Computing power identifier recursive analysis and resource allocation method and device based on domain name system

Abstract

The invention provides a computing power identifier recursive analysis and resource allocation method and device based on a domain name system, which support analysis and addressing of wide area network computing power identifiers based on the domain name system based on a domain name service infrastructure, and have higher reliability, safety and stability than a new identification system. On the basis of domain name service nodes, analysis of computing power resources and allocation scheduling of computing power demands can be synchronously carried out in the identification analysis process, utilization of the computing power resources is efficiently achieved, and computing network integration is achieved; the analysis and resource allocation method from the top to the bottom of the root node is beneficial to macro-regulation and allocation of computing power resources between and within calculations in the wide area network range, and can realize service equalization of the computing power resources on the network level so as to improve the comprehensive service performance of the computing power network.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and device for recursive resolution and resource allocation of computing power identification based on a domain name system. Background Art

[0002] It is predicted that the amount of newly created data in the next three years will exceed the total of the past 30 years, and the amount of data created in the next five years will be more than three times that of the previous five years. This will bring about a large amount of data storage, computing, transmission and application needs, and the importance of new infrastructure such as 5G, fiber-optic broadband, and data centers will become increasingly prominent. Computing network technology focuses on the diversity of resources in the network and the diversity of computing services. Among them, the diversity of computing resources includes the diversity of resource node scale and location (large cloud computing nodes, edge computing nodes scattered at the edge of the network, etc.), the diversity of resource node computing power types (general computing power, intelligent computing power, supercomputing power), and the diversity of resource ownership (cloud service providers, telecom operators, small and medium-sized enterprises, supercomputing centers, research institutions, etc.).

[0003] The computing power identification is globally unified and verifiable, and is used to identify computing power in different dimensions such as computing power resources, functions, functions and applications. Users indicate the required services through computing power identification, and the network obtains information such as the target computing power service and computing power demand by parsing the computing power identification, providing a basis for computing power scheduling. At present, various research and standardization work around computing power identification is still ongoing, but most of it remains in the experimental exploration stage. The relevant technologies for realizing computing power resource allocation and scheduling based on the transformation of network routing equipment, etc. are mainly aimed at computing power resource scheduling and application of edge networks, but the unified management and application of computing power resources cannot be achieved in large-scale, cross-regional, multi-identification scenarios. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method and device for recursive resolution of computing power identification and resource allocation based on a domain name system.

[0005] A first aspect of the present invention provides a method for recursive resolution and resource allocation of computing power identification based on a domain name system, which is applied to a recursive service node in a computing power identification resolution system, and the method includes: Sending a computing power resource usage request to the computing power resolution root node, wherein the computing power resource usage request includes relevant information of the computing task; Receiving the node identifier of the subordinate node returned by the computing power resolution root node, and sending the computing power resource usage request to the subordinate node based on the node identifier; Receive the resource node identifier and the corresponding resource description file of the candidate resource node returned by the lower-level node, and determine the target resource node for executing the computing task based on the resource node identifier and the corresponding resource description file of the candidate resource node; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected in sequence; there are multiple subordinate nodes in each layer; the computing power resolution root node and the subordinate nodes sequentially determine the subordinate nodes or the candidate resource nodes for executing the computing tasks based on the computing power identification and the corresponding resource description files managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node; The computing power identification resolution system is built based on the domain name system.

[0006] Optionally, the relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

[0007] Optionally, the method further comprises: receiving the computing resource usage request sent by the user equipment; and Return the address information of the target resource node to the user equipment.

[0008] Optionally, the at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the multiple resource nodes.

[0009] A second aspect of the present invention provides a method for recursive resolution and resource allocation of computing power identification based on a domain name system, which is applied to a computing power resolution root node in a computing power identification resolution system, and the method includes: Receive a computing power resource usage request sent by a recursive service node, wherein the computing power resource usage request includes relevant information of a computing task; Based on the locally managed computing power identifier and the corresponding resource description file, determine the subordinate node for executing the computing task, and return the node identifier of the determined subordinate node to the recursive service node, so that the recursive service node can determine the target resource node for executing the computing task; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected in sequence; there are multiple subordinate nodes in each layer; the subordinate nodes determine the subordinate nodes or candidate resource nodes for executing the computing tasks in sequence based on the computing power identifications and corresponding resource description files managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node, and the target resource node is determined by the recursive service node based on the resource node identification of the candidate resource node, the corresponding resource description file and the network status information; The computing power identification resolution system is built based on the domain name system.

[0010] Optionally, the relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

[0011] Optionally, the at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the multiple resource nodes.

[0012] Optionally, the method further comprises: Receive the updated resource description file sent by the regional secondary node.

[0013] Optionally, the resource description file corresponding to the computing power analysis root node includes one or a combination of geographical location, resource type, total amount, and load rate.

[0014] A third aspect of the present invention provides a method for recursive resolution and resource allocation of computing power identification based on a domain name system, which is applied to a lower-level node in a computing power identification resolution system, and the method includes: Receive a computing power resource usage request sent by the recursive service node based on a node identifier corresponding to the lower-level node, wherein the computing power resource usage request includes relevant information of the computing task; the node identifier is determined by the computing power resolution root node and returned to the recursive service node; Based on the locally managed computing power identifier and the corresponding resource description file, determine the subordinate node or candidate resource node for executing the computing task, and return the node identifier of the determined subordinate node or the resource node identifier corresponding to the candidate resource node to the recursive service node, so that the recursive service node determines the target resource node for executing the computing task; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected to each other in sequence; there are multiple subordinate nodes in each layer; the computing power resolution root node and the subordinate nodes sequentially determine the subordinate nodes or the candidate resource nodes used to execute the computing tasks based on the computing power identifications and corresponding resource description files managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node, and the target resource node is determined by the recursive service node based on the resource node identification of the candidate resource node, the corresponding resource description file and the network status information; The computing power identification resolution system is built based on the domain name system.

[0015] Optionally, the relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

[0016] Optionally, the at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the multiple resource nodes.

[0017] Optionally, the method further comprises: receiving an updated resource description file sent by the service provider node; and / or Send the updated resource description file to the computing power resolution root node.

[0018] Optionally, the resource description file corresponding to the subordinate node includes one or a combination of resource type, total amount, load rate, price, stability.

[0019] Optionally, the determining a subordinate node or a target resource node for executing the computing task based on the locally managed computing power identifier and the corresponding resource description file includes: Based on the locally managed computing power identifier, the corresponding resource description file and the network dynamic data, the subordinate node or the target resource node for executing the computing task is determined.

[0020] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any of the above-mentioned methods for recursive resolution and resource allocation of computing power identification based on the domain name system.

[0021] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any of the above-mentioned domain name system-based computing power identification recursive resolution and resource allocation methods.

[0022] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned domain name system-based computing power identification recursive resolution and resource allocation methods.

[0023] The method and device for recursive resolution and resource allocation of computing power identification based on the domain name system provided by the present invention are based on the domain name service infrastructure, support resolution and addressing of wide area network computing power identification based on the domain name system, and have higher reliability, security and stability than a newly built identification system; based on the domain name service node, the resolution of computing power resources and the allocation and scheduling of computing power requirements are simultaneously performed during the identification resolution process, so as to efficiently realize the utilization of computing power resources and realize the integration of computing power and network; the top-down resolution and resource allocation method from the root node is helpful for the macro-control and allocation of computing power resources between and within the wide area network, and can achieve balancing at the computing power resource and network levels to improve the comprehensive service performance of the computing power network. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 It is a flowchart of a method for recursive resolution and resource allocation of computing power identification based on a domain name system provided in one embodiment of the present invention.

[0026] Figure 2 An example schematic diagram of a computing power identifier provided in an embodiment of the present invention.

[0027] Figure 3 A schematic diagram of the management format of the computing resource description file provided in an embodiment of the present invention.

[0028] Figure 4 A flowchart of a method for recursive resolution of computing power identification and resource allocation based on a domain name system is provided for another embodiment of the present invention.

[0029] Figure 5 A flowchart of a method for recursive resolution and resource allocation of computing power identification based on a domain name system is provided for yet another embodiment of the present invention.

[0030] Figure 6A flowchart of a method for recursive resolution of computing power identification and resource allocation based on a domain name system is provided for another embodiment of the present invention.

[0031] Figure 7 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] The domain name system has significant stability and reliability characteristics. It is an important Internet infrastructure and the most important form of Internet identification. Research on the recursive resolution and allocation method of computing power identification based on the domain name system and related technologies can flexibly meet the diverse needs of computing power services. The various embodiments of the present invention utilize the hierarchical and structured design characteristics of domain names, as well as the stability and reliability service advantages, to provide a method for unified resolution services and resource allocation that is compatible with various computing power resource identifications. In the process of realizing the resolution of computing power identification, the matching calculation and scheduling of various computing power resources are realized simultaneously, which can effectively improve the utilization level of various computing power resources. The computing power identification resolution system mentioned in the embodiment of the present invention is established based on the domain name system. It can be based on the existing structure of the domain name system, and the functional nodes in the domain name system are transformed to increase their functions, such as improving the recursive service nodes, so that they have the functions of computing power identification resolution and resource allocation.

[0034] Figure 1 FIG. 1 is a flow chart of a method for recursive resolution and resource allocation of computing power identifiers based on a domain name system provided by an embodiment of the present invention. Figure 1 As shown, the method can be applied to the recursive service node in the computing power identification resolution system, and specifically includes the following steps: Step 101: Send a computing power resource usage request to a computing power resolution root node, where the computing power resource usage request includes relevant information of a computing task; The embodiments of the present invention rely on the Domain Name System (DNS) and related infrastructure, combined with the design of recursive service nodes and computing resource management nodes MN at all levels (such as service provider nodes, regional secondary nodes, root nodes, etc.), to achieve the parsing, matching and scheduling of computing resources within the wide area network.

[0035] The recursive service node SN is a network access node (device) that provides computing resource query, access and resolution services to users. It is mainly responsible for information query and application to computing resource management nodes MN at all levels.

[0036] When a user has a computing task and needs to apply for computing resources from the network to perform the computing task, the user sends a computing resource usage request to the SN through the user equipment to apply for computing resources from the network. The computing resource usage request includes relevant information of the computing task, and the relevant information is used to describe the computing task. For example, the relevant information may include one or a combination of task type, computing amount, time requirement, and performance requirement. The network can allocate appropriate computing resources to the computing task based on the relevant information.

[0037] After receiving the computing power resource usage request sent by the user equipment, the SN sends the computing power resource usage request to the computing power resolution root node, requesting the computing power resolution root node to parse the relevant information and allocate appropriate computing power resources accordingly.

[0038] In the embodiment of the present invention, in combination with the computing power identity resolution system service infrastructure, the user equipment can autonomously configure its corresponding recursive service node, or automatically obtain the corresponding recursive service node through the computing power identity resolution system.

[0039] Step 102: receiving the node identifier of the subordinate node returned by the computing power resolution root node, and sending the computing power resource usage request to the subordinate node based on the node identifier; In the embodiment of the present invention, each level of computing resource management node MN in the computing power identification resolution system maintains computing power identification and its corresponding description file. Figure 2 An example schematic diagram of a computing power identifier provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown in the figure, a computing power identifier includes two parts: computing power resource identifier and computing power node identifier. The relatively static information (regional location, resource number, computing power type, computing power architecture, computing power level, etc.) that reflects the key attributes of computing power resources is reflected in the form of computing power node identifier + computing power resource identifier. The node identifier and resource identifier are separated by / . For better compatibility with the DNS domain name resolution system, the two identifiers encode each field in turn, and "." is used to separate each field.

[0040] The computing power resource description file is the key description of the computing power resource and is a supplement to the computing power identifier. The computing power identifier and the computing power resource description file must be used simultaneously during the computing power identifier resolution process. The basic attributes of the computing power resource have been reflected through the computing power identifier. The dynamic description information of the computing power resource (computing load / real-time memory, number of service sessions, bandwidth, QoS, computing latency, etc.) is mainly achieved through the management of resource description files by MNs at all levels. MN uses the domain name service infrastructure and other network devices to dynamically collect computing power resource nodes, obtain the above dynamic description information, and store and apply it through the management form of metadata in the description file. Figure 3 A schematic diagram of the management format of the computing resource description file provided in an embodiment of the present invention.

[0041] The computing power resource management nodes MN at all levels are responsible for managing the computing power identification and resource description files registered with them. The resource description files contain the core metadata information corresponding to the computing power identification. Among them, due to the different positioning of the identification resolution service functions of different nodes, the content of the resource description files of nodes at all levels can be different (the core metadata is selected according to the corresponding resolution decision parameters) to support the specific use in the computing power resolution process. For example, the root node and the regional secondary node are mainly responsible for the allocation of computing resources within the wide area network, so the description files they manage can include metadata information such as the total amount of available resources, computing power subclasses, and comprehensive load; the service provider node is mainly responsible for the allocation of computing resource nodes within the local area or edge computing nodes, so the description files it manages can contain dynamic information such as resource node load, available resources, storage capacity, and bandwidth capacity.

[0042] Computing resource management nodes at all levels jointly undertake the updating and maintenance of computing resource descriptions. For example, the service provider node will mainly collect and update the resource node identifiers and corresponding description files. When the resources of the resource node change, it will trigger the change of the relevant metadata information in the service provider node, and upload the regional secondary node and root node in turn to achieve the management and update of the dynamic description information of the nodes managed by different levels. Computing resource management nodes at all levels update the corresponding resource description file information in real time for calculation and selection of resources at the corresponding level.

[0043] In the embodiment of the present invention, after receiving the computing power resource usage request sent by the recursive service node, the computing power resolution root node parses the relevant information of the computing task included in the computing power resource usage request to determine the task type, computing amount, time requirement and performance requirement of the computing task. The computing power resolution root node determines the subordinate node suitable for providing computing power resources for the computing task based on the locally maintained computing power identification and its corresponding description file.

[0044] In an embodiment of the present invention, the computing power identification resolution system includes a recursive service node, a computing power resolution root node, and at least one layer of subordinate nodes (each embodiment of the present invention is illustrated by taking two layers of subordinate nodes as an example, and the two layers of subordinate nodes include regional secondary nodes and service provider nodes), the uppermost layer of subordinate nodes (regional secondary nodes) are connected in communication with the computing power resolution root node, the lowermost layer of subordinate nodes (service provider nodes) are connected in communication with multiple resource nodes (i.e., nodes for providing computing power resources), and the subordinate nodes are connected in communication in sequence; each layer has multiple subordinate nodes, i.e., multiple regional secondary nodes and multiple service provider nodes. The computing power resolution root node, the regional secondary node, and the service provider node determine the subordinate node or the candidate resource node for executing the computing task in sequence based on the computing power identification and the corresponding resource description file managed by each node, and return the node identification of the determined subordinate node or the candidate resource node identification to the recursive service node.

[0045] After the computing power resolution root node determines that the subordinate node suitable for providing computing power resources for the computing task is a regional secondary node, the node identifier of the regional secondary node is returned to the recursive service node. The recursive service node can send the computing power resource usage request to the regional secondary node based on the node identifier to request the regional secondary node to allocate a suitable service provider node for the computing task.

[0046] Step 103: Receive the resource node identifier and the corresponding resource description file of the candidate resource node returned by the lower-level node, and determine the target resource node for executing the computing task based on the resource node identifier and the corresponding resource description file of the candidate resource node.

[0047] The service provider node can determine the candidate resource node for executing the computing task based on the locally maintained computing power identification and the corresponding resource description file, and return the resource node identification of the candidate resource node and its corresponding resource description file to the recursive service node. The candidate resource node is determined by the lowest-level subordinate node in the computing power identification resolution system from the multiple resource nodes registered on it.

[0048] Then, the recursive service node can determine the target resource node for executing the computing task based on the resource node identifier of the candidate resource node, its corresponding resource description file and network status information. Specifically, the recursive service node can determine the target resource node in combination with the network status information between the user device and the location of the user device. Then, the resource node identifier of the target resource node (for example, the address information of the target resource node) is sent to the user device, and the user device sends the computing task to the target resource node based on the address information of the target resource node to execute the computing task.

[0049] In an embodiment of the present invention, after receiving a service request from SN, MN will match and select the management node (device) for calculation according to the computing power identifier and the relevant information in its description file (computing power type, load, capacity, etc.) and network dynamic data, and perform the control, scheduling, and allocation of computing power resources step by step. MN can implement parsing services and resource allocation between wide-area computing power networks, similar to the computing network orchestration management center, and can select management strategies and control strategies to achieve collaborative scheduling of computing power networks according to resource and network deployment conditions. In an embodiment of the present invention, the service provider node MN can dynamically collect network equipment information and perform dynamic resource matching, and together with computing power resource management nodes at all levels, realize collaborative scheduling of computing networks within the scope of the wide area network, and send the parsing and allocation results to the computing power resource recursive service node SN according to the computing power resource allocation strategy. After receiving the results of the parsing and allocation of computing power resources, SN executes a specific computing power connection.

[0050] The method for recursive resolution and resource allocation of computing power identifiers based on the domain name system provided in the embodiment of the present invention is based on the domain name service infrastructure, supports resolution and addressing of wide area network computing power identifiers based on the domain name system, and has higher reliability, security and stability than a newly built identification system; based on the domain name service node, the resolution of computing power resources and the allocation and scheduling of computing power requirements are simultaneously performed during the identification resolution process, so as to efficiently realize the utilization of computing power resources and achieve computing network integration; the top-down resolution and resource allocation method from the root node is helpful for the macro-control and allocation of computing power resources between and within the wide area network, and can achieve balancing at the computing power resource and network levels to improve the comprehensive service performance of the computing power network.

[0051] Figure 4 A flowchart of a method for recursive resolution and resource allocation of computing power identification based on a domain name system is provided for another embodiment of the present invention, such as Figure 4 As shown, the method can be applied to the computing power resolution root node in the computing power identification resolution system, and specifically includes the following steps: Step 401: Receive a computing resource usage request sent by a recursive service node, where the computing resource usage request includes relevant information of a computing task; When a user has a computing task and needs to apply for computing resources from the network to perform the computing task, the user sends a computing resource usage request to the SN through the user equipment to apply for computing resources from the network. The computing resource usage request includes relevant information of the computing task, and the relevant information is used to describe the computing task. For example, the relevant information may include one or a combination of task type, computing amount, time requirement, and performance requirement. The network can allocate appropriate computing resources to the computing task based on the relevant information.

[0052] After receiving the computing power resource usage request sent by the user equipment, the SN sends the computing power resource usage request to the computing power resolution root node, requesting the computing power resolution root node to parse the relevant information and allocate appropriate computing power resources accordingly.

[0053] Step 402: Based on the locally managed computing power identifier and the corresponding resource description file, determine the lower-level node for executing the computing task, and return the node identifier of the determined lower-level node to the recursive service node, so that the recursive service node can determine the target resource node for executing the computing task; After receiving the computing resource usage request sent by the recursive service node, the computing power resolution root node parses the relevant information of the computing task included in the computing resource usage request to determine the task type, computing amount, time requirement, performance requirement, etc. of the computing task. The computing power resolution root node determines the subordinate node suitable for providing computing resources for the computing task based on the locally maintained computing power identification and its corresponding description file.

[0054] In an embodiment of the present invention, a computing power identification resolution system includes a recursive service node, a computing power resolution root node, and at least one layer of subordinate nodes (each embodiment of the present invention is illustrated by taking two layers of subordinate nodes as an example, and the two layers of subordinate nodes include regional secondary nodes and service provider nodes), the uppermost layer of subordinate nodes (regional secondary nodes) are connected in communication with the computing power resolution root node, and the lowermost layer of subordinate nodes (service provider nodes) are connected in communication with multiple resource nodes (i.e., nodes for providing computing power resources), and the subordinate nodes are connected in communication in sequence; each layer has multiple subordinate nodes, i.e., multiple regional secondary nodes and multiple service provider nodes. The computing power resolution root node, the regional secondary node, and the service provider node sequentially determine the subordinate node or the candidate resource node for executing the computing task based on the computing power identification and the corresponding resource description file managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node. The recursive service node can determine the target resource node for executing the computing task based on the resource node identification of the candidate resource node and the resource description file corresponding to the candidate resource node sent by the lower node.

[0055] After the computing power resolution root node determines that the subordinate node suitable for providing computing power resources for the computing task is a regional secondary node, the node identifier of the regional secondary node is returned to the recursive service node. The recursive service node can send the computing power resource usage request to the regional secondary node based on the node identifier to request the regional secondary node to allocate a suitable service provider node for the computing task.

[0056] The service provider node can determine the candidate resource node for executing the computing task based on the locally maintained computing power identification and the corresponding resource description file, and return the node identification of the candidate resource node to the recursive service node. The candidate resource node is determined by the lowest-level subordinate node in the computing power identification resolution system from the multiple resource nodes registered on it.

[0057] Then, the recursive service node can determine the target resource node for executing the computing task based on the resource node identifier of the candidate resource node, its corresponding resource description file and network status information. Specifically, the recursive service node can determine the target resource node in combination with the network status between the user device and the location of the user device. Then, the resource node identifier of the target resource node (for example, the address information of the target resource node) is sent to the user device, and the user device sends the computing task to the target resource node based on the address information of the target resource node to execute the computing task.

[0058] In an embodiment of the present invention, after receiving a service request from SN, MN will match and select the management node (device) for calculation according to the computing power identifier and the relevant information in its description file (computing power type, load, capacity, etc.) and network dynamic data, and perform the control, scheduling, and allocation of computing power resources step by step. MN can implement parsing services and resource allocation between wide-area computing power networks, similar to the computing network orchestration management center, and can select management strategies and control strategies to achieve collaborative scheduling of computing power networks according to resource and network deployment conditions. In an embodiment of the present invention, the service provider node MN can dynamically collect network equipment information and perform dynamic resource matching, and together with computing power resource management nodes at all levels, realize collaborative scheduling of computing networks within the scope of the wide area network, and send the parsing and allocation results to the computing power resource recursive service node SN according to the computing power resource allocation strategy. After receiving the results of the parsing and allocation of computing power resources, SN executes a specific computing power connection.

[0059] The method for recursive resolution and resource allocation of computing power identifiers based on the domain name system provided in the embodiment of the present invention is based on the domain name service infrastructure, supports resolution and addressing of wide area network computing power identifiers based on the domain name system, and has higher reliability, security and stability than a newly built identification system; based on the domain name service node, the resolution of computing power resources and the allocation and scheduling of computing power requirements are simultaneously performed during the identification resolution process, so as to efficiently realize the utilization of computing power resources and achieve computing network integration; the top-down resolution and resource allocation method from the root node is helpful for the macro-control and allocation of computing power resources between and within the wide area network, and can achieve balancing at the computing power resource and network levels to improve the comprehensive service performance of the computing power network.

[0060] Figure 5 A flowchart of a method for recursive resolution and resource allocation of computing power identification based on a domain name system is provided for another embodiment of the present invention, as shown in FIG. Figure 5 As shown, the method can be applied to the lower-level nodes in the computing power identification resolution system, and specifically includes the following steps: Step 501: receiving a computing power resource usage request sent by a recursive service node based on a node identifier corresponding to the subordinate node, wherein the computing power resource usage request includes relevant information of a computing task; the node identifier is determined by a computing power resolution root node and returned to the recursive service node; In an embodiment of the present invention, the computing power identification resolution system includes a recursive service node, a computing power resolution root node, and at least one layer of subordinate nodes (the embodiment of the present invention is illustrated by two layers of subordinate nodes, and the two layers of subordinate nodes include regional secondary nodes and service provider nodes), the uppermost layer of subordinate nodes (regional secondary nodes) are connected in communication with the computing power resolution root node, the lowermost layer of subordinate nodes (service provider nodes) are connected in communication with multiple resource nodes (i.e., nodes for providing computing power resources), and the subordinate nodes are connected in communication in sequence; each layer has multiple subordinate nodes, i.e., multiple regional secondary nodes and multiple service provider nodes. The computing power resolution root node, the regional secondary node, and the service provider node determine the subordinate node or the candidate resource node for executing the computing task in sequence based on the computing power identification and the corresponding resource description file managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node.

[0061] When a user has a computing task and needs to apply for computing resources from the network to perform the computing task, the user sends a computing resource usage request to the SN through the user equipment to apply for computing resources from the network. The computing resource usage request includes relevant information of the computing task, and the relevant information is used to describe the computing task. For example, the relevant information may include one or a combination of task type, computing amount, time requirement, and performance requirement. The network can allocate appropriate computing resources to the computing task based on the relevant information.

[0062] After receiving the computing power resource usage request sent by the user equipment, the SN sends the computing power resource usage request to the computing power resolution root node, requesting the computing power resolution root node to parse the relevant information and allocate appropriate computing power resources accordingly.

[0063] After receiving the computing resource usage request sent by the recursive service node, the computing power resolution root node parses the relevant information of the computing task included in the computing resource usage request to determine the task type, computing amount, time requirement, performance requirement, etc. of the computing task. The computing power resolution root node determines the subordinate node suitable for providing computing resources for the computing task based on the locally maintained computing power identification and its corresponding description file.

[0064] Step 502: Based on the locally managed computing power identifier and the corresponding resource description file, determine the subordinate node or candidate resource node for executing the computing task, and return the node identifier of the determined subordinate node or the resource node identifier corresponding to the candidate resource node to the recursive service node, so that the recursive service node determines the target resource node for executing the computing task; After the computing power resolution root node determines that the subordinate node suitable for providing computing power resources for the computing task is a regional secondary node, the node identifier of the regional secondary node is returned to the recursive service node. The recursive service node can send the computing power resource usage request to the regional secondary node based on the node identifier to request the regional secondary node to allocate a suitable service provider node for the computing task.

[0065] The service provider node can determine a list of candidate resource nodes (which may include multiple candidate resource nodes) for executing the computing task based on the locally maintained computing power identification and the corresponding resource description file, and feed the candidate resource node list and the corresponding resource description file back to the recursive service node, which performs calculations and determines the final target resource node identification and returns it to the recursive service node. The candidate resource node is determined by the lowest-level subordinate node in the computing power identification resolution system from the multiple resource nodes registered on it.

[0066] Then, the recursive service node can determine the target resource node for executing the computing task based on the resource node identifier of the candidate resource node, its corresponding resource description file, and network status information. Specifically, the recursive service node can determine the target resource node in combination with the network status between the user device and the location of the user device. Then, the resource node identifier of the target resource node (for example, the address information of the target resource node) is sent to the user device, and the user device sends the computing task to the target resource node based on the address information of the target resource node to execute the computing task.

[0067] In an embodiment of the present invention, after receiving a service request from SN, MN will match and select the management node (device) for calculation according to the computing power identifier and the relevant information in its description file (computing power type, load, capacity, etc.) and network dynamic data, and perform the control, scheduling, and allocation of computing power resources step by step. MN can implement parsing services and resource allocation between wide-area computing power networks, similar to the computing network orchestration management center, and can select management strategies and control strategies to achieve collaborative scheduling of computing power networks according to resource and network deployment conditions. In an embodiment of the present invention, the service provider node MN can dynamically collect network equipment information and perform dynamic resource matching, and together with computing power resource management nodes at all levels, realize collaborative scheduling of computing networks within the scope of the wide area network, and send the parsing and allocation results to the computing power resource recursive service node SN according to the computing power resource allocation strategy. After receiving the results of the parsing and allocation of computing power resources, SN executes a specific computing power connection.

[0068] In an embodiment of the present invention, the subordinate node determines the subordinate node or target resource node for executing the computing task based on the locally managed computing power identifier and the corresponding resource description file, including: determining the subordinate node or target resource node for executing the computing task based on the locally managed computing power identifier, the corresponding resource description file and the network dynamic data. Specifically, for example, when a regional secondary node selects a suitable service provider node, it can dynamically determine the service provider node based on the current network dynamic data such as network bandwidth jitter and other actual conditions in combination with the computing power identifier and the corresponding resource description file. Accordingly, when the service provider node selects a suitable resource node, it can dynamically determine the target resource node based on the current network dynamic data such as network bandwidth jitter and other actual conditions in combination with the computing power identifier and the corresponding resource description file.

[0069] The method for recursive resolution and resource allocation of computing power identifiers based on the domain name system provided in the embodiment of the present invention is based on the domain name service infrastructure, supports resolution and addressing of wide area network computing power identifiers based on the domain name system, and has higher reliability, security and stability than a newly built identification system; based on the domain name service node, the resolution of computing power resources and the allocation and scheduling of computing power requirements are simultaneously performed during the identification resolution process, so as to efficiently realize the utilization of computing power resources and achieve computing network integration; the top-down resolution and resource allocation method from the computing power resolution root node is helpful for the macro-control and allocation of computing power resources between and within the wide area network, and can achieve balancing at the computing power resource and network levels to improve the comprehensive service performance of the computing power network.

[0070] Figure 6A flowchart of a method for recursive resolution and resource allocation of computing power identification based on a domain name system provided by another embodiment of the present invention is provided. In combination with a hierarchical computing power resource management node, a multi-level computing power identification recursive resolution and resource allocation method is designed in the embodiment of the present invention. The computing power identification and related description file information can be allocated to different regional computing power resource scheduling levels according to the characteristic requirements, architecture and price requirements of the computing task, so as to perform more efficient resource matching, such as Figure 6 As shown, the method comprises the following steps: 1. The user initiates an application for computing resource usage to the recursive service node. The application needs to describe the computing task type, computing amount, time requirements, performance requirements, etc.

[0071] 2-3. The recursive service node sends the above application request to the computing power resolution root node. The root node selects the optimal path based on the local files and resource description files, such as the user's geographical location, available resources and other information, assigns the task to the corresponding regional secondary node, and feeds back the node identifier to the recursive service node; 4-5. The recursive service node applies for computing power service requirements from the regional secondary node. The secondary node can allocate tasks to the corresponding service provider node based on the local files and resource description files, combined with information such as available resources, comprehensive load, and overall network performance, and feedback the node identifier to the recursive service node; 6-7. The recursive service node applies for computing power service requirements from the service provider node. After receiving the application, the service provider node can match the task to the corresponding resource node based on the local file and resource description file, combined with factors such as available resources, comprehensive load, storage capacity, and geographical location, and feed back the node identification and analysis results to the recursive service node; 8-9. The recursive service node feeds back the resource node identification and parsing information to the user; 10. The user accesses the computing resource node according to the target resource node identification and parsed information and sends the computing task.

[0072] In an embodiment of the present invention, the computing power resolution root node receives an updated resource description file sent by a regional secondary node, the regional secondary node receives an updated resource description file sent by the service provider node, and the regional secondary node sends the updated resource description file to the computing power resolution root node. Figure 6 As shown, the computing resource node confirms the task request and executes it, and applies to the service provider node for the update of its resource description file; the service provider node applies to the regional secondary node for the update of the resource description file, and the regional secondary node applies to the computing power resolution root node for the update of the resource description file.

[0073] The method for recursive resolution and resource allocation of computing power identification based on the domain name system provided in the embodiment of the present invention associates computing power identification and key attributes through resource description files, and supports dynamic management and updating of files. Different computing power resource management nodes manage the identification and resource description files of the corresponding levels in the form of zone files, and have configurable properties. The resource description file is dynamically managed and updated in the form of metadata. When a computing power resource is newly registered or changed, the description file update of the corresponding computing power resource management node will be initiated, and the computing power resource management nodes at all levels will only update the relevant metadata in the resource description file. The computing power resource management nodes at all levels will perform computing power resolution and allocation according to the computing power identification and its current resource description information to support the dynamic allocation and scheduling of computing power resources.

[0074] In the computing resource management node, the service provider node will mainly collect and manage the resource node identification and corresponding description files. When the resources of the resource node change, it will trigger the change of the relevant metadata information in its registration identification management node, and upload it to the upper management node and the computing power analysis root node in turn to achieve the management and update of the dynamic description information of the nodes managed by different levels. Each node updates the corresponding resource description file information in real time for calculation and selection of resources at the corresponding level.

[0075] The identification information of the resource node that has completed registration is stored (area file) in the corresponding computing resource management node (such as the service provider node), and managed together with the resource description data file, and the updated data is reported to the upper node synchronously. After the upper node updates the corresponding resource description file, it continues to report the updated data to the computing power resolution root node step by step. The management node and the computing power resolution root node update the corresponding resource description file in turn. At this point, all data updates in the registration process are completed.

[0076] When resource node resources change actively, or after resources are allocated according to the analysis, they need to be reported to the computing resource management node (such as the service provider node) to update the data of the corresponding description file. After the computing resource management node updates the resource node information, it needs to report the key resource statistics and other change data step by step (for example, the regional secondary node uniformly manages the service provider node identification information and the corresponding resource description file, and updates it synchronously according to the information reported by the service provider node), until the computing power analysis root node synchronously updates the corresponding resource description file.

[0077] The identifier resolution infrastructure of the computing power identifier resolution system in the embodiment of the present invention can realize unified and efficient computing power identifier recursive resolution and scheduling through recursive service nodes, coordinated computing power resolution root nodes, regional secondary nodes, service provider nodes and other multi-level architectures. The computing power resource identifier resolution refers to the process in which the recursive service node sends the user's computing resource request to a specific computing power resource node according to specific rules, and the computing power resource scheduling method contained therein refers to matching and selecting according to the computing power identifier and the relevant information in its resource description file (computing power type, load, capacity, etc.), network dynamic data, etc., and sequentially directing tasks from the computing power resolution root node to the regional secondary node and the service provider node. Comprehensive scheduling and matching method.

[0078] In the embodiment of the present invention, the recursive service node can trigger the top-down parsing and allocation from the root node according to the user's computing power requirements, which specifically includes: The root node can perform the first task matching based on the computing power identification it manages and the relevant information in the resource description file (resource type, total amount, load rate, geographical location, etc.), and feed back the secondary node of the designated corresponding area to the recursive service node; The regional secondary node can perform secondary task allocation based on the computing power identification it manages and the relevant information in the resource description file (resource type, total amount, load rate, price, etc.), and feed back the designated corresponding service provider node to the recursive service node; The service provider node, or more levels of management nodes set according to demand, can make further task allocations based on the computing power identification it manages and the relevant information in the resource description file (resource type, total amount, load rate, stability, etc.) and network dynamic information, and finally select the optimal computing power resource node, and feed back the node identification and parsing information to the recursive service node.

[0079] Users can connect and use computing resources based on the above information fed back by recursive nodes.

[0080] Figure 7 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the computing power identification recursive resolution and resource allocation method based on the domain name system provided in the above embodiments.

[0081] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0082] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the domain name system-based computing power identification recursive resolution and resource allocation method provided in the above-mentioned embodiments.

[0083] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is used by a processor to execute the domain name system-based computing power identification recursive resolution and resource allocation method provided in the above-mentioned embodiments.

[0084] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for recursive resolution and resource allocation of computing power identification based on a domain name system, characterized in that: Applied to a recursive service node in a computing power identification resolution system, the method comprises: Sending a computing power resource usage request to the computing power resolution root node, wherein the computing power resource usage request includes relevant information of the computing task; Receiving the node identifier of the subordinate node returned by the computing power resolution root node, and sending the computing power resource usage request to the subordinate node based on the node identifier; Receive the resource node identifier and the corresponding resource description file of the candidate resource node returned by the subordinate node, and determine the target resource node for executing the computing task according to a specific computing method based on the candidate resource node identifier and the corresponding resource description file; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected in sequence; there are multiple subordinate nodes in each layer; the computing power resolution root node and the subordinate nodes sequentially determine the subordinate nodes or the candidate resource nodes for executing the computing tasks based on the computing power identifications and corresponding resource description files managed by each node, and return the node identifications of the determined subordinate nodes or the resource node identifications of the candidate resource nodes to the recursive service node; The computing power identification resolution system is built based on the domain name system.

2. The method for recursive resolution and resource allocation of computing power identification based on the domain name system according to claim 1, characterized in that: The relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

3. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 1 or 2, characterized in that: The method further comprises: receiving the computing resource usage request sent by the user equipment; and Return the address information of the target resource node to the user equipment.

4. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 1 or 2, characterized in that: The at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the plurality of resource nodes.

5. A method for recursive resolution and resource allocation of computing power identification based on a domain name system, characterized in that: The method applied to the computing power resolution root node in the computing power identification resolution system includes: Receive a computing power resource usage request sent by a recursive service node, wherein the computing power resource usage request includes relevant information of a computing task; Based on the locally managed computing power identifier and the corresponding resource description file, determine the subordinate node for executing the computing task, and return the node identifier of the determined subordinate node to the recursive service node, so that the recursive service node can determine the target resource node for executing the computing task; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected in sequence; there are multiple subordinate nodes in each layer; the subordinate nodes determine the subordinate nodes or candidate resource nodes for executing the computing tasks in sequence based on the computing power identifications and corresponding resource description files managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node, and the target resource node is determined by the recursive service node based on the resource node identification of the candidate resource node, the corresponding resource description file and the network status information; The computing power identification resolution system is built based on the domain name system.

6. The method for recursive resolution and resource allocation of computing power identification based on the domain name system according to claim 5, characterized in that: The relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

7. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 5 or 6, characterized in that: The at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the plurality of resource nodes.

8. The method for recursive resolution and resource allocation of computing power identification based on domain name system according to claim 7, characterized in that: The method further comprises: Receive the updated resource description file sent by the regional secondary node.

9. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 5 or 6, characterized in that: The resource description file corresponding to the computing power analysis root node includes one or a combination of geographical location, resource type, total amount, and load rate.

10. A method for recursive resolution and resource allocation of computing power identification based on a domain name system, characterized in that: Applied to a lower-level node in a computing power identification resolution system, the method includes: Receive a computing power resource usage request sent by the recursive service node based on a node identifier corresponding to the lower-level node, wherein the computing power resource usage request includes relevant information of the computing task; the node identifier is determined by the computing power resolution root node and returned to the recursive service node; Based on the locally managed computing power identifier and the corresponding resource description file, determine the subordinate node or candidate resource node for executing the computing task, and return the node identifier of the determined subordinate node or the resource node identifier corresponding to the candidate resource node to the recursive service node, so that the recursive service node determines the target resource node for executing the computing task; The computing power identification resolution system includes the recursive service node, the computing power resolution root node and at least one layer of subordinate nodes, the uppermost layer of subordinate nodes are communicatively connected to the computing power resolution root node, the lowermost layer of subordinate nodes are communicatively connected to multiple resource nodes, and the subordinate nodes are communicatively connected to each other in sequence; there are multiple subordinate nodes in each layer; the computing power resolution root node and the subordinate nodes sequentially determine the subordinate nodes or the candidate resource nodes used to execute the computing tasks based on the computing power identifications and corresponding resource description files managed by each node, and return the node identification of the determined subordinate node or the resource node identification of the candidate resource node to the recursive service node, and the target resource node is determined by the recursive service node based on the resource node identification of the candidate resource node, the corresponding resource description file and the network status information; The computing power identification resolution system is built based on the domain name system.

11. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 10, characterized in that: The relevant information of the computing task includes one or a combination of task type, computing amount, time requirement, and performance requirement.

12. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 10 or 11, characterized in that: The at least one layer of lower-level nodes includes a regional secondary node and a service provider node; wherein the regional secondary node is communicatively connected to the computing power resolution root node, and the service provider node is communicatively connected to the regional secondary node and the plurality of resource nodes.

13. The method for recursive resolution of computing power identification and resource allocation based on a domain name system according to claim 12, characterized in that: The method further comprises: receiving an updated resource description file sent by the service provider node; and / or Send the updated resource description file to the computing power resolution root node.

14. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 10 or 11, characterized in that: The resource description file corresponding to the subordinate node includes one or a combination of resource type, total amount, load rate, price, and stability.

15. The method for recursive resolution and resource allocation of computing power identification based on a domain name system according to claim 10 or 11, characterized in that: The determining of a subordinate node or a target resource node for executing the computing task based on the locally managed computing power identifier and the corresponding resource description file includes: Based on the locally managed computing power identifier, the corresponding resource description file and the network dynamic data, the subordinate node or the target resource node for executing the computing task is determined.

16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for recursive resolution and resource allocation of computing power identification based on the domain name system as described in any one of claims 1 to 15 is implemented.

17. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for recursive resolution and resource allocation of computing power identification based on a domain name system as described in any one of claims 1 to 15 is implemented.

18. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for recursive resolution and resource allocation of computing power identification based on a domain name system as described in any one of claims 1 to 15 is implemented.

Images