Data processing method and apparatus, and nonvolatile storage medium

Abstract

The application discloses a data processing method and device and a nonvolatile storage medium. The method comprises the following steps: collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a special network; in the plurality of network data packets, the data amount transmitted by each application program under the same source IP address within a preset time range is counted; the application priority information and the application load information of each application program under the same source IP address are acquired, and the application score of the application program is determined; the load index of the network node at a target moment is acquired, and in the case that the load index is greater than a preset threshold, the target traffic corresponding to a target application program under a target source IP address forwarded by the network node is subjected to shunt processing. The application solves the technical problem that, due to the lack of effective node load monitoring mechanism and dynamic routing adjustment strategy, the route of data request of each access unit forwarded to the exclusive cloud is not reasonable and low in efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cloud network operation, in particular, to a data processing method and device, and a nonvolatile storage medium. BACKGROUND

[0002] With the cloud network integration technology and the rapid development of modern industries, operators establish special networks for various industries and build dedicated clouds on the basis of the special networks to deploy various industry applications and serve various levels. By deploying various industry applications on the dedicated cloud, various aspects such as production management, business process optimization, and intelligent monitoring can be covered.

[0003] In the special network of various industries, for example, the special network of the education industry: kindergartens, primary schools, middle schools, and educational institutions will access the network through the access layer network, connect to the education dedicated cloud through the aggregation and core network, and realize global network access, financial management, electronic patrol examination, video monitoring, and chemical examination application scenarios. In actual business scenarios, the load of data request forwarding of the nodes of the above units to the dedicated cloud is dynamically changed in different use time periods. How to monitor the node load and dynamically adjust the routing strategy to make the route of data request forwarding of each access unit to the dedicated cloud more reasonable and efficient is a problem to be solved.

[0004] At present, no effective solution has been proposed for the above problems. SUMMARY

[0005] The present application provides a data processing method and device, and a nonvolatile storage medium to at least solve the technical problem of unreasonable and inefficient route of data request forwarding of each access unit to the dedicated cloud due to the lack of effective node load monitoring mechanism and dynamic routing adjustment strategy.

[0006] According to an aspect of the present application, a data processing method is provided, comprising: collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet comprises at least a source IP address and a target IP address; in the plurality of network data packets, counting a data volume sent by a same source IP address within a preset time range, and counting a data volume sent by each application program under the same source IP address within the preset time range; obtaining application priority information and application load information of each application program under the same source IP address, and determining an application score of each application program according to the application priority information and the application load information of each application program; obtaining a load index of the network nodes at a target time, and in a case where the load index is greater than a preset threshold, performing shunt processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network nodes, wherein a difference between the target time and an end time in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data volume sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data volume sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0007] Optionally, the shunt processing on the target traffic corresponding to the target application program under the target source IP address forwarded by the network nodes comprises: obtaining network topology information corresponding to the cloud platform of the private network, wherein the network topology information comprises connection relationships between the network nodes and real-time state information of links between the network nodes, and the real-time state information at least comprises link bandwidth, delay, and packet loss rate; determining a plurality of candidate links from the network node whose load index is greater than the preset threshold to other network nodes based on the network topology information; for each candidate link, performing weighted summation on the link bandwidth, the delay, and the packet loss rate therein to obtain a target length of each candidate link; obtaining load indexes of the other network nodes, and determining a node set composed of nodes whose load indexes are less than a fifth preset threshold among the other network nodes, wherein the load index is determined at least according to CPU usage and memory occupancy of the network nodes; in the node set, determining a first network node with the shortest target length, and sending the target traffic to the first network node to forward the target traffic through the first network node.

[0008] Optionally, the method further comprises: if there are multiple second network nodes with the shortest target length in the set of nodes, calculating a reliability index of each second network node according to an availability index of the second network node, an average time interval between two adjacent failures of the second network node, and an average time required by the second network node from failure to recovery, wherein the availability index is determined by total running time, failure downtime, and total running time; determining a third network node with the largest reliability index among the multiple second network nodes, and sending the target traffic to the third network node for forwarding the target traffic by the third network node.

[0009] Optionally, after obtaining the network topology information corresponding to the cloud platform of the private network, the method further comprises: encapsulating the real-time state information in a standardized format based on the Telemetry protocol, wherein the standardized format adopts a predefined JSON or binary encoding structure; transmitting the encapsulation result to the central management server through a secure encryption channel, wherein the secure encryption channel adopts a Secure Sockets Layer or a Transport Layer Security protocol; presenting the link bandwidth, delay, and packet loss rate in the encapsulation result in the form of a visual curve by the central management server; obtaining a performance threshold, and triggering an alarm when any index in the encapsulation result exceeds the performance threshold, wherein the performance threshold is dynamically adjusted based on the network service level agreement and historical state information of the network nodes.

[0010] Optionally, the method further comprises: in a case where the load index is less than the preset threshold and a difference between the load index and the preset threshold is less than a fifth preset threshold, sending early warning information to the management object of the private network.

[0011] Optionally, the application priority information and the application load information of each application program under the same source IP address are obtained by: obtaining an application load model table, wherein the application load model table includes application name information, application description information, application priority information, application address information, application port number information, application state information, and application load information; and screening the application priority information and the application load information of each application program under the same source IP address in the application load model table.

[0012] Optionally, the multiple network data packets forwarded by the multiple network nodes in the cloud platform of the private network are collected by: enabling a target protocol in a target node connected to the cloud platform of the private network in the public network to collect the multiple network data packets forwarded by the multiple network nodes in the cloud platform of the private network, wherein the target protocol includes the Telemetry protocol.

[0013] According to still another aspect of the present application, a data processing apparatus is also provided, comprising: a collecting module configured to collect a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet comprises at least a source IP address and a target IP address; a counting module configured to count, among the plurality of network data packets, a data volume sent by a same source IP address within a preset time range and count a data volume sent by each application program under the same source IP address within the preset time range; a determining module configured to obtain application priority information and application load information of each application program under the same source IP address, and determine an application score of each application program according to the application priority information and the application load information of each application program; and a processing module configured to obtain a load index of the network node at a target time, and perform traffic splitting processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node in a case where the load index is greater than a preset threshold, wherein a difference between the target time and an end time in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data volume sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data volume sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0014] According to still another aspect of the present application, a non-volatile storage medium is also provided, comprising a stored program, wherein the program, when executed, controls a device in which the storage medium is located to perform the above data processing method.

[0015] According to still another aspect of the present application, an electronic device is also provided, comprising a memory and a processor, wherein the processor is configured to execute a program stored in the memory, and the program, when executed, performs the above data processing method.

[0016] According to still another aspect of the present application, a computer program is also provided, wherein the computer program, when executed by a processor, implements the above data processing method.

[0017] According to still another aspect of the present application, a computer program product is also provided, comprising a non-volatile computer readable storage medium, wherein the non-volatile computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the above data processing method.

[0018] In the present application, a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a special collection network are adopted, wherein each network data packet at least includes a source IP address and a target IP address; in the plurality of network data packets, the data amount transmitted by the same source IP address within a preset time range is counted, and the data amount transmitted by each application program under the same source IP address within the preset time range is counted; the application priority information and the application load information of each application program under the same source IP address are acquired, and the application score of the application program is determined according to the application priority information and the application load information of each application program; the load index of the network node at a target moment is acquired, and in the case that the load index is greater than a preset threshold, the target traffic corresponding to the target application program under the target source IP address forwarded by the network node is shunted, wherein the difference between the target moment and the end moment in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data amount transmitted within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data amount transmitted within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold, so as to achieve the purpose of effectively monitoring the node load and dynamically adjusting the routing strategy, thereby realizing the technical effect that the route of the data request of each access unit forwarded to the exclusive cloud is more reasonable and efficient, and further solving the technical problems that the route of the data request of each access unit forwarded to the exclusive cloud is not reasonable and efficient due to the lack of effective node load monitoring mechanism and dynamic routing adjustment strategy. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate certain illustrative embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0020] Figure 1 is a flowchart of a data processing method according to an embodiment of the present application;

[0021] Figure 2 is a structural diagram of a data processing system according to an embodiment of the present application;

[0022] Figure 3 is a flowchart of another data processing method according to an embodiment of the present application;

[0023] Figure 4 is a structural diagram of a data processing device according to an embodiment of the present application;

[0024] Figure 5 is a hardware structural block diagram of a computer terminal of a data processing method according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the person skilled in the art better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should be within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] In the related art, the load of a single node of a fixed forwarding node is too large, and part of the nodes are idle, so there are problems such as uneven distribution of data forwarding, inability to add a monitoring system on a customer cloud, and insufficient network elasticity. In order to solve this problem, the related solutions are provided in the embodiments of the present application, which will be described in detail below.

[0028] According to the embodiments of the present application, a method embodiment of a data processing method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0029] Figure 1 is a flowchart of a data processing method according to the embodiments of the present application, as shown in Figure 1 The method comprises the following steps:

[0030] Step S102, collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a special network, wherein each network data packet at least includes a source IP address and a target IP address.

[0031] In step S102, in the private network of the cloud platform, the network data packets forwarded by the network nodes are collected in real time by a Telemetry module integrated with a software-defined network (SDN) controller. The data packet collection includes but is not limited to source IP address, target IP address, source port number, target port number, and data packet byte number, etc. The Telemetry module is configured in a high-precision and low-delay data collection mode to ensure that the collected data packet information can accurately reflect the network state.

[0032] In step S104, the data amount transmitted by the same source IP address within a preset time range is counted in a plurality of network data packets, and the data amount transmitted by each application program under the same source IP address within a preset time range is counted.

[0033] Specifically, the network data packets are classified according to the source IP address, and the total data amount transmitted by each source IP address within a preset time range (for example, the last 5 minutes, 1 hour, etc.) is counted. Then, in combination with the application load model table, the application programs under each source IP address are determined, and the data amount transmitted by each application program within the same preset time range is further counted. This process can be accelerated by establishing a hash table or database index for query and statistics.

[0034] In step S106, the application priority information and the application load information of each application program under the same source IP address are obtained, and the application score of each application program is determined according to the application priority information and the application load information of each application program.

[0035] In step S106, the priority information and the load information of each application program are obtained from the application load model table. Specifically, the application priority information (AppPriority) and the application load information (AppLevel) are used to calculate the application score (AppScore) of the application program. The calculation method of the application score can be the weighted average of the application priority and the application load, or the application priority multiplied by the application load level. The calculation result of the application score will be used for subsequent traffic adjustment strategy.

[0036] In step S108, the load index of the network node at the target time is obtained, and in the case that the load index is greater than a preset threshold, the target traffic corresponding to the target application program under the target source IP address forwarded by the network node is shunted, wherein the difference between the target time and the end time in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data amount transmitted within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data amount transmitted within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0037] In step S108, the load index of each network node is obtained at a target time (e.g., the current time point). If the load index of any node exceeds a preset threshold, a traffic diversion strategy is triggered. The triggering condition of this strategy can also be: the difference between the target time and the end time of the preset time range is less than a first preset threshold (e.g., 1 minute), which indicates that the traffic analysis is based on the most recent data.

[0038] It should be noted that the target source IP address is the source IP address that sends data volumes greater than a second preset threshold (e.g., 1GB) within a preset timeframe. The target application is the application that sends data volumes greater than a third preset threshold (e.g., 100MB) and has an application score less than a fourth preset threshold (e.g., below average) within the target source IP address. Once the target traffic is determined, the SDN controller sends instructions to the network, automatically shifting traffic from high-load nodes to lower-load nodes for dynamic balancing.

[0039] According to the above steps, a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a collection dedicated network are used, wherein each network data packet includes at least: a source IP address and a destination IP address; in the plurality of network data packets, the amount of data sent by the same source IP address within a preset time range is counted, and the amount of data sent by each application under the same source IP address within a preset time range is counted; application priority information and application load information of each application under the same source IP address are obtained, and application score of the application is determined according to the application priority information and application load information of each application; the load index of the network node at the target time is obtained, and when the load index is greater than Under the preset threshold, the target traffic corresponding to the target application under the target source IP address forwarded by the network node is diverted, wherein the difference between the target time and the end time in the preset time range is less than the first preset threshold, the target source IP address is the source IP address whose data volume sent within the preset time range is greater than the second preset threshold, and the target application is the application in the target source IP address whose data volume sent within the preset time range is greater than the third preset threshold and whose application score is less than the fourth preset threshold. This achieves the purpose of effectively monitoring the node load and dynamically adjusting the routing strategy, thereby realizing a more reasonable and efficient technical effect of forwarding the data requests of each access unit to the dedicated cloud.

[0040] The following Figure 1 The steps shown are exemplified and explained.

[0041] According to some optional embodiments of the present application, the shunting processing of the target traffic corresponding to the target application under the target source IP address forwarded by the network node can be achieved by the following steps: obtaining network topology information corresponding to a cloud platform of a private network, wherein the network topology information includes connection relationships between network nodes and real-time state information of links between the network nodes, and the real-time state information at least includes link bandwidth, delay and packet loss rate; determining a plurality of candidate links from a network node with a load index greater than a preset threshold to other network nodes based on the network topology information; for each candidate link, performing weighted summation on the link bandwidth, delay and packet loss rate therein to obtain a target length of each candidate link; obtaining load indexes of the other network nodes, and determining a node set composed of nodes with load indexes less than a fifth preset threshold among the other network nodes, wherein the load index is determined at least according to CPU usage and memory occupancy of the network node; determining a first network node with the shortest target length in the node set, and sending the target traffic to the first network node to forward the target traffic through the first network node.

[0042] In the above embodiments, first, the network topology information in the cloud platform of the private network is obtained in real time by using the topology discovery function of the SDN controller. The topology information includes the connection relationships between the network nodes and the real-time state of the links, such as link bandwidth, delay and packet loss rate. The Telemetry protocol is started on each network node to collect node performance indicators (such as CPU usage and memory occupancy) and link state information, which are uploaded to the SDN controller in real time for updating the real-time state of the network topology information. The SDN controller processes the collected network state data to establish and maintain a dynamically updated network topology database, which records the link state and node load information.

[0043] Then, the load indicators of each network node are continuously monitored, and once it is found that the load indicators (such as CPU usage and memory occupancy) of a certain node exceed the preset threshold (Threshold), the node is marked as a high-load node. Starting from the high-load node, the network topology information of the SDN controller is used to calculate all possible paths to all other network nodes. In this process, the shortest path algorithm such as Dijkstra algorithm or Bellman-Ford algorithm is adopted, while considering the real-time information of the link state. According to the calculated paths, multiple candidate links from the network node with load indicators greater than the preset threshold to other network nodes are determined, and the real-time state information of each candidate link is recorded, including link bandwidth, delay and packet loss rate. The weight factors of link bandwidth, delay and packet loss rate are set, and for each candidate link, its target length is calculated, wherein the bandwidth, delay and packet loss rate are quantitatively processed according to their real-time state information and converted into comparable numerical values. According to the calculated target length, the comprehensive performance of each candidate link is evaluated, and the smaller the target length, the better the comprehensive performance of the link.

[0044] Finally, based on the real-time data collected by the Telemetry protocol, the load indicators of all network nodes are obtained. Specifically, a fifth preset threshold of node load (such as CPU usage less than 60% and memory occupancy less than 50%) is set, and network nodes with load indicators lower than the threshold are screened out to form a set of low-load nodes. The target lengths of the candidate links between all low-load nodes and high-load nodes are compared, and the first network node connected by the link with the shortest target length is determined. The SDN controller sends a redirection instruction to the network to reconfigure the target traffic (i.e., the application traffic that needs to be offloaded on the high-load node) to be forwarded through the first network node with the shortest target length.

[0045] Through the above steps, the SDN technology and the Telemetry protocol are used to dynamically adjust the traffic in the private network, to realize the reasonable allocation and optimization of network resources, especially when dealing with high-load nodes, by comprehensively evaluating the low-load nodes and link states, the optimal traffic forwarding path is intelligently selected.

[0046] Preferably, if there are multiple second network nodes with the shortest target length in the node set, the following steps can also be performed:

[0047] The reliability index of each second network node is calculated according to the availability index of the second network node, the average time interval between adjacent failures of the second network node, and the average time required for the second network node to recover from failure to normal operation, wherein the availability index is determined by the total running time, the failure downtime, and the total running time; among the plurality of second network nodes, a third network node with the maximum reliability index is determined, and the target traffic is sent to the third network node for forwarding by the third network node.

[0048] In the above embodiment, the reliability index of each second network node is calculated according to the availability index of the second network node, the average time interval between adjacent failures of the second network node, and the average time required for the second network node to recover from failure to normal operation. First, the availability index is calculated, and the total running time and the failure downtime are recorded, wherein the total running time is the continuous running time of each network node since the last restart, and the failure downtime is the total failure downtime of each network node in the recent period of time. For example, if the total running time of a network node is 8760 hours (one year) and the failure downtime is 1 hour, then its availability index is: (8760-1) / 8760=0.999897. Then the average value of the time interval between adjacent failures of the second network node is calculated, and the average value of the time required for the second network node to recover from failure to completely normal operation is calculated, which reflects the failure recovery capability of the network node. According to the availability index, the failure interval, and the failure recovery time, the reliability index of each second network node can be calculated.

[0049] Then the reliability indexes of all second network nodes are compared, and the node with the highest reliability index is found as the third network node. This node is considered to be the most stable and reliable, and can provide high-quality data forwarding service. Once the third network node is determined, a redirection instruction is sent to the network through the SDN controller, and the instruction content includes the identification of the target traffic (such as source IP address and port number) and the identification of the third network node (such as node ID or IP address), which requires the target traffic to be routed to the third network node. After the SDN controller receives the instruction, it adjusts the network forwarding strategy to ensure that the target traffic is forwarded through the third network node. At the same time, the running state and performance indicators of the third network node, such as link bandwidth, delay, and packet loss rate, are continuously monitored to evaluate the effect of traffic adjustment and respond to any abnormalities in time.

[0050] Through the above implementation, the most suitable node for traffic forwarding can be intelligently selected according to the reliability indexes of multiple network nodes, ensuring efficient use of network resources and smooth operation of services. This dynamic traffic adjustment mechanism based on reliability and performance is crucial for improving the performance, stability, and security of the dedicated network of the cloud platform.

[0051] In some optional embodiments of the present application, after obtaining the network topology information corresponding to the cloud platform of the private network, the method further includes the following steps: encapsulating the real-time state information in a standardized format based on the Telemetry protocol, wherein the standardized format adopts a predefined JSON or binary encoding structure; transmitting the encapsulation result to the central management server through a secure encrypted channel, wherein the secure encrypted channel adopts a Secure Sockets Layer or a Transport Layer Security protocol; the central management server receives the encapsulation result and presents the link bandwidth, delay, and packet loss rate in the form of a visual curve; and obtaining a performance threshold, and triggering an alarm when any index in the encapsulation result exceeds the performance threshold, wherein the performance threshold is dynamically adjusted based on the network service level agreement and historical state information of the network nodes.

[0052] In the above embodiments, a standardized data format is first designed, and JSON (JavaScript Object Notation) or binary encoding (such as Protobuf) is used as the structure of data encapsulation. Specifically, JSON is easy to read and write, and is suitable for human-computer interaction, while binary encoding is more compact and is suitable for machine-to-machine communication, improving transmission efficiency. At the same time, necessary fields are defined in the standardized format, including link bandwidth, delay, packet loss rate, CPU usage, memory occupancy, and other performance indicators of network nodes, as well as timestamp, source node ID, target node ID, and other metadata fields, to ensure the integrity and accuracy of the data. Using the Telemetry protocol, real-time performance data is collected and encapsulated, and encoded according to the predefined standardized format. It should be noted that data encapsulation should consider the efficiency and security of network transmission, avoid unnecessary data redundancy, and ensure the real-time and security of data. The encapsulated data is transmitted to the central management server through a secure encrypted channel. During transmission, the availability of the monitoring channel and the integrity of data transmission are ensured to ensure that the data can reach the central management server in a timely and accurate manner.

[0053] After the central management server receives the encapsulated data, it uses the corresponding parser (such as JSON parser, binary decoder) to parse the data from the standardized format, and extracts the link bandwidth, delay, packet loss rate, and other key performance indicators. Then the parsed performance indicator data is processed, such as outlier detection, data smoothing, etc., to improve the accuracy and reliability of the data. And using data visualization tools (such as Grafana, Kibana, etc.), the link bandwidth, delay, packet loss rate, and other performance indicators are presented in the form of a curve chart, which can intuitively understand the real-time changes and historical trends of network performance.

[0054] Finally, set the threshold values of link bandwidth, delay, packet loss rate and other performance indicators, which are dynamically adjusted according to the requirements of the network service level agreement (SLA) and the historical state information of the network nodes to adapt to the real-time changes of the network and the business requirements. By analyzing the historical state information of the network nodes, such as long-term peak usage rate, average bandwidth consumption, seasonal changes of delay, etc., a threshold adjustment model is established. The model can be based on machine learning algorithms such as time series analysis, anomaly detection, etc. to predict and adjust the performance thresholds. Real-time monitoring data, when any performance indicator (such as link bandwidth, delay or packet loss rate) exceeds its corresponding dynamically adjusted performance threshold, the central control server should immediately trigger an alarm. The alarm can be notified to the operation and maintenance personnel in the form of email, SMS or internal system message, and the abnormal link or node is marked with a prominent color or icon on the visual interface for quick positioning and response to problems.

[0055] Through the above implementation, the network performance can be monitored in real time, the data is transmitted through a secure channel, the network status is intuitively displayed using a visualization tool, and alarm triggering and processing are performed according to dynamically adjusted performance thresholds, thereby effectively guaranteeing the quality of network services, improving the fault response speed, and enhancing the stability and reliability of the network.

[0056] As some optional embodiments of the present application, the above data processing method further includes the following steps: in the case that the load indicator is less than the preset threshold value and the difference between the load indicator and the preset threshold value is less than the fifth preset threshold value, sending a warning information to the management object of the private network.

[0057] In the above embodiments, the SDN controller continuously monitors the load indicators of the network nodes, including but not limited to CPU usage, memory occupancy, disk I / O, etc. At the same time, a preset threshold (Threshold) is set for each network node as the upper limit of the normal operating range. The setting of the preset threshold needs to be optimized according to the actual operation of the network and historical data. When the load indicator of the network node is lower than the preset threshold, the difference between the load indicator and the preset threshold is further calculated. At the same time, a fifth preset threshold (Delta_Threshold) is set to determine whether the difference between the load indicator and the preset threshold is close to identify the potential low load situation. When the difference between the load indicator and the preset threshold is less than the fifth preset threshold, it is considered that the node has the risk of too low load, and the warning condition is triggered to generate warning information, including but not limited to the name of the node, the current load indicator, the preset threshold, the difference, etc. The warning information can be sent to the management object of the dedicated network in various ways, such as email, SMS, system message push, etc., to ensure the timeliness and reliability of the information. After receiving the warning information, the management object can take action according to the warning information and the recommended measures, such as manually adjusting resource allocation, optimizing network strategy or implementing automatic resource scheduling, to avoid resource waste and improve network efficiency.

[0058] Through the above implementation, the load state of the network node can be effectively monitored, not only when overloaded, but also when the load is too low and the resources are not fully utilized, the warning information is sent to the management object to help timely adjust the network strategy to ensure the effective use of resources and the efficiency of network operation. This warning mechanism is particularly important for the dedicated network of the cloud platform, which can help the operation and maintenance personnel make more reasonable decisions in resource management and allocation, reduce unnecessary resource waste, and improve the overall performance and stability of the system.

[0059] In some optional embodiments of the present application, the application priority information and the application load information of each application program under the same source IP address are obtained by the following steps: obtaining an application load model table, wherein the application load model table includes application name information, application description information, application priority information, application address information, application port number information, application state information, and application load information; and filtering the application priority information and the application load information of each application program under the same source IP address in the application load model table.

[0060] In the above embodiment, first, an application load model table is created, containing the following fields: application name information (AppName), application description information (AppDesc), application priority information (AppPriority), application address information (AppAddress), application port number information (AppPort), application state information (AppState), and application load information (AppLoad). These fields are used to store key information related to each application running on the cloud platform, including priority and load conditions. Then, the basic information of each application is entered into the application load model table, and the real-time state and load information of each application is updated regularly. Data updates can be event-driven, triggered immediately when the Telemetry protocol detects changes in application state or load, or periodic refresh, automatically updating data every certain time (such as 5 minutes or 15 minutes).

[0061] All applications with the same source IP address can be filtered from the application load model table using SQL queries or database query functions. The following SQL statement can be used:

[0062] SELECT AppName, AppPriority, AppLoad

[0063] FROM AppLoadModel

[0064] WHERE AppAddress ='specified source IP address';

[0065] Or use a more complex query, combining source port number information, to further refine the query results, such as:

[0066] SELECT AppName, AppPriority, AppLoad

[0067] FROM AppLoadModel

[0068] WHERE AppAddress ='specified source IP address' AND AppPort ='specified source port number'.

[0069] The application load model table can also be used to analyze node and application traffic usage and node load status, and based on application priority AP and application load level AL, the application score AP*AL = AppScore is derived, the applications are sorted, and the current traffic dynamic consumption of the data sending source is derived

[0070] For each application screened, further processing and analysis of its application priority information (AppPriority) and application load information (AppLoad) are performed. The application priority information reflects the importance of the application in business processing, while the application load information indicates the current resource consumption of the application. By comparing the priority and load of each application, it can be determined which applications may need more resource support, or which applications have a load that exceeds the resources allocated by their priority.

[0071] Through the above embodiments, the information in the application load model table can be effectively utilized to screen, score, sort and identify the applications under the same source IP address, providing a basis for decision-making for subsequent traffic adjustment and resource optimization, ensuring efficient use of network resources and smooth operation of business. This dynamic adjustment mechanism based on application priority and load is crucial for improving the performance and stability of the cloud platform's private network.

[0072] As another optional embodiment of the present application, collecting a plurality of network data packets forwarded by a plurality of network nodes in the cloud platform of the private network can be achieved by the following steps: the target node connected to the cloud platform of the private network in the public network enables a target protocol to collect a plurality of network data packets forwarded by a plurality of network nodes in the cloud platform of the private network, wherein the target protocol includes a Telemetry protocol.

[0073] In the above embodiment, first, install and configure the Telemetry protocol client on the target node, which can communicate with network devices in the cloud platform of the private network to collect real-time network packet information. Configure the collection frequency and data type of the Telemetry protocol, the collection frequency is high enough to reflect the network status in real time, but also consider the limitations of network bandwidth and device performance, the data type includes source IP address, target IP address, source port number, target port number, packet size, etc., to analyze network traffic and node load.

[0074] The target node starts collecting network data packets forwarded by a plurality of network nodes in the private network through the Telemetry protocol. The collection of data packets can be continuous, or dynamically adjusted according to network conditions and collection needs. The Telemetry protocol transmits the collected network packet information to the target node in real time. Encryption technology such as SSL / TLS is used in the transmission process to ensure data security and privacy protection. At the same time, in order to improve the efficiency and reliability of data transmission, streaming can be used to push data packet information to the target node in real time, avoiding the delay and potential data loss caused by batch transmission of a large amount of data.

[0075] After the target node receives the network packet information, it uses a dedicated data processing program for parsing and formatting. The parsed content includes key information such as the size of the packet, the IP addresses and port numbers of the source and target nodes. By analyzing the network packet information, the data packet forwarding volume of each dedicated network node is calculated. This helps to assess the load of the node and provides a basis for subsequent traffic adjustment and resource optimization. By analyzing the packet information, the target node can detect network anomalies and potential performance bottlenecks, providing support for rapid positioning and processing of network faults.

[0076] Specifically, the traffic alert threshold Threshold is set according to the load status of the node. When the threshold is exceeded, the shunting operation is automatically performed, that is, by analyzing the size of the data packets sent by each source IP address in combination with the current load status of the node, the appropriate sending source is selected, which ensures that the utilization rate of the current node is reasonable and the load of the node is normal.

[0077]

[0078] When the target node load is too large, the appropriate scheme is dynamically selected through the relationship between data flow and threshold, for example, when approaching the threshold, a warning message is sent to the operator to prompt the operator to control the traffic and reduce the convergence layer load in time. At this time, manual operation can be performed, and when the threshold is exceeded, the device will select the data sending source with large traffic consumption and low APPScore to perform shunting operation preferentially.

[0079] Through the above implementation, the target node in the public network can collect and analyze the network packet information in the cloud platform of the dedicated network in real time by enabling the Telemetry protocol, providing accurate data support for traffic monitoring and early warning and dynamic traffic adjustment. This real-time monitoring and dynamic adjustment mechanism based on the Telemetry protocol helps to improve the stability and efficiency of the network, while reducing the operation and maintenance cost, and is one of the key technologies for efficient operation of the cloud platform dedicated network.

[0080] Figure 2 is a structural diagram of a data processing system according to an embodiment of the present application, Figure 2The system architecture in the figure mainly includes the following parts: SAAS (Software as a Service) represents various application programs on the cloud platform, and users can access and use these application programs through the network. PAAS (Platform as a Service) represents the operating system, database. SAAS and PAAS provide underlying cloud resources through customer private clouds to support the operation of upper-layer services. Below, the node traffic monitoring and early warning and adjustment device and SDN (Software-Defined Networking) are the core. The node traffic monitoring and early warning and adjustment device is responsible for monitoring network traffic, analyzing node load, warning traffic anomalies, and dynamically adjusting data forwarding strategies. SDN is the core control layer of the network, which intelligently manages network resources through the instructions of the monitoring and early warning device, and realizes the optimal allocation of traffic. Data is transmitted from SDN to the destination through the core / bone network, and then aggregated through the aggregation layer, or distributed to each node from SDN. The hierarchical relationship of the entire system architecture and the interaction between components are shown.

[0081] The following will be combined with Figure 2 The data processing method is described, and the data processing method can also be realized through the following steps.

[0082] Step S201, waiting for the data packet sent by the receiving node, analyzing the data packet, monitoring and warning the traffic usage.

[0083] Specifically, the data packet receiving device needs to be powered on first. This device receives data (including source IP address, target IP address, source port number, target port number and data packet byte number), analyzes the data, and is the core device for monitoring and warning.

[0084] Step S202, connect the node of the customer private cloud to start the Telemetry protocol, monitor and record the performance indicators of the network equipment, such as bandwidth utilization, delay, packet loss rate, etc., and send the collected data to the traffic monitoring and early warning device for network analysis.

[0085] Specifically, the load node starts the Telemetry protocol to monitor network performance, troubleshoot and warn of faults, monitor security and detect threats, plan capacity and optimize resources, manage service quality, and visually monitor and report, etc., providing comprehensive, real-time and intelligent network management capabilities to help network administrators better manage and maintain the network.

[0086] Step S203, traffic monitoring and analysis.

[0087] The analysis method of the embodiment involved in step S203 is composed of the following five steps:

[0088] S2031, receiving data collected by the node starting Telemetry (including source IP address, target IP address, source port number, target port number and packet byte number).

[0089] S2032, according to the data format sent, the source IP address, target IP address, source port number, target port number and packet byte number of the packet are parsed out.

[0090] S2033, according to the parsed data, the size of the data packet sent by each source IP address is analyzed Where k is the number of packets, BW n is the byte number of the nth packet, and the packet size of each source IP address is sorted (IP1, IP2,..., IP i ), an application load model table is introduced, and the table is designed as follows: application name (AppName), application description (AppDesc), application priority (AppPriority), application address (AppAddress), application port number (AppPort), application state (AppState), application load level (AppLevel). The traffic analysis device analyzes the node and application traffic usage and node load state according to the above model table, obtains the application score AP*AL=AppScore according to the application priority AP and the application load level AL, sorts the applications, and obtains the current traffic dynamic consumption largest data sending source

[0091] S2034, according to the load status of the node, set the traffic alarm threshold, when approaching the threshold, send warning information to the operator, prompt the operator to control the traffic, and reduce the node load in time.

[0092] S2035, according to the load status of the node, set the traffic alarm threshold Threshold, when exceeding the threshold, then automatically perform shunt operation, that is, through a certain algorithm to analyze the size of the data packet sent by each source IP address combined with the current load status of the node, select the appropriate sending source, both ensure the reasonable use rate of the current node, and ensure the normal load of the node.

[0093]

[0094] Specifically, when the monitored node is overloaded, the appropriate solution is dynamically selected through the relationship between the data flow and the threshold value, for example, when approaching the threshold value, a warning message is sent to the operator to prompt the operator to control the flow and reduce the convergence layer load in time, which can be manually operated, when the threshold value is exceeded, the device will select the data sending source with larger flow consumption and lower APPScore to perform shunting operation according to the step S2033. Select and analyze, and push the data source value SDN that needs to change the forwarding route.

[0095] Step S204, adjusting the data forwarding route.

[0096] The instructions pushed by the flow monitoring and alarm device are received by the SDN, and the load conditions of multiple nodes are monitored by the SDN. The SDN sorts the nodes according to the load conditions (Load1, Load2,..., Load n ), and the data forwarding route is adjusted according to the minimum load and the shortest route

[0097] Figure 3 The flow chart of another data processing method according to an embodiment of the present application is shown in Figure 3 , and the method specifically includes the following steps.

[0098] Step S301, starting the data packet receiving device.

[0099] TrafficMonitoringMain.start(); / / System overall framework starts;

[0100] TMListener.start(); / / Receiver starts, receives data packets sent from nodes and other operations.

[0101] Step S302, starting the data analysis device.

[0102] Node.init(); / / Connect the node of the customer private cloud to start the Telemetry protocol, monitor and record the performance indicators of network equipment such as bandwidth utilization, delay, packet loss rate, etc.

[0103] Step S303, starting the flow monitoring and warning device, and analyzing the flow data.

[0104] The load conditions of each time period of the node are monitored and analyzed, and different solutions are set for different conditions.

[0105] The analysis method of the present embodiment involved in step S303 consists of the following five steps:

[0106] S3031, start the monitoring receiving device, receive the data collected by the node starting Telemetry (including source IP address, target IP address, source port number, target port number and packet byte number).

[0107] TMListener.start(); / / receiver start, receive data packets sent from the node and other operations.

[0108] S3032, start the data analysis device, according to the data format, parse the source IP address, target IP address, source port number, target port number and packet byte number of the data packet.

[0109] TM.init(); / / data analysis device, responsible for parsing the source IP address, target IP address, source port number, target port number and packet byte number of the data packet from the received data.

[0110] S3033, start the traffic analysis device, according to the parsed data, summarize and analyze the size of data packets sent by each source IP address , where k is the number of packets, BW n is the byte number of the nth packet, and the size of the data packet of each source IP address is sorted (IP1, IP2,..., IP i ), an application load model table is introduced, and the traffic analysis device analyzes the node and application traffic usage and node load state according to the model table, and according to the application priority AP and application load level AL, the application score AppScore is obtained, the application is sorted, and the current traffic dynamic consumption largest data sending source is obtained

[0111] TMAnalysis.start(); / / traffic analysis device starts, and the data packets of each source IP address are statistically analyzed and summarized.

[0112] S3034, start the traffic alarm device, set the traffic alarm threshold according to the load status of the node, when approaching the threshold, send warning information to the operator, prompt the operator to control the traffic and reduce the node load in time.

[0113] TMAlarm.start(); / / traffic alarm device starts, according to the set traffic alarm threshold, when the load approaches the alarm threshold, send warning information to the operator through email or other ways, prompt the operator to control the traffic and reduce the node load in time.

[0114] S3035, the automatic shunt device is started, the traffic alarm threshold is set according to the load condition of the node, when the threshold is exceeded, the automatic shunt operation is carried out, that is, the size of the data packet sent by each source IP address is analyzed by a certain algorithm, and the current load condition of the node is combined to select a suitable sending source, so that the utilization rate of the current node is reasonable, and the load of the node is normal.

[0115]

[0116] TMShunt.start(); / / Shunt device starts, according to the set traffic alarm threshold, when the load exceeds the alarm threshold, the automatic shunt operation is carried out.

[0117] Step S304, the shunt device is started, and the data forwarding route is adjusted.

[0118] The instructions pushed by the SDN receive traffic monitoring and alarm device are received, the load conditions of multiple nodes are monitored through the SDN, the nodes are sorted (Load1, Load2,..., Load n ) according to the load conditions, and the data forwarding route is adjusted according to the minimum load and the shortest route

[0119] TMSendInstructions.start(); / / Adjust the data forwarding route device to start, when the traffic alarm exceeds the threshold and the operator does not perform manual processing, the shunt device will select a suitable data source according to a certain algorithm, generate a response instruction, and adjust the forwarding route of the data source.

[0120] In summary, Figure 3 The specific steps of the node traffic monitoring and early warning and adjustment device are shown in the above table, including a data packet receiving device, a data analysis device, a traffic analysis device, a traffic warning device and a shunt device. First, the nodes of the customer private cloud are initialized, the customer private cloud includes SAAS (customer application) and PAAS (operating system, database), then the Telemetry protocol is started, the data is sent to the traffic monitoring and early warning device for analysis, including data packet receiving, data analysis, traffic analysis, traffic warning and shunt, finally the obtained data is input into the SDN, and a complete node traffic monitoring and data forwarding route adjustment cycle is completed.

[0121] Figure 4 is a structural diagram of a data processing device according to an embodiment of the present application, as shown in Figure 4 , the device comprises:

[0122] The collection module 40 is configured to collect a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet comprises at least a source IP address and a target IP address.

[0123] The statistics module 42 is configured to, in the plurality of network data packets, count a data amount sent by a same source IP address within a preset time range, and count a data amount sent by each application program under the same source IP address within the preset time range.

[0124] The determination module 44 is configured to acquire application priority information and application load information of each application program under the same source IP address, and determine an application score of each application program according to the application priority information and the application load information of each application program.

[0125] The processing module 46 is configured to acquire a load index of the network node at a target moment, and perform shunting processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node, in a case where the load index is greater than a preset threshold, wherein a difference between the target moment and an end moment in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data amount sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data amount sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0126] Optionally, the processing module 46 is further configured to perform the following steps: acquiring network topology information corresponding to the cloud platform of the private network, wherein the network topology information comprises a connection relationship between the network nodes and real-time state information of links between the network nodes, and the real-time state information at least comprises a link bandwidth, a delay and a packet loss rate; determining a plurality of candidate links from the network node whose load index is greater than the preset threshold to other network nodes based on the network topology information; for each candidate link, performing weighted summation on the link bandwidth, the delay and the packet loss rate in the candidate link to obtain a target length of each candidate link; acquiring load indexes of the other network nodes, and determining a node set composed of nodes whose load indexes are less than a fifth preset threshold among the other network nodes, wherein the load index is determined at least according to a CPU usage rate and a memory occupancy rate of the network node; in the node set, determining a first network node with a shortest target length, and sending the target traffic to the first network node to forward the target traffic through the first network node.

[0127] Optionally, the data processing apparatus is further configured to perform the following steps: if there are multiple second network nodes with the shortest target length in the node set, calculating a reliability index of each second network node according to an availability index of the second network node, an average time interval between two adjacent failures of the second network node, and an average time required by the second network node from failure to recovery, wherein the availability index is determined by total running time, failure downtime, and total running time; determining a third network node with the largest reliability index among the multiple second network nodes, and sending the target traffic to the third network node for forwarding the target traffic by the third network node.

[0128] Optionally, the data processing apparatus is further configured to perform the following steps after obtaining the network topology information corresponding to the cloud platform of the private network: encapsulating the real-time state information in a standardized format based on the Telemetry protocol, wherein the standardized format adopts a predefined JSON or binary encoding structure; transmitting the encapsulation result to the central management server through a secure encryption channel, wherein the secure encryption channel adopts a Secure Sockets Layer or a Transport Layer Security protocol; receiving, by the central management server, the encapsulation result, and presenting the link bandwidth, delay, and packet loss rate in the encapsulation result in the form of a visual curve; obtaining a performance threshold, and triggering an alarm when any index in the encapsulation result exceeds the performance threshold, wherein the performance threshold is dynamically adjusted based on the network service level agreement and historical state information of the network nodes.

[0129] Optionally, the data processing apparatus is further configured to perform the following steps: in a case where the load index is less than the preset threshold and a difference between the load index and the preset threshold is less than a fifth preset threshold, sending a pre-warning information to the management object of the private network.

[0130] Optionally, the determining module 44 is further configured to perform the following steps: obtaining an application load model table, wherein the application load model table includes application name information, application description information, application priority information, application address information, application port number information, application state information, and application load information; and filtering, in the application load model table, the application priority information and the application load information of each application program with the same source IP address.

[0131] Optionally, the collecting module 40 is further configured to perform the following steps: the target node connected to the cloud platform of the private network in the public network collects multiple network data packets forwarded by multiple network nodes in the cloud platform of the private network by enabling a target protocol, wherein the target protocol includes the Telemetry protocol.

[0132] It should be noted that the above Figure 4Each module in the above-mentioned embodiments can be a program module (for example, a program instruction set for implementing certain specific functions) or a hardware module. For the hardware module, it can be in the form of, but not limited to, a processor or a processor for implementing the functions of the above-mentioned modules.

[0133] It should be noted that, Figure 4 The preferred implementation of the embodiments shown can be understood with reference to Figure 1 The related description of the embodiments shown will not be repeated here.

[0134] Figure 5 A hardware structure block diagram of a computer terminal for implementing the data processing method is shown. As shown in Figure 5 The computer terminal 50 can include one or more processors 502 (the processor 502 can include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 504 for storing data, and a transmission module 506 for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that, Figure 5 The structure shown is only schematic, and does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 50 can include more or fewer components than those shown in Figure 5 or have a different configuration than that shown in Figure 5 .

[0135] It should be noted that the one or more processors 502 and / or other data processing circuits described above can be referred to herein as "data processing circuits" in general. The data processing circuit can be embodied in whole or in part as software, hardware, firmware or any combination thereof. In addition, the data processing circuit can be a single independent processing module, or any one of the other elements combined into the computer terminal 50 in whole or in part. As referred to in the embodiments of the present application, the data processing circuit serves as a processor for controlling (for example, the selection of the variable resistance terminal path connected to the interface).

[0136] The memory 504 can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the data processing method in the embodiments of the present application. The processor 502 executes various functional applications and data processing by running the software programs and modules stored in the memory 504, i.e., implements the above-mentioned data processing method. The memory 504 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 504 can further include a memory remotely arranged with respect to the processor 502, which can be connected to the computer terminal 50 through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0137] The transmission module 506 is configured to receive or send data via a network. Specific examples of the above-mentioned network can include a wireless network provided by a communication provider of the computer terminal 50. In one example, the transmission module 506 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to be able to communicate with the Internet. In one example, the transmission module 506 can be a radio frequency (RF) module, which is configured to communicate with the Internet in a wireless manner.

[0138] The display can be, for example, a touch screen type liquid crystal display (LCD), which can enable a user to interact with the user interface of the computer terminal 50.

[0139] It should be noted that, in some optional embodiments, the above-mentioned Figure 5 The computer terminal shown can include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that, Figure 5 is only one example of a particular implementation and is intended to illustrate the types of components that can be present in the above-mentioned computer terminal.

[0140] It should be noted that, Figure 5 The computer terminal shown is configured to execute Figure 1 The data processing method shown, and the related explanations in the execution method of the above-mentioned commands also apply to the electronic device, which will not be described here again.

[0141] The embodiments of the present application also provide a non-volatile storage medium, which includes a stored program, wherein the program controls the device where the storage medium is arranged to execute the above-mentioned data processing method when running.

[0142] The non-volatile storage medium executes a program for the following functions: collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet at least includes a source IP address and a target IP address; in the plurality of network data packets, counting a data volume sent by the same source IP address within a preset time range and counting a data volume sent by each application program under the same source IP address within the preset time range; obtaining application priority information and application load information of each application program under the same source IP address, and determining an application score of the application program according to the application priority information and the application load information of each application program; obtaining a load index of the network node at a target moment, and performing shunt processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node in a case where the load index is greater than a preset threshold, wherein a difference between the target moment and an end moment in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data volume sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data volume sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0143] The application further provides an electronic device, comprising a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program is configured to perform the data processing method.

[0144] The processor is configured to run a program for the following functions: collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet at least includes a source IP address and a target IP address; in the plurality of network data packets, counting a data volume sent by the same source IP address within a preset time range and counting a data volume sent by each application program under the same source IP address within the preset time range; obtaining application priority information and application load information of each application program under the same source IP address, and determining an application score of the application program according to the application priority information and the application load information of each application program; obtaining a load index of the network node at a target moment, and performing shunt processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node in a case where the load index is greater than a preset threshold, wherein a difference between the target moment and an end moment in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data volume sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data volume sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

[0145] The above sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0146] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0147] In the above embodiments of the present application, the collected information is information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant laws, regulations and standards, necessary protection measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0148] In the several embodiments of the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division is only a description of logical function division, and there can be another division manner in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0149] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0150] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0151] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part that essentially contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0152] The above description is only the preferred embodiments of the present application. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. A data processing method, characterized by, The method comprises: Collecting a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a special-purpose network, wherein each of the network data packets comprises at least a source IP address and a target IP address; In a plurality of the network data packets, statistics the data volume sent by the same source IP address within a preset time range, and statistics the data volume sent by each application program under the same source IP address within a preset time range; Obtaining application priority information and application load information of each application program under the same source IP address, and determining an application score of each application program according to the application priority information and the application load information of each application program; Obtaining a load index of the network node at a target time, and performing traffic splitting processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node in a case where the load index is greater than a preset threshold, wherein the difference between the target time and the end time in the preset time range is less than a first preset threshold, the target source IP address is a source IP address whose data volume sent within the preset time range is greater than a second preset threshold, and the target application program is an application program whose data volume sent within the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

2. The method of claim 1, wherein, The traffic splitting processing on the target traffic corresponding to the target application program under the target source IP address forwarded by the network node comprises: Obtaining network topology information corresponding to the cloud platform of the special-purpose network, wherein the network topology information comprises connection relationships between the network nodes and real-time state information of links between the network nodes, and the real-time state information at least comprises link bandwidth, delay and packet loss rate; Based on the network topology information, determining a plurality of candidate links from the network node whose load index is greater than a preset threshold to other network nodes; For each of the candidate links, performing weighted summation on the link bandwidth, the delay and the packet loss rate therein to obtain a target length of each of the candidate links; Obtaining load indexes of other network nodes, and determining a node set composed of nodes whose load indexes are less than a fifth preset threshold among the other network nodes, wherein the load index is determined at least according to CPU usage and memory occupancy of a network node; In the node set, determining a first network node with the shortest target length, and sending the target traffic to the first network node to forward the target traffic through the first network node.

3. The method of claim 2, wherein, The method further comprises: If there are a plurality of second network nodes with the shortest target length in the node set, calculating a reliability index of each of the second network nodes according to an availability index of the second network node, an average time interval between adjacent two failures of the second network node, and an average time required by the second network node from failure occurrence to recovery to normal operation, wherein the availability index is determined by total running time, failure downtime and total running time. Among the second network nodes, a third network node with the largest reliability index is determined, and the target traffic is sent to the third network node to forward the target traffic through the third network node.

4. The method of claim 2, wherein, After obtaining the network topology information corresponding to the cloud platform of the private network, the method further comprises: Based on the Telemetry protocol, the real-time state information is packaged in a standardized format, wherein the standardized format adopts a predefined JSON or binary encoding structure; The packaging result is transmitted to the central management server through a secure encryption channel, wherein the secure encryption channel adopts a secure socket layer or a transport layer security protocol; The central management server receives the packaging result, and presents the link bandwidth, delay and packet loss rate in the packaging result in the form of a visual curve; A performance threshold is obtained, and an alarm is triggered when any index in the packaging result exceeds the performance threshold, wherein the performance threshold is dynamically adjusted based on a network service level agreement and historical state information of network nodes.

5. The method of claim 1, wherein, The method further comprises: in a case where the load index is less than the preset threshold and a difference between the load index and the preset threshold is less than a fifth preset threshold, sending early warning information to a management object of the private network.

6. The method of claim 1, wherein, Application priority information and application load information of each application under the same source IP address are obtained, including: An application load model table is obtained, wherein the application load model table includes application name information, application description information, application priority information, application address information, application port number information, application state information and application load information. The application priority information and the application load information of each application under the same source IP address are filtered in the application load model table.

7. The method of claim 1, wherein, A plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network are collected, including: a target node connected to the cloud platform of the private network in a public network collects a plurality of network data packets forwarded by a plurality of network nodes in the cloud platform of the private network by enabling a target protocol, wherein the target protocol includes a Telemetry protocol.

8. A data processing apparatus, characterized by, The method comprises: A collection module is configured to collect a plurality of network data packets forwarded by a plurality of network nodes in a cloud platform of a private network, wherein each network data packet includes at least a source IP address and a target IP address; A statistical module is configured to, among a plurality of network data packets, count a data amount sent by the same source IP address within a preset time range, and count a data amount sent by each application under the same source IP address within a preset time range; A determination module is configured to obtain application priority information and application load information of each application under the same source IP address, and determine an application score of each application based on the application priority information and the application load information of the application. The processing module is configured to acquire a load index of the network node at a target time point, and perform shunt processing on target traffic corresponding to a target application program under a target source IP address forwarded by the network node, if the load index is greater than a preset threshold, wherein the target time point is less than a first preset threshold from an end time point in the preset time range, the target source IP address is a source IP address whose data amount sent in the preset time range is greater than a second preset threshold, and the target application program is an application program whose data amount sent in the preset time range is greater than a third preset threshold and whose application score is less than a fourth preset threshold.

9. A non-volatile storage medium, comprising: The non-volatile storage medium comprises a stored program, wherein the program, when executed, controls a device in which the non-volatile storage medium is located to perform the data processing method of any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the data processing method of any one of claims 1 to 7.

Images