Computing power routing generation method, computing power routing scheduling method, device, storage medium and program product

Abstract

The present application relates to a computing power routing generation method, a computing power routing scheduling method, a computer device, a storage medium, and a computer program product. The computing power service instance status information of the computing power service instance deployed on the computing power resource is divided into at least two levels arranged according to a rule; the method includes: based on the target number, compressing the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level to obtain the target computing power service instance status information; transmitting the target computing power service instance status information to the corresponding computing power gateway device; each computing power gateway device is used to generate a computing power service instance status information set; and generating computing power routing based on the computing power service instance status information set. The use of this method can compress the number of computing power service instance status information and ensure the addressing efficiency of the computing power service status.

Description

Technical Field

[0001] The present application relates to the field of network technology, and in particular to a computing power routing generation method, a computing power routing scheduling method, a computer device, a storage medium, and a computer program product. Background Art

[0002] Computing power routing is different from traditional routing. By introducing "computing power + network" status information as a routing selection factor, it realizes an integrated routing scheduling method that coordinates computing power and network, reflecting the innovation of IP technology.

[0003] The computing power routing mechanism works as follows: The computing power routing node at the edge of the computing network fully perceives the network and resource status information of all computing resources for all computing services. It then generates a computing power route for each computing power resource. The computing power route includes network path information (latency, bandwidth, jitter, packet loss rate, etc.) to the computing power resource, as well as computing power service instance status information (computing power information such as the number of CPU cores in the service node, CPU utilization, and available memory). When a user's computing power request enters the computing network, the computing power routing node at the edge of the computing network selects a computing power route that meets the user's computing power status and network performance requirements based on the user's service quality requirements and the locally generated network-wide computing power routing table. The route is then forwarded to the corresponding computing power resource through the computing power route, thereby optimizing the utilization of computing power resources.

[0004] However, to meet users' varying needs for service latency, service efficiency, and computing power resources, similar services support the creation of multiple computing service instances across regions to achieve local access, service backup, and resource integration. On the one hand, the massive amount of computing power resources will result in the generation of a large amount of computing power routing information. This computing power routing information also includes network path status information to the computing power resources and computing power service instance status information. Unlike ordinary routing, it cannot be aggregated through network segments. Computing power routing will far exceed the scale of traditional routing entries. On the other hand, when addressing the traffic of computing power requests, computing power routing cannot be performed according to the traditional longest match algorithm. Instead, addressing must be completed based on the user's specific requirements for computing power resources and network performance, resulting in excessively long addressing times. Summary of the Invention

[0005] Based on this, it is necessary to provide a computing power routing generation method, computing power routing scheduling method, computer equipment, computer-readable storage medium and computer program product that can compress the number of computing power service states and ensure the addressing efficiency of computing power routing to address the above technical problems.

[0006] In a first aspect, the present application provides a computing power routing generation method, wherein computing power service instance status information of a computing power service instance deployed on a computing power resource is divided into at least two levels arranged according to a rule, the at least two levels including a basic level and at least one target level, wherein the computing power service instance status information is divided into different target groups in the basic level according to a preset rule, and the first group in each of the target levels is obtained by merging the corresponding second groups in the next level, and when the next level is the basic level, the second group is the corresponding target group, and when the next level is not the basic level, the second group is different from the target group; the method includes:

[0007] Get the configured target quantity;

[0008] Based on the target number, compress the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level to obtain target computing power service instance status information;

[0009] The target computing power service instance status information is transmitted to the corresponding computing power gateway device; each computing power gateway device is used to generate a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic layer and the target computing power service instance status information compressed by each target layer received; and generate a computing power route based on the computing power service instance status information set.

[0010] In one embodiment, the method further comprises:

[0011] Receiving computing power service instance status information in the first group in the target layer reported by the next layer;

[0012] Before compressing the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number to obtain the target computing power service instance status information, the method further includes:

[0013] Determine computing power service instance status information within the first group at the target level and each of the second groups included in the first group;

[0014] Determine computing power service instance status information within each second group included in the first group;

[0015] Based on the computing power service instance status information within each second group included in the first group and the computing power service instance status information within the first group, the computing power service instance status information within the first group at the target level and the computing power service instance status information outside each second group at the next level are obtained.

[0016] In one embodiment, compressing the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number to obtain the target computing power service instance status information includes:

[0017] Determine various resource states corresponding to the pending computing power service instance state information that is within the first group at the target level and outside the second group at the next level;

[0018] Determine the first evaluation value and weight of each resource status;

[0019] Based on the first evaluation value and weight of each resource status, a comprehensive evaluation value of the status information of the computing power service instance to be processed is obtained;

[0020] Sorting the status information of the computing power service instances to be processed based on the comprehensive evaluation value;

[0021] The target computing power service instance status information is obtained by filtering the sorted computing power service instance status information to be processed based on the target quantity.

[0022] In one embodiment, each group in the basic level is obtained based on geographical area division; each group in the target level is obtained based on each group in the corresponding next level whose geographical area relationship satisfies a preset relationship.

[0023] In a second aspect, the present application further provides a computing power routing scheduling method, which is applied to a computing power gateway device. The computing power routing scheduling method includes:

[0024] Receive computing power requests;

[0025] Determining target computing power routing information based on the computing power request and the computing power routing, wherein the computing power routing is generated based on the computing power routing generation method described above;

[0026] The forwarding processing of the computing power request is completed based on the target computing power routing information.

[0027] In one embodiment, before determining target computing power routing information based on the computing power request and the computing power routing, the method further includes:

[0028] Perform network layer status detection on each of the computing power routes to obtain network status information corresponding to each of the computing power routes, and the network status information is used to determine the target computing power route information.

[0029] In one embodiment, determining target computing power routing information based on the computing power request and the computing power routing includes:

[0030] Detecting, based on the computing power request, whether network status information in the computing power routing at the base level and computing power service instance status information meet screening requirements;

[0031] When the computing power routing that meets the screening requirement exists in the basic layer, obtaining target computing power routing information based on the computing power routing that meets the screening requirement;

[0032] When the computing power route that meets the screening requirements does not exist in the basic layer, obtaining the current target layer, and detecting whether the corresponding network status information and the target computing power service instance status information in the computing power route of the current target layer meet the screening requirements;

[0033] When a computing power route that meets the screening requirement exists in the current target level, obtaining target computing power route information based on the computing power route that meets the screening requirement;

[0034] When there is no computing power route that meets the screening requirements in the current target level, the next target level is obtained as the current target level, and the steps of detecting whether the corresponding network status information in the computing power route of the current target level and the target computing power service instance status information meet the screening requirements are continued until there is a computing power route that meets the screening requirements in the current target level or the computing power routes of each level are detected.

[0035] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the above embodiments when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method in any one of the above-mentioned embodiments when the computer program is executed by a processor.

[0037] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, which implements the steps of the method in any one of the above embodiments when executed by a processor.

[0038] The above-mentioned computing power routing generation method, computing power routing scheduling method, computer equipment, storage medium and computer program product, the computing power service instance status information deployed on the computing power resources is divided into at least two levels arranged according to rules, and the at least two levels include a basic level and at least one target level, wherein the computing power service instance status information is divided into different target groups in the basic level according to preset rules, and the first group in each target level is obtained by merging the corresponding second group in the next level, and when the next level is the basic level, the second group is the corresponding target group, and each computing power determination platform of each target level obtains the target number of the configuration, and can perform the calculation on the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number. The target computing power service instance status information is obtained by row compression and transmitted to the corresponding computing power gateway device. Each computing power gateway device generates a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic layer and the target computing power service instance status information obtained by filtering the received layers, and generates a computing power route based on the computing power service instance status information set. In this way, the computing power service instance status information outside the second group is aggregated and then issued step by step, so that the amount of computing power service instance status information that finally reaches the computing power gateway device is greatly reduced, thereby reducing the storage amount of computing power service instance status information in the computing power service instance status information set of each computing power gateway device, and also reducing the amount of computing power routing, thereby improving the addressing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a diagram of an application environment of a computing power routing generation method in one embodiment;

[0041] Figure 2 is a schematic diagram of a basic layer in one embodiment;

[0042] Figure 3 1 is a flow chart of a method for generating computing power routing according to an embodiment;

[0043] Figure 4 1 is a flow chart of a computing power routing scheduling method according to an embodiment;

[0044] Figure 5 This is a structural block diagram of a computing power routing generation device in one embodiment;

[0045] Figure 6 This is a structural block diagram of a computing power routing and scheduling device in one embodiment;

[0046] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0048] The computing power routing generation method and computing power routing scheduling method provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown. The computing power service instance status information deployed on the computing power resources is divided into at least two levels arranged according to rules, and the at least two levels include a basic level and at least one target level, wherein the computing power service instance status information in each level is divided into different groups, wherein in the basic level, the computing power service instance status information is divided into different target groups in the basic level according to preset rules, and the first group in each target level is obtained by merging the corresponding second group in the next level, and when the next level is the basic level, the second group is the corresponding target group. Therefore, different groups in each level include different computing power service instance status information.

[0049] Specifically, the computing power service instance status information deployed on the computing power resources is divided into at least two levels, including a basic level and target levels. The computing power service instance status information in each level is divided into different groups. The first group in the target level is obtained by merging the second group in the next level, and the target group in the basic level is obtained by grouping the actual computing power service instance status information. In this way, different groups include different computing power service instance status information.

[0050] The basic level includes at least two target groups. There is no specific limit on the number of target groups. Figure 2 As shown, the basic layer includes multiple target groups, specifically L1 layer-a domain, L1 layer-b domain, L1 layer-c domain, L1 layer-d domain, L1 layer-e domain, etc.

[0051] For each target level, for example, Ln (n>=2, and is a positive integer), the hierarchical division method is: multiple geographically close lower-level areas are merged into a higher-level area, supporting the establishment of multiple levels upward. The first group in the target level is obtained by merging the second group of the next level, such as Figure 2The target packets L1-a domain, L1-b domain, and L1-c domain in the basic layer are merged to obtain the first packet L2-a domain of the first target layer, the target packets L1-d domain and L1-e domain in the basic layer are merged to obtain the first packet L2-b domain of the first target layer, the first packet in the first target layer (relative to the second packet in the second target layer, the packet in the first target layer is called the first packet) L2-a domain and L2-b domain are merged to obtain the second packet in the second target layer (relative to the second packet in the first target layer, the packet in the second target layer is called the second packet) L3-a domain.

[0052] Optionally, each target group in the basic layer is obtained based on geographical area division; the first group in each target layer is obtained based on each second group in the corresponding next layer whose geographical area relationship satisfies a preset relationship. In this embodiment, the computing power service instance status information of the basic layer is divided according to geographical area to obtain multiple target groups, and the target group in the basic layer includes each computing power service instance status information. The first group in each target layer is obtained by merging multiple second groups in the next layer that are close to each other in geographical area, so that each first group in each target layer also includes computing power service instance status information.

[0053] Among them combined Figure 2 As shown, Figure 2 This is a schematic diagram of the base layer in one embodiment. The base layer includes computing services, computing gateway devices, and a computing power determination platform deployed on computing resources. Computing resources may include public clouds, private clouds, edge computing, etc., without specific limitations here. In this embodiment, the computing service instance status information of the base layer is divided based on preset rules to obtain different target groups. The computing service instance status information in each target group of the base layer is different, and the same computing service instance status information cannot be simultaneously attributed to multiple different groups in the same layer.

[0054] Among them, each target group at the basic level includes a first computing power determination platform, which has three functions: first, reading all computing power service instance status information for all computing power service types in all distributed computing power nodes in the corresponding target group; second, receiving the target computing power service instance status information issued by each target level; third, sending the computing power service instance status information and the target computing power service instance status information in the corresponding target group to the computing power gateway device.

[0055] Optionally, the computing power service instance status information includes the computing power service identifier, the computing power service instance identifier, the computing power service instance status information attributes, and the network location information of the access service node (service access address, port, etc.), wherein the computing power service instance status information attributes may include attributes used to generate computing power routing and other attributes, wherein the attributes used to generate computing power routing may include computing power information such as the number of CPU cores occupied by the service node, CPU utilization, available memory, etc. Other attributes are not related to the generation of computing power routing and are not specifically restricted here.

[0056] Each target group at the base level includes at least one computing power gateway device, which has two functions: First, it generates a computing power service instance status information set based on the computing power service instance status information within the target group and the target computing power service instance status information compressed from each target level, and then generates a computing power route based on the computing power service instance status information set. Specifically, after the computing power service instance status information is delivered to the computing power gateway, a computing power route is generated one-to-one with the network location information of the computing power service instance status information as the destination. The computing power route points to the path to the computing power service and includes the computing power service instance status information. Second, the computing power gateway device also receives computing power requests and determines the target computing power route information based on the computing power request and the generated computing power route.

[0057] Each first group of each target level includes a second computing power determination platform, and the functions of the second computing power determination platform include four: first, summarizing the computing power service instance status information within the first group, for example, obtaining the second group located in the first group and in the next level, obtaining the computing power service instance status information recorded by the computing power determination platform corresponding to each second group, summarizing the computing power service instance status information recorded by the computing power determination platform corresponding to each second group, and obtaining the computing power service instance status information corresponding to the first group; second, the second computing power determination platform can also determine a target number, and the target number is used to compress the computing power service instance status information within the first group of the target level and outside the second group of the next level; third, based on the target number, compress the computing power service instance status information within the first group to obtain the target computing power service instance status information. Specifically, compress the computing power service instance status information within the first group of the target level and outside the second group of the next level to obtain the target computing power service instance status information. Specifically, assuming that the first group of the target level is A, which includes the second group a, the second group b and the second group c, it can be determined that the computing power service instance status information within the first group A and outside the second group a is the computing power service instance status information within the second group b and the second group c, and the computing power service instance status information within the second group b and the second group c is compressed to obtain the target computing power service instance status information; the computing power service instance status information within the first group A and outside the second group b is determined to be the computing power service instance status information within the second group a and the second group c, and the computing power service instance status information within the second group a and the second group c is compressed to obtain the target computing power service instance status information; the computing power service instance status information within the first group A and outside the second group c is determined to be the computing power service instance status information within the second group a and the second group b, and the computing power service instance status information within the second group a and the second group b is compressed to obtain the target computing power service instance status information.This can reduce the computing power service instance status information outside each second group of the next level, and transmit the target computing power service instance status information to the computing power determination platform of the corresponding second group of the next level; Fourth, the second computing power determination platform is also used to receive the target computing power service instance status information issued by the computing power determination platform of the upper level, and transmit it to the first computing power determination platform of the basic level layer by layer, that is, send it to the next level in turn until it is sent to the first computing power determination platform of the basic level, for example, it is sent by the computing power determination platform corresponding to the L3 layer-a domain to the computing power determination platform corresponding to the L2 layer-a domain and the computing power determination platform corresponding to the L2 layer-b domain, and sent by the computing power determination platform corresponding to the L2 layer-a domain to the first computing power determination platform corresponding to the L1 layer-a domain, the first computing power determination platform corresponding to the L1 layer-b domain, and the first computing power determination platform corresponding to the L1 layer-c domain, and sent by the computing power determination platform corresponding to the L2 layer-b domain to the first computing power determination platform corresponding to the L1 layer-d domain and the first computing power determination platform corresponding to the L1 layer-e domain.

[0058] In addition, it should be noted that the groups corresponding to the computing power determination platform for transmitting computing power service instance status information have an inclusion relationship and are located at adjacent levels.

[0059] In an exemplary embodiment, Figure 3 As shown, a computing power routing generation method is provided, which is applied to Figure 1 The second computing power determination platform in the example is used to illustrate, including the following steps 302 to 306. Among them:

[0060] S302: Obtain the configured target number, which is used to compress the number of computing power service instance status information in the first group of the target layer.

[0061] The target number is pre-configured by each computing power determination platform at each target level. This target number is used to compress the amount of computing power service instance status information within the first group of the target level. The target number is the maximum number k of computing power service instance status information within the first group of the target level and outside the second group of the next level. k is an integer greater than or equal to 0 and less than the threshold for computing power service instance status information. The threshold for computing power service instance status information is the maximum number of computing power service instance status information within the first group of the target level and outside the second group of the target level. This target number controls the maximum amount of computing power service instance status information for each computing power service that is ultimately filtered and issued by the first group of the Ln level to the second group of the Ln-1 level. This target number regulates the number of computing power service instance status information entries within the first group of the Ln level and outside the second group of the Ln-1 level that are ultimately generated on the computing power gateway device by the first group of the Ln level. With the help of layer-by-layer aggregation, screening and control of computing power information, the amount of computing power information finally sent to the computing power gateway device is greatly reduced.

[0062] S304: Based on the target number, compress the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level to obtain the target computing power service instance status information, where the second group is located in the first group.

[0063] Among them, in each first group of each target level, for the second group of the next level to be managed, the out-of-region computing power service instance status information located within the first group of the target level Ln and outside the second group of the next level Ln-1 is screened, and the maximum number of computing power service instance status information of each type of computing power service is k. Specifically, if the number of out-of-region computing power service instance status information located within the first group of the target level Ln and outside the second group of the next level Ln-1 is greater than or equal to k, it is compressed to obtain k target computing power service instance status information; if the number of out-of-region computing power service instance status information located within the first group of the target level Ln and outside the second group of the next level Ln-1 is less than k, it is not compressed.

[0064] Specifically, combined Figure 1As shown, for the L1-a domain, L1-b domain, and L1-c domain managed by the L2-a domain, the corresponding target computing service instance status information is calculated respectively. Therefore, optionally, the corresponding number of threads is determined based on the number of second groups managed by the first group, so that the target computing service instance status information is obtained by compressing the number of computing service instance status information outside the group corresponding to the second group in each thread, wherein each thread can be a parallel thread. For example, for the L1-a domain, the number of computing service instance status information in the L1-b domain and the L1-c domain is compressed in one thread to obtain k target computing service instance status information; or when the number of computing service instance status information in the L1-b domain and the L1-c domain is less than k, it is not compressed and the computing service instance status information of all L1-b domain and L1-c domain is retained. Similarly, the target computing service instance status information is calculated for the L1-b domain and the L1-c domain accordingly.

[0065] In one of the optional embodiments, the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level is screened based on the target number to obtain the target computing power service instance status information, including: determining the resource statuses corresponding to the pending computing power service instance status information located in the first group of the target level and outside the second group of the next level; determining the first evaluation value and weight of each resource status; obtaining a comprehensive evaluation value of the pending computing power service instance status information based on the first evaluation value and weight of each resource status; sorting the pending computing power service instance status information based on the comprehensive evaluation value; and screening the target computing power service instance status information from the sorted pending computing power service instance status information based on the target number.

[0066] Among them, for each second group, the various resource states of the pending computing power service instance status information located within the first group of the target layer and outside the second group of the next layer can be determined. For example, for the L1 layer-a domain above, the computing power service instance status information in the L1 layer-b domain and the L1 layer-c domain is determined to be the pending computing power service instance status information, and the various resource states of the pending computing power service instance status information are obtained.

[0067] The various resources may include the cloud host CPU load, memory usage, disk, etc., and no specific restrictions are made here. The resource status of each resource can be scored to obtain a first evaluation value, wherein the scoring rules for the first evaluation value can follow any rules, and no specific restrictions are made on the scoring rules here. Finally, the first evaluation value and weight of each resource status are combined to obtain a comprehensive evaluation value of the status information of the computing power service instance to be processed, wherein the weight of each resource status can be manually set and dynamically adjusted, or it can be calculated based on a certain algorithm, such as an artificial intelligence algorithm, etc., and no specific restrictions are made here. Optionally, the weight of each resource is equal.

[0068] After calculating the comprehensive evaluation value, the status information of the computing power service instances to be processed is sorted based on the comprehensive evaluation value, and then the top k status information of the computing power service instances to be processed are selected as the target computing power service instance status information, thereby achieving the purpose of reducing the number of status information of the computing power service instances to be processed.

[0069] S306: The target computing power service instance status information is transmitted to the corresponding computing power gateway device; each computing power gateway device is used to generate a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic layer and the target computing power service instance status information compressed by each target layer received; and generate a computing power route based on the computing power service instance status information set.

[0070] Among them, in this embodiment, the computing power gateway device corresponding to the target computing power service instance status information refers to the computing power gateway device of the target group of the basic layer corresponding to the target computing power service instance status information, wherein the transmission process is to transmit the target computing power service instance status information to the computing power determination platform of the corresponding group in the corresponding layer in sequence. Figure 1 The target computing power service instance status information corresponding to the L2-a domain is calculated by the second computing power determination platform in the L3-a domain, and the second computing power determination platform in the L3-a domain sends the target computing power service instance status information to the second computing power determination platform in the L2-a domain. The second computing power determination platform in the L2-a domain then transmits the target computing power service instance status information to the first computing power determination platforms in the L1-a domain, the L1-b domain, and the L1-c domain. The target computing power service instance status information corresponding to the L1-a domain is calculated by the second computing power determination platform in the L2-a domain, and the second computing power determination platform in the L2-a domain sends it to the first computing power determination platform corresponding to the L1-a domain.

[0071] Each computing power gateway device stores computing power service instance status information within the target group of the basic layer in which it is located. The computing power service instance status information within the target group of the basic layer is obtained by the first computing power determination platform within the target group of the basic layer in which the computing power gateway device is located and transmitted to the computing power gateway device. Each computing power gateway device also stores the target computing power service instance status information compressed by each target layer received. As mentioned above, the first computing power determination platform corresponding to the L1 layer-a domain stores the target computing power service instance status information corresponding to the L1 layer-a domain calculated by the second computing power determination platform of the L2 layer-a domain and the target computing power service instance status information corresponding to the L2 layer-a domain calculated by the second computing power determination platform of the L3 layer-a domain.

[0072] The computing power gateway device is used to generate a computing power service instance status information set based on the computing power service instance status information within the target group corresponding to the base layer and the target computing power service instance status information compressed from each target layer. The specific method for generating the computing power service instance status information set is described below. Subsequently, the computing power gateway device generates a computing power route based on the compressed computing power service instance status information set. After the specific computing power service instance status information is delivered to the computing power gateway, a computing power route is generated for each route, with the network location information of the computing power service instance status information as the destination. The computing power route points to the path to the computing power service and contains the computing power service instance status information.

[0073] In the above-mentioned computing power routing generation method, each computing power determination platform of each target level of the computing power service instance status information obtains the target number of configurations, and can compress the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number to obtain the target computing power service instance status information, and transmit it to the corresponding computing power gateway device. Each computing power gateway device generates a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic level and the target computing power service instance status information obtained by screening the received levels, and generates a computing power route based on the computing power service instance status information set. In this way, the computing power service instance status information outside the second group is aggregated and then issued step by step, so that the number of computing power service instance status information that finally reaches the computing power gateway device is greatly reduced, thereby reducing the storage amount of computing power service instance status information in the computing power service instance status information set of each computing power gateway device, and also reducing the amount of computing power routing, thereby improving the addressing efficiency.

[0074] In one of the optional embodiments, the method also includes: receiving computing power service instance status information in the first group of the target level reported by the next level; compressing the number of computing power service instance status information in the first group of the target level and outside the second group of the next level based on the target number, and before obtaining the target computing power service instance status information, it also includes: determining the computing power service instance status information in the first group of the target level and each second group corresponding to the first group; determining the computing power service instance status information in each second group; based on the computing power service instance status information in each second group and the computing power service instance status information in the first group, obtain the computing power service instance status information in the first group of the target level and the computing power service instance status information outside each second group of the next level.

[0075] Among them, the computing power service instance status information in each group of each level is pre-aggregated, and the target computing power service instance status information in each group of the basic level is obtained by each first computing power determination platform reading and collecting the computing power service instance status information of each type of computing power service in all distributed computing power nodes in the target group. For example, each first computing power determination platform reads and collects all computing power service instance status information of all computing power service types in all distributed computing power nodes in the target group.

[0076] The computing power service instance status information of each subsequent first group of each target level is obtained based on the computing power service instance status information of each group of the next level it manages. For example, the second computing power determination platform of each first group of the target level Ln is connected to the computing power determination platform of each second group of the next level Ln-1 managed by the first group, and the computing power service instance status information of all distributed computing power nodes of each second group of the next level Ln-1 recorded in the computing power determination platform of each second group of the next level Ln-1 is read, so that each first group of the target level Ln obtains the computing power service instance status information in all distributed computing power nodes in the area under its jurisdiction.

[0077] Optionally, based on the computing power service instance status information within the second group and the computing power service instance status information within each first group, the computing power service instance status information outside each first group can be determined, thereby facilitating subsequent compression of the computing power service instance status information outside the first group.

[0078] In the above embodiment, the amount of computing power service instance status information outside the first group managed by each second group in each target layer is compressed, thereby reducing the amount of the final computing power service instance status information set of the computing power gateway device.

[0079] In an exemplary embodiment, Figure 4As shown, a computing power routing scheduling method is provided, which is applied to Figure 1 The computing power gateway device in the example is used to illustrate the process, including the following steps 402 to 406. Among them:

[0080] S402: Receive a computing power request.

[0081] The computing power request can be sent by a user terminal to a computing power gateway device. Each group at the basic level corresponds to a computing power gateway device. The computing power gateway device corresponding to the user terminal can be determined based on the location relationship between the computing power gateway device and the user terminal. In this way, when the user terminal issues a computing power request, the corresponding computing power gateway device receives the computing power request. When the groups at the basic level are grouped based on geographic location, when a user terminal located in the geographic location area corresponding to a group issues a computing power request, the computing power gateway device of the group receives the computing power request and processes it. The computing power request can carry computing power screening requirements, which can include computing power service instance status information requirements and network requirements.

[0082] S404: Determine target computing power routing information based on the computing power request and the computing power routing, wherein the computing power routing is generated based on the computing power routing generation method in any one of the above embodiments.

[0083] S406: Complete forwarding processing of the computing power request based on the target computing power routing information.

[0084] The computing power routing is generated based on the computing power routing generation method in any of the above embodiments. The specific generation method can be found above and is not specifically limited here.

[0085] When receiving a computing power request from a user, the computing power gateway device selects a computing power route based on the computing power service identifier of the request and the computing power requirements and network requirements carried in the computing power request.

[0086] In one of the optional embodiments, the target computing power service status is determined based on the computing power request and the computing power route, including: detecting whether the network status information and the computing power service instance status information in the computing power route of the basic layer meet the screening requirements based on the computing power request; when there is a computing power route that meets the screening requirements in the basic layer, obtaining the target computing power route information based on the computing power route that meets the screening requirements; when there is no computing power route that meets the screening requirements in the basic layer, obtaining the current target layer, detecting whether the corresponding network status information and the target computing power service instance status information in the computing power route of the current target layer meet the screening requirements; when there is a computing power route that meets the screening requirements in the current target layer, obtaining the target computing power route information based on the computing power route that meets the screening requirements; when there is no computing power route that meets the screening requirements in the current target layer, obtaining the next target layer as the current target layer, and continuing to execute the step of detecting whether the corresponding network status information and the target computing power service instance status information in the computing power route of the current target layer meet the screening requirements, until there is a computing power route that meets the screening requirements in the current target layer or the computing power routes of each layer are detected.

[0087] Specifically, the computing power gateway device selects computing power routes from L1-Ln in sequence, giving priority to computing power routes within the L1 group. If no computing power route that meets the user's requirements is selected based on the computing power service instance status information and network status information, it continues to select from the computing power routes outside the area generated by the L2 layer. If no computing power route that meets the user's requirements is selected based on the target computing power service instance status information and network status information, it continues to select from the computing power routes outside the area generated by the upper Ln layer until the target computing power route information is obtained or the computing power routes at all levels are fully tested. If the computing power routes at all levels are fully tested, it means that no computing power route that meets the screening requirements exists, which means that the forwarding has failed.

[0088] In one of the optional embodiments, before determining the target computing power service status based on the computing power request and computing power routing, it also includes: performing network layer status detection on each computing power routing to obtain the network status information corresponding to each computing power routing, and the network status information is used to determine the target computing power routing information.

[0089] Specifically, network layer status detection is performed based on each specific computing power route to obtain network status information of each computing power service instance in the computing power route. The network status information includes path delay, jitter, bandwidth and other information, and no specific restrictions are made here.

[0090] Therefore, when generating the target computing power route, the computing power route can be selected based on the status information of each computing power service instance and the network status information in the computing power route, so as to obtain the target computing power route that meets the screening requirements.

[0091] In the above embodiment, computing power service instance status information is divided into multiple levels of computing power regions by region. The computing power information determination platform within each level dynamically adjusts the target number K based on the actual amount of computing power information in the jurisdiction. By filtering and integrating computing power information at each level, the number of computing power service status tables generated on the network layer computing power gateway device is reduced. This reduces the computational overhead and storage pressure of the computing power service status node, ensuring the quality of user computing power service scheduling.

[0092] For ease of understanding, an embodiment of a method and system for realizing hierarchical computing power routing generation and computing power routing scheduling by using the method of the present application is provided below:

[0093] First, build the system:

[0094] First, a three-tiered computing network system will be established within JS Province: The L1 level is the county level, with JN District of NJ City forming the L1-NJ-JN region, JY District of NJ City forming the L1-NJ-JY region, XC District of SZ City forming the L1-SZ-XC region, and HQ District of SZ City forming the L1-SZ-HQ region. The L2 level is the prefecture-level city level, with NJ City forming the L2-NJ1 region, encompassing two L1 regions: L1-NJ-JN and L1-NJ-JY. SZ City forming the L2-SZ1 region, encompassing two L1 regions: L1-SZ-XC and L1-SZ-HQ. The L3 level is the provincial level, with JS Province forming the L3-JS1 region, currently encompassing two L2 regions: L2-NJ1 and L2-SZ1. The inclusion relationships between regions can be added, deleted, or modified based on business deployment needs. The L1 layer is the base layer mentioned above, the L2 layer is the first target layer, and the L3 layer is the second target layer. It should be noted that the regions of each layer in this embodiment are groups corresponding to each layer, which are called regions for convenience.

[0095] Second, each L1 zone contains key resources such as computing gateway devices, computing resources (public cloud, private cloud, and edge cloud), computing request users, and the first computing power determination platform. These physical resources are divided into unique L1 zones based on administrative regions. A second computing power determination platform is deployed within each L2 and L3 zone. All components are interconnected via the internet.

[0096] Third, two computing service instances are created in each of the four L1-level regions for the same service SID1. A total of eight computing service instances are created in the four L1-level regions to provide the same type of service to users.

[0097] Secondly, the computing power service instance status information is notified, that is, reported to the computing power determination platform at each level.

[0098] The four L1 regions (L1-NJ-JN, L1-NJ-JY, L1-SZ-XC, and L1-SZ-HQ) periodically read the status information of each computing service instance. This information is generated and notified to the high-level computing power determination platform in the L2 region, which then sends it to the computing power gateway device in the L1 region.

[0099] The L1-NJ-JN first computing power determination platform obtains the computing power service instance status information in the region:

[0100]

[0101] The L1-NJ-JY first computing power confirmation platform obtains the computing power service instance status information in the region:

[0102]

[0103] The L1-SZ-XC first computing power confirmation platform obtains the status information of the computing power service instances in the region:

[0104]

[0105] The L1-SZ-HQ first computing power confirmation platform obtains the computing power service instance status information in the region:

[0106]

[0107] Second, the second computing power determination platform in the L2-layer region receives the computing power service instance status information message sent by the L1-layer region, obtains the computing power service instance status information of all regions within the included L1-layer region, and continues to report to the L3-layer region. The higher-level computing power determination platform in the L3-layer region receives the computing power service instance status information sent by the L2-layer region, and obtains the computing power service instance status information of all regions within the included L2-layer region.

[0108] Third, the maximum number of computing service instance status information for various computing services within the region of the second computing power determination platform at the L2 and L3 levels and outside the region of the next level is configured to be 1. Each level filters and generates computing power information outside the region. The screening method is: score according to the resource information status of the service cloud host CPU, memory, disk, etc., and then combine the multi-factor weighted algorithm to accumulate the total score, sort, and select the computing service instance status information with the highest ranking.

[0109] After L2-NJ1 screening is completed, the status information of the local computing service instance is as follows:

[0110]

[0111] After L2-SZ1 screening is completed, the local computing service instance status information is as follows:

[0112]

[0113] After L3-JS1 screening is completed, the local computing service instance status information is as follows:

[0114]

[0115] Fourth, the L2 and L3 second computing power determination platforms transmit the filtered out-of-region computing power service instance status information to the corresponding lower-level regions. The L2 layer transmits the received out-of-region computing power service instance status information filtered out by the L3 layer to the first computing power determination platforms within all L1 regions under its jurisdiction.

[0116] The first computing power determination platform in the fifth L1 layer sends the status information of all out-of-region computing power service instances to the computing power gateway device in the region.

[0117] Taking the L1-NJ-JN internal computing gateway device as an example, the following computing service instance status information will be received:

[0118]

[0119] Sixth, each computing power gateway in the L1 layer area begins to generate computing power service instance status information. Based on the received computing power service instance status information and combined with the network layer routing information formed by the local device through the routing protocol announcement, it generates forwarding path information to the destination of each computing power service instance, namely, computing power routing, and performs a performance status test on the network path to the destination of the computing power service instance to obtain network performance parameters.

[0120] Taking the L1-NJ-JN internal computing power gateway device as an example, the computing power routing information is as follows:

[0121]

[0122] Seventh, a user within the L1 layer initiates a service request for SID1, along with the service instance's computing power service instance status information and network performance requirements. Upon receiving the service request, the computing power gateway parses the message to obtain the SID1 service identifier, computing power service instance status information requirements, and network performance requirements. Based on the computing power service instance status information and network status information within the computing power gateway node, the computing power routing selection is performed, calculating the computing power service status entry that best meets the user's computing power service instance status information and network performance requirements. The message's destination address and destination port are then replaced with the service instance access address and service instance access port in the computing power routing's computing power service instance status information, and the message is forwarded according to the next hop information.

[0123] In the above embodiment, by dividing computing power service instance status information by region to construct multi-level computing power regions, the computing power information determination platform within each level of region dynamically adjusts the target number k based on the actual amount of computing power information in the jurisdiction. By filtering and integrating computing power information at each level, the amount of computing power service instance status information generated on the network layer computing power gateway device is reduced, thereby also reducing the number of computing power routes generated. This reduces the computational overhead and storage pressure of the computing power service status node, ensuring the quality of user computing power service scheduling.

[0124] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0125] Based on the same inventive concept, the embodiments of the present application also provide a computing power routing generation device for implementing the computing power routing generation method and a computing power routing scheduling device for implementing the computing power routing scheduling method involved above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more computing power routing generation devices and computing power routing scheduling device embodiments provided below can be found in the above-mentioned limitations of the computing power routing generation method and computing power routing scheduling method, and will not be repeated here.

[0126] In an exemplary embodiment, Figure 5 As shown, a computing power routing generation device is provided, wherein computing power service instance status information of computing power service instances deployed on computing power resources is divided into at least two levels arranged according to a rule, and the at least two levels include a base level and at least one target level, wherein the computing power service instance status information is divided into different target groups in the base level according to a preset rule, and the first group in each target level is obtained by merging the corresponding second group in the next level, and when the next level is the base level, the second group is the corresponding target group, including:

[0127] The target quantity acquisition module 501 is used to obtain the configured target quantity;

[0128] A compression module 502 is configured to compress the number of computing power service instance status information located in a first group at a target level and outside a second group at a next level based on a target number, thereby obtaining target computing power service instance status information;

[0129] The computing power routing generation module 503 is used to transmit the target computing power service instance status information to the corresponding computing power gateway device; each computing power gateway device is used to generate a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic layer and the target computing power service instance status information compressed by each target layer; and generate computing power routing based on the computing power service instance status information set.

[0130] In one of the optional embodiments, the above device further includes:

[0131] A notification module, configured to receive computing power service instance status information in the first group in the target layer reported by the upper layer;

[0132] A resource determination module is used to determine the computing power service instance status information within the first group at the target level and the second groups corresponding to the first group; determine the computing power service instance status information within each second group; based on the computing power service instance status information within each second group and the computing power service instance status information within the first group, obtain the computing power service instance status information within the first group at the target level and the computing power service instance status information outside the second groups at the next level.

[0133] In one of the optional embodiments, the compression module 502 is specifically used to determine the resource states corresponding to the pending computing service instance state information that is located in the first group of the target level and outside the second group of the next level; determine the first evaluation value and weight of each resource state; obtain the comprehensive evaluation value of the pending computing service instance state information based on the first evaluation value and weight of each resource state; sort the pending computing service instance state information based on the comprehensive evaluation value; and filter the target computing service instance state information from the sorted pending computing service instance state information based on the target number.

[0134] In one optional embodiment, each group in the basic level is obtained based on geographical area division; the group in each target level is obtained based on each group in the corresponding next level whose geographical area relationship meets a preset relationship.

[0135] In an exemplary embodiment, Figure 6 As shown, a computing power routing scheduling device is provided, including:

[0136] Receiving module 601, used to receive computing power requests;

[0137] A scheduling module 602 is configured to determine target computing power routing information based on the computing power request and the computing power routing, wherein the computing power routing is generated based on the computing power routing generation method in any of the above embodiments;

[0138] The forwarding module 603 is used to complete the forwarding processing of the computing power request based on the target computing power routing information.

[0139] In one of the optional embodiments, the network status information determination module is used to perform network layer status detection on the status information of each computing power service instance to obtain the network status information corresponding to the status information of each computing power service instance, and the network status information is used to determine the target computing power routing information.

[0140] In one of the optional embodiments, the scheduling module 602 is specifically used to detect whether the network status information and the computing power service instance status information in the computing power routing of the basic layer meet the screening requirements based on the computing power request; when there is a computing power routing that meets the screening requirements in the basic layer, the target computing power routing information is obtained based on the computing power routing that meets the screening requirements; when there is no computing power routing that meets the screening requirements in the basic layer, the current target layer is obtained, and the corresponding network status information and the target computing power service instance status information in the computing power routing of the current target layer meet the screening requirements; when there is a computing power routing that meets the screening requirements in the current target layer, the target computing power routing information is obtained based on the computing power routing that meets the screening requirements; when there is no computing power routing that meets the screening requirements in the current target layer, the next target layer is obtained as the current target layer, and the step of detecting whether the corresponding network status information and the target computing power service instance status information in the computing power routing of the current target layer meet the screening requirements is continued until there is a computing power routing that meets the screening requirements in the current target layer or the computing power routings of each layer are detected.

[0141] Each module in the computing power routing generation device and computing power routing scheduling device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0142] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store computing power service instance status information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a computing power routing generation method and a computing power routing scheduling method are implemented.

[0143] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0144] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0146] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0147] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0148] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A computing power routing generation method, characterized in that: The computing service instance status information of the computing service instance deployed on the computing resource is divided into at least two levels arranged according to a rule, wherein the at least two levels include a basic level and at least one target level, wherein the computing service instance status information is divided into different target groups in the basic level according to a preset rule, and the first group in each target level is obtained by merging the corresponding second group in the next level, and when the next level is the basic level, the second group is the corresponding target group; the method includes: Obtaining a configured target number, and based on the target number, compressing the number of computing power service instance status information located within the first group of the target level and outside the second group of the next level, to obtain target computing power service instance status information; The target computing power service instance status information is transmitted to the corresponding computing power gateway device; each computing power gateway device is used to generate a computing power service instance status information set based on the computing power service instance status information in the target group corresponding to the basic layer and the target computing power service instance status information compressed by each target layer received; and generate a computing power route based on the computing power service instance status information set.

2. The method according to claim 1, characterized in that The method further comprises: Receiving computing power service instance status information in the first group in the target layer reported by the next layer; Before compressing the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number to obtain the target computing power service instance status information, the method further includes: Determine computing power service instance status information within the first group at the target level and each of the second groups included in the first group; Determine computing power service instance status information within each second group included in the first group; Based on the computing power service instance status information within each second group included in the first group and the computing power service instance status information within the first group, the computing power service instance status information within the first group at the target level and the computing power service instance status information outside each second group at the next level are obtained.

3. The method according to claim 1, characterized in that The step of compressing the number of computing power service instance status information located in the first group of the target level and outside the second group of the next level based on the target number to obtain target computing power service instance status information includes: Determine various resource states corresponding to the pending computing power service instance state information that is within the first group at the target level and outside the second group at the next level; Determine the first evaluation value and weight of each resource status; Based on the first evaluation value and weight of each resource status, a comprehensive evaluation value of the status information of the computing power service instance to be processed is obtained; Sorting the status information of the computing power service instances to be processed based on the comprehensive evaluation value; The target computing power service instance status information is obtained by filtering the sorted computing power service instance status information to be processed based on the target quantity.

4. The method according to any one of claims 1 to 3, characterized in that Each grouping in the basic level is obtained based on geographical area division; each grouping in the target level is obtained based on each grouping in the corresponding next level whose geographical area relationship meets a preset relationship.

5. A computing power routing scheduling method, characterized in that: Applied to a computing power gateway device, the computing power routing scheduling method includes: Receive computing power requests; Determining target computing power routing information based on the computing power request and the computing power routing, wherein the computing power routing is generated based on the computing power routing generation method according to any one of claims 1 to 4; The forwarding processing of the computing power request is completed based on the target computing power routing information.

6. The method according to claim 5, characterized in that Before determining target computing power routing information based on the computing power request and the computing power routing, the method further includes: Perform network layer status detection on each of the computing power routes to obtain network status information corresponding to each of the computing power routes, and the network status information is used to determine the target computing power route information.

7. The method according to claim 6, characterized in that The determining target computing power routing information based on the computing power request and the computing power routing includes: Detecting, based on the computing power request, whether network status information in the computing power routing at the base level and computing power service instance status information meet screening requirements; When the computing power routing that meets the screening requirement exists in the basic layer, obtaining target computing power routing information based on the computing power routing that meets the screening requirement; When the computing power route that meets the screening requirements does not exist in the basic layer, obtaining the current target layer, and detecting whether the corresponding network status information and the target computing power service instance status information in the computing power route of the current target layer meet the screening requirements; When a computing power route that meets the screening requirement exists in the current target level, obtaining target computing power route information based on the computing power route that meets the screening requirement; When there is no computing power route that meets the screening requirements in the current target level, the next target level is obtained as the current target level, and the steps of detecting whether the corresponding network status information in the computing power route of the current target level and the target computing power service instance status information meet the screening requirements are continued until there is a computing power route that meets the screening requirements in the current target level or the computing power routes of each level are detected.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images