Content distribution task processing method and device, equipment and storage medium

Abstract

The invention discloses a content distribution task processing method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a content distribution task to be processed, and real-time node resource information and real-time service feature information of each available node; calculating a task adaptation score of each available node based on the task information of the content distribution task and the real-time node resource information and the real-time service feature information of each available node; taking the available node with the highest task adaptation score in the available nodes as a target node; and executing the content distribution task by using the target node. According to the technical scheme, the node resource utilization rate can be effectively improved, and then the overall operation efficiency of the system is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for processing content distribution tasks. Background Technology

[0002] Content Delivery Networks (CDNs) have been widely used in various internet services, effectively improving content delivery efficiency, reducing network response latency, and enhancing the end-user experience. In typical content distribution scenarios, when a new content distribution task (such as video stream distribution, file download, live streaming, game update package push, etc.) arises, the system needs to select a suitable node from numerous available nodes (such as edge servers, cache nodes, etc.) to execute the task.

[0003] However, most existing methods for handling content distribution tasks allocate tasks based on preset static node weights or priorities, or use a simple round-robin approach to select target nodes. While these methods are simple to implement, they cannot match the most suitable execution node for each task based on actual operating conditions, which can easily lead to uneven load distribution among nodes—some nodes are overloaded while other nodes are idle, resulting in a decrease in the overall efficiency of the content distribution system.

[0004] Therefore, there is an urgent need to propose a new method to solve the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for processing content distribution tasks, which can effectively improve the utilization rate of node resources and thus significantly improve the overall operating efficiency of the system.

[0006] In a first aspect, embodiments of the present invention provide a method for processing content distribution tasks, the method comprising:

[0007] Obtain the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information;

[0008] Based on the task information of the content distribution task, the real-time node resource information and real-time business characteristic information of each available node, the task adaptation score of each available node is calculated.

[0009] The node with the highest task adaptation score among all available nodes is selected as the target node.

[0010] The content distribution task is executed using the target node.

[0011] The technical solution of this invention first acquires the content distribution task to be processed, real-time node resource information of each available node, and real-time business characteristic information, providing a data foundation for subsequent calculation of the task adaptation score of each available node. Next, based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information, the task adaptation score of each available node is calculated. This achieves a quantitative evaluation of the matching degree between each available node and the content distribution task based on the actual operating status of the nodes, and improves the accuracy of the quantitative results, thus providing reliable data support for accurate matching between nodes and tasks. Then, the available node with the highest task adaptation score among all available nodes is selected as the target node, which can effectively reduce resource waste and transmission latency, improve content transmission rate, and shorten task completion time. This ensures the execution quality of individual tasks while optimizing the utilization rate of network resources and comprehensively improving service quality. Finally, using the target node to execute the content distribution task can optimize the overall network resource allocation, reduce resource waste and operating costs, ensure the access experience of end users, comprehensively improve service quality, and enhance the overall stability of the system, effectively reducing the risk of failure. Therefore, the technical solution of the present invention solves the technical problem in the prior art that it is impossible to match the optimal execution node for the task according to the actual operation of the node, which leads to load imbalance between nodes and reduced overall content distribution system operating efficiency.

[0012] Secondly, embodiments of the present invention also provide a processing apparatus for a content distribution task, the apparatus comprising:

[0013] The acquisition module is used to acquire the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information.

[0014] The calculation module is used to calculate the task adaptation score of each available node based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information.

[0015] The determination module is used to select the available node with the highest task adaptation score among all available nodes as the target node.

[0016] An execution module is used to execute the content distribution task using the target node.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to said at least one processor;

[0019] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the content distribution task processing method described in any embodiment of the present invention.

[0020] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, implement the content distribution task processing method described in any embodiment of the present invention.

[0021] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the content distribution task processing device, or it may be packaged separately from the processor of the content distribution task processing device; this application does not impose any limitations on this.

[0022] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0023] In this application, the name of the processing device for the aforementioned content distribution task does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0024] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a content distribution task processing method provided in an embodiment of the present invention;

[0027] Figure 2 A flowchart illustrating another method for processing content distribution tasks provided in an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of a content distribution task processing device provided in an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0031] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0032] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0033] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0034] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, without conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0035] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] Figure 1 This is a flowchart illustrating a content distribution task processing method according to an embodiment of the present invention. This embodiment is applicable to situations where it is necessary to allocate adaptation nodes for content distribution tasks in a content distribution network and complete task execution. This method can be executed by a content distribution task processing device, which can be implemented in software and / or hardware. For example, the device can be an electronic device. (See reference...) Figure 1 The content distribution task processing method in this embodiment specifically includes the following steps:

[0038] Step 110: Obtain the content distribution task to be processed, the real-time node resource information of each available node, and the real-time business characteristic information.

[0039] Specifically, a content distribution task refers to the task of transmitting or copying specific content (such as audio / video files, static resources, data packets, etc.) from the source (i.e., the initiator of the content distribution task) to a target node, which then provides content access services to end users. An available node refers to a network node in the content distribution network that is currently operating normally, has content processing capabilities, and can receive distribution instructions and perform content storage, forwarding, or push operations. Common types include edge nodes, content distribution network nodes, and relay servers. Real-time node resource information refers to the actual operating status data of a node's hardware and network resources at the current moment. This information may include CPU utilization, memory usage, remaining disk space, network bandwidth utilization, node load, and concurrent connections. Real-time business characteristic information refers to the dynamic operating status data of a node related to the current distribution business. This information may include the current period's business request volume, peak user access times, content popularity, access demand density in different regions, and historical business characteristics.

[0040] In practice, pending content distribution tasks can be acquired by listening to message queues, capturing requests from the application programming interface gateway, or periodically scanning the task database for new records. Then, the acquired pending content distribution tasks are parsed in a structured manner to obtain their task information. Simultaneously, after acquiring the pending content distribution tasks, available nodes can be selected from the entire content delivery network based on node status information. Then, a lightweight monitoring agent deployed on each available node collects real-time node resource information and real-time business characteristic information for each node. The node status information refers to data characterizing the current operating status of the node, including its availability and unavailability.

[0041] In this embodiment, the above steps provide a data foundation for the subsequent calculation of the task adaptation score of each available node.

[0042] Step 120: Calculate the task adaptation score of each available node based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information.

[0043] Specifically, task information refers to a data set describing the specific requirements and characteristics of a content distribution task, such as task type, content size, transmission priority, target coverage, latency requirements, and content type. Task adaptation score is a quantitative score calculated using the task information of the content distribution task, the real-time node resource information of each node, and real-time business characteristic information. It measures the degree of matching between a given available node and the current content distribution task; a higher score indicates that the node is more suitable to execute the task.

[0044] In the specific implementation, for each available node, the task information of the content distribution task, as well as the real-time node resource information and real-time business characteristic information of that available node, are input into a pre-trained task adaptation score determination model to obtain the task adaptation score of the available node. The task adaptation score determination model is obtained by supervised training of a machine learning model based on historical content distribution task data, historical node status time-series data (including node resource information and business characteristic information), and the actual task adaptation scores corresponding to the above data.

[0045] In this embodiment, the above steps not only enable a quantitative assessment of the matching degree between each available node and the content distribution task based on the actual operation of the node, but also improve the accuracy of the quantitative results, thereby providing reliable data support for the accurate matching of nodes and tasks.

[0046] Step 130: Select the available node with the highest task adaptation score among all available nodes as the target node.

[0047] Specifically, the target node refers to the node selected from all available nodes to perform this content distribution task.

[0048] In practice, after obtaining the task adaptation scores of each available node, the available node with the highest task adaptation score can be used as the target node. This can effectively reduce resource waste and transmission latency, improve content transmission rate, and shorten task completion time. Thus, while ensuring the execution quality of individual tasks, it can optimize the utilization rate of network resources and comprehensively improve service quality.

[0049] Step 140: Execute the content distribution task using the target node.

[0050] In specific implementation, after determining the target node, an execution instruction containing all information about the content distribution task can be generated first. This instruction covers core elements such as basic task information, transmission requirements, and service requirements. Then, the execution instruction is sent to the target node. Upon receiving the instruction, the target node first performs security verification and feasibility assessment. After successful verification, the target node executes the content distribution task based on the instruction. After the task is completed, the target node reports the execution results [including whether the task was completed, core performance indicators (such as transmission rate, latency, cache hit rate, etc.), and service quality data (such as user access lag rate, task execution time, etc.). Furthermore, the content distribution task processing method provided in this embodiment can be applied to a central scheduling system. The central scheduling system is the core control and decision-making hub of the content distribution network, responsible for coordinating all network node resources, managing the lifecycle of content distribution tasks, and achieving optimal matching between tasks and nodes.

[0051] In this embodiment, the above steps optimize resource allocation, reduce resource waste, and lower operating costs. Simultaneously, they ensure a better user experience and comprehensively improve service quality. Furthermore, they enhance overall system stability and effectively reduce the risk of failures.

[0052] The content distribution task processing method provided in this embodiment of the invention first acquires the content distribution task to be processed, real-time node resource information of each available node, and real-time business characteristic information, providing a data foundation for subsequent calculation of the task adaptation score of each available node. Next, based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information, the task adaptation score of each available node is calculated. This not only achieves a quantitative evaluation of the matching degree between each available node and the content distribution task based on the actual operating status of the nodes, but also improves the accuracy of the quantitative results, thus providing reliable data support for accurate matching between nodes and tasks. Then, the available node with the highest task adaptation score among all available nodes is selected as the target node, which can effectively reduce resource waste and transmission latency, improve content transmission rate, and shorten task completion time, thereby optimizing the utilization rate of network resources and comprehensively improving service quality while ensuring the execution quality of individual tasks. Finally, using the target node to execute the content distribution task can optimize resource allocation, reduce resource waste, and lower operating costs. At the same time, it can ensure the access experience of end users and comprehensively improve service quality. Furthermore, it can enhance the overall stability of the system and effectively reduce the risk of failure. Therefore, the technical solution of the present invention solves the technical problem in the prior art that it is impossible to match the optimal execution node for the task according to the actual operation of the node, which leads to load imbalance between nodes and reduced overall content distribution system operating efficiency.

[0053] Figure 2This is a flowchart illustrating another content distribution task processing method provided by an embodiment of the present invention. This embodiment is a specific embodiment based on the above embodiment. In this embodiment, the method may further include:

[0054] Step 210: Obtain the content distribution task to be processed, the real-time node resource information of each available node, and the real-time business characteristic information.

[0055] Step 211: Calculate the task adaptation score of each available node based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information.

[0056] Optionally, task information includes task type and task objective parameters.

[0057] Further, step 211 may specifically include: determining the constraints for node selection based on task target parameters and real-time business characteristic information; selecting each available node based on the constraints to obtain the selected available nodes; determining the node resource association information of the corresponding node based on the real-time node resource information of each available node; predicting the future node resource information of the corresponding node based on the historical node resource information and node resource association information of each available node; and determining the task adaptation score of each available node based on the task type and the future node resource information of each available node.

[0058] Specifically, task type refers to the core classification identifier that distinguishes different business scenarios of content distribution tasks, including on-demand and live streaming. Task target parameters refer to the core quantitative indicators that measure the performance of content distribution tasks and are the basis for formulating node selection constraints. Task target parameters may include latency thresholds, transmission rate requirements, target coverage areas, cache validity periods, and task priorities. Node selection constraints refer to the node admission rules determined based on task target parameters and real-time business characteristic information of nodes. These rules are used to filter available nodes that do not meet the basic requirements of the task and narrow down the range of suitable nodes. Historical node resource information refers to the time-series operation data records of a node's hardware and network resources over a past period (such as the past month, week, day, or hour). Future node resource information refers to the node resource change trend data and key indicator prediction values ​​(such as future peak bandwidth utilization and average latency) over a future period (such as the next 5 minutes, 10 minutes, or 30 minutes) determined based on historical resource information and current resource association information.

[0059] In practice, initial constraints can be generated based on task target parameters. For example, if the task target parameters require network bandwidth greater than 10 gigabits per second (Gbps) and packet loss rate less than 0.1%, the initial constraints are set as network bandwidth > 10Gbps and packet loss rate < 0.1%. Then, based on real-time service characteristics, preset constraint adjustment rules are invoked to adjust the initial constraints, resulting in node selection constraints. For example, if the real-time service characteristics are 800,000 concurrent live connections and 80% node bandwidth utilization, and the historical peak is known to be 500,000, the preset constraint adjustment rules are: Rule a: If the number of concurrent live connections exceeds 1.5 times the historical peak, the bandwidth threshold is increased to 1.2 times the initial value; Rule b: If the node bandwidth utilization exceeds 75%, the packet loss rate threshold is tightened to 0.8 times the initial value. After adjustment according to the preset rules, the node selection constraints are updated to network bandwidth > 12Gbps and packet loss rate < 0.08%. Among them, the preset constraint adjustment rules refer to the set of standardized rules that are pre-configured according to the actual situation or needs in the node screening process of the content distribution task, and are used to dynamically adjust the initial constraint conditions of node screening based on real-time business characteristics.

[0060] Then, based on the adjusted constraints, each available node is filtered to obtain the filtered available nodes. For example, the currently available nodes include node 1, node 2, and node 3, with the following specific parameters: node 1: remaining bandwidth is 14Gbps, packet loss rate is 0.06%; node 2: remaining bandwidth is 9Gbps, packet loss rate is 0.05%; node 3: remaining bandwidth is 12.5Gbps, packet loss rate is 0.09%. Then, the filtered available node is node 1.

[0061] Then, for each available node after screening, the following steps can be taken: First, input the real-time node resource information of the node into a pre-trained association information determination model to obtain the node resource association information of that node. Second, input the historical node resource information of the node and the node resource association information obtained above into a pre-trained resource prediction model to obtain the future node resource information of that node. Finally, input the task type of the content distribution task and the future node resource information of the node into a pre-trained score calculation model to obtain the task adaptation score of that node. The association information determination model refers to the model obtained by training a deep learning model (such as a neural network) based on node resource information collected at different points in the past and the corresponding node resource association information. The resource prediction model refers to the model obtained by training a deep learning model (such as a Transformer time series model) based on node resource information, node resource association information, and the future node resource information at a series of consecutive or interval points in the future corresponding to these information. The scoring calculation model refers to the model obtained by training a deep learning model (such as a deep neural network) based on historical content distribution task data (task type), future resource prediction information of the corresponding node of the task, and the labeled task adaptation score obtained after the task is executed under these conditions.

[0062] In this embodiment, the above steps not only improve the accuracy of node selection and business adaptability, but also make scheduling decisions more scientific by quantifying task adaptability assessment and making forward-looking predictions on node resource status; at the same time, they reduce the cost of manual intervention and realize the automation and intelligence of the scheduling process.

[0063] Optionally, future node resource information includes future network bandwidth, future network latency, future packet loss rate, future input / output operands, future throughput, and future queue depth.

[0064] Furthermore, based on the task type and the future node resource information of each available node, the task adaptation score of each available node is determined, including: for the current available node, the network adaptation score of the current available node is calculated based on the future network bandwidth, future network latency and future packet loss rate of the current available node; the disk adaptation score of the current available node is calculated based on the future input / output operands, future throughput and future queue depth of the current available node; the disk adaptation score and network adaptation score are weighted based on the task type to obtain the task adaptation score of the current available node.

[0065] Specifically, future network bandwidth refers to the maximum data transmission capacity that a node's network link can stably carry within a predicted future period (e.g., 5 minutes, 10 minutes, 30 minutes, etc.). Future network latency refers to the average transmission time from the sender to the receiver within a predicted future period. Future packet loss rate refers to the proportion of data packets lost during node network transmission to the total number of data packets sent within a predicted future period. Future input / output operations refer to the number of input / output operations that a node's storage device can complete per second within a predicted future period. Future throughput refers to the total amount of data successfully transmitted per unit time by a node's storage device or network link within a predicted future period. Future queue depth refers to the length of the task queue waiting to be processed by a node's storage device or network interface within a predicted future period. Network adaptation score is a quantitative score calculated based on a node's future network bandwidth, future network latency, and future packet loss rate, used to evaluate the node's network resource support capability for tasks. Disk adaptation score is a quantitative score calculated based on a node's future input / output operations, future throughput, and future queue depth, used to evaluate the node's storage resource support capability for tasks.

[0066] In specific implementation, for currently available nodes, their network adaptation score can be calculated based on the future network bandwidth, future network latency, and future packet loss rate. The specific calculation formula is: Network Adaptation Score = Bandwidth Weight × [(Future Network Bandwidth - Minimum Required Bandwidth for Content Distribution Task) / (Maximum Required Bandwidth for Content Distribution Task - Minimum Required Bandwidth for Content Distribution Task)] + Latency Weight × [1 - (Future Network Latency - Minimum Allowable Network Latency for Content Distribution Task) / (Maximum Allowable Network Latency for Content Distribution Task - Minimum Allowable Network Latency for Content Distribution Task)] + Packet Loss Rate Weight × [1 - (Future Packet Loss Rate - Minimum Allowable Packet Loss Rate for Content Distribution Task) / (Maximum Allowable Packet Loss Rate for Content Distribution Task - Minimum Allowable Packet Loss Rate for Content Distribution Task)]. Here, the bandwidth weight, latency weight, and packet loss rate weight are all pre-set weights based on actual conditions or requirements, and their sum is one. The minimum allowable network latency, maximum allowable network latency, minimum required bandwidth, maximum required bandwidth, maximum allowable packet loss rate, and minimum allowable packet loss rate of the content distribution task are all extracted from the task information of that task. Furthermore, if the future overall network bandwidth is greater than or equal to the maximum required bandwidth, the bandwidth weight for the corresponding item will be multiplied by 1; if the future overall network bandwidth is less than or equal to the minimum required bandwidth, the bandwidth weight for the corresponding item will be multiplied by 0; if the future network latency is less than or equal to the minimum allowable latency, the latency weight for the corresponding item will be multiplied by 1; if the future network latency is greater than or equal to the maximum allowable latency, the latency weight for the corresponding item will be multiplied by 0; if the future packet loss rate is less than or equal to the minimum allowable packet loss rate, the packet loss rate weight for the corresponding item will be multiplied by 1; if the future packet loss rate is greater than or equal to the maximum allowable latency, the packet loss rate weight for the corresponding item will be multiplied by 0.

[0067] Simultaneously, a disk adaptation score can be calculated based on the future input / output operands, future throughput, and future queue depth of currently available nodes. The specific calculation formula is: Disk Adaptation Score = Operand Weight × [(Future Input / Output Operands - Minimum Required Operands for Content Distribution Task) / (Maximum Required Operands for Content Distribution Task - Minimum Required Operands for Content Distribution Task)] + Throughput Weight × [(Future Throughput - Minimum Required Throughput for Content Distribution Task) / (Maximum Required Throughput for Content Distribution Task - Minimum Required Throughput for Content Distribution Task)] + Queue Depth Weight × [1 - (Future Queue Depth - Minimum Allowed Queue Depth for Content Distribution Task) / (Maximum Allowed Queue Depth for Content Distribution Task - Minimum Allowed Queue Depth for Content Distribution Task)]. Here, the operand weight, throughput weight, and queue depth weight are all pre-set weights based on actual conditions or requirements, and the sum of these three is one. The minimum required throughput, maximum required throughput, minimum allowed queue depth, maximum allowed queue depth, minimum required operands, and maximum required operands for the content distribution task are all extracted from the task information of that task.

[0068] Finally, based on the task type, a query is performed in the preset weight allocation table to obtain the weights corresponding to the disk adaptation score and network adaptation score, respectively. These weights are then applied to weight the disk adaptation score and network adaptation score to obtain the task adaptation score of the currently available node. That is, Task Adaptation Score = Disk Weight × Disk Adaptation Score + Network Weight × Network Adaptation Score. The weight allocation table refers to the pre-determined weight allocation rules for different task types based on actual conditions or needs. For example, when the task type is live streaming, the disk weight is 0.3 and the network weight is 0.7; when the task type is video-on-demand, the disk weight is 0.7 and the network weight is 0.3.

[0069] In this embodiment, the above steps not only effectively avoid the one-sidedness caused by single-dimensional scoring, but also accurately match the differentiated resource requirements of tasks on different nodes, significantly improving the matching accuracy between nodes and tasks. At the same time, the mechanism of differentiated weight allocation based on task type further enhances the flexibility and adaptability of scheduling decisions.

[0070] Furthermore, after weighting the disk adaptation score and network adaptation score based on task type to obtain the task adaptation score of the currently available node, the process also includes: determining the historical successful execution count and the total execution count of the currently available node for the task type; calculating the ratio of the historical successful execution count to the total execution count to obtain the historical adaptation score of the currently available node; and updating the task adaptation score of the currently available node using the historical adaptation score to obtain the updated task adaptation score of the currently available node.

[0071] Specifically, the historical successful execution count refers to the number of times that a currently available node has met preset success criteria when performing similar content distribution tasks in the past. These success criteria can be predefined based on the task type; for example, the success criteria for a live streaming task are smooth playback without buffering, packet loss rate below a threshold, and latency stable within the required range. For a video-on-demand task, the success criteria are complete file download and response time below a threshold. The total execution count refers to the cumulative number of times a currently available node has performed similar content distribution tasks in the past. The historical adaptation score is a quantitative score obtained by calculating the ratio of the historical successful execution count to the total execution count for the same type of task, reflecting the node's historical performance and stable adaptation capability for that type of task.

[0072] In the specific implementation, after weighting the disk adaptation score and network adaptation score based on task type to obtain the task adaptation score (i.e., the initial task adaptation score) of the currently available node, the historical execution success count and total execution count for that task type can be determined through the historical task logs of the currently available node. Then, the ratio of the historical execution success count to the total execution count is calculated to obtain the historical adaptation score of the currently available node. Finally, the task adaptation score of the currently available node is updated using the historical adaptation score to obtain the updated task adaptation score of the currently available node. Specifically, the updated task adaptation score of the currently available node = historical weight × historical adaptation score + initial weight × initial task adaptation score. Here, the historical weight and initial weight are pre-set weights based on actual conditions or requirements, and their sum is 1.

[0073] In this embodiment, the above steps not only improve the comprehensiveness and reliability of the score evaluation, but also enhance the risk resistance of task scheduling decisions, thereby effectively reducing the trial and error cost of the scheduling system.

[0074] Step 212: Determine whether there are any available nodes among the available nodes whose task adaptation score is greater than the preset score threshold.

[0075] If it exists, proceed to step 213; if it does not exist, proceed to step 214.

[0076] Specifically, the preset score threshold refers to the adaptation score threshold set in advance according to the actual situation or needs. It is a quantitative standard for judging whether a node is qualified to undertake tasks. For example, the preset score threshold is 0.6.

[0077] In practice, after obtaining the task adaptation scores of each available node, it can be determined whether there are any available nodes whose task adaptation scores are greater than a preset score threshold. If so, it means that at least one available node's overall performance can meet the overall requirements of the task, and the available node with the highest task adaptation score can be selected as the target node. If not, it means that no single node has sufficient performance to independently handle the task, and the content distribution task can be split into a preset number of sub-distribution tasks, and the top preset number of available nodes with the highest task adaptation scores can be selected as the target nodes for each sub-distribution task.

[0078] In this embodiment, the above steps not only achieve the standardization and automation of node selection, replacing subjective human judgment with quantitative judgment, significantly improving the scheduling efficiency and decision-making accuracy of large-scale node clusters; but also ensure the basic adaptability of task execution, effectively reducing task execution risks, and providing clear and reliable decision-making premises for the formulation of subsequent scheduling strategies.

[0079] Step 213: Select the available node with the highest task adaptation score among all available nodes as the target node.

[0080] Step 214: Divide the content distribution task into a preset number of sub-distribution tasks, and select the preset number of available nodes with the highest task adaptation scores as the target nodes for each sub-distribution task.

[0081] Specifically, the preset quantity refers to the number of sub-distribution tasks to be split according to actual conditions or needs, and it is also the number of target nodes to be selected. The preset quantity must be greater than 1. For example, the preset quantity for a large file distribution task is 5, which means it is split into 5 sub-distribution tasks, and 5 nodes with the highest adaptation scores are selected to execute them respectively. A sub-distribution task refers to an independently executable task unit formed by breaking down the original content distribution task according to preset rules (such as data fragmentation, task stage splitting, user group division, etc.). For example, splitting a 10 gigabyte (GB) large file into 5 2GB file fragments, the transmission of each fragment is a sub-distribution task.

[0082] In practice, after determining that there are no available nodes with a task adaptation score greater than a preset score threshold, the content distribution task can be split into a preset number of sub-distribution tasks. Then, the top preset number of nodes with the highest task adaptation scores among all available nodes are selected as the target nodes for each sub-distribution task. For example, if the content distribution task is a 20GB video file, the preset score threshold is 0.7, and the preset number is 4. The task adaptation scores of the available nodes are as follows: Node 1: 0.65, Node 2: 0.62, Node 3: 0.68, Node 4: 0.6, Node 5: 0.66. At this point, the 20GB video file can be split into four 5GB sub-distribution tasks according to the file splitting rules. The five available nodes are sorted from high to low score as follows: Node 3 (0.68) > Node 5 (0.66) > Node 1 (0.65) > Node 2 (0.62) > Node 4 (0.60). The top four nodes are selected as the target nodes for the sub-distribution tasks. Finally, sub-distribution task 1 is assigned to node 3, sub-distribution task 2 is assigned to node 5, sub-distribution task 3 is assigned to node 1, and sub-distribution task 4 is assigned to node 2 in sequence.

[0083] In addition, to ensure that sub-distribution tasks can be completed stably under the existing resource conditions of the nodes, the execution parameters of each sub-distribution task can be adaptively adjusted, such as reducing the resource consumption threshold of a single sub-distribution task and extending the execution timeout of the sub-distribution task.

[0084] Additionally, if the number of available nodes is less than the preset number, the current task splitting and node allocation process is paused, and the content distribution task is transferred to the preset backup node pool. Then, the task adaptation score for the nodes in the backup node pool is recalculated, and the "score vs. threshold comparison – node quantity verification" filtering process is executed again: This determines whether any nodes in the backup node pool have a task adaptation score greater than the preset score threshold. If so, the node with the highest task adaptation score is selected as the target node; if not, it determines whether the number of nodes in the backup node pool meets the preset requirement. If it does, the task splitting and allocation operation continues; if not, an alarm mechanism is triggered to notify operations personnel to expand node capacity or adjust task priorities. The backup node pool refers to a pre-planned set of backup computing / storage node resources, independent of the regular available node pool, in the content distribution scheduling system. It serves as a redundant supplement to the main node pool, used to cope with unexpected scenarios such as insufficient main node pool resources, node failures, or abnormal task scheduling.

[0085] In this embodiment, the above steps not only ensure the continuous execution of content distribution tasks without interruption, but also significantly improve resource utilization, effectively reduce system scheduling costs, and further enhance the flexibility and scenario adaptability of the scheduling system.

[0086] Step 215: Determine whether the target node is currently performing other business tasks.

[0087] If the target node is performing other business tasks, proceed to step 216; if the target node is not performing other business tasks, proceed to step 217.

[0088] Specifically, other business tasks refer to a collective term for various computing or business processing tasks that are not related to this content distribution task, such as: other file transmission and distribution tasks, node local resource monitoring tasks, data verification tasks, low-priority test tasks, etc.

[0089] In practice, after identifying the target node, it can be determined whether the target node is currently executing other business tasks. If the target node is executing other business tasks, it means that the target node is currently under load and its resources are being used. In this case, the task execution strategy of the target node can be determined based on the priority of the content distribution task and the current business task. If the target node is not executing other business tasks, it means that the target node is currently idle and has sufficient available resources. In this case, the content distribution task can be executed directly using the target node.

[0090] In this embodiment, the above steps not only provide accurate basis for task scheduling strategies and improve the rationality of decision-making, but also effectively avoid node resource overload, ensure the stability of task execution, and reduce task execution conflicts.

[0091] Step 216: Determine the task execution strategy for the target node based on the priority of the content distribution task and the current business task.

[0092] Specifically, the current business task refers to various computational or business processing tasks that the target node has already accepted and is executing before the content distribution task is assigned to it, and which are unrelated to the current content distribution task. Priority refers to the pre-defined execution order for each task based on actual conditions or needs, such as low, medium, and high priorities. Task execution strategy refers to the differentiated task processing plan formulated based on the task priority comparison results.

[0093] In practice, the priority of the content distribution task is determined relative to the priority of the current business task: If the priority of the content distribution task is higher than that of the current business task, the current business task is paused and its running status is cached, and the content distribution task is executed directly using the target node; after the content distribution task is completed, the current business task is resumed; if the priority of the content distribution task is equal to that of the current business task, the resource quota of the target node is dynamically allocated to enable the two types of tasks to be executed in parallel, and the resource usage status is monitored in real time to avoid task lag; if the priority of the content distribution task is lower than that of the current business task, the content distribution task is added to the task waiting queue of the target node, and the content distribution task is started to be executed only after the target node completes the current business task.

[0094] In this embodiment, the above steps not only achieve differentiated scheduling of tasks and ensure the priority execution of core businesses, but also optimize the efficiency of node resource allocation, avoiding resource waste and overload; at the same time, they reduce the risk of task interruption, ensure business continuity, and further enhance the flexibility and robustness of the scheduling system, enabling it to efficiently adapt to various complex business scenarios.

[0095] Further, step 216 may specifically include: determining whether the priority of the content distribution task is higher than the priority of the current business task; if it is higher, then stop the target node from accessing new requests for the current business task and cache incomplete requests and task running status data; determine the migration node for the current business task and smoothly migrate the current business task to the migration node; and use the target node to execute the content distribution task; if it is not higher, then after the target node completes the current business task, use the target node to execute the content distribution task.

[0096] Specifically, an incomplete request refers to a user request or transaction that has been received but not yet processed on the target node at the moment of "stopping new requests." Task execution status data refers to the core data set generated in real-time and continuously updated during the execution of the current business task on the target node, used to characterize task execution progress, resource usage, and data interaction status. A migration node refers to another node, selected and determined through screening, used to receive and take over the current business task from the target node.

[0097] In practice, the priority of the content distribution task is first determined based on a preset priority level judgment rule (e.g., a numerical level of 1-10, with level 1 being the highest; or divided into low, medium, and high levels, with high being the highest). If the priority is higher, the target node is immediately stopped from receiving new requests for the current business task to avoid new requests continuously occupying node resources. At the same time, the node's local caching mechanism is triggered to completely cache the requests received but not yet processed in the current business task, as well as the task's running status data (including execution progress, resource usage, data interaction context, etc.), to the node's temporary storage area or the system's shared storage cluster. The system selects the node with the best hardware resources from the idle nodes (i.e., nodes that are not currently undertaking any business tasks) in the backup node pool or the primary node pool as the migration node. The cached unfinished requests and task running status data are transmitted to the migration node through a high-speed data synchronization channel. After receiving the data, the migration node restores the execution context of the current business task based on the task running status data, resumes processing unfinished requests from the breakpoint, and continues to take over the current business task. After the migration node stably runs the current business task, the target node releases its resource occupation of the business and starts the execution process of the content distribution task, that is, it uses the target node to execute the content distribution task.

[0098] If the value is not higher, the content distribution task will be added to the task waiting queue of the target node; at the same time, the execution progress monitoring mechanism of the current business task will be started. Once the target node has completed all request processing for the current business task, the content distribution task will be executed using the target node.

[0099] In this embodiment, the above steps not only ensure the priority execution of high-priority content distribution tasks and improve the quality of core business services, but also enable seamless migration of current business tasks, ensuring business continuity and data integrity. At the same time, they optimize the refined management and control of node resources, effectively improving resource utilization.

[0100] Step 217: Execute the content distribution task using the target node.

[0101] The content distribution task processing method provided in this embodiment of the invention first acquires the content distribution task to be processed, real-time node resource information of each available node, and real-time business characteristic information, providing a data foundation for subsequent calculation of the task adaptation score of each available node. Next, based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information, the task adaptation score of each available node is calculated. This achieves a quantitative evaluation of the matching degree between each available node and the content distribution task based on the actual operating status of the nodes, and improves the accuracy of the quantitative results, thus providing reliable data support for accurate matching of nodes and tasks. Then, it is determined whether there are any available nodes among the available nodes whose task adaptation score is greater than a preset score threshold. If so, the available node with the highest task adaptation score among the available nodes is selected as the target node. This effectively reduces resource waste and transmission latency, improves content transmission rate, and shortens task completion time, thereby optimizing the utilization rate of network resources and comprehensively improving service quality while ensuring the execution quality of individual tasks. If no such task exists, the content distribution task is split into a preset number of sub-distribution tasks. The top preset number of available nodes with the highest task adaptation scores are selected as the target nodes for each sub-distribution task. This not only ensures the continuous execution of the content distribution task without interruption but also significantly improves resource utilization and effectively reduces system scheduling costs, further enhancing the flexibility and scenario adaptability of the scheduling system. Next, it is determined whether the target node is currently executing other business tasks. If the target node is executing other business tasks, a task execution strategy is determined based on the priority of the content distribution task and the current business task. This not only achieves differentiated task scheduling, ensuring the priority execution of core business tasks, but also optimizes node resource allocation efficiency, avoiding resource waste and overload; it also reduces the risk of task interruption, ensuring business continuity; and further enhances the flexibility and robustness of the scheduling system, enabling efficient adaptation to various complex business scenarios. If the target node is not executing other business tasks, the content distribution task is executed using the target node. This optimizes the overall network resource allocation, reduces resource waste and operating costs, ensures the access experience for end users, comprehensively improves service quality, and enhances overall system stability, effectively reducing the risk of failure. Therefore, the technical solution of the present invention solves the technical problem in the prior art that it is impossible to match the optimal execution node for the task according to the actual operation of the node, which leads to load imbalance between nodes and reduced overall content distribution system operating efficiency.

[0102] Figure 3 This is a schematic diagram of a content distribution task processing apparatus provided in an embodiment of the present invention. This apparatus belongs to the same inventive concept as the content distribution task processing methods in the above embodiments. Details not described in detail in the embodiments of the content distribution task processing apparatus can be found in the embodiments of the content distribution task processing methods described above. Figure 3As shown, the device includes:

[0103] like Figure 3 As shown, the device includes:

[0104] The acquisition module 310 is used to acquire the content distribution task to be processed, the real-time node resource information of each available node, and the real-time business characteristic information.

[0105] The calculation module 320 is used to calculate the task adaptation score of each available node based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information.

[0106] The determination module 330 is used to select the available node with the highest task adaptation score among all available nodes as the target node.

[0107] The execution module 340 is used to execute the content distribution task using the target node.

[0108] Based on the above embodiments, the task information includes task type and task target parameters, and the calculation module 320 is specifically used for:

[0109] Based on the task objective parameters and the real-time business characteristic information, the constraints for node selection are determined; based on the constraints, each available node is selected to obtain the selected available nodes; based on the real-time node resource information of each available node, the node resource association information of the corresponding node is determined; based on the historical node resource information and node resource association information of each available node, the future node resource information of the corresponding node is predicted; based on the task type and the future node resource information of each available node, the task adaptation score of each available node is determined.

[0110] Based on the above embodiments, the future node resource information includes future network bandwidth, future network latency, future packet loss rate, future input / output operands, future throughput, and future queue depth. The calculation module 320 determines the task adaptation score of each available node based on the task type and the future node resource information of each available node, including:

[0111] For a currently available node, calculate the network adaptation score based on the node's future network bandwidth, future network latency, and future packet loss rate; calculate the disk adaptation score based on the node's future input / output operands, future throughput, and future queue depth; and weight the disk adaptation score and the network adaptation score based on the task type to obtain the node's task adaptation score.

[0112] Based on the above embodiments, the device further includes:

[0113] The update module is used to, after weighting the disk adaptation score and the network adaptation score based on the task type to obtain the task adaptation score of the currently available node, determine the historical successful execution count and the total execution count of the currently available node for the task type; calculate the ratio of the historical successful execution count to the total execution count to obtain the historical adaptation score of the currently available node; and update the task adaptation score of the currently available node using the historical adaptation score to obtain the updated task adaptation score of the currently available node.

[0114] Based on the above embodiments, the device further includes:

[0115] The first judgment module is used to determine whether there are any available nodes with a task adaptation score greater than a preset score threshold among the available nodes before using the available node with the highest task adaptation score among the available nodes as the target node; if there are, the available node with the highest task adaptation score among the available nodes is used as the target node; if there are, the content distribution task is split into a preset number of sub-distribution tasks, and the top preset number of available nodes with the highest task adaptation scores are selected as the target nodes of each sub-distribution task.

[0116] Based on the above embodiments, the device further includes:

[0117] The second judgment module is used to determine the content distribution task before using the target node.

[0118] Determine whether the target node is currently performing other business tasks; if the target node is currently performing other business tasks, determine the task execution strategy of the target node based on the priority of the content distribution task and the current business task; if the target node is not performing other business tasks, then utilize the target node to execute the content distribution task.

[0119] Based on the above embodiments, the second judgment module determines the task execution strategy of the target node based on the priority of the content distribution task and the current business task, including:

[0120] Determine whether the priority of the content distribution task is higher than the priority of the current business task: if it is higher, stop the target node from accessing new requests for the current business task and cache incomplete requests and task running status data; determine the migration node for the current business task and smoothly migrate the current business task to the migration node; use the target node to execute the content distribution task; if it is not higher, use the target node to execute the content distribution task after the target node completes the current business task.

[0121] The content distribution task processing apparatus provided in this embodiment of the invention can execute the content distribution task processing method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] It is worth noting that in the embodiments of the above-mentioned content distribution task processing device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0123] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0124] like Figure 4 As shown, electronic device 4 is represented in the form of a general-purpose computing electronic device. The components of electronic device 4 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0125] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0126] Electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0127] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0128] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0129] Electronic device 4 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 4, and / or with any device that enables electronic device 4 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 4 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 4 As shown, network adapter 20 communicates with other modules of electronic device 4 via bus 18. It should be understood that, although... Figure 4 Not shown, it can be combined with electronic device 4 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0130] Processing unit 16 executes various functional applications and page displays by running programs stored in system memory 28, such as implementing the content distribution task processing method provided in this embodiment of the invention, which includes:

[0131] Obtain the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information;

[0132] Based on the task information of the content distribution task, the real-time node resource information and real-time business characteristic information of each available node, the task adaptation score of each available node is calculated.

[0133] The node with the highest task adaptation score among all available nodes is selected as the target node.

[0134] The content distribution task is executed using the target node.

[0135] Of course, those skilled in the art will understand that the processor can also implement the technical solution of the content distribution task processing method provided in any embodiment of the present invention.

[0136] This invention provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements, for example, a content distribution task processing method provided in this invention, the method comprising:

[0137] Obtain the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information;

[0138] Based on the task information of the content distribution task, the real-time node resource information and real-time business characteristic information of each available node, the task adaptation score of each available node is calculated.

[0139] The node with the highest task adaptation score among all available nodes is selected as the target node.

[0140] The content distribution task is executed using the target node.

[0141] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0142] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0143] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0144] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0145] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0146] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant laws and regulations.

[0147] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for processing content distribution tasks, characterized in that, The method includes: Obtain the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information; Based on the task information of the content distribution task, the real-time node resource information and real-time business characteristic information of each available node, the task adaptation score of each available node is calculated. The node with the highest task adaptation score among all available nodes is selected as the target node. The content distribution task is executed using the target node.

2. The method according to claim 1, characterized in that, The task information includes task type and task target parameters. Based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information, the task adaptation score of each available node is calculated, including: Based on the task objective parameters and the real-time business characteristic information, determine the constraints for node selection; Based on the aforementioned constraints, each available node is filtered to obtain the filtered available nodes; The node resource association information of the corresponding node is determined based on the real-time node resource information of each available node. Based on the historical node resource information and node resource association information of each available node, predict the future node resource information of the corresponding node; Based on the task type and the future node resource information of each available node, the task adaptation score of each available node is determined.

3. The method according to claim 2, characterized in that, The future node resource information includes future network bandwidth, future network latency, future packet loss rate, future input / output operands, future throughput, and future queue depth. Based on the task type and the future node resource information of each available node, determine the task adaptation score of each available node, including: For currently available nodes, calculate the network adaptation score of the currently available nodes based on the future network bandwidth, future network latency, and future packet loss rate of the currently available nodes; Calculate the disk adaptation score of the currently available nodes based on the future number of input / output operands, future throughput, and future queue depth of the currently available nodes. The disk adaptation score and the network adaptation score are weighted based on the task type to obtain the task adaptation score of the currently available node.

4. The method according to claim 3, characterized in that, After weighting the disk adaptation score and the network adaptation score based on the task type to obtain the task adaptation score of the currently available node, the process further includes: Determine the historical successful execution count and total execution count for the given task type on the currently available nodes; Calculate the ratio of the historical successful execution count to the total execution count to obtain the historical adaptation score of the currently available node; The task adaptation score of the currently available node is updated using the historical adaptation score to obtain the updated task adaptation score of the currently available node.

5. The method according to claim 1, characterized in that, Before selecting the available node with the highest task adaptation score from among all available nodes as the target node, the following steps are also included: Determine whether there are any available nodes among the available nodes whose task adaptation score is greater than the preset score threshold; If it exists, the available node with the highest task adaptation score among all available nodes will be used as the target node; If it does not exist, the content distribution task will be split into a preset number of sub-distribution tasks, and the top preset number of available nodes with the highest task adaptation scores will be selected as the target nodes for each sub-distribution task.

6. The method according to claim 1, characterized in that, Before executing the content distribution task using the target node, the following is also included: Determine whether the target node is currently performing other business tasks; If the target node is performing other business tasks, the task execution strategy of the target node is determined based on the priority of the content distribution task and the current business task; If the target node is not performing other business tasks, then the content distribution task is performed using the target node.

7. The method according to claim 6, characterized in that, Based on the priority of the content distribution task and the current business task, the task execution strategy of the target node is determined, including: Determine whether the priority of the content distribution task is higher than the priority of the current business task: If the value is higher, then stop the target node from accessing new requests for the current business task, and cache incomplete requests and task running status data; determine the migration node for the current business task, and smoothly migrate the current business task to the migration node; use the target node to execute the content distribution task; If the value is not higher, then after the target node completes the current business task, the content distribution task will be executed using the target node.

8. A processing apparatus for a content distribution task, characterized in that, The device includes: The acquisition module is used to acquire the content distribution tasks to be processed, real-time node resource information of each available node, and real-time business characteristic information. The calculation module is used to calculate the task adaptation score of each available node based on the task information of the content distribution task, the real-time node resource information of each available node, and the real-time business characteristic information. The determination module is used to select the available node with the highest task adaptation score among all available nodes as the target node. An execution module is used to execute the content distribution task using the target node.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the processing method for the content distribution task as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the processing method for the content distribution task described in any one of claims 1-7.

Images