Heterogeneous computing power fused cloud computing platform, resource scheduling method and device, equipment and medium

Abstract

The invention relates to a heterogeneous computing power fused cloud computing platform, a resource scheduling method and device, computer equipment and a computer readable storage medium. The cloud computing platform comprises a heterogeneous node management module used for managing hardware resources of different architectures to a computing power cluster; the heterogeneous computing power scheduling module is used for receiving a computing power calling request sent by a user, the computing power calling request carries resource type demand information and architecture demand information, and a computing power resource creation instruction is generated according to the resource type demand information and the architecture demand information; the cloud computing platform can automatically select appropriate hardware resources according to the computing power resource creation instruction, and the task is completed through a container or a virtual machine. By the adoption of the method and device, effective management and scheduling of heterogeneous hardware resources can be achieved through cooperation of the heterogeneous node management module, the heterogeneous computing power scheduling module, the container management module and the virtualization management module, and the utilization rate of computing resources is increased.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology, and in particular to a cloud computing platform, resource scheduling method, device, equipment and medium for integrating heterogeneous computing power. Background Art

[0002] With the development of cloud computing technology, the demand for computing resources by enterprises and individual users is increasing. Different types of applications have different requirements for computing power and performance. Currently, many cloud service providers have proposed heterogeneous computing architectures to use ARM and x86_64 processors to improve performance and energy efficiency, but this solution consumes a lot of infrastructure resources. Summary of the invention

[0003] Based on this, it is necessary to provide a cloud computing platform, resource scheduling method, device, equipment and medium that integrates heterogeneous computing power and can save construction resources to address the above technical problems.

[0004] In a first aspect, the present application provides a cloud computing platform for integrating heterogeneous computing power, the cloud computing platform comprising a heterogeneous node management module, a heterogeneous computing power scheduling module, a container management module and a virtualization management module, wherein:

[0005] The heterogeneous node management module is used to manage hardware resources of different architectures into the computing power cluster;

[0006] The heterogeneous computing power scheduling module is used to receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information; when the resource type requirement information represents the requirement for virtual machine computing power resources, the computing power resource creation instruction is sent to the virtualization management module; when the resource type requirement information represents the requirement for container computing power resources, the computing power resource creation instruction is sent to the container management module;

[0007] The container management module is used to create a container computing resource matching the computing resource creation instruction by using the hardware resources in the computing cluster, so as to be called by the user;

[0008] The virtualization management module is used to utilize the hardware resources in the computing power cluster to create virtual machine computing power resources that match the computing power resource creation instruction for the user to call.

[0009] In one embodiment, the hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources;

[0010] The container management module is also used to determine the target architecture hardware resources that match the architecture requirement information from the first architecture hardware resources and the second architecture hardware resources based on the architecture requirement information carried in the computing power resource creation instruction; and is also used to use the target architecture hardware resources in the computing power cluster to create container computing power resources as container computing power resources that match the computing power resource creation instruction for user invocation.

[0011] In one embodiment, the hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources;

[0012] The virtualization management module is also used to determine the target architecture hardware resources that match the architecture requirement information from the first architecture hardware resources and the second architecture hardware resources based on the architecture requirement information carried in the computing power resource creation instruction; and is also used to use the target architecture hardware resources in the computing power cluster to create virtual machine computing power resources as virtual machine computing power resources that match the computing power resource creation instruction for user invocation.

[0013] In one of the embodiments, the computing power cluster is obtained based on a preset container orchestration platform; the heterogeneous node management module is used to manage hardware resources of different architectures to the preset container orchestration platform to obtain the computing power cluster.

[0014] In one of the embodiments, the container management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, and obtain the container computing power resources that match the target architecture hardware resources from the preset container orchestration platform as the container computing power resources that match the computing power resource creation instruction.

[0015] In one of the embodiments, the virtualization management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, obtain the target architecture hardware resources from the computing power cluster, and use the preset virtualization technology to convert the target architecture hardware resources into virtual machine computing power resources as the virtual machine computing power resources that match the computing power resource creation instruction.

[0016] In a second aspect, the present application provides a resource scheduling method, which is applied to the cloud computing platform for heterogeneous computing power integration as described in the first aspect, and the method includes:

[0017] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0018] In the case where the resource type requirement information indicates a requirement for virtual machine computing resources, using hardware resources in the computing cluster to create a container computing resource that matches the computing resource creation instruction for the user to call;

[0019] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instruction for the user to call.

[0020] In a third aspect, the present application further provides a resource scheduling device, including:

[0021] A request receiving module is used to receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0022] A first computing power creation module is used to create a container computing power resource matching the computing power resource creation instruction by using hardware resources in the computing power cluster when the resource type requirement information represents a requirement for a virtual machine computing power resource, so as to be called by the user;

[0023] The second computing power creation module is used to create virtual machine computing power resources matching the computing power resource creation instructions by using the hardware resources in the computing power cluster when the resource type requirement information represents the required container computing power resources, for the user to call.

[0024] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0025] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0026] In the case where the resource type requirement information indicates a requirement for virtual machine computing resources, using hardware resources in the computing cluster to create a container computing resource that matches the computing resource creation instruction for the user to call;

[0027] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instruction for the user to call.

[0028] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0029] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0030] In the case where the resource type requirement information indicates a requirement for virtual machine computing resources, using hardware resources in the computing cluster to create a container computing resource that matches the computing resource creation instruction for the user to call;

[0031] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instruction for the user to call.

[0032] The above-mentioned cloud computing platform, resource scheduling method, device, equipment and medium for integrating heterogeneous computing power, the cloud computing platform includes a heterogeneous node management module, a heterogeneous computing power scheduling module, a container management module and a virtualization management module, wherein: the heterogeneous node management module is used to manage hardware resources of different architectures into a computing power cluster; the heterogeneous computing power scheduling module is used to receive a computing power call request sent by a user, the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information; in the resource type requirement information In the case of representing the demand for virtual machine computing power resources, the computing power resource creation instruction is sent to the virtualization management module; in the case of the resource type requirement information representing the demand for container computing power resources, the computing power resource creation instruction is sent to the container management module; the container management module is used to use the hardware resources in the computing power cluster to create container computing power resources that match the computing power resource creation instruction for the user to call; the virtualization management module is used to use the hardware resources in the computing power cluster to create virtual machine computing power resources that match the computing power resource creation instruction for the user to call. This application realizes the effective management and scheduling of heterogeneous hardware resources through the collaboration of heterogeneous node management module, heterogeneous computing power scheduling module, container management module and virtualization management module. The user only needs to submit a computing power call request, and the cloud computing platform will automatically select the appropriate hardware resources to complete the task through containers or virtual machines, thereby improving the utilization of computing resources and flexibly responding to different demand scenarios. The architecture of this cloud computing platform can provide strong support for diversified applications in a cloud environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A schematic diagram of the structure of a cloud computing platform integrating heterogeneous computing power in one embodiment;

[0035] Figure 2 A schematic diagram of a resource scheduling method in one embodiment;

[0036] Figure 3 A flowchart of an execution process for a user's computing power call requirement in a cloud computing architecture in one embodiment;

[0037] Figure 4 is a structural block diagram of a resource scheduling device in one embodiment;

[0038] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] In an exemplary embodiment, Figure 1 As shown, a cloud computing platform integrating heterogeneous computing power is provided, and the cloud computing platform includes a heterogeneous node management module 102, a heterogeneous computing power scheduling module 104, a container management module 106, and a virtualization management module 108, wherein:

[0041] The above-mentioned heterogeneous node management module is used to manage hardware resources of different architectures into the computing power cluster.

[0042] Among them, managing hardware resources of different architectures into a computing cluster can refer to integrating computing resources from different hardware architectures into a unified computing cluster. Hardware resources can include a variety of processors (such as CPUs and GPUs), storage devices, network devices and other resources. Integrating can refer to the process of integrating new hardware resources, software systems or services into existing infrastructure and ensuring that they can be effectively managed and utilized in the field of information technology, especially in cloud computing and data center management.

[0043] Exemplarily, the heterogeneous node management module can use specific protocols to automatically detect and identify various hardware resources, and then store the detected resource information (such as model, performance indicators, status, etc.) in a unified format into the resource management database to form a computing power cluster.

[0044] The above-mentioned heterogeneous computing power scheduling module is used to receive computing power call requests sent by users, and the above-mentioned computing power call requests carry resource type requirement information and architecture requirement information, and generate computing power resource creation instructions based on the above-mentioned resource type requirement information and the above-mentioned architecture requirement information; when the above-mentioned resource type requirement information represents the demand for virtual machine computing power resources, the above-mentioned computing power resource creation instructions are sent to the above-mentioned virtualization management module; when the above-mentioned resource type requirement information represents the demand for container computing power resources, the above-mentioned computing power resource creation instructions are sent to the above-mentioned container management module.

[0045] Among them, resource type requirement information may refer to the specific types of computing resources required by the user, such as virtual machine computing resources and container computing resources; architecture requirement information may refer to the hardware architecture or specific computing standards behind the computing resources required by the user, such as ARM architecture computing resources and x86_64 architecture computing resources.

[0046] Among them, the heterogeneous computing power scheduling module can use the API interface to receive computing power call requests from users, parse out specific resource type demand information and architecture demand information according to the resource type (virtual machine or container) and architecture requirements in the user request, and then generate corresponding computing power resource creation instructions based on the parsed demand information. Its specific implementation can use a decision tree algorithm or other scheduling algorithms to make reasonable resource allocation decisions. Then, the instructions are sent to the virtualization management module or the container management module according to the demand type.

[0047] The container management module is used to utilize the hardware resources in the computing power cluster to create container computing power resources that match the computing power resource creation instruction for the user to call.

[0048] Among them, container computing resources may refer to computing resources running in the container.

[0049] Among them, the container management module can select suitable hardware resources based on the received computing power resource creation instructions, and then use container technology to create containers that match the requirements. For example, first select and configure the container image, call the API running the container to start and manage the container instance, and finally bind the created container resources to the user's computing power call request to ensure that the user can access and call these resources.

[0050] The above-mentioned virtualization management module is used to utilize the hardware resources in the above-mentioned computing power cluster to create virtual machine computing power resources that match the above-mentioned computing power resource creation instructions for the above-mentioned user to call.

[0051] Among them, virtual machine computing resources may refer to computing resources provided by virtual machines created on physical hardware through virtualization technology.

[0052] Among them, after receiving the computing resource creation instruction, the above-mentioned virtualization management module can select a suitable physical server for virtualization according to the computing resource creation instruction, and create a virtual machine through virtualization technology, such as specifying CPU, memory, storage and other resources, and then configuring the operating system and necessary applications; after the virtual machine is created, the relevant information is returned to the heterogeneous computing power scheduling module for subsequent user calls.

[0053] The above-mentioned cloud computing platform with heterogeneous computing power integration realizes the effective management and scheduling of heterogeneous hardware resources through the collaboration of heterogeneous node management module, heterogeneous computing power scheduling module, container management module and virtualization management module. Users only need to submit computing power call requests, and the cloud computing platform will automatically select appropriate hardware resources to complete tasks through containers or virtual machines, thereby improving the utilization of computing resources and flexibly responding to different demand scenarios. The architecture of this cloud computing platform can provide strong support for diversified applications in the cloud environment.

[0054] In an exemplary embodiment, the hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources; the container management module is also used to determine the target architecture hardware resources that match the above-mentioned architecture requirement information from the above-mentioned first architecture hardware resources and the above-mentioned second architecture hardware resources according to the architecture requirement information carried in the above-mentioned computing power resource creation instruction; and is also used to use the target architecture hardware resources in the above-mentioned computing power cluster to create container computing power resources as container computing power resources that match the above-mentioned computing power resource creation instruction for user call.

[0055] Among them, the hardware resources of the above-mentioned different architectures may refer to hardware resources of different CPU architectures. The first architecture hardware resources may be computing resources of the ARM architecture, and the second architecture hardware resources may be computing resources of the x86_64 architecture. The first architecture hardware resources may also be computing resources of the x86_64 architecture, and the second architecture hardware resources may also be computing resources of the ARM architecture.

[0056] Among them, CPU (Central Processing Unit): CPU is the core component of the computer, responsible for executing instructions, performing calculations and controlling data flow. ARM (Advanced RISC Machine) can be a processor architecture based on reduced instruction set computing (RISC), which is used in mobile devices, embedded systems and low-power applications. X86_64 can be a 64-bit processor architecture based on complex instruction set computing. It expands the traditional x86 architecture, supports 64-bit computing, can handle larger memory capacity and perform more complex computing tasks.

[0057] Exemplarily, the first architecture hardware resource is a computing resource of the ARM architecture, and the second architecture hardware resource is a computing resource of the x86_64 architecture; the above-mentioned container management module is also used to determine the first architecture hardware resource as the target architecture hardware resource when it is determined to be the ARM architecture according to the architecture requirement information carried in the above-mentioned computing power resource creation instruction; when it is determined to be the x86_64 architecture according to the architecture requirement information carried in the above-mentioned computing power resource creation instruction, the second architecture hardware resource is determined to be the target architecture hardware resource; and corresponding container computing power resources can also be created on the selected target architecture hardware resources, for example, using container tools such as Docker or Kubernetes to build and allocate corresponding containers as container computing power resources that match the above-mentioned computing power resource creation instruction for user call.

[0058] In this embodiment, through the precise matching and dynamic allocation of hardware resources, the utilization efficiency of computing power can be significantly improved, and idle resources and waste can be avoided; the cloud computing platform supports hardware resources of various architectures, so that the container management module can flexibly select appropriate resources according to different task requirements and create corresponding container computing power resources, which greatly improves the scalability of the cloud computing platform.

[0059] In an exemplary embodiment, the hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources; the virtualization management module is also used to determine the target architecture hardware resources that match the architecture requirement information from the first architecture hardware resources and the second architecture hardware resources based on the architecture requirement information carried in the computing power resource creation instruction; and is also used to use the target architecture hardware resources in the computing power cluster to create virtual machine computing power resources as virtual machine computing power resources that match the computing power resource creation instruction for user call.

[0060] Among them, the hardware resources of the above-mentioned different architectures may refer to hardware resources of different CPU architectures. The first architecture hardware resources may be computing resources of the ARM architecture, and the second architecture hardware resources may be computing resources of the x86_64 architecture. The first architecture hardware resources may also be computing resources of the x86_64 architecture, and the second architecture hardware resources may also be computing resources of the ARM architecture.

[0061] Among them, CPU (Central Processing Unit): CPU is the core component of the computer, responsible for executing instructions, performing calculations and controlling data flow. ARM (Advanced RISC Machine) can be a processor architecture based on reduced instruction set computing (RISC), which is used in mobile devices, embedded systems and low-power applications. X86_64 can be a 64-bit processor architecture based on complex instruction set computing. It expands the traditional x86 architecture, supports 64-bit computing, can handle larger memory capacity and perform more complex computing tasks.

[0062] Exemplarily, the first architecture hardware resources are computing resources of the ARM architecture, and the second architecture hardware resources are computing resources of the x86_64 architecture; the virtualization management module is also used to determine the first architecture hardware resources as the target architecture hardware resources when it is determined that the ARM architecture is carried according to the architecture requirement information carried in the above-mentioned computing power resource creation instruction; when it is determined that the x86_64 architecture is carried according to the architecture requirement information carried in the above-mentioned computing power resource creation instruction, the second architecture hardware resources are determined as the target architecture hardware resources; and it is also possible to create a corresponding virtual machine instance on the selected target architecture hardware resource to form a virtual machine computing power resource as a virtual machine computing power resource that matches the above-mentioned computing power resource creation instruction for user call.

[0063] In this embodiment, through the precise matching and dynamic allocation of hardware resources, the utilization efficiency of computing power can be significantly improved, and resource idleness and waste can be avoided; the cloud computing platform supports hardware resources of various architectures, so that the virtualization management module can flexibly select appropriate resources according to different task requirements and create corresponding virtual machine computing power resources, greatly improving the scalability of the cloud computing platform.

[0064] In an exemplary embodiment, the computing power cluster is obtained based on a preset container orchestration platform; the heterogeneous node management module is used to manage hardware resources of different architectures to the preset container orchestration platform to obtain the computing power cluster.

[0065] Among them, the preset container orchestration platform may refer to the open source Kubernetes (cloud native operating system), which is used to automatically deploy, scale, and manage containerized applications.

[0066] Exemplarily, the heterogeneous node management module determines the container orchestration platform to be used, and installs and configures it to support the management and scheduling of containers; and identifies hardware resources of different architectures, including but not limited to CPU, GPU, and FPGA, and registers these resources to the container orchestration platform, where the CPU may include ARM architecture and x86_64 architecture; the heterogeneous node management module can incorporate different types of computing nodes (such as virtual machines based on x86 architecture, physical servers running ARM architecture, etc.) into the computing power cluster.

[0067] In this embodiment, through container orchestration, users can dynamically expand or shrink the computing cluster according to demand, and bring hardware resources of different architectures into unified management, so that the computing cluster can flexibly respond to various computing needs and achieve optimal configuration and utilization of resources.

[0068] In an exemplary embodiment, the container management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, and obtain the container computing power resources that match the target architecture hardware resources from the preset container orchestration platform as the container computing power resources that match the computing power resource creation instruction.

[0069] Exemplarily, after receiving the computing resource creation instruction, the container management module first parses the instruction content, extracts the resource type requirement information and the architecture requirement information required by the user, and then compares the hardware resources defined in the preset container orchestration platform based on the parsed requirement information, and accurately searches for the target architecture hardware resources that match the computing power call request sent by the user. After determining the target architecture hardware resources, the container management module will retrieve the container computing power resources corresponding to this architecture, and then return the required computing power resources to the user in the form of a container instance.

[0070] In this embodiment, the resource matching capability of the container management module is used to ensure that users can obtain container computing resources that are highly matched with their computing power requirements, thereby optimizing resource utilization efficiency.

[0071] In an exemplary embodiment, the virtualization management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, obtain the target architecture hardware resources from the computing power cluster, and use the preset virtualization technology to convert the target architecture hardware resources into virtual machine computing power resources as the virtual machine computing power resources that match the computing power resource creation instruction.

[0072] The preset virtualization technology may refer to a virtualization technology implemented by Kubevirt (virtualization component), which may provide a virtualization API management capability.

[0073] Exemplarily, the virtualization management module parses the computing resource creation instructions, identifies the target architecture hardware resources that match the user's needs from the computing cluster, then obtains the target architecture hardware resources from the computing cluster, and then uses the preset virtualization technology to convert the target architecture hardware resources into virtual machine computing resources. The virtual machine computing resource information can then be returned to the user, and the corresponding access interface can be provided so that the user can use these virtual machine computing resources.

[0074] In this embodiment, through the effective matching of the virtualization management module, it is ensured that the optimal hardware resources can be used when the virtual machine computing resources are created, thereby avoiding resource waste and improving the utilization efficiency of computing power.

[0075] In an exemplary embodiment, the present application also provides a resource scheduling method, which is applied to the cloud computing platform with heterogeneous computing power integration as described above. Figure 2 As shown, the method includes steps S202 to S206. Among them:

[0076] Step S202: Receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction based on the resource type requirement information and the architecture requirement information.

[0077] Among them, the computing power call request may refer to a request sent by a user to the cloud computing platform, which contains the resource type requirement information and architecture requirement information required by the user. The resource type requirement information may refer to the information of the computing resource category required by the user, such as virtual machine computing power resources, container computing power resources, etc. The architecture requirement information may refer to the user's architecture requirements for computing resources, such as the required CPU architecture (x86, ARM, etc.), memory configuration, storage type, etc. The computing power resource creation instruction may refer to the instruction generated by the cloud computing platform based on the user's computing power call request, indicating how to create computing resources that match the user's needs.

[0078] Step S204, when the resource type requirement information indicates the requirement for virtual machine computing resources, the hardware resources in the computing cluster are used to create a container computing resource that matches the computing resource creation instruction for the user to call.

[0079] Among them, a computing cluster can refer to a collection of multiple computing nodes, which can be physical servers or virtualized computing instances, which together provide computing power for users. Container computing resources can refer to computing resources provided by container technology, which support the operation of applications in a containerized manner.

[0080] Step S206, when the resource type requirement information indicates the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instruction for the user to call.

[0081] Among them, virtual machine computing resources can refer to computing resources provided by virtualization technology, simulating an independent computing environment.

[0082] In this embodiment, through the above-mentioned resource scheduling method, the computing resources required by the user can be accurately matched, avoiding waste of resources, thereby improving the resource utilization of the entire computing power cluster.

[0083] In an exemplary embodiment, the present application also provides a cloud computing architecture for integrating heterogeneous computing power. The execution process for the user computing power call demand in the above cloud computing architecture is as follows: Figure 3 As shown, it specifically includes: heterogeneous node management module, heterogeneous computing power scheduling module, virtualization management module, and container management module. Among them:

[0084] The above heterogeneous node management module is responsible for managing heterogeneous hardware in a unified manner into the computing power cluster, including arm and x86_64 hardware resources. Execution subject: The node actively initiates a registration request, and the cluster will perform identity verification on it. If it passes, it will be added to the cluster and become a computing power node. Data flow: computing power node -> node management module.

[0085] The above-mentioned heterogeneous computing power scheduling module has the following functions: to schedule computing power according to the application type submitted by the user. According to the computing power carrier of the application, it is decided to call the interface of the virtualization management module or the container management module to create the corresponding carrier; and according to the CPU architecture of the application, it is decided to schedule it to the ARM node or the X86_64 node. Execution subject: The user initiates the application request, which is decided by the heterogeneous computing power scheduling module and finally executed by the virtualization management module or the container management module. Data flow: user->heterogeneous computing power scheduling module->virtualization management module or user->heterogeneous computing power scheduling module->container management module.

[0086] The above virtualization management module is responsible for receiving calls from the heterogeneous computing power scheduling module, and is ultimately responsible for creating a virtual machine on the desired computing power node (arm or x86_64) for use by upper-layer applications. Execution subject: The computing power node is responsible for creating the desired virtual machine computing power resources. Data flow: virtualization management module -> heterogeneous computing power scheduling module.

[0087] The above container management module is responsible for receiving calls from the heterogeneous computing power scheduling module, and is ultimately responsible for creating containers on the desired computing power nodes (arm or x86_64) for use by upper-layer applications. Execution subject: The computing power node is responsible for creating the desired container computing power resources. Data flow: container management module -> heterogeneous computing power scheduling module.

[0088] The above cloud computing architecture with heterogeneous computing power integration realizes the computing power output of multiple CPU architectures by building a cloud platform based on hardware of multiple CPU architectures, thus achieving true heterogeneous computing power integration. It also expands the management capabilities of Kubernetes, enabling it to simultaneously schedule and orchestrate computing power resources of multiple carriers, including container computing power and virtual machine computing power.

[0089] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0090] Based on the same inventive concept, the embodiment of the present application also provides a resource scheduling device for implementing the resource scheduling method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more resource scheduling device embodiments provided below can refer to the limitations on the resource scheduling method above, and will not be repeated here.

[0091] In an exemplary embodiment, Figure 4 As shown, a resource scheduling device is provided, including: a request receiving module 901, a first computing power creation module 902, and a second computing power creation module 903, wherein:

[0092] The request receiving module 901 is used to receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0093] The first computing power creation module 902 is used to create a container computing power resource matching the computing power resource creation instruction by using the hardware resources in the computing power cluster when the resource type requirement information indicates that a virtual machine computing power resource is required, so as to be called by the user;

[0094] The second computing power creation module 903 is used to create virtual machine computing power resources matching the computing power resource creation instruction by using the hardware resources in the computing power cluster when the resource type requirement information represents the requirement container computing power resources, so as to be called by the user.

[0095] Each module in the resource scheduling device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0096] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a resource scheduling method is implemented.

[0097] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0099] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0100] In the case where the resource type requirement information indicates the requirement for virtual machine computing resources, the hardware resources in the computing cluster are used to create a container computing resource that matches the computing resource creation instruction, for the user to call;

[0101] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instructions for the user to call.

[0102] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0103] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0104] In the case where the resource type requirement information indicates the requirement for virtual machine computing resources, the hardware resources in the computing cluster are used to create a container computing resource that matches the computing resource creation instruction, for the user to call;

[0105] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instructions for the user to call.

[0106] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0107] Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information;

[0108] In the case where the resource type requirement information indicates the requirement for virtual machine computing resources, the hardware resources in the computing cluster are used to create a container computing resource that matches the computing resource creation instruction, for the user to call;

[0109] In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instructions for the user to call.

[0110] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0111] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0112] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A cloud computing platform integrating heterogeneous computing power, characterized in that: The cloud computing platform includes a heterogeneous node management module, a heterogeneous computing power scheduling module, a container management module and a virtualization management module, wherein: The heterogeneous node management module is used to manage hardware resources of different architectures into the computing power cluster; The heterogeneous computing power scheduling module is used to receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information; when the resource type requirement information represents the requirement for virtual machine computing power resources, the computing power resource creation instruction is sent to the virtualization management module; when the resource type requirement information represents the requirement for container computing power resources, the computing power resource creation instruction is sent to the container management module; The container management module is used to create a container computing resource matching the computing resource creation instruction by using the hardware resources in the computing cluster, so as to be called by the user; The virtualization management module is used to utilize the hardware resources in the computing power cluster to create virtual machine computing power resources that match the computing power resource creation instruction for the user to call.

2. The cloud computing platform according to claim 1, characterized in that: The hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources; The container management module is also used to determine the target architecture hardware resources that match the architecture requirement information from the first architecture hardware resources and the second architecture hardware resources based on the architecture requirement information carried in the computing power resource creation instruction; and is also used to use the target architecture hardware resources in the computing power cluster to create container computing power resources as container computing power resources that match the computing power resource creation instruction for user invocation.

3. The cloud computing platform according to claim 1, characterized in that: The hardware resources of different architectures include first architecture hardware resources and second architecture hardware resources; The virtualization management module is also used to determine the target architecture hardware resources that match the architecture requirement information from the first architecture hardware resources and the second architecture hardware resources based on the architecture requirement information carried in the computing power resource creation instruction; and is also used to use the target architecture hardware resources in the computing power cluster to create virtual machine computing power resources as virtual machine computing power resources that match the computing power resource creation instruction for user invocation.

4. The cloud computing platform according to claim 1, characterized in that: The computing power cluster is obtained based on a preset container orchestration platform; The heterogeneous node management module is used to manage hardware resources of different architectures to the preset container orchestration platform to obtain the computing power cluster.

5. The cloud computing platform according to claim 4, characterized in that: The container management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, and obtain the container computing power resources that match the target architecture hardware resources from the preset container orchestration platform as the container computing power resources that match the computing power resource creation instruction.

6. The cloud computing platform according to claim 4, characterized in that: The virtualization management module is also used to determine the target architecture hardware resources that match the computing power resource creation instruction, obtain the target architecture hardware resources from the computing power cluster, and use the preset virtualization technology to convert the target architecture hardware resources into virtual machine computing power resources as the virtual machine computing power resources that match the computing power resource creation instruction.

7. A resource scheduling method, characterized in that: Applied to the cloud computing platform for integrating heterogeneous computing power as claimed in claim 1, the method comprises: Receive a computing power call request sent by a user, the computing power call request carrying resource type requirement information and architecture requirement information, and generate a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information; In the case where the resource type requirement information indicates a requirement for virtual machine computing resources, using hardware resources in the computing cluster to create a container computing resource that matches the computing resource creation instruction for the user to call; In the case where the resource type requirement information represents the requirement for container computing resources, the hardware resources in the computing cluster are used to create virtual machine computing resources that match the computing resource creation instruction for the user to call.

8. A resource scheduling device, characterized in that: The device comprises: A request receiving module is used to receive a computing power call request sent by a user, wherein the computing power call request carries resource type requirement information and architecture requirement information, and generates a computing power resource creation instruction according to the resource type requirement information and the architecture requirement information; A first computing power creation module is used to create a container computing power resource matching the computing power resource creation instruction by using hardware resources in the computing power cluster when the resource type requirement information represents a requirement for a virtual machine computing power resource, so as to be called by the user; The second computing power creation module is used to create virtual machine computing power resources matching the computing power resource creation instructions by using the hardware resources in the computing power cluster when the resource type requirement information represents the required container computing power resources, for the user to call.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 7 are implemented.

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

Images