Computing resource allocation method and device, equipment, medium and product

By dynamically allocating computing resources in the metauniverse environment, the problems of resource waste and load imbalance in the allocation of metauniverse computing resources are solved, and efficient resource utilization and load balancing are achieved.

CN119065854APending Publication Date: 2024-12-03CHINA MOBILE INFORMATION TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411296161.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional computing resource allocation schemes cannot meet the super-large-scale calls of computing resources in the metacosmic environment, resulting in resource waste and unbalanced node loads.

Method used

By predividing the computing resources into multiple resource blocks on the target computing node, dynamically allocate tasks to appropriate resource blocks according to the resource demand status of the operation and maintenance task, and preferentially select resource blocks with small remaining resources to retain more resource blocks. Large resource blocks ensure the processing capability of subsequent tasks.

Benefits of technology

Effectively balance the system load, avoid node load imbalance and performance bottlenecks, improve resource utilization, reduce resource waste, and improve system response speed and service quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065854A_ABST
    Figure CN119065854A_ABST
Patent Text Reader

Abstract

The invention discloses a computing resource allocation method and device, equipment, a medium and a product, and is applied to the technical field of meta-universe operation and maintenance. In the embodiment of the invention, the target computing node selects the resource blocks according to the original sequence of the resource blocks under the condition that the resource quantity demand state does not meet the preset condition, so that the target resource block for executing the operation and maintenance task can be efficiently determined. And under the condition that the resource quantity demand state meets the preset condition, the tasks are preferentially allocated to the resource blocks with the small residual resource quantity, and more resource blocks with the larger residual resource quantity are reserved as much as possible, so that it is ensured that when a subsequent operation and maintenance task arrives, the resource blocks with the processing capacity still exist in the computing node. Therefore, according to the scheme, the dynamic allocation and adjustment of the resources are realized, the system load is effectively balanced, the node load imbalance and the performance bottleneck are avoided, the resource utilization rate is improved, and the resource waste is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of metaverse operation and maintenance technology, and in particular, relates to a computing resource allocation method, device, equipment, medium and product. Background Art

[0002] In the actual application environment of Metaverse O&M, there are usually a large number of heterogeneous O&M tasks that need to be performed on edge computing nodes, such as data processing, network management, and security monitoring. At the same time, these O&M tasks may have different resource requirements. Therefore, designing a task scheduling algorithm to assign O&M tasks to more appropriate computing nodes is crucial to improving O&M efficiency and resource utilization.

[0003] Traditional computing resource allocation schemes are all based on settings for regular business. They cannot meet the ultra-large-scale calls for computing resources in the metaverse environment, nor can they reasonably schedule tasks according to the resource requirements of the tasks, resulting in resource waste and unbalanced node load problems. Summary of the invention

[0004] The embodiments of the present application provide a computing resource allocation method, device, equipment, medium and product, which can solve the problems of resource waste and node load imbalance.

[0005] On the one hand, an embodiment of the present application provides a computing resource allocation method, which is applied to a target computing node, wherein the computing resources of the target computing node are pre-divided into multiple resource blocks; the method includes:

[0006] When receiving the target operation and maintenance task from the operation and maintenance terminal, obtain the resource demand status of each operation and maintenance task received by itself;

[0007] Determine whether the resource demand state meets a preset condition; the preset condition includes that the number of first operation and maintenance tasks exceeds a threshold value within a preset historical time period, and the first operation and maintenance task is an operation and maintenance task whose resource demand is greater than the resource threshold value;

[0008] In the case that the resource quantity demand state does not meet the preset condition, among the resource blocks of the own, according to the original order of the resource blocks, the first resource block that meets the resource quantity demand of the target operation and maintenance task is determined as the target resource block;

[0009] In the case where the resource demand state meets the preset condition, among the resource blocks of the resource block, the resource block with the smallest remaining resource amount and meeting the resource demand of the target operation and maintenance task is determined as the target resource block;

[0010] Allocate the target operation and maintenance task to the selected target resource block.

[0011] On the other hand, when the resource demand state satisfies the preset condition, among the resource blocks thereof, the resource block having the smallest remaining resource amount and satisfying the resource demand of the target operation and maintenance task is determined as the target resource block, including:

[0012] Sort each resource block of the resource block in the ascending order of remaining resource amount to obtain a sorting result;

[0013] According to the sorting result, traverse each resource block of the own;

[0014] The first traversed resource block that meets the resource quantity requirement of the target operation and maintenance task is determined as the target resource block.

[0015] On the other hand, when receiving the target operation and maintenance task from the operation and maintenance terminal, obtaining the resource demand state of each operation and maintenance task received by itself includes:

[0016] Obtaining each second operation and maintenance task received within the preset historical time period;

[0017] Determine the corresponding resource demand based on the number of CPU cores and / or the size of the memory occupied by the second operation and maintenance task;

[0018] Comparing the resource requirement of each of the second operation and maintenance tasks with the resource threshold;

[0019] Determine the second operation and maintenance task whose resource demand is greater than the resource threshold as the first operation and maintenance task;

[0020] Determine the number of the first operation and maintenance tasks.

[0021] On the other hand, an embodiment of the present application provides a computing resource allocation method, which is applied to a central server, and the method includes:

[0022] Upon receiving a target operation and maintenance task requirement from the operation and maintenance terminal, determining a target computing node for completing the target operation and maintenance task from among the computing nodes;

[0023] The target operation and maintenance task is allocated to the target computing node, so that the target computing node executes the computing resource allocation method applied to the target computing node as described above.

[0024] On the other hand, in the case of receiving the target operation and maintenance task requirement sent by the operation and maintenance terminal, determining the target computing node for completing the target operation and maintenance task in each computing node includes:

[0025] Get the distance between each computing node and the operation and maintenance terminal;

[0026] The computing nodes whose distance to the operation and maintenance terminal is less than the maximum distance threshold are determined as pending computing nodes;

[0027] The target computing node is selected from the pending computing nodes.

[0028] On the other hand, the step of selecting the target computing node from the pending computing nodes includes:

[0029] Based on the probability determination rule, determine the selection probability value corresponding to each of the pending computing nodes;

[0030] Based on the selection probability value, the target computing node is selected from each of the pending computing nodes; the selection probability value is positively correlated with the probability of the pending computing node being selected.

[0031] On the other hand, the determining of the selection probability value corresponding to each of the pending computing nodes based on the probability determination rule includes any one or any combination of the following:

[0032] Determine the selection probability value based on the remaining resources of the pending computing node; the remaining resources of the pending computing node are positively correlated with the selection probability value;

[0033] The selection probability value is determined based on the distance between each of the pending computing nodes and the operation and maintenance terminal; the distance between the pending computing node and the operation and maintenance terminal is negatively correlated with the selection probability value.

[0034] On the other hand, after allocating the target operation and maintenance task to the target computing node, the method further includes:

[0035] The selection probability value corresponding to the target computing node is reduced.

[0036] On the other hand, selecting the target computing node from the pending computing nodes based on the selection probability value includes:

[0037] According to the selection probability values ​​corresponding to the pending computing nodes, a target digital set is constructed; the pending computing nodes correspond to the numbers in the target digital set, and the selection probability values ​​of the pending computing nodes are positively correlated with a first number; the first number is the number of numbers corresponding to the pending computing nodes in the target digital set;

[0038] Randomly select a target number from the target number set;

[0039] The undetermined computing node corresponding to the target number is determined as the target computing node.

[0040] On the other hand, before determining the computing node whose distance to the operation and maintenance terminal is less than the maximum distance threshold as the pending computing node, the method further includes:

[0041] Obtaining the timeliness index of the target operation and maintenance task;

[0042] The maximum distance threshold is determined according to the timeliness index; the timeliness index is negatively correlated with the maximum distance threshold.

[0043] On the other hand, an embodiment of the present application provides a computing resource allocation device, which is applied to a target computing node, wherein the computing resources of the target computing node are pre-divided into a plurality of resource blocks; the device comprises:

[0044] A first acquisition module is used to obtain the resource demand status of each operation and maintenance task received by itself when receiving the target operation and maintenance task from the operation and maintenance terminal;

[0045] A judgment module is used to judge whether the resource demand state meets a preset condition; the preset condition includes that the number of first operation and maintenance tasks exceeds a threshold value within a preset historical time period, and the first operation and maintenance task is an operation and maintenance task whose resource demand is greater than the resource threshold value; if the resource demand state does not meet the preset condition, triggering a first determination module; if the resource demand state meets the preset condition, triggering a second determination module;

[0046] The first determination module is used to determine, among its own resource blocks, the first resource block that meets the resource quantity requirement of the target operation and maintenance task according to the original order of the resource blocks as the target resource block;

[0047] The second determination module is used to determine, among its own resource blocks, a resource block with the smallest remaining resource amount and meeting the resource amount requirement of the target operation and maintenance task as a target resource block;

[0048] The allocation module is used to allocate the target operation and maintenance task to the selected target resource block.

[0049] In another aspect, an embodiment of the present application provides a computing resource allocation device, the device comprising: a processor and a memory storing computer program instructions;

[0050] When the processor executes the computer program instructions, the computing resource allocation method as described above is implemented.

[0051] On the other hand, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the computing resource allocation method described above is implemented.

[0052] On the other hand, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the computing resource allocation method as described above.

[0053] A computing resource allocation method of an embodiment of the present application, when the target computing node receives the target operation and maintenance task, obtains the resource demand state of each operation and maintenance task received by itself, and then determines whether the resource demand state meets the preset conditions. For example, when the resource demand state does not meet the preset conditions, the resource blocks are selected according to the original order of each resource block, and the target resource block for executing the operation and maintenance task can be efficiently determined. When the resource demand state meets the preset conditions, that is, when there are more first operation and maintenance tasks with larger resource demands, it indicates that more resource blocks with larger remaining resources are needed in the current time period; at this time, tasks are preferentially assigned to resource blocks with smaller remaining resources, and more resource blocks with larger remaining resources are reserved as much as possible to ensure that when subsequent operation and maintenance tasks arrive, there are still resource blocks with processing capabilities in the computing node. It can be seen that this scheme realizes the dynamic allocation and adjustment of resources, effectively balances the system load, avoids node load imbalance and performance bottlenecks, improves resource utilization, and reduces resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 A schematic diagram of a flow chart of a computing resource allocation method applied to a target computing node provided by an embodiment of the present application is shown;

[0056] Figure 2 A schematic diagram of a flow chart of a computing resource allocation method applied to a central server provided by an embodiment of the present application is shown;

[0057] Figure 3 A specific flow chart of a method for allocating computing resources for Metaverse operation and maintenance provided by an embodiment of the present application is shown;

[0058] Figure 4 A schematic diagram of the structure of a computing resource allocation device applied to a target computing node provided in an embodiment of the present application is shown;

[0059] Figure 5 A schematic diagram of the structure of a computing resource allocation device applied to a central server provided in an embodiment of the present application is shown;

[0060] Figure 6 A schematic diagram of the hardware structure of a computing resource allocation device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0061] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0062] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "include..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0063] With the development of cloud-native technology, the complexity of application systems has increased exponentially, and operation and maintenance personnel are required to participate in ensuring the stability of the platform. Operation and maintenance involves multiple departments and teams. In the operation and maintenance process, there are problems such as information asymmetry among all parties, scattered operation and maintenance data, and lack of effective sedimentation of operation and maintenance data. It is urgent to improve the digital level of operation and maintenance to support the digital transformation of enterprises; break through the boundaries of time and space, construct an operation and maintenance information interaction platform that combines virtual and real, empower operation and maintenance business scenarios, and realize an immersive operation and maintenance experience. Specifically, metaverse technology can be used to improve operation and maintenance capabilities and realize a new model of digital reconstruction of operation and maintenance assurance; produce a set of polymorphic metaverse operation and maintenance solutions, and explore the application of various metaverse technologies in operation and maintenance scenarios.

[0064] This solution takes the Metaverse space as the core, connects the command and dispatch scenarios of the integrated network management system of Internet technology in the entire network, integrates digital, voice, and communication capability components, and pushes operation and maintenance data of local applications and controls the authority of operation and maintenance terminals to meet the business scenarios of coordinated fault dispatch of the entire network in the Metaverse system.

[0065] Traditional computing resource allocation schemes are all based on the settings of regular business, which cannot meet the ultra-large-scale call for computing resources in the metaverse environment. Unreasonable task scheduling will lead to resource waste and unbalanced node load.

[0066] In order to solve the problems of the traditional solution, the embodiment of the present application provides a computing resource allocation method, device, equipment, medium and product. The computing resource allocation method provided by the embodiment of the present application is first introduced below. Figure 1 A schematic diagram of a process flow of a computing resource allocation method applied to a target computing node provided by an embodiment of the present application is shown; Figure 1 As shown, the method includes the following steps: S101 to S105.

[0067] S101: When receiving a target operation and maintenance task from an operation and maintenance terminal, obtain the resource demand status of each operation and maintenance task received by itself.

[0068] In actual scenarios, there are multiple operation and maintenance terminals, which are located in different geographical locations. The operation and maintenance personnel of these operation and maintenance terminals will issue some operation and maintenance tasks. The system used to perform these tasks includes a central processor and multiple computing nodes (such as edge computing nodes or cloud service nodes). The central processor will assign these operation and maintenance tasks to the corresponding computing nodes. After the computing nodes complete the tasks, they will return the execution results to the operation and maintenance terminals.

[0069] For example, when an operation and maintenance terminal sends a target operation and maintenance task, the central processor selects a suitable target computing node from each computing node and assigns the target operation and maintenance task to the selected target computing node. When selecting the target computing node, the distance between the operation and maintenance terminal and the computing node, as well as the remaining resources of the computing node, can be considered. After the target computing node completes the target operation and maintenance task, it returns the execution result to the operation and maintenance terminal.

[0070] When the target computing node receives the target operation and maintenance task from the operation and maintenance terminal, it will obtain the resource demand status of each operation and maintenance task received by itself, which may include the number of large resource blocks required to run each operation and maintenance task, etc. The resource demand status can be characterized by the number of first operation and maintenance tasks. For example, within a preset historical time period, the first operation and maintenance task among the received operation and maintenance tasks is determined, and then the number of first operation and maintenance tasks is counted. Here, the first operation and maintenance task is an operation and maintenance task whose resource demand is greater than the resource threshold.

[0071] The specific size of the resource threshold in the above text is not limited and can be set according to the actual situation. In practice, the resource amount can be characterized by the number of CPU cores and / or the size of the memory occupied by the operation and maintenance task. The specific length of the above preset historical time period can also be selected according to actual needs, for example, one hour before the current time can be selected.

[0072] S102: Determine whether the resource demand state meets the preset conditions; if the resource demand state does not meet the preset conditions, proceed to S103; if the resource demand state meets the preset conditions, proceed to S104.

[0073] After counting the number of first operation and maintenance tasks in the above text, it is possible to determine whether the resource demand state meets the preset condition based on the number of first operation and maintenance tasks. The specific content of the preset condition is determined according to the actual situation, and can be set as the number of first operation and maintenance tasks exceeding the threshold in the preset historical time period. The size of the threshold is set according to demand.

[0074] S103: Among its own resource blocks, according to the original order of the resource blocks, determine the first resource block that meets the resource quantity requirement of the target operation and maintenance task as the target resource block.

[0075] The computing resources of the computing node can be divided into multiple resource blocks according to the preset granularity. Each resource block of the target computing node itself has an original sequence. When the resource demand state does not meet the preset conditions, it indicates that the resource demand of the operation and maintenance task at this time is too small. At this time, the target computing node traverses its own resource blocks in the original order until it finds the first resource block that meets the resource demand of the target operation and maintenance task, and then determines the found resource block as the target resource block. By traversing in the original order, no additional special processing is required, and the target resource block for executing the target operation and maintenance task can be efficiently determined.

[0076] S104: Among its own resource blocks, determine the resource block with the smallest remaining resource amount and meeting the resource amount requirement of the target operation and maintenance task as the target resource block.

[0077] When the resource demand state meets the preset conditions, it means that there are more first operation and maintenance tasks with larger resource demand, and more resource blocks with larger remaining resources are needed at this time. Therefore, it is necessary to give priority to assigning operation and maintenance tasks to resource blocks with smaller remaining resources, and keep as many resource blocks with larger remaining resources as possible to ensure that there are still resource blocks with processing capabilities in the computing nodes when subsequent operation and maintenance tasks arrive.

[0078] Specifically, the target computing node determines the resource block with the smallest remaining resource amount among its own resource blocks and that meets the resource amount requirement of the target operation and maintenance task as the target resource block, thereby retaining those resource blocks with more remaining resource amounts to ensure that subsequent operation and maintenance tasks can be completed normally.

[0079] S105: Allocate the target operation and maintenance task to the selected target resource block.

[0080] Through the different resource block determination schemes adopted in the above two different situations, when the resource demand state is normal, a scheme for quickly determining the target resource block is adopted; and when the resource demand state indicates that the current resource quantity is tight, resource blocks with small remaining resources are preferred. Using different target resource block determination schemes for different situations can effectively balance the system load, avoid node load imbalance and performance bottlenecks, improve resource utilization, and reduce resource waste.

[0081] After the target resource block is determined, the target operation and maintenance task is assigned to the selected target resource block, the target resource block will execute the target operation and maintenance task, obtain the execution result, and finally return the execution result to the operation and maintenance terminal.

[0082] The embodiment of the present application can maximize the use of computing resources of edge computing nodes, improve resource utilization, and reduce resource waste by dynamically adjusting resource selection probability values ​​and intelligent resource scheduling algorithms. It can realize dynamic allocation and adjustment of resources according to node load conditions and operation and maintenance terminal requirements, effectively balance system loads, and avoid node load imbalances and performance bottlenecks. By real-time monitoring of operation and maintenance terminal requirements and node status, as well as a fast resource allocation and adjustment mechanism, it can respond to operation and maintenance terminal requests in a timely manner, and improve the response speed and service quality of the system. It can be dynamically adjusted according to the system status and load conditions, maintain the stability and reliability of the system, effectively respond to sudden loads and failures, and improve the fault tolerance of the system.

[0083] A computing resource allocation method of an embodiment of the present application, when the target computing node receives the target operation and maintenance task, obtains the resource demand state of each operation and maintenance task received by itself, and then determines whether the resource demand state meets the preset conditions. For example, when the resource demand state does not meet the preset conditions, the resource blocks are selected according to the original order of each resource block, and the target resource block for executing the operation and maintenance task can be efficiently determined. When the resource demand state meets the preset conditions, that is, when there are more first operation and maintenance tasks with larger resource demands, it indicates that more resource blocks with larger remaining resources are needed in the current time period; at this time, tasks are preferentially assigned to resource blocks with smaller remaining resources, and more resource blocks with larger remaining resources are reserved as much as possible to ensure that when subsequent operation and maintenance tasks arrive, there are still resource blocks with processing capabilities in the computing node. It can be seen that this scheme realizes the dynamic allocation and adjustment of resources, effectively balances the system load, avoids node load imbalance and performance bottlenecks, improves resource utilization, and reduces resource waste.

[0084] The above embodiment mentioned that when the resource demand state meets the preset conditions, among the resource blocks of the resource block, the resource block with the smallest remaining resource amount and meeting the resource demand of the target operation and maintenance task is determined as the target resource block. The present application does not limit the specific determination scheme. For example, the resource blocks that meet the resource demand of the target operation and maintenance task can be counted first, and then the resource block with the smallest remaining resource amount can be determined from these resource blocks as the target resource block. However, this method requires judging whether each resource block meets the resource demand, and the task volume is large.

[0085] In order to quickly find the resource block with the smallest remaining resource amount and meeting the resource amount requirement, the embodiment of the present application provides a specific implementation scheme. First, the remaining resource amount of each resource block is obtained, and then the resource blocks of the system are sorted in order from small to large in the order of the remaining resource amount to obtain the sorting result. Then, according to the sorting result, the resource blocks of the system are traversed until the resource block that meets the resource amount requirement of the target operation and maintenance task is traversed, and then the first resource block that meets the resource amount requirement of the target operation and maintenance task is determined as the target resource block.

[0086] In the target resource block determination scheme provided in the embodiment of the present application, when the resource quantity demand state meets the preset conditions, the target resource block with the smallest remaining resource quantity and meeting the requirements can be quickly found by sorting and traversing each resource block according to the remaining resource quantity from small to large.

[0087] The above embodiment mentioned that the preset condition can be set as the number of first operation and maintenance tasks exceeding a threshold value within a preset historical time period. The embodiment of the present application provides a specific solution for determining the number of first operation and maintenance tasks.

[0088] First, when receiving the target operation and maintenance task of the operation and maintenance terminal, first obtain each second operation and maintenance task received within a preset historical time period. Then, based on the number of cores of the central processing unit occupied by the second operation and maintenance task and / or the size of the memory occupied, determine the corresponding resource demand; and compare the resource demand of each second operation and maintenance task with the resource threshold; the second operation and maintenance task whose resource demand is greater than the resource threshold is determined as the first operation and maintenance task. The determined first operation and maintenance tasks can be marked, and finally the number of marked tasks within the preset historical time period is counted to obtain the number of first operation and maintenance tasks. In practical applications, it is also possible to use a counting accumulation method, that is, to set a variable with an initial value of zero. Each time a first operation and maintenance task is determined, the value of the variable is increased by one, and finally the value of the variable represents the number of first operation and maintenance tasks.

[0089] In the solution proposed in the embodiment of the present application, the resource requirement of the task can be determined more accurately based on the number of cores of the central processing unit corresponding to the task and / or the size of the memory occupied.

[0090] In order to solve the above technical problems, the present application also provides a computing resource allocation method applied to a central server. Figure 2 A flow chart of a computing resource allocation method applied to a central server provided by an embodiment of the present application is shown; Figure 2 As shown; the method comprises the following steps:

[0091] S201: Upon receiving a target operation and maintenance task requirement from an operation and maintenance terminal, a target computing node for completing the target operation and maintenance task is determined among the computing nodes.

[0092] S202: Allocate the target operation and maintenance task to the target computing node, so that the target computing node executes the computing resource allocation method mentioned in the above embodiment.

[0093] As mentioned above, there are usually multiple computing nodes, so the central processing unit will select a suitable one from these computing nodes as the target computing node to perform the target operation and maintenance task.

[0094] The computing resource allocation method applied to the central server provided in the embodiment of the present application is the same as the computing resource allocation method applied to the target computing node in the above embodiment, so the two have the same embodiments and beneficial effects, which will not be repeated here.

[0095] In actual applications, if the distance between the target computing node and the operation and maintenance terminal is too long, the timeliness of the operation and maintenance task processing will be low, making it impossible to meet actual needs. Therefore, when the central server determines the target computing node, it is necessary to avoid the distance between the target computing node and the operation and maintenance terminal being too long. A maximum distance threshold can be set first, and when selecting the target computing node, computing nodes that exceed this maximum distance threshold are not considered.

[0096] Specifically, when receiving the target operation and maintenance task requirements issued by the operation and maintenance terminal, the distance between each computing node and the operation and maintenance terminal is first obtained, and then the computing nodes whose distance to the operation and maintenance terminal is less than the maximum distance threshold are determined as pending computing nodes; finally, the target computing node is determined from the pending computing nodes within these maximum distance thresholds. The maximum distance threshold can be determined according to the given timeliness index. Generally, the higher the timeliness index, the shorter the maximum distance threshold needs to be set.

[0097] The embodiment of the present application avoids the situation where the distance between the target computing node and the operation and maintenance terminal is too long by setting the maximum allowable distance between the operation and maintenance terminal and the target computing node, thereby avoiding the situation where the business response is too slow and the timeliness is low.

[0098] After determining the pending computing nodes within the maximum distance threshold, it is necessary to select the target computing node from these pending computing nodes to perform the target operation and maintenance task. The specific method can be to first determine the selection probability value corresponding to each pending computing node based on the probability determination rule, and then select the target computing node from each pending computing node based on the selection probability value; the selection probability value is positively correlated with the probability of the pending computing node being selected.

[0099] The embodiment of the present application sets a corresponding selection probability value for each pending computing node, thereby enabling the target computing node that better meets the requirements to be selected to be selected first.

[0100] The specific content of the probability determination rule mentioned above can be determined according to the actual situation. Generally, the more remaining resources of the pending computing node, the more suitable it is for executing the target operation and maintenance task. Therefore, the probability determination rule is that the remaining resources of the pending computing node are positively correlated with the selection probability value.

[0101] The embodiment of the present application sets that the more remaining resources the pending computing node has, the higher the corresponding selection probability value is, ensuring that the selected target computing node has sufficient remaining resources to handle the operation and maintenance task. After being assigned an operation and maintenance task, the corresponding computing node has less remaining resources, and the probability value needs to be reduced so that the selection probability value of each computing node is more in line with actual needs.

[0102] The embodiment of the present application also provides the specific content of another probability determination rule, that is, the distance between the pending computing node and the operation and maintenance terminal is negatively correlated with the selection probability value. Therefore, based on the probability determination rule, the selection probability value corresponding to each pending computing node is determined, including: determining the distance between each pending computing node and the operation and maintenance terminal; determining the selection probability value corresponding to each pending computing node according to the distance between the computing node and the operation and maintenance terminal.

[0103] In the embodiment of the present application, the closer the distance between the pending computing node and the operation and maintenance terminal is, the higher the corresponding selection probability value is, and the service node can be provided nearby, effectively utilizing edge computing resources, reducing operation and maintenance costs and delays, and improving operation and maintenance efficiency and business responsiveness.

[0104] In addition, after the target operation and maintenance task is assigned to the target computing node, a portion of the resources of the target computing node will inevitably be occupied. Therefore, the selection probability value corresponding to the target computing node can be correspondingly reduced at this time.

[0105] The above provides some specific methods for determining the selection probability value, and after determining the selection probability value, it is also necessary to select the target computing node from each pending computing node based on the selection probability value. The embodiment of the present application provides an implementation method for constructing a target digital set, which is as follows.

[0106] First, a target digital set is constructed according to the selection probability value corresponding to each pending computing node; the pending computing node corresponds to the number in the target digital set, and the selection probability value of the pending computing node is positively correlated with the first number; the first number is the number of corresponding numbers of the pending computing node in the target digital set.

[0107] It can be seen that, under normal circumstances, the closer the distance between the pending computing node and the operation and maintenance terminal, and the more remaining resources, the more numbers it occupies in the target number set. After determining the target number set, a target number is randomly selected from the target number set, and the pending computing node corresponding to the target number is determined as the target computing node. Based on the above scheme, it can be ensured that the pending computing node with a larger selection probability value has a greater possibility of being selected as the target computing node.

[0108] The scheme proposed in this embodiment constructs a target number set based on the rule that the higher the selection probability value, the more numbers it occupies; and then randomly selects numbers from the target number set to determine the target computing node, thereby ensuring high efficiency of the selection and ensuring that the selected target computing node has a higher degree of match with the actually required computing node.

[0109] As mentioned above, in order to ensure the timeliness of the operation and maintenance tasks, a maximum distance threshold is set. Only computing nodes within the maximum distance threshold range of the operation and maintenance terminal will be selected as pending computing nodes. The specific size of the maximum distance threshold can be determined according to actual conditions. This embodiment provides a specific determination scheme. Before determining the computing nodes whose distance from the operation and maintenance terminal is less than the maximum distance threshold as pending computing nodes, the timeliness index of the target operation and maintenance task is first obtained, and then the maximum distance threshold is determined based on the timeliness index. In the process of determining the maximum distance threshold, it is ensured that the timeliness index is negatively correlated with the maximum distance threshold.

[0110] This embodiment determines the corresponding maximum distance threshold according to the timeliness requirement of the target operation and maintenance task. When the timeliness requirement is low, a larger maximum distance threshold can be set to provide more options. When the timeliness requirement is high, a smaller maximum distance threshold can be set to ensure timeliness.

[0111] The embodiment of the present application is to maximize the use of computing resources of edge computing nodes, improve resource utilization, and reduce resource waste by dynamically adjusting resource selection probability values ​​and intelligent resource scheduling algorithms. And according to the node load conditions and operation and maintenance terminal requirements, dynamic allocation and adjustment of resources are achieved to effectively balance the system load and avoid node load imbalance and performance bottlenecks. Figure 3 A specific flow chart of a method for allocating computing resources for Metaverse operation and maintenance provided by an embodiment of the present application is shown; Figure 3 As shown, the following steps are included: S301 to S309.

[0112] S301: Distribute multiple computing nodes throughout the system.

[0113] Each edge computing node has its own geographical location. During the distributed layout of edge computing nodes, it is first necessary to determine the deployment strategy of the edge computing nodes. You can consider deploying them in different geographical areas or network areas based on actual conditions.

[0114] Then, according to the deployment strategy, select appropriate locations in the entire system to deploy edge computing nodes. These locations can be located in city centers, densely populated areas, network bottlenecks, etc.

[0115] Next, edge computing nodes are established at the selected locations to ensure that the coverage between nodes is reasonable and can cover the operation and maintenance terminal groups that need to provide services.

[0116] Finally, the geographical location information needs to be determined, which can be done in the following ways: 1. Global Positioning System (GPS) positioning. For physical devices, the accurate geographical location information of the node can be obtained through GPS positioning and other technologies. 2. Network topology analysis. For virtualized edge computing nodes or cloud service nodes, their geographical location can be determined through network topology analysis, for example, based on the Internet Protocol (IP) address segment or network domain where the node is located to infer its approximate geographical location. 3. Manual recording. Manually record the geographical location information of edge computing nodes and enter it into the system for management and distribution.

[0117] S302: Divide the computing resources of each computing node into resource blocks of fixed sizes.

[0118] Here are two resource partitioning strategies. 1. Determine the size of resource blocks: First, you need to determine how large the resource blocks of each edge computing node's computing resources should be divided into. This can be determined based on the total amount of resources at the node and the flexibility of demand. 2. Determine the granularity of resource partitioning, that is, how many resource blocks are divided into. The granularity can be flexibly adjusted according to actual conditions, usually in the smallest unit that can meet the task requirements.

[0119] Resource block division can be divided into automatic division and manual division. Automatic division: The system can automatically divide the computing resources of each edge computing node into fixed-size resource blocks according to the set strategy. This can be achieved through scripts or automation tools, and the division is based on the total resource volume and division granularity of the node. Manual division: In some cases, it may be necessary to manually divide the computing resources. The administrator can manually divide the resource blocks of each edge computing node according to actual needs and system architecture.

[0120] Finally, resource block management is performed to identify and manage each resource block, ensuring that each resource block has a unique identifier, which makes it easier for the system to identify and manage each resource block.

[0121] S303: The central processing unit sets a maximum distance threshold between the operation and maintenance terminal and the edge computing node.

[0122] According to actual needs and system architecture, the CPU sets the maximum distance threshold allowed based on the calculated distance between the operation and maintenance terminal and the node. The set maximum distance threshold can be adjusted according to business needs and system performance requirements, for example, it can be determined based on the timeliness and response requirements of the task. If the business has high timeliness requirements, a relatively small maximum distance needs to be set; if the business has low timeliness requirements, a relatively large maximum distance can be set.

[0123] Here is the specific calculation method through the following example:

[0124] 1) The CPU pre-sets the corresponding relationship between the service type and the timeliness requirement. For example, the timeliness requirement is divided into 10 levels, and different services correspond to different levels. The higher the level of timeliness requirement, the higher the timeliness requirement.

[0125] 2) Set the correspondence between the timeliness requirement and the maximum distance threshold.

[0126] 3) Count the business types of all businesses in the recent period, and obtain the number of businesses with each type of timeliness requirement based on the corresponding relationship between business types and timeliness requirements.

[0127] 4) Arrange the number of businesses at each timeliness level from low to high.

[0128] 5) Select a timeliness level so that the ratio of the number of services less than or equal to the timeliness level to the total number of services just exceeds a predetermined value, such as 80%. For example, if the number of services of timeliness levels 1-5 accounts for 70% and the number of services of timeliness levels 1-6 accounts for 85%, then the selected timeliness level is 6.

[0129] 6) Determine the corresponding maximum distance threshold according to the selected timeliness level.

[0130] S304: When the operation and maintenance terminal sends a metaverse operation and maintenance request to the central server, the central server calculates the distance between the operation and maintenance terminal and each computing node, and selects computing nodes whose distance is less than the maximum distance threshold as pending computing nodes.

[0131] First, the central server obtains the geographic location information of the operation and maintenance terminal, which can be obtained through GPS positioning, IP address positioning, etc.

[0132] Then, the central server continues to obtain the geographic location information of each edge computing node, and can obtain the geographic location of the node through GPS positioning, network topology analysis, etc.

[0133] Next, the central server uses the acquired geographic location information of the operation and maintenance terminal and the edge computing node to calculate the geographic distance between the operation and maintenance terminal and each edge computing node through tools such as a map interface or a geographic information system (GIS).

[0134] Finally, the central server determines the calculated distance between each operation and maintenance terminal and the node to determine whether the distance is less than the set maximum distance threshold.

[0135] If the distance is less than the maximum distance, the computing node is determined to be in the list of pending computing nodes.

[0136] S305: The central server allocates the target operation and maintenance task to the target computing node according to the selected probability value.

[0137] First, the selection probability value is calculated. Initially, the selection probability value can be set to a distance-weighted distribution method, that is, the smaller the distance, the higher the distribution probability. For each pending computing node, the central server calculates the selection probability value based on the distance between the operation and maintenance terminal and the pending computing node. The smaller the distance, the higher the selection probability value.

[0138] A linear or nonlinear distance weighting function may be used to calculate the selection probability value, such as an exponential function, a reciprocal function, and the like.

[0139] For example, there are N pending computing nodes, and the distances between the operation and maintenance terminal and these nodes are: L i , i is a positive integer ranging from 1 to N. Then the probability is:

[0140]

[0141] Finally, based on the calculated selection probability value, the central server determines the final target computing node. Random sampling can be used to determine the allocation node based on the probability distribution. The following example illustrates this.

[0142] For example, the probability of the pending computing node a is 20%, the probability of b is 30%, the probability of c is 40%, and the probability of d is 10%. Then their probability value ranges are: a[1,20]b[21,50]c[51,90]d[91,100]. Then take a random number from [1,100] and select the corresponding node if it falls into the range.

[0143] The algorithm is described as follows: 1. Place each item on the one-dimensional coordinate system in sequence (the order can be random) according to the probability value starting from the origin, so that each item corresponds to a value interval. 2. Randomly select a point within the total interval, and select the item that falls in the interval corresponding to the item. 3. Assign tasks: The central server assigns the metaverse operation and maintenance tasks of the operation and maintenance terminal to the determined target computing node as the node that executes the task.

[0144] S306: Each computing node determines whether the resource demand state meets the preset conditions, if not, execute S307, and if so, execute S308.

[0145] First, monitor the operation and maintenance tasks. Each computing node monitors the assigned operation and maintenance tasks, including information such as the task's resource requirements and execution time.

[0146] Then, the operation and maintenance task data within a certain period of time is counted, such as the amount of resources allocated to the operation and maintenance tasks within a recent period of time (for example, one hour).

[0147] Next, determine whether the resource volume is a large resource demand. For each operation and maintenance task in the monitoring cycle, determine whether its resource volume is a large resource demand. This can be determined by setting thresholds, such as the number of CPU cores, memory size, etc.

[0148] If the resource volume of the operation and maintenance task exceeds the set threshold, it is determined to be a large resource demand.

[0149] Finally, determine the frequency of large resource demand: count the frequency of large resource demand within a certain period of time, such as the number of large resource demands per hour. If the frequency of large resource demand does not exceed the preset threshold, continue to execute S307, that is, the normal resource allocation and task execution process; otherwise, it is determined to be a large resource pulse state, and execute S308, that is, adjust the resource allocation strategy to deal with the sudden situation of large resource demand.

[0150] S307: All resource blocks are arranged according to the initial order, and each resource block is polled in turn to find the first resource block whose remaining resource volume is greater than the resource volume required by the operation and maintenance task, and provide it to the operation and maintenance terminal, and return to S304.

[0151] Sort the resource blocks first: Sort all resource blocks according to the initial order to ensure that the order of the resource blocks is fixed.

[0152] Then poll the resource blocks (i.e. traverse): poll each resource block in the sorted resource block list in turn, and check them one by one in order. That is, check the resource amount, and for each resource block, check whether its remaining resource amount is greater than the resource amount required by the operation and maintenance terminal.

[0153] If the amount of resources meets the needs of the operation and maintenance terminal, the resource block is selected and provided to the operation and maintenance terminal.

[0154] The resource blocks that meet the conditions are provided to the operation and maintenance terminal as the execution node of the task. After the requirements of the operation and maintenance terminal are met, the task can be executed.

[0155] Under normal processing conditions, the response efficiency is mainly considered, and resources are polled according to the fixed order of resource blocks. As long as a resource block that meets the resource requirements is found, the service can be provided.

[0156] S308: Arrange all resource blocks from small to large according to the remaining resource amount, poll each resource block in turn, find the first resource block whose remaining resource amount is greater than the resource amount required by the operation and maintenance task, provide it to the operation and maintenance terminal, and send a request to the central server to reduce the probability value of selecting the corresponding computing node.

[0157] The resource blocks are also sorted first, but this time all resource blocks are sorted from small to large according to the amount of remaining computing resources.

[0158] Next, poll the resource blocks: poll each resource block in the sorted resource block list in turn, and check them one by one in order. For each resource block, check whether its remaining computing resources are greater than the resources required by the operation and maintenance terminal. If the resources meet the requirements of the operation and maintenance terminal, select the resource block and provide it to the operation and maintenance terminal. Provide the resource blocks that meet the conditions to the operation and maintenance terminal as the execution node of the task.

[0159] After the operation and maintenance tasks are assigned, the computing node sends a request to the central server to reduce its own selection probability value. The request can contain information such as the node's unique identifier and the reduction ratio.

[0160] In the case of large resource pulses, when there is a large demand for large resources, it is more necessary to give priority to retaining resource blocks with large remaining resources to meet subsequent large resource business needs. Therefore, it is necessary to start querying from resource blocks with small remaining resources to save as many resource blocks as possible. The server is notified to reduce the probability of task allocation.

[0161] S309: The central server reduces the selection probability value of the computing node according to a predetermined algorithm and returns to S304.

[0162] The central server calculates the selection probability value that needs to be reduced according to a predetermined algorithm, such as a reduction in a fixed ratio or a dynamic adjustment based on historical load, etc. Determine a method for reducing the selection probability value, such as reducing a fixed ratio, reducing in proportion, etc. Taking a fixed ratio as an example, it can be reduced by 1% each time.

[0163] The embodiment of the present application distributes multiple edge computing nodes throughout the system, and each edge computing node has its own geographical location. The central processor sets the maximum allowable distance between the operation and maintenance terminal and the edge computing node. When the operation and maintenance terminal sends a metaverse operation and maintenance requirement to the central server, the central server calculates the distance between the operation and maintenance terminal and each edge computing node, and selects an edge computing node with a distance less than the maximum allowable distance as an alternative edge computing node. It is possible to provide service nodes nearby and improve business responsiveness.

[0164] The central server allocates the operation and maintenance terminal demand to a certain edge computing node according to the selection probability value. Initially, the selection probability value can be set to a distance-weighted allocation method, that is, the smaller the distance, the higher the allocation probability. Each edge computing node monitors the allocated operation and maintenance terminal demand. If it is monitored whether the amount of resources allocated to the operation and maintenance terminal demand in the recent period belongs to a large amount of resources demand, if the frequency of the large amount of resources demand does not exceed the threshold, perform regular operations, that is, all resource blocks are arranged according to the initial order, and each resource block is polled in turn to find the first resource block with a remaining amount of resources greater than the amount of resources required by the operation and maintenance terminal. Otherwise, it is determined to be a large amount of resources pulse state, and the corresponding operation of the large amount of resources pulse state is performed. By identifying large amount of data demand and regular demand, targeted and differentiated processing methods can be provided.

[0165] The operation corresponding to the large resource pulse state is: all resource blocks are arranged from small to large according to the remaining computing resources, and each resource block is polled in turn to find the first resource block whose remaining resources are greater than the required resources of the operation and maintenance terminal, and provide it to the operation and maintenance terminal, and send a request to the central server to reduce the selection probability value. The central server reduces the selection probability value of the edge computing node according to a predetermined algorithm (for example, by reducing a fixed ratio). It can prepare more resources in advance for large data volume services and improve the processing capacity of large data volume services.

[0166] In order to solve the above technical problems, an embodiment of the present application provides a computing resource allocation device, which is applied to a target computing node, and the computing resources of the target computing node are pre-divided into multiple resource blocks. Figure 4 FIG. 4 shows a schematic diagram of the structure of a computing resource allocation device applied to a target computing node provided in an embodiment of the present application; Figure 4 As shown, the device includes the following modules:

[0167] The first acquisition module 401 is used to obtain the resource demand status of each operation and maintenance task received by itself when receiving the target operation and maintenance task from the operation and maintenance terminal;

[0168] The judgment module 402 is used to judge whether the resource demand state meets the preset conditions; the preset conditions include that the number of the first operation and maintenance tasks exceeds the threshold value within the preset historical time period, and the first operation and maintenance task is an operation and maintenance task with a resource demand greater than the resource threshold value; if the resource demand state does not meet the preset conditions, the first determination module 403 is triggered; if the resource demand state meets the preset conditions, the second determination module 404 is triggered;

[0169] The first determination module 403 is used to determine, among its own resource blocks, the first resource block that meets the resource quantity requirement of the target operation and maintenance task according to the original order of the resource blocks as the target resource block;

[0170] The second determination module 404 is used to determine, among its own resource blocks, a resource block with the smallest remaining resource amount and meeting the resource amount requirement of the target operation and maintenance task as a target resource block;

[0171] The allocation module 405 is used to allocate the target operation and maintenance task to the selected target resource block.

[0172] In some embodiments, the second determining module 404 is specifically configured to:

[0173] Sort each resource block of the resource block in the ascending order of remaining resource amount to obtain a sorting result;

[0174] According to the sorting results, traverse each resource block of itself;

[0175] The first resource block found that meets the resource requirement of the target operation and maintenance task is determined as the target resource block.

[0176] In some embodiments, the first acquisition module 401 is specifically configured to:

[0177] Obtain each second operation and maintenance task received within a preset historical time period;

[0178] Determine the corresponding resource demand based on the number of CPU cores and / or the size of the memory occupied by the second operation and maintenance task;

[0179] Compare the resource requirement of each second operation and maintenance task with the resource threshold;

[0180] Determine the second operation and maintenance task whose resource demand is greater than the resource threshold as the first operation and maintenance task;

[0181] Determine the number of first operation and maintenance tasks.

[0182] In order to solve the above technical problems, the present application also provides a computing resource allocation device applied to a central server. Figure 5 The schematic diagram of the structure of the computing resource allocation device applied to the central server provided in the embodiment of the present application is shown; Figure 5 As shown, the device includes the following modules:

[0183] The third determination module 501 is used to determine, among the computing nodes, a target computing node for completing the target operation and maintenance task when receiving a target operation and maintenance task requirement from the operation and maintenance terminal;

[0184] The sending module 502 is used to allocate the target operation and maintenance task to the target computing node, so that the target computing node can execute the computing resource allocation method mentioned in the above embodiment.

[0185] In some embodiments, the third determining module 501 is specifically configured to:

[0186] Get the distance between each computing node and the operation and maintenance terminal;

[0187] The computing nodes whose distance to the operation and maintenance terminal is less than the maximum distance threshold are determined as pending computing nodes;

[0188] A target computing node is selected from the pending computing nodes.

[0189] In some embodiments, the third determining module 501 is specifically configured to:

[0190] Based on the probability determination rule, determine the selection probability value corresponding to each pending computing node;

[0191] Based on the selection probability value, a target computing node is selected from each pending computing node; the selection probability value is positively correlated with the probability of the pending computing node being selected.

[0192] In some embodiments, the computing resource allocation device applied to the central server further includes: a processing module, which is used to reduce the selection probability value corresponding to the target computing node after allocating the target operation and maintenance task to the target computing node.

[0193] In some embodiments, the third determining module 501 is specifically configured to:

[0194] Determine the distance between each pending computing node and the operation and maintenance terminal;

[0195] According to the distance from the operation and maintenance terminal, the selection probability value corresponding to each pending computing node is determined.

[0196] In some embodiments, the third determining module 501 is specifically configured to:

[0197] According to the selection probability values ​​corresponding to the pending computing nodes, a target digital set is constructed; the pending computing nodes correspond to the numbers in the target digital set, and the selection probability values ​​of the pending computing nodes are positively correlated with the first number; the first number is the number of numbers corresponding to the pending computing nodes in the target digital set;

[0198] Randomly select a target number from the target number set;

[0199] The pending computing node corresponding to the target number is determined as the target computing node.

[0200] In some embodiments, the computing resource allocation device applied to the central server further includes:

[0201] The second acquisition module is used to obtain the timeliness index of the target operation and maintenance task;

[0202] The fourth determination module is used to determine the maximum distance threshold according to the timeliness index; the timeliness index is negatively correlated with the maximum distance threshold.

[0203] The device provided in the embodiment of the present application is the same as the method in the above embodiment, so both have the same embodiments and beneficial effects, which will not be repeated here.

[0204] Figure 6 The hardware structure diagram of the computing resource allocation device provided in the embodiment of the present application is shown; Figure 6 As shown, the computing resource allocation device may include a processor 601 and a memory 602 storing computer program instructions.

[0205] Specifically, the processor 601 may include a CPU, or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0206] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0207] The memory 602 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0208] The processor 601 implements any one of the computing resource allocation methods in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0209] In one example, the computing resource allocation device may further include a communication interface 603 and a bus 604. The processor 601, the memory 602, and the communication interface 603 are connected via the bus 604 and communicate with each other.

[0210] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0211] Bus 604 includes hardware, software or both, and the parts of computing resource allocation equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 604 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0212] In addition, in combination with the computing resource allocation method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the computing resource allocation methods in the above embodiment is implemented.

[0213] An embodiment of the present application also provides a computer program product, including a computer program, which implements any one of the computing resource allocation methods in the above embodiments when the computer program is processed and executed.

[0214] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0215] The functional blocks shown in the block diagram above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0216] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0217] Aspects of the present disclosure are described above with reference to a flowchart and / or block diagram of a computing resource allocation method, device, equipment, medium and product according to an embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0218] The above contents are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. A computing resource allocation method, It is characterized in that Applied to a target computing node, the computing resources of the target computing node are pre-divided into a plurality of resource blocks; the method comprises: When receiving the target operation and maintenance task from the operation and maintenance terminal, obtain the resource demand status of each operation and maintenance task received by itself; Determine whether the resource demand state meets a preset condition; the preset condition includes that the number of first operation and maintenance tasks exceeds a threshold value within a preset historical time period, and the first operation and maintenance task is an operation and maintenance task whose resource demand is greater than the resource threshold value; In the case that the resource quantity demand state does not meet the preset condition, among the resource blocks of the own, according to the original order of the resource blocks, the first resource block that meets the resource quantity demand of the target operation and maintenance task is determined as the target resource block; In the case where the resource demand state meets the preset condition, among the resource blocks of the resource block, the resource block with the smallest remaining resource amount and meeting the resource demand of the target operation and maintenance task is determined as the target resource block; Allocate the target operation and maintenance task to the selected target resource block.

2. The computing resource allocation method according to claim 1, It is characterized in that When the resource demand state satisfies the preset condition, among the resource blocks of the resource block, the resource block with the smallest remaining resource amount and satisfying the resource demand of the target operation and maintenance task is determined as the target resource block, including: Sort each resource block of the resource block in the ascending order of the remaining resource amount to obtain a sorting result; According to the sorting result, traverse each resource block of the own; The first traversed resource block that meets the resource quantity requirement of the target operation and maintenance task is determined as the target resource block.

3. The computing resource allocation method according to claim 1, It is characterized in that When receiving the target operation and maintenance task from the operation and maintenance terminal, obtaining the resource demand state of each operation and maintenance task received by itself includes: Obtaining each second operation and maintenance task received within the preset historical time period; Determine the corresponding resource demand based on the number of CPU cores and / or the size of the memory occupied by the second operation and maintenance task; Comparing the resource requirement of each of the second operation and maintenance tasks with the resource threshold; Determine the second operation and maintenance task whose resource demand is greater than the resource threshold as the first operation and maintenance task; Determine the number of the first operation and maintenance tasks.

4. A method for allocating computing resources, It is characterized in that Applied to a central server, the method comprises: Upon receiving a target operation and maintenance task requirement from the operation and maintenance terminal, determining a target computing node for completing the target operation and maintenance task from among the computing nodes; The target operation and maintenance task is allocated to the target computing node so that the target computing node executes the computing resource allocation method according to any one of claims 1 to 3.

5. The computing resource allocation method according to claim 4, It is characterized in that In the case of receiving the target operation and maintenance task requirement sent by the operation and maintenance terminal, determining the target computing node for completing the target operation and maintenance task in each computing node includes: Get the distance between each computing node and the operation and maintenance terminal; The computing nodes whose distance to the operation and maintenance terminal is less than the maximum distance threshold are determined as pending computing nodes; The target computing node is selected from the pending computing nodes.

6. The computing resource allocation method according to claim 5, It is characterized in that The selecting the target computing node from the pending computing nodes includes: Based on the probability determination rule, determine the selection probability value corresponding to each of the pending computing nodes; Based on the selection probability value, the target computing node is selected from each of the pending computing nodes; the selection probability value is positively correlated with the probability of the pending computing node being selected.

7. The computing resource allocation method according to claim 6, It is characterized in that The determining of the selection probability value corresponding to each of the pending computing nodes based on the probability determination rule includes any one or any combination of the following: Determine the selection probability value based on the remaining resources of the pending computing node; the remaining resources of the pending computing node are positively correlated with the selection probability value; Determining the selection probability value based on the distance between each of the pending computing nodes and the operation and maintenance terminal; The distance between the pending computing node and the operation and maintenance terminal is negatively correlated with the selection probability value.

8. The computing resource allocation method according to claim 6, It is characterized in that After allocating the target operation and maintenance task to the target computing node, the method further includes: The selection probability value corresponding to the target computing node is reduced.

9. The computing resource allocation method according to claim 6, It is characterized in that The selecting the target computing node from the pending computing nodes based on the selection probability value includes: According to the selection probability values ​​corresponding to the pending computing nodes, a target digital set is constructed; the pending computing nodes correspond to the numbers in the target digital set, and the selection probability values ​​of the pending computing nodes are positively correlated with a first number; the first number is the number of numbers corresponding to the pending computing nodes in the target digital set; Randomly select a target number from the target number set; The undetermined computing node corresponding to the target number is determined as the target computing node.

10. The computing resource allocation method according to claim 5, It is characterized in that Before determining the computing node whose distance to the operation and maintenance terminal is less than the maximum distance threshold as the pending computing node, the method further includes: Obtaining the timeliness index of the target operation and maintenance task; The maximum distance threshold is determined according to the timeliness index; the timeliness index is negatively correlated with the maximum distance threshold.

11. A computing resource allocation device, It is characterized in that Applied to a target computing node, the computing resources of the target computing node are pre-divided into a plurality of resource blocks; the device comprises: A first acquisition module is used to obtain the resource demand status of each operation and maintenance task received by itself when receiving the target operation and maintenance task from the operation and maintenance terminal; A judgment module is used to judge whether the resource demand state meets a preset condition; the preset condition includes that the number of first operation and maintenance tasks exceeds a threshold value within a preset historical time period, and the first operation and maintenance task is an operation and maintenance task whose resource demand is greater than the resource threshold value; if the resource demand state does not meet the preset condition, triggering a first determination module; if the resource demand state meets the preset condition, triggering a second determination module; The first determination module is used to determine, among its own resource blocks, the first resource block that meets the resource quantity requirement of the target operation and maintenance task according to the original order of the resource blocks as the target resource block; The second determination module is used to determine, among its own resource blocks, a resource block with the smallest remaining resource amount and meeting the resource amount requirement of the target operation and maintenance task as a target resource block; The allocation module is used to allocate the target operation and maintenance task to the selected target resource block.

12. A computing resource allocation device, It is characterized in that The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the computing resource allocation method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the computing resource allocation method according to any one of claims 1 to 10 is implemented.

14. A computer program product, It is characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the computing resource allocation method as described in any one of claims 1 to 10.