Computing resource determination method and device and related equipment
By mapping the user's computing power service requests into computing resource demand information and matching the computing resource supply information in the computing power network, the problem of consumers' difficulty in evaluating computing power and network conditions is solved, simplifying the usage process and reducing costs. Adaptive resource matching and efficient resource scheduling are realized.
Patent Information
- Application Number
- CN202410994912.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-26
AI Technical Summary
When consumers purchase computing power network services, it is difficult for them to accurately evaluate the specific computing power and network conditions, resulting in complex usage processes.
By mapping the user's computing power service requests into computing resource demand information and matching the computing resource supply information in the computing power network based on declarative encoding, appropriate computing resources are automatically determined to perform computing power tasks, and the user-side usage process is simplified.
It reduces the difficulty and cost of users' use of computing power network services, realizes adaptive resource matching, replaces the process of manual resource evaluation, and improves the flexibility and service quality of resource scheduling.
Smart Images

Figure CN119025261A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of cloud computing, and in particular to a method and apparatus for determining computing resources and related equipment. Background Art
[0002] The computing power network is a distributed computing network that aims to provide users with high-performance computing capabilities and services by integrating and sharing computing resources within a certain range.
[0003] However, when consumers purchase computing force network services, it is often difficult to accurately assess how much computing power, what kind of computing power, and what kind of network conditions are needed to meet their business needs. Only after guidance and evaluation by professionals can they choose the appropriate computing force network (CFN) service.
[0004] In other words, the usage process of the computing power network provided by the relevant technology is relatively complicated. Summary of the invention
[0005] The purpose of the present disclosure is to provide a method, device and related equipment for determining computing resources, so as to solve the technical problem of complex computing power network usage process provided by related technologies.
[0006] In a first aspect, an embodiment of the present disclosure provides a method for determining a computing resource, the method comprising:
[0007] Mapping a computing power service request of a user into computing resource demand information, wherein the computing power service request is a request for requesting allocation of computing resources formed based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request;
[0008] According to the computing resource demand information and the plurality of computing resource supply information, determining at least one target computing resource matching the computing resource demand information among the plurality of computing resources included in the computing power network, wherein the plurality of computing resource supply information and the plurality of computing resources correspond one to one, and each computing resource supply information is information formed by the corresponding computing resource based on declarative coding;
[0009] The at least one target computing resource is determined as a computing resource for executing the computing task corresponding to the computing service request.
[0010] In a second aspect, an embodiment of the present disclosure provides a device for determining computing resources, the device comprising:
[0011] A mapping module, used to map a computing power service request of a user into computing resource demand information, wherein the computing power service request is a request for requesting allocation of computing resources formed based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request;
[0012] A first determination module is used to determine, according to the computing resource demand information and the plurality of computing resource supply information, at least one target computing resource that matches the computing resource demand information among the plurality of computing resources included in the computing power network, wherein the plurality of computing resource supply information and the plurality of computing resources correspond one to one, and each computing resource supply information is information formed by the corresponding computing resource based on declarative coding;
[0013] The second determination module is used to determine the at least one target computing resource as a computing resource used to execute the computing task corresponding to the computing service request.
[0014] In a third aspect, the present disclosure provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the first aspect.
[0015] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
[0016] In a fifth aspect, the present disclosure provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method described in the first aspect.
[0017] In the present disclosure, the user's demand for computing resources and the multiple computing resources that the computing power network can provide are abstracted into declarative information, and a mapping process for the user's demand for computing resources is provided. The computing resource demand information obtained after mapping and the multiple computing resource supply information corresponding to the multiple computing resources are matched with resources to determine the computing resources used to execute the computing power task corresponding to the computing power service request. The process of manually evaluating resources adopted by related technologies is replaced by adaptive resource matching, which simplifies the use process of the computing power network on the user side and reduces the difficulty and cost of using the computing power network service for users. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is an architecture diagram of a computing power network platform provided by an embodiment of the present application;
[0019] Figure 2 It is a flowchart of a method for determining computing resources provided in an embodiment of the present application;
[0020] Figure 3 It is a structural diagram of a computing resource determination device provided in an embodiment of the present application;
[0021] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0023] The present disclosure provides a computing power network platform, the architecture of which can be as follows: Figure 1 As shown, it includes: API Server, Scheduler, Controller Manager, Computing Provider, and NetworkProvider.
[0024] Computing Provider can be understood as a module in the computing network platform that is used to manage and monitor multiple computing resources included in the computing network platform. It can provide computing power and monitor the execution of computing tasks, and is responsible for reporting the status of computing resources and computing tasks to the API Server.
[0025] Network Provider can be understood as a module in the computing power network platform that is used to manage and monitor multiple network resources included in the computing power network platform. It can provide network resources and monitor network connection status, and is responsible for reporting network resources and network connection status to the API Server.
[0026] The API Server can be understood as a module in the computing network platform that is used to manage all declarative information. The client can report declarative computing resource requirements to the API Server based on the preset interface.
[0027] Controller Manager can be understood as a controller registration and lifecycle management module for various computing resources in the computing network platform. It includes multiple Controllers, each of which is responsible for monitoring and controlling a resource item (referring to a computing service request carrying a computing task type). Multiple resource items correspond to multiple resource application scenarios, such as VR application scenarios, AI application scenarios, math application scenarios, etc.
[0028] Scheduler can be understood as a module in the computing network platform that is used to make resource scheduling decisions.
[0029] It should be understood that both Computing Provider and Network Provider report the corresponding computing resources and network resources through declarative coding. The reported computing resources include at least computing type, computing size, computing cost, memory, number of cores, hardware architecture or other computing attribute information. Examples are as follows:
[0030] apiVersion:provider / v1
[0031] type:compute
[0032] metadata:
[0033] region:region1
[0034] az:az2
[0035] id:1
[0036] spec:
[0037] GPU:
[0038] -type:X
[0039] module:A100
[0040] compute_power:14
[0041] memory:16G
[0042] cores:5120
[0043] total_compute_power: 14000
[0044] cost:2
[0045] -type:Y
[0046] module:6900XT
[0047] compute_power:23
[0048] memory:16G
[0049] cores:5120
[0050] total_compute_power: 23000
[0051] cost:0.5
[0052] The above example shows that the computing resource numbered 1 includes a GPU of brand X and a GPU of brand Y, wherein the computing power, memory, number of cores, and computing power cost of the GPU of brand X are 14000, 16G, 5120 cores, and 2 respectively; the computing power, memory, number of cores, and computing power cost of the GPU of brand Y are 23000, 16G, 5120 cores, and 0.5 respectively.
[0053] The reported network resources include at least network bandwidth, network latency, network packet loss, network cost, network access protocol, network availability or other information related to network attributes, as shown below:
[0054] apiVersion:provider / v1
[0055] type:network
[0056] metadata:
[0057] location:loc01
[0058] spec:
[0059] network_resources:
[0060] -type:5G
[0061] capacity:100Gbps
[0062] cost:1
[0063] -type:wire
[0064] capacity:200Gbps
[0065] cost:0.5
[0066] compute_nodes:
[0067] -id:1
[0068] bandwidth:10Gbps
[0069] latency: 1ms
[0070] packet_loss: 0.2%
[0071] -id:2
[0072] bandwidth:5Gbps
[0073] latency:3ms
[0074] packet_loss: 0.3%
[0075] -id:3
[0076] bandwidth:2Gbps
[0077] latency:4ms
[0078] packet_loss: 0.4%
[0079] The network resource indication in the above example can provide two types of network transmission services, 5G network and wire network, where the network capacity of the 5G network is 100Gbps and the network cost is 1; the network capacity of the wire network is 200Gbps and the network cost is 0.5; wherein, the network resources provide three transmission links, namely, link number 1 with a bandwidth of 10Gbps, a latency of 1ms, and a packet loss rate of 0.2%, link number 2 with a bandwidth of 5Gbps, a latency of 3ms, and a packet loss rate of 0.3%, and link number 3 with a bandwidth of 2Gbps, a latency of 4ms, and a packet loss rate of 0.4%.
[0080] The present disclosure provides a method for determining computing resources, which is applied to a computing power network platform. Figure 2 As shown, the method includes:
[0081] Step 201: Map the user's computing power service request into computing resource demand information.
[0082] The computing power service request is a request for allocation of computing resources based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request.
[0083] Specifically, the computing power service request can be understood as a request reported by a user to the aforementioned API Server through a corresponding client based on a preset interface, as shown in the following example:
[0084] apiVersion:apps / v1
[0085] type:VR
[0086] metadata:
[0087] user:ZhangSan
[0088] id:zs8888
[0089] requirements:
[0090] location_code:999
[0091] device:Oculus2
[0092] network:5G
[0093] Resolution: 1080p
[0094] maximum_tolerable_latency:50ms
[0095] content:games
[0096] unit_cost:5
[0097] In this example, user zhangSan initiates a computing resource request for the corresponding VR application scenario, which is specifically used in the game application of the Oculus2 product. The required network is a 5G network, which is required to support 1080p resolution image transmission, with a maximum transmission delay of 50ms and a unit overhead of 5.
[0098] When monitoring the computing power service request shown in the above example, the VRController in the Controller Manager executes the action of step 201 for the computing power service request in the example, and completes the mapping conversion from the computing power service request to the computing resource demand information.
[0099] Step 202: Based on the computing resource demand information and multiple computing resource supply information, determine at least one target computing resource that matches the computing resource demand information from multiple computing resources included in the computing power network.
[0100] The plurality of computing resource supply information correspond to the plurality of computing resources in one-to-one correspondence, and each piece of computing resource supply information is information formed by the corresponding computing resource based on declarative coding.
[0101] The computing network includes multiple computing resources, including multiple computing resources managed by Computing Provider and multiple network resources managed by Network Provider.
[0102] Step 203: Determine the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request.
[0103] It should be noted that the computing resource demand information formed after mapping will be reported to the API Server, and the Scheduler will obtain the computing resource demand information and the multiple computing resource supply information from the API Server, and perform resource scheduling according to the resource scheduling function pre-set in the Scheduler to form a scheduling result. The scheduling result will also be reported to the API Server, and the API Server will notify the Computing Provider and Network Provider to create / update resources based on the scheduling result (that is, for use in corresponding computing tasks).
[0104] In the present disclosure, the user's demand for computing resources and the multiple computing resources that the computing power network can provide are abstracted into declarative information, and a mapping process for the user's demand for computing resources is provided. The computing resource demand information obtained after mapping and the multiple computing resource supply information corresponding to the multiple computing resources are matched with resources to determine the computing resources used to execute the computing power task corresponding to the computing power service request. The process of manually evaluating resources adopted by related technologies is replaced by adaptive resource matching, which simplifies the use process of the computing power network on the user side and reduces the difficulty and cost of using the computing power network service for users.
[0105] In one embodiment, the computing power service request includes a task type identifier and a task requirement;
[0106] Mapping the user's computing service request into computing resource demand information includes:
[0107] Determining a target mapping rule from a plurality of pre-set mapping rules according to the task type identifier, wherein the plurality of mapping rules correspond to a plurality of different computing power task types;
[0108] The task requirement is mapped according to the target mapping rule to obtain computing resource requirement information, wherein the number of computing resources indicated by the computing resource requirement information matches the task requirement.
[0109] Among them, the task type identifier is used to indicate the resource application scenario corresponding to the computing power service request, which can be understood as the field value corresponding to the type field in the aforementioned example; the task requirement is used to indicate the computing power task corresponding to the computing power service request, which can be understood as the requirement information corresponding to the requirements field in the aforementioned example.
[0110] This application makes the computing resource demand information obtained by mapping more accurate by differentiating resource application scenarios (such as VR, AI, math, etc.) and setting different mapping rules for different resource application scenarios.
[0111] Herein, the matching of the number of computing resources indicated by the computing resource requirement information with the task requirement should be understood as: the number of computing resources indicated by the computing resource requirement information is the minimum number of resources required to complete the task requirement.
[0112] In one embodiment, before mapping the computing power service request of the user into computing resource demand information, the method further includes:
[0113] Traversing a plurality of computing resources included in the computing power network to form the plurality of computing resource supply information;
[0114] The traversal of the i-th computing resource includes:
[0115] In the case where the i-th computing resource is a computing power resource, the computing power attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the computing power attributes include a first attribute indicating a computing power type, a second attribute indicating a computing power size, a third attribute indicating a computing power cost, a fourth attribute indicating a memory, a fifth attribute indicating a core number, and a sixth attribute indicating a hardware architecture to which the resource belongs;
[0116] In the case where the i-th computing resource is a network resource, network attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the network attributes include a seventh attribute indicating network bandwidth, an eighth attribute indicating network delay attributes, a ninth attribute indicating network packet loss, a tenth attribute indicating network cost, an eleventh attribute indicating a network access protocol, and a twelfth attribute indicating network availability;
[0117] The i-th computing resource is any one of the multiple computing resources, and i is a positive integer.
[0118] In one embodiment, after determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further includes:
[0119] When receiving the first adjustment instruction, in response to the first adjustment instruction, deleting the computing power task corresponding to the computing power service request to obtain the remaining computing power task;
[0120] Removing a deleted portion of computing resources used to execute the computing task from the at least one target computing resource to obtain remaining computing resources, wherein the deleted portion is a portion deleted by the first adjustment instruction from the computing task;
[0121] The remaining computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
[0122] The above-mentioned first adjustment instruction can be understood as an instruction for reducing / lowering the resource requirements of the computing power service request. After determining the computing resources used to execute the computing power task corresponding to the computing power service request, if the above-mentioned first adjustment instruction is received, the deleted part of the computing power task corresponding to the computing power service request and the computing resources allocated to the deleted part are removed, so that the remaining computing resources can be used to continue to execute the remaining part of the computing power task corresponding to the computing power service request. This can make the resource scheduling of the computing power service request more flexible and reduce the overhead of the computing power network platform in responding to the first adjustment instruction.
[0123] In one embodiment, after determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further includes:
[0124] In the case of receiving the second adjustment instruction, in response to the second adjustment instruction, adding a supplementary computing power task to the computing power task corresponding to the computing power service request;
[0125] Determining a supplementary computing resource from the plurality of computing resources, wherein the supplementary computing resource is a computing resource other than the at least one target computing resource, and the supplementary computing resource matches the supplementary computing task;
[0126] The at least one target computing resource and the supplementary computing resource are determined as computing resources for executing the computing task corresponding to the computing service request.
[0127] The above-mentioned second adjustment instruction can be understood as an instruction for increasing the resource requirements of the computing power service request. After determining the computing resources used to execute the computing power task corresponding to the computing power service request, if the above-mentioned second adjustment instruction is received, then on the basis of the computing power task corresponding to the computing power service request, additional supplementary computing power tasks are added, and the above-mentioned resource scheduling is repeated at the same time to determine new computing resources (i.e., supplementary computing resources) for executing the supplementary computing power tasks, so that the computing power tasks corresponding to the adjusted computing power service request can be jointly executed with the originally allocated computing resources and the newly determined supplementary computing resources. This can make the resource scheduling of the computing power service request more flexible and reduce the overhead of the computing power network platform in responding to the second adjustment instruction.
[0128] The matching of the supplementary computing resources with the supplementary computing power task can be understood as that the number of resources of the supplementary computing resources is greater than or equal to the number of resources required by the supplementary computing power task.
[0129] It should be understood that both the first adjustment instruction and the second adjustment instruction are received and responded by the API Server.
[0130] In one embodiment, after determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further includes:
[0131] In the case where it is monitored that the at least one target computing resource includes an adjustment computing resource, generating adjustment resource demand information according to a task associated with the adjustment computing resource in the computing task, wherein the adjustment computing resource is a target computing resource in the at least one target computing resource in which a resource change occurs;
[0132] Determine, according to the adjusted resource requirement information, at least one alternative computing resource matching the adjusted resource requirement information among the plurality of computing resources, wherein the alternative computing resource is another computing resource other than the at least one target computing resource;
[0133] The target computing resources and the substitute computing resources remaining except the adjusted computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
[0134] In the event of resource changes in the allocated computing resources, alternative computing resources are reselected from the remaining multiple computing resources, and the target computing resources with resource changes are replaced with the alternative computing resources to avoid the computing power scheduling interference caused by resource changes, adapt to the changes in computing resources in the application, realize dynamic scheduling of computing power service requests, and improve service quality and automated operation and maintenance efficiency.
[0135] For example, abnormal failures or status changes of the network or hardware (such as changes in peak-time rates, network congestion, etc.) can be understood as resource changes in the corresponding computing resources.
[0136] For ease of understanding, the following examples are provided:
[0137] against Figure 1 The computing power network platform architecture shown in the figure, in the initial stage, Computing Provider and Network Provider register the topological data (declarative coding) of the computing power resources and network resources they manage to the API Server. In the application stage, Computing Provider and Network Provider respectively monitor the computing power resources and network resources they manage, and in the event of resource changes, notify the API Server to update the topological data of the corresponding computing resources. The Scheduler obtains the topological data from the API Server and makes scheduling decisions based on the user's request.
[0138] Specifically, based on the pre-set API interface, the client can initiate a declarative resource deployment request (i.e., the aforementioned computing service request) to the API Server. The API Server will create a resource item based on the resource deployment request, which carries a task type identifier and task requirements.
[0139] After listening to the creation of the resource item, the Controller that matches the task type identifier in the Controller Manager obtains the task requirements carried by the resource item from the API Server, and maps the task requirements to corresponding computing resource deployment requests and network resource deployment requests (that is, the aforementioned computing resource demand information). The above mapping process can be understood as the process of converting the user's abstract requirements into specific resource demand data.
[0140] The mapped computing resource deployment request and network resource deployment request will be reported to the API Server and written into the corresponding resource item. The API Server then notifies the Scheduler to retrieve the computing resource deployment request, network resource deployment request and the idle / available computing resources and network resources of the current computing network platform from the corresponding resource item, and complete the scheduling decision of the computing resources (that is, according to the computing resource demand information and multiple computing resource supply information, at least one target computing resource that matches the computing resource demand information is determined among the multiple computing resources included in the computing network). The formed decision result is written into the corresponding resource item. Finally, the API Server notifies the Computing Provider and the Network Provider to create / update resources based on the aforementioned decision result (that is, to determine the at least one target computing resource as the computing resource for executing the computing task corresponding to the computing service request).
[0141] Through the above settings, consumers' computing power service needs are encapsulated in a declarative API manner based on application scenarios. At the same time, the CFN platform solidifies the professional knowledge and experience of the corresponding scenarios (i.e., the multiple mapping rules), and can automatically map consumers' abstract service needs into resource requirements that CFN can understand. This effectively reduces the technical threshold and cost for consumers to use computing power network services.
[0142] In case of failures / changes in computing power or network, or when customers need online adjustments, dynamic recovery and adjustment of resources can be achieved by setting up service requests and corresponding computing power network resources, as well as corresponding resource update measures, effectively improving the computing power network service quality and automated operation and maintenance capabilities.
[0143] By applying the method described in this application, the user usage threshold of the CFN platform can be lowered, while the service quality of the CFN platform can be maintained at a high level, so as to help the implementation and promotion of the CFN platform.
[0144] The present disclosure also provides a computing resource determination device, such as Figure 3 As shown, the computing resource determination device 300 includes:
[0145] A mapping module 301 is used to map a computing power service request of a user into computing resource demand information, wherein the computing power service request is a request for requesting allocation of computing resources formed based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request;
[0146] A first determination module 302 is used to determine, according to the computing resource demand information and the plurality of computing resource supply information, at least one target computing resource that matches the computing resource demand information among the plurality of computing resources included in the computing power network, wherein the plurality of computing resource supply information and the plurality of computing resources correspond one to one, and each computing resource supply information is information formed by the corresponding computing resource based on declarative coding;
[0147] The second determination module 303 is used to determine the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request.
[0148] In one embodiment, the computing power service request includes a task type identifier and a task requirement;
[0149] The mapping module 301 is specifically used for:
[0150] Determining a target mapping rule from a plurality of pre-set mapping rules according to the task type identifier, wherein the plurality of mapping rules correspond to a plurality of different computing power task types;
[0151] The task requirement is mapped according to the target mapping rule to obtain computing resource requirement information, wherein the number of computing resources indicated by the computing resource requirement information matches the task requirement.
[0152] In one embodiment, the apparatus 300 further includes:
[0153] A traversal module, used to traverse the multiple computing resources included in the computing power network to form the multiple computing resource supply information;
[0154] The traversal of the i-th computing resource includes:
[0155] In the case where the i-th computing resource is a computing power resource, the computing power attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the computing power attributes include a first attribute indicating a computing power type, a second attribute indicating a computing power size, a third attribute indicating a computing power cost, a fourth attribute indicating a memory, a fifth attribute indicating a core number, and a sixth attribute indicating a hardware architecture to which the resource belongs;
[0156] In the case where the i-th computing resource is a network resource, network attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the network attributes include a seventh attribute indicating network bandwidth, an eighth attribute indicating network delay attributes, a ninth attribute indicating network packet loss, a tenth attribute indicating network cost, an eleventh attribute indicating a network access protocol, and a twelfth attribute indicating network availability;
[0157] The i-th computing resource is any one of the multiple computing resources, and i is a positive integer.
[0158] In one embodiment, the apparatus 300 further includes a third determining module, and the third determining module is specifically configured to:
[0159] When receiving the first adjustment instruction, in response to the first adjustment instruction, deleting the computing power task corresponding to the computing power service request to obtain the remaining computing power task;
[0160] Removing a deleted portion of computing resources used to execute the computing task from the at least one target computing resource to obtain remaining computing resources, wherein the deleted portion is a portion deleted by the first adjustment instruction from the computing task;
[0161] The remaining computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
[0162] In one embodiment, the apparatus 300 further includes a fourth determining module, and the fourth determining module is specifically configured to:
[0163] In the case of receiving the second adjustment instruction, in response to the second adjustment instruction, adding a supplementary computing power task to the computing power task corresponding to the computing power service request;
[0164] Determining a supplementary computing resource from the plurality of computing resources, wherein the supplementary computing resource is a computing resource other than the at least one target computing resource, and the supplementary computing resource matches the supplementary computing task;
[0165] The at least one target computing resource and the supplementary computing resource are determined as computing resources for executing the computing task corresponding to the computing service request.
[0166] In one embodiment, the apparatus 300 further includes a fifth determining module, and the fifth determining module is specifically configured to:
[0167] In the case where it is monitored that the at least one target computing resource includes an adjustment computing resource, generating adjustment resource demand information according to a task associated with the adjustment computing resource in the computing task, wherein the adjustment computing resource is a target computing resource in the at least one target computing resource in which a resource change occurs;
[0168] Determine, according to the adjusted resource requirement information, at least one alternative computing resource matching the adjusted resource requirement information among the plurality of computing resources, wherein the alternative computing resource is another computing resource other than the at least one target computing resource;
[0169] The target computing resources and the substitute computing resources remaining except the adjusted computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
[0170] The computing resource determination device 300 provided in the embodiment of the present disclosure can implement each process in the above-mentioned computing resource determination method embodiment, and will not be described again here to avoid repetition.
[0171] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
[0172] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0173] like Figure 4As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 to a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0174] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0175] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as a method for determining computing resources. For example, in some embodiments, the method for determining computing resources may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method for determining computing resources described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the computing resource determination method in any other appropriate manner (for example, by means of firmware).
[0176] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0177] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0178] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0179] As used herein, the term "machine-readable medium" refers to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.
[0180] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0181] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0182] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0183] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.
[0184] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0185] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for determining computing resources, characterized in that: The method comprises: Mapping a computing power service request of a user into computing resource demand information, wherein the computing power service request is a request for requesting allocation of computing resources formed based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request; According to the computing resource demand information and the plurality of computing resource supply information, determining at least one target computing resource matching the computing resource demand information among the plurality of computing resources included in the computing power network, wherein the plurality of computing resource supply information and the plurality of computing resources correspond one to one, and each computing resource supply information is information formed by the corresponding computing resource based on declarative coding; The at least one target computing resource is determined as a computing resource for executing the computing task corresponding to the computing service request.
2. The method according to claim 1, characterized in that The computing power service request includes a task type identifier and task requirements; Mapping the user's computing service request into computing resource demand information includes: Determining a target mapping rule from a plurality of pre-set mapping rules according to the task type identifier, wherein the plurality of mapping rules correspond to a plurality of different computing power task types; The task requirement is mapped according to the target mapping rule to obtain computing resource requirement information, wherein the number of computing resources indicated by the computing resource requirement information matches the task requirement.
3. The method according to claim 1, characterized in that Before mapping the computing power service request of the user into computing resource demand information, the method further includes: Traversing a plurality of computing resources included in the computing power network to form the plurality of computing resource supply information; The traversal of the i-th computing resource includes: In the case where the i-th computing resource is a computing power resource, the computing power attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the computing power attributes include a first attribute indicating a computing power type, a second attribute indicating a computing power size, a third attribute indicating a computing power cost, a fourth attribute indicating a memory, a fifth attribute indicating a core number, and a sixth attribute indicating a hardware architecture to which the resource belongs; In the case where the i-th computing resource is a network resource, network attributes included in the i-th computing resource are declaratively encapsulated to obtain computing resource supply information corresponding to the i-th computing resource, where the network attributes include a seventh attribute indicating network bandwidth, an eighth attribute indicating network delay attributes, a ninth attribute indicating network packet loss, a tenth attribute indicating network cost, an eleventh attribute indicating a network access protocol, and a twelfth attribute indicating network availability; The i-th computing resource is any one of the multiple computing resources, and i is a positive integer.
4. The method according to any one of claims 1 to 3, characterized in that After determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further comprises: When receiving the first adjustment instruction, in response to the first adjustment instruction, deleting the computing power task corresponding to the computing power service request to obtain the remaining computing power task; Removing a deleted portion of computing resources used to execute the computing task from the at least one target computing resource to obtain remaining computing resources, wherein the deleted portion is a portion deleted by the first adjustment instruction from the computing task; The remaining computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
5. The method according to any one of claims 1 to 3, characterized in that: After determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further comprises: In the case of receiving the second adjustment instruction, in response to the second adjustment instruction, adding a supplementary computing power task to the computing power task corresponding to the computing power service request; Determining a supplementary computing resource from the plurality of computing resources, wherein the supplementary computing resource is a computing resource other than the at least one target computing resource, and the supplementary computing resource matches the supplementary computing task; The at least one target computing resource and the supplementary computing resource are determined as computing resources for executing the computing task corresponding to the computing service request.
6. The method according to any one of claims 1 to 3, characterized in that After determining the at least one target computing resource as a computing resource for executing the computing task corresponding to the computing service request, the method further comprises: In the case where it is monitored that the at least one target computing resource includes an adjustment computing resource, generating adjustment resource demand information according to a task associated with the adjustment computing resource in the computing task, wherein the adjustment computing resource is a target computing resource in the at least one target computing resource in which a resource change occurs; Determine, according to the adjusted resource requirement information, at least one alternative computing resource matching the adjusted resource requirement information among the plurality of computing resources, wherein the alternative computing resource is another computing resource other than the at least one target computing resource; The target computing resources and the substitute computing resources remaining except the adjusted computing resources are determined as computing resources for executing the computing task corresponding to the computing service request.
7. A device for determining computing resources, characterized in that: The device comprises: A mapping module, used to map a computing power service request of a user into computing resource demand information, wherein the computing power service request is a request for requesting allocation of computing resources formed based on declarative coding, and the computing resource demand information is used to quantify the amount of computing resources requested by the computing power service request; A first determination module is used to determine, according to the computing resource demand information and the plurality of computing resource supply information, at least one target computing resource that matches the computing resource demand information among the plurality of computing resources included in the computing power network, wherein the plurality of computing resource supply information and the plurality of computing resources correspond one to one, and each computing resource supply information is information formed by the corresponding computing resource based on declarative coding; The second determination module is used to determine the at least one target computing resource as a computing resource used to execute the computing task corresponding to the computing service request.
8. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 6 when executed by the processor.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.
Citation Information
Cited By
Method and device for intelligent computing center to provide computing power resources through computing power package
CN119739442A
Method and apparatus for intelligent computing center to provide computing power resource by means of computing power package
WO2026184504A1
