Computing power resource sharing method, service deployment method and electronic equipment

Abstract

Provided are a computing power resource sharing method, a service deployment method and an electronic device, the computing power resource sharing method comprising: a first network node receiving a computing power resource acquisition request sent by a second network node, the computing power resource acquisition request carrying computing power demand information, and then the first network node determines a shared network node satisfying the computing power demand information from a computing power pool containing a plurality of network nodes, and sends identification information of the shared network node to a second network node, so that the second network node performs target service deployment on the shared network node according to the identification information. In the embodiment of the invention, the first network node determines the shared network node from the computing power pool containing the plurality of network nodes for the second network node, so that the second network node can deploy own service on the shared network node, thereby realizing resource sharing among the network nodes; the resource utilization rate of network nodes can be improved, and the operation cost of operators can be reduced.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a computing resource sharing method, a service deployment method, and an electronic device. Background Art

[0002] With the rapid development of cloud computing, big data and other businesses, the computing power requirements of network nodes such as base stations and servers are getting higher and higher, and many resource scheduling methods for network nodes have emerged.

[0003] However, the relevant resource scheduling methods only achieve the allocation of computing resources within the network nodes. For network nodes with increased load, it is often necessary to expand the capacity by planning hardware resources, etc., which has the disadvantages of slow response speed, large workload and manual participation. It can be seen that the problems of traditional resource scheduling methods make it difficult to meet the needs of the current rapid development of business. Summary of the invention

[0004] The embodiments of the present application provide a computing resource sharing method, a service deployment method, and an electronic device, which can realize resource sharing among network nodes and improve the resource utilization of network nodes.

[0005] In a first aspect, an embodiment of the present application provides a computing resource sharing method, which is applied to a first network node, and the method includes:

[0006] Receive a computing power resource acquisition request sent by the second network node, where the computing power resource acquisition request carries computing power demand information;

[0007] Determine a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes;

[0008] The identification information of the shared network node is sent to the second network node, so that the second network node deploys the target service on the shared network node according to the identification information.

[0009] In a second aspect, an embodiment of the present application provides a service deployment method, which is applied to a second network node, and the method includes:

[0010] Sending a computing power resource acquisition request carrying computing power requirement information to the first network node, so that the first network node determines a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes;

[0011] receiving identification information of the shared network node sent by the first network node;

[0012] The target service is deployed on the shared network node according to the identification information.

[0013] In a third aspect, an embodiment of the present application provides a computing resource sharing system, the system comprising a first network node and a plurality of second network nodes, the first network node and the plurality of second network nodes forming a computing power pool, wherein:

[0014] The first network node is used to receive a computing power resource acquisition request sent by a second network node, the computing power resource acquisition request carries computing power demand information, determine a shared network node that meets the computing power demand information from the computing power pool, and send identification information of the shared network node to the second network node, so that the second network node deploys a target service on the shared network node according to the identification information;

[0015] The second network node is used to send a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node determines a shared network node that meets the computing power demand information from the computing power pool, receives the identification information of the shared network node sent by the first network node, and deploys the target service on the shared network node according to the identification information.

[0016] In a fourth aspect, an embodiment of the present application provides an electronic device, including:

[0017] one or more processors;

[0018] A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the computing power resource sharing method as described in the first aspect above; or, implement the service deployment method as described in the second aspect above.

[0019] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the computing power resource sharing method described in the first aspect above; or, it implements the service deployment method described in the second aspect above.

[0020] In an embodiment of the present application, a first network node receives a computing power resource acquisition request sent by a second network node, and the computing power resource acquisition request carries computing power demand information. Then, the first network node determines a shared network node that meets the computing power demand information from a computing power pool including multiple network nodes, and sends the identification information of the shared network node to the second network node, so that the second network node deploys a target service on the shared network node according to the identification information. In an embodiment of the present application, the first network node determines a corresponding shared network node from a computing power pool including multiple network nodes for the second network node, so that the second network node can deploy its own service on the shared network node, thereby realizing resource sharing between network nodes, improving the resource utilization of network nodes and reducing the operating costs of operators, and meeting the current high-speed business requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0022] Figure 1 This is a schematic diagram of a network architecture provided by an embodiment of the present application;

[0023] Figure 2 It is a flowchart of a computing resource sharing method provided by an embodiment of the present application;

[0024] Figure 3 is a flowchart of a computing resource sharing method provided by another embodiment of the present application;

[0025] Figure 4 is a flowchart of a computing resource sharing method provided by another embodiment of the present application;

[0026] Figure 5 It is a flowchart of a service deployment method provided by an embodiment of the present application;

[0027] Figure 6 is a flow chart of a service deployment method provided by another embodiment of the present application;

[0028] Figure 7 is a schematic diagram of an implementation of a service deployment method provided by another embodiment of the present application;

[0029] Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable technical personnel in this field to better understand the technical solution of the present application, the computing power resource sharing method, service deployment method, computing power resource sharing system, electronic device, and computer-readable storage medium provided by the present application are described in detail below in conjunction with the accompanying drawings.

[0031] The exemplary embodiments will be described more fully below with reference to the accompanying drawings, but the described exemplary embodiments may be embodied in different forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make this application thorough and complete and to enable those skilled in the art to fully understand the scope of this application.

[0032] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0033] The terms used herein are only used to describe specific embodiments and are not intended to limit the present application. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0034] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0035] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present application, and will not be interpreted as having an idealized or excessive formal meaning, unless clearly defined in the present application examples.

[0036] With the rapid development of cloud computing, big data and other businesses, the computing power requirements of network nodes such as base stations and servers are getting higher and higher, and many resource scheduling methods for network nodes have emerged.

[0037] However, the relevant resource scheduling methods only achieve the allocation of computing resources within the network nodes. For network nodes with increased load, it is often necessary to expand the capacity by planning hardware resources, etc., which has the disadvantages of slow response speed, large workload and manual participation. It can be seen that the problems of traditional resource scheduling methods make it difficult to meet the needs of the current rapid development of business.

[0038] Based on this, the embodiments of the present application propose a computing resource sharing method, a service deployment method and an electronic device, which can realize resource sharing among network nodes and improve the resource utilization of network nodes.

[0039] Before introducing the technical solution of the embodiment of the present application, the network architecture of the embodiment of the present application is first exemplified. The network architecture of the embodiment of the present application includes multiple network nodes, and each network node can communicate with each other to perform data exchange and state perception. Figure 1 , Figure 1 is a schematic diagram of a network architecture provided by an embodiment of the present application, such as Figure 1 As shown, the network architecture includes a first network node 101, a second network node 201, a second network node 202, a second network node 203, a second network node 204, etc. The above-mentioned multiple network nodes constitute a computing power pool, and the network nodes in the computing power pool can communicate with each other, wherein the first network node serves as the master station in the computing power pool, and the second network nodes in the computing power pool except the first network node all serve as slave stations, and the slave stations report heartbeats, their own resources, applications and other data to the master station, and the master station is responsible for monitoring the heartbeats of the slave stations and receiving and storing the data reported by the slave stations, wherein the network nodes can be physical nodes such as base stations, general x86 servers, etc. that can provide computing power resources.

[0040] The present application embodiment first proposes a computing resource sharing method, which is applied to a first network node. Figure 2 , Figure 2 A computing resource sharing method provided by an embodiment of the present application is shown. Figure 2 As shown, the method includes but is not limited to steps S110 to S130.

[0041] Step S110: receiving a computing power resource acquisition request sent by the second network node, where the computing power resource acquisition request carries computing power demand information.

[0042] It can be understood that the first network node and the second network node are members of the computing power pool, the first network node is the master station in the computing power pool, and the second network node is the slave station in the computing power pool. When the second network node’s own resources are insufficient, the second network node sends a computing power resource acquisition request carrying computing power demand information to the first network node, and the first network node selects and allocates shared network nodes based on the computing power demand information.

[0043] It should be understood that the computing power requirement information may be the requirement information of at least one of the resources such as CPU, GPU, memory, storage, etc.

[0044] Step S120, determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes.

[0045] It should be noted that network nodes in different regions can be included in the computing power pool as resource nodes, and the included network nodes can be continuously managed and monitored through the main station of the computing power pool, so as to continuously expand the computing power pool and increase shared computing power resources. Through the subsequent cross-site deployment of services, the idle resources of network nodes can be utilized across regions, which not only reduces manual intervention and improves operation and maintenance efficiency, but also cuts costs and improves resource utilization and energy efficiency.

[0046] Step S130: sending the identification information of the shared network node to the second network node, so that the second network node deploys the target service on the shared network node according to the identification information.

[0047] It should be understood that after the first network node determines the shared network node from the computing power pool, the first network node sends the identification information of the shared network node, such as the IP address, MAC address, host number or port number of the shared network node, to the second network node, and the second network node establishes a communication connection with the shared network node based on the identification information, so that the second network node can complete the deployment of the target service on the shared network node.

[0048] Through the computing power resource sharing method provided by the embodiment of the present application, the services on the network nodes can be deployed across stations to any network node in the computing power pool, realizing the computing power resource sharing of multiple network nodes in the computing power pool, and the network nodes in different regions can complement each other in terms of software and hardware resources, solving a series of computing power shortage problems caused by tidal effects, regional business differences, high computing power requirements, etc., and at the same time maximizing the use of idle resources of each network node. Compared with the traditional resource sharing method that is limited to the internal resource allocation of the base station, the embodiment of the present application breaks through the spatial limitations of computing power resource sharing, and can achieve nearly unlimited resource sharing capabilities by continuously accessing more network nodes and utilizing the multi-node computing power sharing capabilities.

[0049] In some embodiments, the computing resource sharing method provided in the embodiments of the present application also includes step S210.

[0050] Step S210, receiving reporting information sent by the target network node in the computing power pool.

[0051] It can be understood that each target network node in the computing power pool can periodically send reporting information to the first network node serving as the master station of the computing power pool. For example, each target network node sends reporting information to the first network node every 30 seconds, and the first network node continuously receives reporting information sent by each target network node, thereby realizing the monitoring of each network node in the computing power pool; each target network node in the computing power pool can also send reporting information to the first network node serving as the master station of the computing power pool according to conditions or user triggers, or the above methods can exist at the same time (such as sending reporting information according to user triggers while periodically sending reporting information), and the present invention is not limited to this.

[0052] In some embodiments, the computing resource sharing method provided in the embodiments of the present application also includes step S310.

[0053] Step S310: Mark the target network node as being in an abnormal state or a normal state according to the reported information.

[0054] See also Figure 3 , Figure 3 This is a computing resource sharing method provided by an embodiment of the present application, such as Figure 3 As shown, after the master station and the slave station in the computing power pool are configured, the first network node as the master station starts to monitor the status of the second network node as the slave station in the computing power pool, the second network node sends reporting information to the first network node, and the first network node receives and stores the reporting information of each second network node, wherein the first network node marks the network node as abnormal or normal according to the reporting information. Specifically, when the first network node receives the reporting information sent by the target network node within the first preset time interval, the first network node believes that the target network node is operating normally and marks the target network node as normal, and when the first network node is within the first preset If the first network node does not receive the reporting information sent by the target network node within a preset time interval, the first network node considers that the target network node is in an abnormal state and marks the target network node as an abnormal state. Further, when the first network node does not receive the reporting information sent by the target network node within a second preset time interval, the first network node considers that the target network node is out of connection and marks the target network node as a lost connection state in the abnormal state, wherein the second preset time interval is greater than the first preset time interval, that is, compared with marking the target network node as an abnormal state, the first network node will mark the target network node as a lost connection state only when it does not receive the reporting information within a longer time interval.

[0055] For example, Figure 3As shown, the first preset time interval can be called the abnormal time, and the second preset time interval can be called the lost connection time. For the second network node A in the computing power pool, if the first network node does not receive the reported information sent by it within the abnormal time, the second network node A will be marked as an abnormal state by the first network node as the master station. If after the lost connection time, the first network node still does not receive the reported information sent by the second network node A, the second network node A will be marked as a lost connection state by the first network node as the master station.

[0056] It can be understood that when the target network node is marked as abnormal (or disconnected) by the first network node, the target network node will not be used as a shared network node. That is to say, the first network node only determines the shared network node that meets the computing power requirement information from the network nodes in normal state.

[0057] The first network node monitors the status of each network node in the computing power pool to achieve automatic management of the computing power pool, reduce the cost of manual intervention and improve operation and maintenance efficiency.

[0058] It should be understood that the target network node may fail to send the reporting information to the first network node due to a device failure or busy business, or the first network node may fail to receive the reporting information sent by the target network node due to a communication link failure between the target network node and the first network node, thereby causing the target network node to be marked as abnormal (or disconnected) by the first network node. When the problem that caused the first network node to fail to receive the reporting information sent by the second network node is eliminated, Figure 3 As shown, the first network node receives the reporting information sent by the target network node marked as abnormal state (or lost connection state), and re-marks the target network node as normal state, indicating that the target network node can continue to participate in computing resource sharing.

[0059] In some embodiments, the reported information includes resource usage information of the target network node, and determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes includes:

[0060] According to the resource usage information, a shared network node that meets the computing power demand information is determined from a computing power pool containing multiple network nodes.

[0061] It is understandable that each target network node in the computing power pool sends resource usage information to the first network node, and the resource usage information includes the resource usage of each target network node. Thus, the first network node can determine from the computing power pool a shared network node that can meet the computing power requirements of the second network node and has more computing power resources based on the resource usage information of each network node, so that the second network node can deploy the target service on the shared network node and operate normally.

[0062] In some embodiments, the resource usage information may include at least one of a CPU real-time utilization rate, a GPU real-time utilization rate, a memory real-time occupancy rate, or a hard disk real-time occupancy rate.

[0063] In some embodiments, the reported information includes the operating status information of the target network node, and determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes includes:

[0064] According to the operation status information, a shared network node that meets the computing power demand information is determined from a computing power pool containing multiple network nodes.

[0065] It is understandable that each target network node in the computing power pool sends running status information to the first network node, and the running status information includes the running status of each target network node. Thus, the first network node can determine a shared network node in the computing power pool that can meet the computing power requirements of the second network node and has a good running status according to the running status information of each network node, thereby improving the service quality of the target service deployed by the second network node on the shared network node.

[0066] In some embodiments, the operating status information may include: base station connection status information, including whether the base station is online, the connection status with the core network, and whether there is a disconnection; base station signal quality information, including quality indicator information of received and transmitted signals, such as signal strength, signal-to-noise ratio, bit error rate, etc.; power and power supply status information, including the status of the main power supply and backup power supply, power consumption and other information; user connection and traffic statistics information, including the number of users currently connected to the base station, the number of active users, data traffic, call volume and other statistical data; and at least one of latency information, service software version, etc.

[0067] Exemplarily, the first network node selects multiple network nodes with short bandwidth latency and high service software compatibility from the computing power pool as the service deployment circle of the second network node according to the latency information or service software version in the running status information, and the first network node further determines a shared network node in the service deployment circle of the second network node.

[0068] In some embodiments, determining a shared network node that meets the computing power requirement information from a computing power pool comprising multiple network nodes includes step S410 and step S420.

[0069] Step S410, obtaining historical service deployment records.

[0070] Step S420, determining a shared network node that meets the computing power demand information from a computing power pool including multiple network nodes according to historical service deployment records.

[0071] It can be understood that when the first network node allocates shared network nodes, it obtains historical service deployment records and uses the historical service deployment records to perform KPI modeling, and screens the network nodes in the computing power pool from the perspective of improving service deployment efficiency, so that the first network node can allocate shared network nodes that significantly improve service deployment efficiency to the second network node.

[0072] In some embodiments, the historical service deployment record may include at least one of the deployed service type, service business data, etc. The service deployment record may be formed by the second network node in the process of deploying the target service on the shared network node.

[0073] It should be understood that the first network node can determine the shared network node that meets the computing power demand information from the computing power pool containing multiple network nodes based on at least one of the resource usage information, the operating status information, and the historical service deployment record. That is to say, the first network node can select any one of the resource usage information, the operating status information, and the historical service deployment record, or any two or all three as the basis for selecting the shared network node. For example, when the first network node allocates the shared network node, it determines the shared network node that meets the computing power demand information from the computing power pool containing multiple network nodes based on the resource usage information, the operating status, and the historical service deployment record. On the one hand, the resource usage information can be used to determine the network node that not only meets the computing power demand information but also has more computing power resources in the computing power pool; on the other hand, the operating status information can be used to screen the high-quality service deployment circle of the second network node in the computing power pool; on the other hand, the first network node can use the historical service deployment record to perform KPI modeling, screen the network nodes in the computing power pool from the level of service deployment efficiency improvement, and allocate the shared network node with significant service deployment efficiency improvement to the second network node. Therefore, the first network node can select a shared network node with more shared resources and better service deployment effect in the service deployment circle of the second network node according to the resource usage information, operation status information and historical service deployment records.

[0074] For example, see Figure 4 , Figure 4A schematic diagram of a computing resource sharing method provided in an embodiment of the present application is shown. Figure 4 As shown, the first network node uses a preset orchestration model to perform orchestration calculations to obtain a shared network node that can meet the computing power demand information, wherein the orchestration model involves three parameter dimensions: resource supply capability, service deployment efficiency improvement capability, and service deployment circle, and the orchestration calculation is performed through the resource usage information, operating status information, and historical service deployment records of the network node. That is to say, in some embodiments, the first network node determines the shared network node that meets the computing power demand information from a computing power pool containing multiple network nodes based on the resource usage information, operating status information, and historical service deployment records, and is used to score and rank the network nodes in the computing power pool in terms of resource supply capability, service deployment circle, and service deployment efficiency improvement capability, so as to select network nodes with more shared resources and better service deployment effects from the service deployment circle of the second network node as much as possible, so as to maximize the efficiency of service deployment.

[0075] In some embodiments, the computing resource sharing method provided in the embodiments of the present application also includes steps S510 to S530.

[0076] Step S510, obtaining the service deployment record.

[0077] Step S520, obtaining the operation information of the target service according to the service deployment record.

[0078] Step S530, determining the next shared network node selection strategy of the computing power pool according to the operation information.

[0079] It can be understood that after the shared network node deploys the target service, the second network node records the service deployment information, the first network node obtains the service deployment record, and the first network node analyzes the service deployment record and determines the next shared network node selection strategy for the computing power pool from the level of service deployment effect based on the operation information.

[0080] In some embodiments, the operational information may include performance indicators of the service, including response time, throughput, number of concurrent connections, and other indicators; availability and reliability indicators, including uptime, mean time to repair MTTR, mean time between failures MTBF, and other indicators; user behavior and experience data, including at least one of the following indicators: user visits, user activity, user retention rate, and other indicators.

[0081] In some embodiments, determining the next shared network node selection strategy of the computing power pool based on the operation information includes step S610 or step S620.

[0082] Step S610: When the operation information meets the preset conditions, the next shared network node selection strategy of the computing power pool is maintained.

[0083] Step S620: When the operation information does not meet the preset conditions, adjust the next shared network node selection strategy of the computing power pool.

[0084] It should be understood that judging whether the operation information of the target service meets the preset conditions, for example, in the performance indicators, judging whether the response time of the target service meets the expected requirements, in the reliability indicators, judging whether the average failure interval time of the target service meets the expected requirements, and in the user behavior indicators, judging whether the user access volume of the target service meets the expected requirements, thereby determining the next shared network node selection strategy of the computing power pool according to the operation information. Specifically, if it is judged that the operation data meets the expected requirements, the current shared network node selection strategy is maintained. If it is judged that the operation data does not meet the expected requirements, the next shared network node selection strategy of the computing power pool is adjusted according to the built-in configuration or adjustment rules to improve the subsequent cross-site deployment quality of the service. Exemplarily, when the target service does not meet the expected requirements in terms of response time and average failure interval time, the next shared network node selection strategy of the computing power pool is adjusted to reduce the response time after the cross-site deployment of the service and reduce the abnormalities and failures of the cross-site deployment of the service.

[0085] For example, the first network node allocates a shared network node B to the second network node A this time, and the second network node A records the service deployment information of this time. After that, the first network node analyzes the service deployment record and learns that: for the second network node A, the shared network node B is not suitable as a shared node for cross-site service deployment. Then, the first network node can adjust the next shared network node selection strategy of the computing power pool, such as reducing the priority of the shared network node B when selecting the shared network node next time. Among them, the shared network node B is not suitable as a shared node for cross-site service deployment, which can be manifested as the response time and mean failure interval time of the target service on the shared network node B not meeting the expected requirements.

[0086] The present application also provides a service deployment method, which is applied to the second network node. Figure 5 , Figure 5 A service deployment method provided by an embodiment of the present application is shown, such as Figure 5 As shown, the service deployment method includes but is not limited to steps S710 to S730.

[0087] Step S710: Send a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node determines a shared network node that meets the computing power demand information from a computing power pool including multiple network nodes.

[0088] Step S720: receiving identification information of a shared network node sent by the first network node.

[0089] Step S730: deploy the target service on the shared network node according to the identification information.

[0090] It can be understood that the second network node acts as a slave station of the computing power pool. When the second network node’s own resources are insufficient, the second network node sends a computing power resource acquisition request carrying computing power demand information to the first network node acting as the master station of the computing power pool. The first network node selects and allocates shared network nodes based on the computing power demand information.

[0091] Through the service deployment method of the embodiment of the present application, the services on the network nodes can be deployed across sites to any network node in the computing power pool, realizing the sharing of computing power resources of multiple network nodes in the computing power pool. Network nodes in different regions can complement each other in terms of software and hardware resources, solving a series of problems of insufficient computing power caused by tidal effects, regional business differences, high computing power requirements, etc., while also maximizing the use of idle resources of each network node.

[0092] In the embodiments of the present application, compared to cloud services, the shared network nodes as resource sharing parties will not affect their own business when sharing resources, and the second network nodes as resource demanders can choose to deploy communication business services with high requirements for response speed and link quality at the local site, and deploy services with low requirements for response speed and link quality, or high computing power requirements, across sites, so that efficient businesses use local site resources, and general businesses use cross-site resources, which can achieve more scientific and reasonable resource sharing, which can not only meet the resource needs of the second network nodes, but also improve the resource utilization of each network node in the computing power pool.

[0093] It should be noted that the specific implementation and beneficial effects of the service deployment method applied to the second network node in the above embodiment can be found in the relevant description of the computing resource sharing method applied to the first network node, and will not be repeated here.

[0094] In some embodiments, in an embodiment of the present application, a computing power resource acquisition request carrying computing power requirement information is sent to the first network node, including but not limited to step S810 and step S820.

[0095] Step S810, when the local idle resources cannot meet the needs of the target service, determine the computing power requirement information of the target service.

[0096] Step S810: Send a computing power resource acquisition request carrying computing power requirement information to the first network node.

[0097] It should be understood that as a slave station in the computing power pool, the second network node monitors the status of its own services. When the local idle resources cannot meet the target service, the second network node first determines the specific computing power demand information of the target service. Then, as the resource demand direction, the second network node sends a computing power resource acquisition request carrying computing power demand information to the first network node, and deploys services across stations based on the identification information of the shared network node returned by the first network node, thus realizing service self-management. For details, please refer to Figure 6 , Figure 6 A schematic diagram of a service deployment method provided in an embodiment of the present application is shown. Figure 6 As shown, when resources are insufficient, the second network node selects to pop up service instance S1. After receiving the identification information of the shared network node sent by the first network node, the second network node establishes a communication connection with the shared network node according to the identification information. Then, the second network node creates a corresponding service instance S1 and deploys the service instance S1 on the shared network node.

[0098] In some embodiments, after the target service is deployed on the shared network node according to the identification information, the embodiment of the present application further includes step S910.

[0099] Step S910, obtaining the local real-time service load, and when the real-time service load is lower than a preset threshold, recovering the target service from the shared network node, and switching the target service to the local.

[0100] In the embodiment of the present application, the service refers to a Kubernetes service, i.e., a container, which can be deployed across sites in the form of a process instance. When the real-time service load of the second network node decreases and is lower than a preset threshold, the second network node can choose to redeploy the target service deployed across sites locally. That is, when the real-time service load of the second network node is lower than the preset threshold, the local idle resources of the second network node can meet the target service deployed across sites. Figure 6 As shown, the second network node creates a service instance S1 of the target service and deploys the service instance S1 on the shared network node, the second network node reclaims the service instance S1 popped up by the target service from the shared network node, and switches the target service to use the local instance, wherein the second network node reclaims the service instance S1 popped up by the target service from the shared network node includes the second network node instructing the shared network node to delete the service instance S1 and migrate the cached data and persistent storage data of the service instance S1 to the second network node, cleans up the cached data and persistent storage data, and releases the hardware resources occupied by the second network node.

[0101] In some embodiments, after the target service is deployed on the shared network node according to the identification information, the embodiment of the present application further includes step S1010 and step S1020.

[0102] Step S1010: When a deployment exception occurs in a target service on a shared network node, the target service is recovered from the shared network node.

[0103] Step S1020: resend a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node re-determines a new shared network node that meets the computing power demand information from a computing power pool including multiple network nodes.

[0104] It is understandable that after the second network node deploys its own service across sites, it monitors the deployed shared network nodes and target services.

[0105] Specifically, the second network node may periodically or regularly send a status query request of the target service to the shared network node, so that the shared network node returns the status information of the target service to the second network node according to the status query request. For example, for an interactive target service, the status information may be whether the service is running normally, the response time of the service during operation, the throughput and other information. If the second network node learns from the status information returned by the shared network node that the target service has a deployment anomaly on the shared network node, such as a response time delay, a decrease in throughput, an abnormal termination of the service due to an operation error, etc., the second network node may choose to recycle the service instance popped up by the target service from the shared network node, and re-deploy the target service across sites to achieve self-repair of the service. Specifically, the second network node re-sends a computing resource acquisition request carrying computing power demand information to the first network node, so that the first network node re-determines a new shared network node that meets the computing power demand information from a computing power pool containing multiple network nodes, and the second network node then deploys the target service across sites on the new shared network node to achieve self-repair of the service, and performs seamless switching of the service when the service deployment is abnormal, so that the user does not perceive or only has a very short interruption when using the service.

[0106] In some embodiments, the service deployment method provided in the embodiments of the present application also includes step S1110.

[0107] Step S1110: Continue to send reporting information to the first network node.

[0108] It can be understood that the second network node, as a slave station in the computing power pool, continuously (periodically, regularly, or triggered by conditions or users, or several methods exist simultaneously) sends reporting information to the first network node, so that the first network node can monitor the status and allocate resources of each network node in the computing power pool according to the reporting information, thereby realizing automatic management of the computing power pool, reducing the cost of manual intervention and improving operation and maintenance efficiency.

[0109] The computing resource sharing method and service deployment method provided in the embodiments of the present application are described below through specific examples.

[0110] See also Figure 7 , Figure 7 A schematic diagram of an implementation of a service deployment method provided by an embodiment of the present application is shown, such as Figure 7 As shown, the computing power pool includes base station A, base station B, base station C, etc., where base station C is the master station in the computing power pool, and base station A, base station B and other base stations are slave stations in the computing power pool. The slave stations periodically send reporting information to the master station, and the master station receives the reporting information sent by the slave stations and uses it to monitor the status of the slave stations. During this period, base station A has insufficient resources and cannot deploy target services SA4 and SA5 at this station. Then base station A, as the resource demand direction, sends computing power resource request information carrying computing power demand information of target services SA4 and SA5 to base station C. After base station C receives the computing power demand information sent by base station A, it determines from each base station in the computing power pool that base station B can meet the computing power demand. Therefore, the master station sends the identification information of base station B to base station A, so that base station A can deploy target services SA4 and SA5 across base stations at base station B.

[0111] The embodiment of the present application also provides a computing resource sharing system, which includes a first network node and a plurality of second network nodes, wherein the first network node and the plurality of second network nodes form a computing pool, wherein:

[0112] The first network node is used to receive a computing resource acquisition request sent by the second network node, the computing resource acquisition request carries computing power demand information, determines a shared network node that meets the computing power demand information from the computing power pool, and sends identification information of the shared network node to the second network node, so that the second network node deploys a target service on the shared network node according to the identification information;

[0113] The second network node is used to send a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node determines a shared network node that meets the computing power demand information from a computing power pool including multiple network nodes, receives identification information of the shared network node sent by the first network node, and deploys a target service on the shared network node according to the identification information.

[0114] It should be noted that the above embodiment describes a computing power resource sharing system. For the first network node and the second network node in the computing power resource sharing system, the specific implementation of the execution steps and the beneficial effects can be found in the relevant descriptions in the computing power resource sharing method and the service deployment method, which will not be repeated here.

[0115] See also Figure 8 The present application also provides an electronic device, the electronic device 2000 includes but is not limited to:

[0116] at least one processor 2001;

[0117] At least one memory 2002, used to store at least one program;

[0118] When at least one program is executed by at least one processor 2001, the computing resource sharing method applied to the first network node as described in any of the above embodiments is executed; or, the service deployment method applied to the second network node as described in any of the above embodiments is executed.

[0119] It should be understood that the processor 2001 and the memory 2002 may be connected via a bus or other means.

[0120] It should be understood that the processor 2001 can use a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. Or the processor 2001 uses one or more integrated circuits to execute related programs to implement the technical solutions provided in the embodiments of the present application.

[0121] The memory 2002, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs, such as the collaborative perception method performed by the electronic device side described in any embodiment of the present application. The processor 2001 implements the computing resource sharing method applied to the first network node as described in any embodiment above by running the non-transient software program and instructions stored in the memory 2002; or implements the service deployment method applied to the second network node as described in any embodiment above.

[0122] The memory 2002 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; and the data storage area may store and execute the above-mentioned collaborative perception method. In addition, the memory 2002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0123] In some embodiments, the memory 2002 may optionally include a memory remotely located relative to the processor 2001, and the remote memory may be connected to the processor 2001 via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] The non-transient software programs and instructions required to implement the above-mentioned computing power resource sharing method or service deployment method are stored in the memory 2002. When executed by one or more processors 2001, the computing power resource sharing method or service deployment method provided by any embodiment of the present application is executed.

[0125] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the computing power resource sharing method applied to the first network node as described in any of the above embodiments; or, it implements the service deployment method applied to the second network node as described in any of the above embodiments.

[0126] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0127] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0128] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0129] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] An embodiment of the present application also provides a computer program product, which stores program instructions. When the program instructions are executed on a computer device, the computer device implements the computing resource sharing method applied to the first network node as described in any of the above embodiments; or implements the service deployment method applied to the second network node as described in any of the above embodiments.

[0131] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above implementation. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the present application.

Claims

1. A computing resource sharing method, applied to a first network node, the method comprising: Receive a computing power resource acquisition request sent by the second network node, where the computing power resource acquisition request carries computing power demand information; Determine a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes; The identification information of the shared network node is sent to the second network node, so that the second network node deploys the target service on the shared network node according to the identification information.

2. The computing resource sharing method according to claim 1, characterized in that: The method further comprises: Receive reporting information sent by the target network node in the computing power pool.

3. The computing resource sharing method according to claim 2, characterized in that: The method further comprises: The target network node is marked as being in an abnormal state or a normal state according to the reported information.

4. The computing resource sharing method according to claim 2, characterized in that: The reported information includes resource usage information of the target network node; The determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes includes: Determine a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes according to the resource usage information.

5. The computing resource sharing method according to claim 2, characterized in that: The reported information includes the operating status information of the target network node; The determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes includes: Determine a shared network node that meets the computing power requirement information from a computing power pool comprising multiple network nodes according to the operating status information.

6. The computing resource sharing method according to claim 1, characterized in that: The determining a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes includes: Get historical service deployment records; According to the historical service deployment record, a shared network node that meets the computing power demand information is determined from a computing power pool including multiple network nodes.

7. The computing resource sharing method according to claim 1, characterized in that: The method further comprises: Get the service deployment record. Obtaining the operation information of the target service according to the service deployment record; The next shared network node selection strategy of the computing power pool is determined according to the operation information.

8. A service deployment method, applied to a second network node, the method comprising: Sending a computing power resource acquisition request carrying computing power requirement information to the first network node, so that the first network node determines a shared network node that meets the computing power requirement information from a computing power pool including multiple network nodes; receiving identification information of the shared network node sent by the first network node; The target service is deployed on the shared network node according to the identification information.

9. The service deployment method according to claim 8, characterized in that: The sending a computing power resource acquisition request carrying computing power requirement information to the first network node includes: When the local idle resources cannot meet the needs of the target service, determine the computing power requirement information of the target service; Send a computing power resource acquisition request carrying the computing power requirement information to the first network node.

10. The service deployment method according to claim 8, characterized in that: After deploying the target service on the shared network node according to the identification information, the method further includes: A local real-time service load is obtained, and when the real-time service load is lower than a preset threshold, the target service is recovered from the shared network node, and the target service is switched to the local node.

11. The service deployment method according to claim 8, characterized in that: After deploying the target service on the shared network node according to the identification information, the method further includes: When there is a deployment exception of the target service on the shared network node, reclaiming the target service from the shared network node; Re-send a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node re-determines a new shared network node that meets the computing power demand information from a computing power pool including multiple network nodes.

12. The service deployment method according to claim 8, characterized in that: The method further comprises: Continue to send reporting information to the first network node.

13. A computing resource sharing system, the system comprising a first network node and a plurality of second network nodes, the first network node and the plurality of second network nodes forming a computing power pool, wherein: The first network node is used to receive a computing power resource acquisition request sent by the second network node, the computing power resource acquisition request carries computing power demand information, determine a shared network node that meets the computing power demand information from the computing power pool, and send identification information of the shared network node to the second network node, so that the second network node deploys a target service on the shared network node according to the identification information; The second network node is used to send a computing power resource acquisition request carrying computing power demand information to the first network node, so that the first network node determines a shared network node that meets the computing power demand information from a computing power pool including multiple network nodes, receives identification information of the shared network node sent by the first network node, and deploys a target service on the shared network node according to the identification information.

14. An electronic device comprising: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the computing resource sharing method as described in any one of claims 1 to 7; or, implement the service deployment method as described in any one of claims 8 to 12.

15. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the computing resource sharing method as described in any one of claims 1 to 7 is implemented; or, the service deployment method as described in any one of claims 8 to 12 is implemented.

Images