A hybrid in-band network telemetry task transmission method and system
Through the hybrid in-band network telemetry method, combined with active and passive methods, the data transmission path is planned, and the problems of low coverage or high cost in large-scale networks are solved, achieving connectivity and efficient data transmission of the entire network link.
Patent Information
- Application Number
- CN202211650811.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-21
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-12-21
AI Technical Summary
The existing active and passive in-band network telemetry methods have problems with low coverage or high cost in large-scale networks, making it difficult to achieve effective measurement of the entire network link.
Adopt a hybrid in-band network telemetry task transmission method, by acquiring link topology diagrams and historical communication tasks, identifying the first and second target nodes and links, combining active and passive methods, planning data transmission paths, reducing costs and improving coverage Rate.
The network telemetry task between the transmitting probe and the receiving probe in a large-scale network is realized, which reduces the cost of active methods, improves coverage, and ensures the connectivity of the entire network link and data transmission efficiency.
Smart Images

Figure CN116094985B_ABST
Abstract
Description
Background Art
[0002] Network measurement is the basis of network management, especially for large networks. Traditional network measurement methods can be divided into three types: active, passive and hybrid. In today's era of big data with rapid network development, traditional network measurement methods are somewhat weak in terms of real-time, accuracy, comprehensiveness and cost. With the development of programmable data planes, in-band network telemetry has become an emerging measurement solution.
[0003] In-band network telemetry (INT) is divided into two types, namely active in-band network telemetry and passive in-band network telemetry. The passive INT method uses existing data packets for telemetry information, which can save a lot of bandwidth overhead. The active INT method realizes purposeful network measurement by constructing detection packets and planning detection paths, which can achieve full network coverage measurement. However, the existing passive INT method has low coverage and cannot guarantee the coverage of the entire network link. The active INT method requires additional equipment costs according to the scale of the network, so both the active INT method and the passive INT method have major problems when deployed in large-scale networks. Summary of the invention
[0004] In order to overcome the problem of low coverage or high cost when the active INT method or the passive INT method is deployed alone in a large-scale network, the present invention provides a hybrid in-band network telemetry task transmission method and system.
[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a hybrid in-band network telemetry task transmission method, the method comprising the following steps:
[0006] Obtain a link topology diagram, which includes multiple probes. There are multiple task nodes between any two probes. There is a link between the probe and the task node, and there is a link between every two task nodes. For each link, the link is used to transmit data packets, and each link corresponds to a transmission delay time when transmitting data packets.
[0007] According to the historical communication task, a plurality of first target nodes and a first target link corresponding to each first target node are determined from each task node, wherein the first target node is a task node included in the historical communication task, and the first target link is a link used to transmit data packets in the historical communication task;
[0008] Taking any first target node as the first current node, if the first current node cannot connect to other first target nodes except itself, then determining a second target link from the links according to each first target node and each link, the second target link being the missing link when the first current node cannot connect to other first target nodes except itself;
[0009] According to the network telemetry task, determine the transmitting probe and the receiving probe, the transmitting probe is a probe used to transmit data packets, and the receiving probe is a probe used to receive data packets;
[0010] A data transmission path between the transmitting probe and the receiving probe is determined according to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link.
[0011] The beneficial effect of a hybrid in-band network telemetry task transmission method provided by the present invention is: through a passive INT method, a first target node and a first target link are determined according to historical communication tasks, and then through an active INT method, a second target link is planned from the link. Therefore, the active INT method and the passive INT method are combined and deployed in a large-scale network to realize the network telemetry task between the transmitting probe and the receiving probe, and only the second target link between some task nodes needs to be planned, which reduces the cost of the active INT method and solves the problem of low coverage or high cost when the active INT method or the passive INT method is deployed separately in a large-scale network.
[0012] On the basis of the above technical solution, the hybrid in-band network telemetry task transmission method of the present invention can also be improved as follows.
[0013] Furthermore, the method further comprises:
[0014] S12, taking any first target node as the second current node;
[0015] S13, taking each first target node connected to the second current node and the second current node as the second target node;
[0016] S14, taking each second target node as a task node set;
[0017] S15, taking any first target node except the second target node as the second current node, and repeating S13-S15 until all first target nodes are included in each task node set;
[0018] Taking any first target node as the first current node, if the first current node cannot connect to all first target nodes except itself, determining a second target link from the links according to each first target node and each link, including:
[0019] Any first target node is used as the first current node. If the first current node cannot connect to all first target nodes except itself, a second target link is determined from the links according to each task node set.
[0020] The beneficial effect of adopting the above further solution is: the second target nodes that can be connected are used as task node sets, so as to actively plan the second target links so that each task node set can be connected.
[0021] Further, the above-mentioned determining the second target link corresponding to each task node set from the link according to each task node set includes:
[0022] Taking each task node set as a first task node set, and taking each task node set except the first task node set as a second task node set;
[0023] For each second target node in the first task node set, obtain a first transmission delay time corresponding to the second target node and each second target node in the second task node set, where the first transmission delay time is a delay time required for a data packet to be transmitted from the second target node to the second target node specified in the second task node set;
[0024] The second target link corresponding to each task node set is determined according to each first transmission delay time and each second target node.
[0025] The beneficial effect of adopting the above further scheme is: when planning the second target link, in order to make the entire data transmission path more efficient, it is necessary to plan a data transmission path with less delay time. Therefore, the second target link is determined based on the first transmission delay time between the second target nodes in different task node sets.
[0026] Further, the above-mentioned determining the second target link corresponding to each task node set according to each first transmission delay time and each second target node includes:
[0027] The first transmission delay time with the shortest duration among the first transmission delay times is used as the first target transmission delay time, and the link between the two second target nodes corresponding to the first target transmission delay time is selected as the second target link corresponding to each task node set.
[0028] The beneficial effect of adopting the above further solution is that according to the first target transmission delay time, the fastest data transmission path between different task node sets, namely the second target link, can be planned.
[0029] Furthermore, the method further comprises:
[0030] According to the transmitting probe, the receiving probe, each task node and each link, all first connected subgraphs between the transmitting probe and the receiving probe are determined, where the first connected subgraph is a path graph formed by the task nodes and links through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0031] According to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link, all second connected subgraphs between the transmitting probe and the receiving probe are determined, where the second connected subgraph is a path graph formed by the first target node, the first target link and the second target link through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0032] Determining a data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link, and each second target link includes:
[0033] A data transmission path between the transmitting probe and the receiving probe is determined according to each of the first connected subgraphs and each of the second connected subgraphs.
[0034] The beneficial effect of adopting the above further solution is that by comparing all the first connected subgraphs with the constructed second connected subgraphs, the best data transmission path between the transmitting probe and the receiving probe can be determined.
[0035] Furthermore, the method further comprises:
[0036] According to each first connected subgraph and each second connected subgraph, determining an overlap rate between each first connected subgraph and each second connected subgraph, wherein the overlap rate is a degree of overlap between the first connected subgraph and the second connected subgraph on a path;
[0037] Determining a data transmission path between a transmitting probe and a receiving probe according to each of the first connected subgraphs and each of the second connected subgraphs includes:
[0038] According to each overlap rate, the data transmission path between the transmitting probe and the receiving probe is determined.
[0039] The beneficial effect of adopting the above further scheme is that there are more data transmission paths between the transmitting probe and the receiving probe, that is, there are more first sub-connected graphs. Therefore, for each first sub-connected graph, there can be a corresponding second sub-connected graph with the highest overlap rate. At this time, the second sub-connected graph can replace the first sub-connected graph as the optimal data transmission path.
[0040] Furthermore, the method further comprises:
[0041] Determine, according to each second connected subgraph, a second transmission delay time corresponding to each second connected subgraph, where the second transmission delay time is a delay time required for a data packet to be transmitted from a transmitting probe to a receiving probe through the second connected subgraph;
[0042] Determining a data transmission path between a transmitting probe and a receiving probe according to each of the first connected subgraphs and each of the second connected subgraphs includes:
[0043] A data transmission path between the transmitting probe and the receiving probe is determined according to each overlap rate and each second transmission delay time.
[0044] The beneficial effect of adopting the above further scheme is: since each link corresponds to a transmission delay time, it is necessary to obtain the second transmission delay time of each second connected subgraph. When selecting the second connected subgraph corresponding to each first connected subgraph, not only the overlap rate but also the second transmission delay time must be considered to ensure that the data transmission path between the transmitting probe and the receiving probe has a higher transmission efficiency.
[0045] In a second aspect, the present invention provides a hybrid in-band network telemetry task transmission system, comprising:
[0046] A link topology map acquisition module is used for a link topology map containing multiple probes, multiple task nodes between any two probes, a link between a probe and a task node, and a link between every two task nodes. For each link, the link is used to transmit data packets, and each link corresponds to a transmission delay time when transmitting a data packet;
[0047] A first acquisition module is used to determine a plurality of first target nodes and a first target link corresponding to each first target node from each task node, wherein the first target node is a task node included in a historical communication task, and the first target link is a link used to transmit data packets in the historical communication task;
[0048] A second target link acquisition module is used to take any first target node as the first current node, and if the first current node cannot connect to other first target nodes except itself, determine the second target link from the links according to each first target node and each link, the second target link being the missing link that the first current node cannot connect to other first target nodes except itself;
[0049] The probe acquisition module is used to determine the transmitting probe and the receiving probe according to the network telemetry task, the transmitting probe is a probe used to transmit data packets, and the receiving probe is a probe used to receive data packets;
[0050] The transmission path acquisition module is used to determine the data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link.
[0051] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps of a hybrid in-band network telemetry task transmission method as described above are implemented.
[0052] In a fourth aspect, the present invention also provides a computer-readable storage medium, characterized in that instructions are stored in the computer-readable storage medium, and when the instructions are executed on a terminal device, the terminal device executes the steps of a hybrid in-band network telemetry task transmission method as described above. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention is further described below in conjunction with the accompanying drawings and embodiments.
[0054] Figure 1 A flow chart of a hybrid in-band network telemetry task transmission method according to an embodiment of the present invention;
[0055] Figure 2 is the link topology diagram;
[0056] Figure 3 A link topology diagram after determining the first target node and the first target link according to the historical communication tasks;
[0057] Figure 4 for Figure 3 A partial view of
[0058] Figure 5 for Figure 4 The view after obtaining the second target link;
[0059] Figure 6 Results of the telemetry task experiment on coverage.
[0060] Figure 7 Results of experiments on bandwidth overhead optimization for telemetry missions;
[0061] Figure 8 The present invention is a schematic diagram of the structure of a hybrid in-band network telemetry task transmission system according to an embodiment of the present invention. DETAILED DESCRIPTION
[0062] The following examples are provided to further explain and supplement the present invention and do not constitute any limitation to the present invention.
[0063] A hybrid in-band network telemetry task transmission method and system according to an embodiment of the present invention will be described below in conjunction with the accompanying drawings.
[0064] like Figure 1 As shown, a hybrid in-band network telemetry task transmission method of an embodiment of the present invention can be applied to a terminal device. In the present application scheme, the terminal device is used as the execution subject to illustrate the present application scheme, wherein the terminal device is connected to a database, and the terminal device can be a computer, a server, etc., for executing a hybrid in-band network telemetry task transmission method, and the database is used to store link topology diagrams and historical communication tasks.
[0065] Specifically, a hybrid in-band network telemetry task transmission method includes the following steps:
[0066] S1, obtaining a link topology map, which includes multiple probes, and multiple task nodes between any two probes. There is a link between the probe and the task node, and there is a link between every two task nodes. For each link, the link is used to transmit data packets, and each link corresponds to a transmission delay time when transmitting data packets;
[0067] S2, according to the historical communication task, determining multiple first target nodes from each task node and a first target link corresponding to each first target node, the first target node is a task node included in the historical communication task, and the first target link is a link used to transmit data packets in the historical communication task;
[0068] S3, taking any first target node as the first current node, if the first current node cannot connect to other first target nodes except itself, then determining a second target link from the links according to each first target node and each link, the second target link being the missing link when the first current node cannot connect to other first target nodes except itself;
[0069] S4, determining a transmitting probe and a receiving probe according to the network telemetry task, wherein the transmitting probe is a probe for transmitting data packets, and the receiving probe is a probe for receiving data packets;
[0070] S5, determining a data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link.
[0071] Optional, such as Figure 2 As shown, a link topology diagram is obtained, in which the host represents the transmitting probe and the receiving probe, the number corresponding to the host represents the serial number, each letter represents a task node, the straight line between the probe and the task node represents a link, the straight line between the task node and the task node also represents a link, and the number on the link represents the corresponding transmission delay time when the data packet is transmitted through the link.
[0072] Alternatively, the passive INT method cannot specify the data transmission path according to the network telemetry task. Therefore, it can only obtain the previous task nodes and links based on the historical communication tasks, such as Figure 3 As shown, the first target node and the first target link are obtained by the terminal device through the database query according to the passive INT method, wherein a represents the first target node and b represents the first target link.
[0073] Optionally, for ease of understanding, each first target node and first target link are extracted to form Figure 4 ,pass Figure 4 It can be seen that since there is a first target link between E, D, G, H, J, and I, E, D, G, H, J, and I can be connected. Similarly, K, L, and O can be connected. However, if any one of E, D, G, H, J, and I is used as the first current node, the first current node cannot be connected to K, L, and O. Based on this, it is necessary to build a new data transmission path through active INT to achieve connectivity between E, D, G, H, J, I, K, L, and O.
[0074] Optionally, the method further includes:
[0075] S12, taking any first target node as the second current node;
[0076] S13, taking each first target node connected to the second current node and the second current node as the second target node;
[0077] S14, taking each second target node as a task node set;
[0078] S15, taking any first target node except the second target node as the second current node, and repeating S13-S15 until all first target nodes are included in each task node set;
[0079] Taking any first target node as the first current node, if the first current node cannot connect to all first target nodes except itself, determining a second target link from the links according to each first target node and each link, including:
[0080] Any first target node is used as the first current node. If the first current node cannot connect to all first target nodes except itself, a second target link is determined from the links according to each task node set.
[0081] Optional, such as Figure 4 As shown, for example, taking E as the second current node, it can be seen that E, D, G, H, J, and I can be connected. Therefore, E, D, G, H, J, and I are taken as a task node set. For another example, taking K as the second current node, it can be seen that K, L, and O can be connected. Therefore, K, L, and O are taken as a task node set. For the sake of convenience, E, D, G, H, J, and I are taken as the first task node set, and K, L, and O are taken as the second task node set.
[0082] Optionally, the above-mentioned determining, from the links, the second target link corresponding to each task node set according to each task node set includes:
[0083] Taking each task node set as a first task node set, and taking each task node set except the first task node set as a second task node set;
[0084] For each second target node in the first task node set, obtain a first transmission delay time corresponding to the second target node and each second target node in the second task node set, where the first transmission delay time is a delay time required for a data packet to be transmitted from the second target node to the second target node specified in the second task node set;
[0085] The second target link corresponding to each task node set is determined according to each first transmission delay time and each second target node.
[0086] Optionally, in order to make the data packet transmission more efficient, when the active INT method constructs a new data transmission path, it is necessary to consider the first transmission delay time between each second target node. The shorter the first transmission delay time, the higher the data packet transmission efficiency. For example, there is a link between I in the first task node set and K in the second task node set (see Figure 2 ), there is a link between J in the first task node set and O in the second task node set. At this time, the first transmission delay time of the link between IK is 4, and the first transmission delay time of the link between JO is 8. Obviously, building a link between IK is more efficient for data packet transmission, and it can also connect E, D, G, H, J, I, K, L, and O. Therefore, if Figure 5 As shown, a second target link is constructed between JK, based on which, according to each first transmission delay time and each second target node, the second target link corresponding to each task node set is determined, including:
[0087] The first transmission delay time with the shortest duration among the first transmission delay times is used as the first target transmission delay time, and the link between the two second target nodes corresponding to the first target transmission delay time is selected as the second target link corresponding to each task node set.
[0088] Optionally, the first transmission delay time between the second target nodes of different task node sets is calculated by using the Dijkstra algorithm. Since the Dijkstra algorithm is a prior art, it is not described in detail.
[0089] Optional, such as Figure 6As shown, when E, D, G, H, J, I, K, L, and O are connected, the data transmission path of the transmitting probe F-receiving probe P can be obtained. When the network telemetry task is to detect FP, the constructed data transmission path can be used. However, EDGHJIKLO in the data transmission path of the transmitting probe F-receiving probe P is not the best path. Therefore, the data transmission path needs to be optimized. The network telemetry task refers to testing the network performance of the data transmission path when data packets are transmitted between the transmitting probe and the receiving probe.
[0090] Optionally, the method further includes:
[0091] According to the transmitting probe, the receiving probe, each task node and each link, all first connected subgraphs between the transmitting probe and the receiving probe are determined, where the first connected subgraph is a path graph formed by the task nodes and links through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0092] According to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link, all second connected subgraphs between the transmitting probe and the receiving probe are determined, where the second connected subgraph is a path graph formed by the first target node, the first target link and the second target link through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0093] Determining a data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link, and each second target link includes:
[0094] A data transmission path between the transmitting probe and the receiving probe is determined according to each of the first connected subgraphs and each of the second connected subgraphs.
[0095] Optional, such as Figure 5 As shown, the data transmission path of the transmitting probe F-receiving probe P includes FEDHIKLOP and FEDIKLOP, so FEDHIKLOP and FEDIKLOP need to be used as the second connected subgraph to determine the optimal data transmission path.
[0096] Optionally, without constructing a new data transmission path, the DFS algorithm is used to obtain the shortest data transmission path between the transmitting probe and the receiving probe, that is, the first sub-connected graph. At this time, the first sub-connected graph may contain the second connected sub-graph, or may not contain the second connected sub-graph. Therefore, it is necessary to obtain the overlap rate between each first sub-connected graph and each second sub-connected graph. For example, the overlap rate between the shortest first sub-connected sub-graph and FEDIKLOP is the highest, and FEDIKLOP is used as the best data transmission path. Based on this, the method also includes:
[0097] According to each first connected subgraph and each second connected subgraph, determining an overlap rate between each first connected subgraph and each second connected subgraph, wherein the overlap rate is a degree of overlap between the first connected subgraph and the second connected subgraph on a path;
[0098] Determining a data transmission path between a transmitting probe and a receiving probe according to each of the first connected subgraphs and each of the second connected subgraphs includes:
[0099] According to each overlap rate, the data transmission path between the transmitting probe and the receiving probe is determined.
[0100] Optionally, although the optimal data transmission path can be determined by the overlap rate, the overlap rate does not take into account the transmission delay time of the link. Based on this, the method further includes:
[0101] Determine, according to each second connected subgraph, a second transmission delay time corresponding to each second connected subgraph, where the second transmission delay time is a delay time required for a data packet to be transmitted from a transmitting probe to a receiving probe through the second connected subgraph;
[0102] Determining a data transmission path between a transmitting probe and a receiving probe according to each of the first connected subgraphs and each of the second connected subgraphs includes:
[0103] A data transmission path between the transmitting probe and the receiving probe is determined according to each overlap rate and each second transmission delay time.
[0104] Optional, such as Figure 5 As shown, the second transmission delay time of FEDHIKLOP is 30, and the second transmission delay time of FEDIKLOP is 26. Therefore, FEDIKLOP not only has the highest overlap rate with the shortest first sub-connected subgraph, but also has the shortest second transmission delay time. Therefore, FEDIKLOP is used as the best data transmission path between the transmitting probe and the receiving probe.
[0105] Optionally, a hybrid in-band network telemetry task transmission method is used in a network telemetry task experiment with a single active INT method or a single passive INT method, and the following is obtained: Figure 6-Figure 7 The results shown, such as Figure 6 As shown in the figure, number of experiments indicates the number of experiments, telemetry coverage ratio indicates the coverage ratio, Proactive INT indicates active INT, Passive INT indicates passive INT, Hawkeys indicates a hybrid in-band network telemetry task transmission method. Figure 6 It can be seen that the passive INT coverage is low, but the present invention can achieve 100% telemetry coverage (full link coverage) every time just like the active INT.
[0106] Another example Figure 7 As shown in the figure, Passive INT coverage ratio represents the passive INT coverage ratio, Bandwldthcost reduction ratio represents the broadband cost reduction ratio, and Avg represents the average bandwidth optimization cost. Figure 7 It can be seen that compared with active INT, the present invention can bring stable bandwidth overhead optimization on the basis of achieving 100% telemetry coverage, and the highest can even reach 88%, while the average bandwidth optimization overhead is only 55.2%.
[0107] like Figure 8 As shown, a hybrid in-band network telemetry task transmission system according to an embodiment of the present invention includes:
[0108] The link topology map acquisition module 201 is used for a link topology map including multiple probes, multiple task nodes between any two probes, one link between the probes and the task nodes, and one link between every two task nodes. For each link, the link is used to transmit a data packet, and each link corresponds to a transmission delay time when transmitting a data packet;
[0109] A first acquisition module 202 is used to determine a plurality of first target nodes and a first target link corresponding to each first target node from each task node, wherein the first target node is a task node included in a historical communication task, and the first target link is a link used to transmit data packets in the historical communication task;
[0110] The second target link acquisition module 203 is used to take any first target node as the first current node. If the first current node cannot connect to other first target nodes except itself, the second target link is determined from the links according to each first target node and each link. The second target link is the missing link when the first current node cannot connect to other first target nodes except itself.
[0111] The probe acquisition module 204 is used to determine a transmitting probe and a receiving probe according to the network telemetry task, wherein the transmitting probe is a probe for transmitting data packets and the receiving probe is a probe for receiving data packets;
[0112] The transmission path acquisition module 205 is used to determine the data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link and each second target link.
[0113] Optionally, the system further includes:
[0114] A second current node acquisition module, used to take any first target node as a second current node;
[0115] A second target node acquisition module, used to take each first target node connected to the second current node and the second current node as the second target node;
[0116] A task node set acquisition module, used to take each second target node as a task node set;
[0117] A judgment module, used to take any first target node except the second target node as the second current node, and repeat the corresponding processing of the second target node acquisition module, the task node set acquisition module and the judgment module until all the first target nodes are included in each task node set;
[0118] Then the second target link acquisition module 203 is further used for:
[0119] Any first target node is used as the first current node. If the first current node cannot connect to all first target nodes except itself, a second target link is determined from the links according to each task node set.
[0120] Optionally, the second target link acquisition module 203 further includes:
[0121] A second acquisition module, used to take each task node set as a first task node set, and take each task node set except the first task node set as a second task node set;
[0122] A first transmission delay time acquisition module is used to obtain, for each second target node in the first task node set, a first transmission delay time corresponding to the second target node and each second target node in the second task node set, wherein the first transmission delay time is a delay time required for a data packet to be transmitted from the second target node to a second target node specified in the second task node set;
[0123] The third acquisition module is used to determine the second target link corresponding to each task node set according to each first transmission delay time and each second target node.
[0124] Optionally, the third acquisition module is further used for:
[0125] The first transmission delay time with the shortest duration among the first transmission delay times is used as the first target transmission delay time, and the link between the two second target nodes corresponding to the first target transmission delay time is selected as the second target link corresponding to each task node set.
[0126] Optionally, the method further includes:
[0127] A first sub-connectivity graph acquisition module is used to determine all first connectivity sub-graphs between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each task node and each link, wherein the first connectivity sub-graph is a path graph formed by the task nodes and links through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0128] A second sub-connectivity graph acquisition module is used to determine all second connectivity sub-graphs between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each first target node, each first target link, and each second target link, wherein the second connectivity sub-graph is a path graph formed by the first target node, the first target link, and the second target link through which the data packet is transmitted from the transmitting probe to the receiving probe;
[0129] The transmission path acquisition module 205 is further used for:
[0130] A data transmission path between the transmitting probe and the receiving probe is determined according to each of the first connected subgraphs and each of the second connected subgraphs.
[0131] Optionally, the method further includes:
[0132] An overlap rate acquisition module is used to determine the overlap rate of each first connected subgraph and each second connected subgraph according to each first connected subgraph and each second connected subgraph, wherein the overlap rate is the overlap degree of the first connected subgraph and the second connected subgraph on the path;
[0133] The transmission path acquisition module 205 is further used for:
[0134] According to each overlap rate, the data transmission path between the transmitting probe and the receiving probe is determined.
[0135] Optionally, the method further includes:
[0136] A second transmission delay time acquisition module, used to determine the second transmission delay time corresponding to each second connected subgraph according to each second connected subgraph, the second transmission delay time being the delay time required for the data packet to be transmitted from the transmitting probe to the receiving probe through the second connected subgraph;
[0137] The transmission path acquisition module 205 is further used for:
[0138] A data transmission path between the transmitting probe and the receiving probe is determined according to each overlap rate and each second transmission delay time.
[0139] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.
[0140] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0141] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A hybrid in-band network telemetry task transmission method, characterized in that: The method comprises the following steps: Obtain a link topology diagram, wherein the link topology diagram includes a plurality of probes, a plurality of task nodes are included between any two of the probes, a link corresponds to a link between the probes and the task nodes, and a link corresponds to a link between every two of the task nodes, and for each of the links, the link is used to transmit a data packet, and each of the links corresponds to a transmission delay time when transmitting a data packet; According to the historical communication task, determining a plurality of first target nodes from each of the task nodes, and a first target link corresponding to each of the first target nodes, wherein the first target node is a task node included in the historical communication task, and the first target link is a link used to transmit the data packet in the historical communication task; Taking any one of the first target nodes as the first current node, if the first current node cannot connect to other first target nodes other than itself through the corresponding first target link, determining a second target link from the links according to each of the first target nodes and each of the links, where the second target link is a missing link when the first current node cannot connect to other first target nodes other than itself; According to the network telemetry task, a transmitting probe and a receiving probe are determined, wherein the transmitting probe is a probe for transmitting data packets, and the receiving probe is a probe for receiving data packets; A data transmission path between the transmitting probe and the receiving probe is determined according to the transmitting probe, the receiving probe, each of the first target nodes, each of the first target links, and each of the second target links.
2. The method according to claim 1, characterized in that Also includes: S12, taking any one of the first target nodes as a second current node; S13, taking each of the first target nodes connected to the second current node and the second current node as second target nodes; S14, taking each of the second target nodes as a task node set; S15, taking any one of the first target nodes except the second target node as the second current node, and repeating S13-S15 until all the first target nodes are included in each task node set; The taking any one of the first target nodes as the first current node, and if the first current node cannot connect to all the first target nodes except itself through the corresponding first target link, determining a second target link from the links according to each of the first target nodes and each of the links, includes: Any one of the first target nodes is used as the first current node. If the first current node cannot connect to all the first target nodes except itself, a second target link is determined from the links according to each of the task node sets.
3. The method according to claim 2, characterized in that The step of determining, from the links, a second target link corresponding to each of the task node sets according to each of the task node sets comprises: Taking each of the task node sets as a first task node set, and taking each of the task node sets except the first task node set as a second task node set; For each of the second target nodes in the first task node set, obtaining a first transmission delay time corresponding to the second target node and each of the second target nodes in the second task node set, wherein the first transmission delay time is a delay time required for the data packet to be transmitted from the second target node in the first task node set to the second target node specified in the second task node set; The second target link corresponding to each of the task node sets is determined according to each of the first transmission delay times and each of the second target nodes.
4. The method according to claim 3, characterized in that The determining, according to each of the first transmission delay times and each of the second target nodes, the second target link corresponding to each of the task node sets comprises: The first transmission delay time with the shortest duration among the first transmission delay times is used as the first target transmission delay time, and the link between the two second target nodes corresponding to the first target transmission delay time is selected as the second target link corresponding to each of the task node sets.
5. The method according to any one of claims 1 to 4, characterized in that: Also includes: According to the transmitting probe, the receiving probe, each of the task nodes and each of the links, all first connected subgraphs between the transmitting probe and the receiving probe are determined, wherein the first connected subgraph is a path graph formed by the task nodes and links through which the data packet is transmitted from the transmitting probe to the receiving probe; According to the transmitting probe, the receiving probe, each of the first target nodes, each of the first target links, and each of the second target links, all second connected subgraphs between the transmitting probe and the receiving probe are determined, where the second connected subgraph is a path graph formed by the first target node, the first target link, and the second target link through which the data packet is transmitted from the transmitting probe to the receiving probe; Determining a data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each of the first target nodes, each of the first target links, and each of the second target links includes: A data transmission path between the transmitting probe and the receiving probe is determined according to each of the first connected subgraphs and each of the second connected subgraphs.
6. The method according to claim 5, characterized in that Also includes: Determine, according to each of the first connected subgraphs and each of the second connected subgraphs, an overlap rate between each of the first connected subgraphs and each of the second connected subgraphs, wherein the overlap rate is a degree of overlap between the first connected subgraph and the second connected subgraph on a path; The determining, according to each of the first connected subgraphs and each of the second connected subgraphs, a data transmission path between the transmitting probe and the receiving probe comprises: A data transmission path between the transmitting probe and the receiving probe is determined according to each of the overlap rates.
7. The method according to claim 6, characterized in that Also includes: Determine, according to each of the second connected subgraphs, a second transmission delay time corresponding to each of the second connected subgraphs, wherein the second transmission delay time is a delay time required for the data packet to be transmitted from the transmitting probe to the receiving probe through the second connected subgraph; The determining, according to each of the first connected subgraphs and each of the second connected subgraphs, a data transmission path between the transmitting probe and the receiving probe comprises: A data transmission path between the transmitting probe and the receiving probe is determined according to each of the overlapping rates and each of the second transmission delay times.
8. A hybrid in-band network telemetry task transmission system, characterized in that: include: A link topology map acquisition module, used for the link topology map including multiple probes, multiple task nodes between any two of the probes, one link between the probes and the task nodes, and one link between every two of the task nodes, for each of the links, the link is used to transmit data packets, and each of the links corresponds to a transmission delay time when transmitting data packets; A first acquisition module, used to determine, from each of the task nodes according to a historical communication task, a plurality of first target nodes and a first target link corresponding to each of the first target nodes, wherein the first target node is a task node included in the historical communication task, and the first target link is a link used to transmit the data packet in the historical communication task; A second target link acquisition module, configured to take any one of the first target nodes as a first current node, and if the first current node cannot connect to other first target nodes other than itself through the corresponding first target link, determine a second target link from the links according to each of the first target nodes and each of the links, the second target link being a missing link that the first current node cannot connect to other first target nodes other than itself; A probe acquisition module is used to determine a transmitting probe and a receiving probe according to a network telemetry task, wherein the transmitting probe is a probe for transmitting data packets, and the receiving probe is a probe for receiving data packets; A transmission path acquisition module is used to determine the data transmission path between the transmitting probe and the receiving probe according to the transmitting probe, the receiving probe, each of the first target nodes, each of the first target links and each of the second target links.
9. An electronic device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a hybrid in-band network telemetry task transmission method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on the terminal device, the terminal device executes the steps of a hybrid in-band network telemetry task transmission method as described in any one of claims 1 to 7.
