through the target alternative path, including: transmitting the sub-data through the target alternative path when the target alternative path is successfully established within the second timeout period.

[0099] If a transmission path has a link failure, an abnormal session corresponding to the transmission path will be triggered on the source node. The abnormal session can be a downstream abnormal session.

[0100] After being triggered, the abnormal session is in the keep-alive state. When the abnormal session is in the keep-alive state, it will wait for the connection of the alternative path corresponding to the transmission path of the link failure. After the connection is made, the remaining data can be transmitted using the newly connected alternative path.

[0101] A second timeout is set for an abnormal session. After the abnormal session is triggered to enter the keep-alive state, the keep-alive state will last for the second timeout. After the second timeout, the abnormal session will release the session and disconnect the old connection to avoid resource waste.

[0102] Therefore, for a transmission path, if a link failure occurs in the transmission path, then it is necessary to obtain a corresponding successfully established alternative path within the second timeout period. If within the second timeout period, the transmission path with the link failure obtains a successfully established alternative path, then the alternative path can be used to continue transmitting its sub-data; if within the second timeout period, the transmission path with the link failure does not obtain a successfully established alternative path, then the sub-data corresponding to the transmission path can only be transmitted using the remaining transmission paths that do not have link failures.

[0103] With the embodiments of the present disclosure, when a link failure occurs in a transmission path and no confirmation message is received, the system can quickly trigger an abnormal session on the source node, which helps to quickly identify and handle problems in the network and reduce transmission delays or data loss caused by link failures. By setting a second timeout for the abnormal session, the system can keep the abnormal session alive for a certain period of time, waiting for the connection of the alternative path. If the alternative path is successfully established within the timeout period, the path can be used to continue to transmit data, thereby effectively utilizing network resources.

[0104] Figure 2 FIG. 1 is a schematic diagram showing a transmission path reconstruction caused by a failure of establishing a connection between nodes according to an embodiment of the present disclosure. Figure 2 As shown: After the dynamic agent detects each CDN node and source station and reports the detection results with detection weights to CCS, the top2N optimal transmission paths with no duplication of transit nodes and the same back-to-source nodes are obtained, including N initial paths and N alternative paths, and the transmission paths are sent to edge nodes through the dynamic agent. Assuming that 3 paths are used for target data transmission, N is 3. The transmission path set is ip1-ip2-ip8-o1; ip1-ip3-ip8-o1; ip1-ip4-ip8-o1; ip1-ip5-ip8-o1; ip1-ip6-ip8-o1; ip1-ip7-ip8-o1.

[0105] Step 1: After receiving the top6 optimal path set sent by the dynamic agent, the edge node ip1 establishes connections with nodes ip2, ip3, and ip4.

[0106] Step 2: The transit parent nodes ip2, ip3, and ip4 establish a connection with the back-to-source node ip8, and the back-to-source node ip8 establishes a connection with the source station o1.

[0107] In the process of establishing each transmission path, it is determined whether the nodes of each transmission path can be successfully connected.

[0108] Step 3: It is found that the connection between nodes fails for the first time. The connection between node ip1 and node ip2 fails. The link ip1-ip5-ip8-o1 is rebuilt. The current multi-channel transmission paths are ip1-ip3-ip8-o1, ip1-ip4-ip8-o1, and ip1-ip5-ip8-o1.

[0109] Step 4: It is found that the connection between nodes fails for the second time. The connection between node ip1 and node ip3 fails. The link ip1-ip6-ip8-o1 is rebuilt. The current multi-channel transmission paths are ip1-ip4-ip8-o1, ip1-ip5-ip8-o1, and ip1-ip6-ip8-o1.

[0110] Step 5: It is found for the third time that the connection between nodes fails, and node ip5 fails to connect to node ip8. Then node ip5 notifies node ip1 to rebuild link ip1-ip7-ip8-o1. The current multi-channel transmission paths are ip1-ip4-ip8-o1, ip1-ip6-ip8-o1, and ip1-ip7-ip8-o1.

[0111] Step 6: The fourth time it is found that the connection between nodes fails, and the connection between node ip1 and node ip7 fails. There is no transmission path that has not been established, so the reconstruction operation of the transmission path is no longer retried. The remaining available transmission paths are used. The current multi-channel transmission paths are ip1-ip4-ip8-o1 and ip1-ip6-ip8-o1.

[0112] Figure 3 FIG. 1 is a schematic diagram showing a transmission path reconstruction caused by a link failure in an embodiment of the present disclosure. Figure 3 As shown: After the dynamic agent detects each CDN node and source station and reports the detection results with detection weights to CCS, CCS obtains the top2N optimal transmission paths with no duplication of transit nodes and the same back-to-source nodes, including N initial paths and N alternative paths, and sends the transmission paths to edge nodes through the dynamic agent. Assuming that 3 paths are used for target data transmission, N is 3. The transmission path set is ip1-ip2-ip8-o1; ip1-ip3-ip8-o1; ip1-ip4-ip8-o1; ip1-ip5-ip8-o1; ip1-ip6-ip8-o1; ip1-ip7-ip8-o1.

[0113] The application acceleration gateway edge node ip1 receives the top6 optimal path set sent by the dynamic agent, establishes connections with the intermediate nodes ip2, ip3, and ip4, and the intermediate nodes ip2, ip3, and ip4 establish connections with the node ip8. The back-to-source node ip8 establishes a connection with the source station o1.

[0114] The edge node ip1 splits the target data to be transmitted, and sends the sub-data of the target data to the intermediate nodes ip2, ip3, and ip4 respectively, and sends the target data to the intermediate nodes in multiple ways; determines whether the data block size corresponding to the sub-data exceeds the minimum compression requirement; if the data block size corresponding to the sub-data exceeds the minimum compression requirement, compresses the sub-data and adds a compression flag to the compressed sub-data protocol header; the edge node caches the sub-data that has been sent.

[0115] Determine whether the sub-data sent by the edge node ip1 receives the confirmation message within the timeout period; if the sub-data does not receive the ACK message returned by the intermediate parent node within the timeout period, it is considered that a link failure occurs in the transmission path of the sub-data; for example, if the edge node does not receive the ACK message returned by the parent node ip2, the edge node considers that a link failure occurs in ip1-ip2-ip8-o1.

[0116] When a link failure occurs during multi-path transmission, the edge node ip1 re-establishes a link to the same source node ip8, and transfers the sub-data of the transmission path with the link failure to the newly created transmission path for transmission; at the same time, if the data block of the sub-data does not have a compression mark and the size exceeds the minimum compression requirement, the data is compressed and the compression mark is added to the protocol header. For example, for ip1-ip2-ip8-o1 with a link failure, ip1-ip5-ip8-o1 is established, that is, the multi-path set is ip1-ip3-ip8-o1, ip1-ip4-ip8-o1, ip1-ip5-ip8-o1; the edge node ip1 transfers the sub-data transmitted by ip1-ip2-ip8-o1 to the newly created link ip1-ip5-ip8-o1 for transmission.

[0117] After receiving the sub-data, the intermediate nodes ip3, ip4, and ip5 analyze the sub-data.

[0118] Each previous hop node ip3, ip4, and ip5 of the source node sets the tcp option field according to the session id to identify the association of multiple connections and pass relevant information to the LVS and the kernel.

[0119] LVS distribution ensures that when the rebuilt link is connected to the source node, LVS distribution can be distributed to the same RS, that is, the source node ip8.

[0120] On the source node, each transmission path has a corresponding abnormal session. When a link failure occurs on a transmission path, the abnormal session on the source node will be triggered, and the abnormal session is in a keep-alive state. Determine whether the source node has received a new connection corresponding to the transmission path with the link failure within the second timeout period. If received, use the new connection to transmit the remaining data, that is, the connection of the transmission path rebuilt for the transmission path with the link failure; if not received, disconnect the session of the old connection, that is, the connection of the transmission path with the link failure. For example, when a link failure occurs on ip1-ip2-ip8-o1, on the source node, the downstream abnormal session corresponding to ip1-ip2-ip8-o1 enters the keep-alive state and waits for a new downstream connection, that is, ip5-ip8, to transmit the remaining data; if the downstream abnormal session does not receive a new connection for a certain period of time, the session is released and the old connection ip2-ip8 is disconnected.

[0121] The back-to-source node kernel distributes the associated connections to the same worker process of the back-to-source node ip8 for processing.

[0122] The back-to-source node identifies whether the protocol header has a compression flag. If so, it decompresses the data, aggregates and splices the data, and returns it to the source station o1.

[0123] The present disclosure can solve the problem of connection failure between CDN nodes in multi-path scenarios, rebuild the transmission path passing through the same source node, always ensure N available links, make full use of node resources, avoid high node load, ensure efficient operation of services, reduce the pressure on the source station, and improve the stability and response speed of the source station.

[0124] The present disclosure can solve the problem of link failure during multi-channel transmission by re-establishing a transmission path to the same source node, distributing the remaining data to the newly created transmission path for transmission, and always ensuring efficient transmission of N transmission paths. At the same time, combined with the advantages of data compression, the transmission efficiency is significantly improved, the use of network bandwidth is reduced, and user satisfaction is improved.

[0125] In general, the link reconstruction method provided by the present invention can make full use of node resources, improve the overall bandwidth utilization efficiency, avoid high node load, and ensure the efficient operation of the service, thereby significantly improving the transmission speed and efficiency, and improving user experience and business operations; at the same time, the node load is balanced and the availability is high, which reduces the direct return to the source due to node failure, reduces the pressure on the source station, and improves the stability and response speed of the source station; in addition, the combination of compression technology can effectively reduce the use of network bandwidth and help enterprises save network transmission costs.

[0126] Figure 4 FIG. 1 is a block diagram of a link reconstruction system shown in an embodiment of the present disclosure. Figure 4 As shown, the system comprises: An acquisition module 410 is used to acquire detection results of each node and each source station, wherein the detection results at least include indicator data representing the transmission performance of the node; A determination module 420 is used to determine, according to the detection result, a plurality of transmission paths having non-repeated intermediate nodes and the same back-to-source node; the plurality of transmission paths include a first number of initial paths and a second number of alternative paths, and the back-to-source node is a previous hop node of the source station; Establishing module 430, used to establish a first number of transmission paths for data transmission according to the priority order of the multiple transmission paths, the first number of transmission paths including the initial path and / or the alternative path, the priority of the initial path is greater than the priority of the alternative path.

[0127] The present disclosure also provides an electronic device, referring to Figure 5 , Figure 5 is a schematic diagram of an electronic device shown in an embodiment of the present disclosure. Figure 5As shown, the electronic device 500 includes: a memory 510 and a processor 520. The memory 510 and the processor 520 are connected via a bus communication. A computer program is stored in the memory 510. The computer program can be run on the processor 520 to implement the steps in the link reconstruction method disclosed in the embodiment of the present disclosure.

[0128] The embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the link reconstruction method disclosed in the embodiment of the present disclosure are implemented.

[0129] The embodiment of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the link reconstruction method disclosed in the embodiment of the present disclosure are implemented.

[0130] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0131] It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, devices or computer program products. Therefore, the embodiments of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] Although some embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present disclosure.

[0136] The link reconstruction method and system provided by the present disclosure are introduced in detail above. The principles and implementation methods of the present disclosure are explained in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present disclosure. At the same time, for those skilled in the art, according to the idea of ​​the present disclosure, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present disclosure.

Claims

1. A link reestablishment method, characterized in that: include: Acquire detection results for each node and each source station, wherein the detection results at least include indicator data characterizing node transmission performance; According to the detection result, multiple transmission paths with no duplication of intermediate nodes and the same back-to-source node are determined; the multiple transmission paths include a first number of initial paths and a second number of alternative paths, and the back-to-source node is a previous hop node of the source station; According to the priority order of the multiple transmission paths, a first number of transmission paths are established for data transmission, the first number of transmission paths including an initial path and / or the alternative path, the priority of the initial path is greater than the priority of the alternative path.

2. The method according to claim 1, characterized in that Establishing a first number of transmission paths for data transmission according to the priority order of the plurality of transmission paths includes: By establishing connections between nodes, each initial path is established for data transmission; or, In the case where the initial path fails to be established, determining a third number of the initial paths that failed to be established; Rebuilding the candidate paths in sequence until the number of the successfully established candidate paths meets the third number; Performing data transmission by establishing the successfully established initial path and the third number of the candidate paths; Wherein, when the second number of candidate paths are all reconstructed and the number of the successfully established candidate paths does not meet the third number, data transmission is performed through the successfully established initial path and the successfully established candidate paths.

3. The method according to claim 1 or 2, characterized in that: Establishing a first number of transmission paths for data transmission according to the priority order of the plurality of transmission paths includes: Splitting the target data for data transmission according to a first quantity to obtain a first quantity of sub-data; The sub-data are respectively transmitted through the first number of transmission paths.

4. The method according to claim 3, characterized in that Also includes: Cache the sub-data in a cache area; Transmitting the sub-data respectively through the first number of transmission paths includes: determining a first timeout period; Determine whether each of the sub-data in the buffer area receives a confirmation message within a first timeout period; In the case that the sub-data has not received a confirmation message, confirming that a link failure occurs in a transmission path corresponding to the sub-data for which the confirmation message has not been received; Reconstructing the candidate paths in sequence to obtain a target candidate path corresponding to the transmission path with link failure; The sub-data corresponding to the transmission path of the link failure is determined from the buffer area, and the sub-data is transmitted through the target alternative path.

5. The method according to claim 4, characterized in that After confirming that a link failure occurs in the transmission path corresponding to the sub-data for which the confirmation message has not been received, the method further includes: At a back-to-source node of the transmission path, triggering an abnormal session of the transmission path; Determining a second timeout period of the abnormal session; The transmitting the sub-data through the target candidate path includes: If the target candidate path is successfully established within the second timeout period, the sub-data is transmitted through the target candidate path.

6. The method according to claim 3, characterized in that Transmitting the sub-data respectively through the first number of transmission paths includes: Determine respectively whether each of the sub-data is greater than a minimum compression requirement; In the case where the sub-data is larger than the minimum compression requirement, the sub-data is compressed, and a compression identifier is added to the protocol header of the compressed sub-data; the compression identifier is used to indicate that: the data is compressed data, so that the end node decompresses the compressed sub-data based on the compression identifier; the end node is determined by the transmission direction of the transmission path; the transmission direction includes uplink transmission or downlink transmission; The compressed sub-data with compression identifiers added thereto are transmitted respectively through the first number of transmission paths.

7. The method according to claim 3, characterized in that Transmitting the sub-data respectively through the first number of transmission paths includes: Determine the previous hop node of the source node in each transmission path respectively; In each of the previous hop nodes, the content of the target option is set according to the session identifier of the target data; wherein the content of the target option is used to identify the association of each connection corresponding to the target data; the connection is a connection between each node in the transmission path; The associated sub-data transmitted through each transmission path are distributed to a server of the same back-source node, so that the sub-data of each transmission path are processed through the same process of the server.

8. The method according to any one of claims 1 to 7, characterized in that: Obtain the detection results of each node and each source station; including: Perform periodic detection on each node and each source station to obtain detection results; After calculating, weighting and smoothing the network jitter of the detection results, the detection weight of each node is determined; the detection weight represents: the priority of the node in determining the transmission path; Adding the detection weight to the detection result to obtain the detection result carrying the detection weight; According to the detection result, multiple transmission paths with no duplication of intermediate nodes and the same back-to-source nodes are determined, including: According to the detection result carrying the detection weight, a plurality of transmission paths with no duplication of intermediate nodes and the same back-to-source nodes are determined.

9. A link reconstruction system, characterized in that: include: An acquisition module, used to acquire detection results of each node and each source station, wherein the detection results at least include indicator data characterizing the transmission performance of the node; A determination module, configured to determine, based on the detection result, a plurality of transmission paths having non-repeated intermediate nodes and the same back-to-source node; the plurality of transmission paths comprising a first number of initial paths and a second number of alternative paths, and the back-to-source node being a previous hop node of the source station; An establishing module is used to establish a first number of transmission paths for data transmission according to the priority order of the multiple transmission paths, wherein the first number of transmission paths includes an initial path and / or the alternative path, and the priority of the initial path is greater than the priority of the alternative path.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the link reconstruction method according to any one of claims 1 to 8 are implemented.

Images