A lightweight multi-domain hyper-converged platform construction method and system compatible with heterogeneous hardware resources

Abstract

The application belongs to the technical field of cloud computing, and discloses a kind of compatible isomorphic hardware resource's lightweight multi-domain super fusion platform construction method, the application adopts compatible isomorphic hardware resource's lightweight super fusion platform architecture, and based on KVM, physical resource is converted into virtual resource on virtual machine, and the difference of underlying hardware is shielded, and based on Ceph, isomorphic storage resource is integrated, and through distributed storage technology, the storage equipment of different manufacturers is integrated into unified storage pool, and is not limited by the type of underlying hardware equipment.Through SDN technology, the network service of OpenStack can decouple the network control plane from the hardware, enabling unified management of different network devices. Through virtualization technology and automated management tools, a simplified elastic expansion solution is provided to easily handle changes in resource demand.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of cloud computing, and particularly relates to a lightweight multi-domain hyper-converged platform construction method and system compatible with heterogeneous hardware resources. BACKGROUND

[0002] With the combination of cloud computing and other frontier technologies, the adoption of hyper-converged architecture to provide cloud computing services has gradually become the mainstream deployment form in the industry, and is a delivery mode with advantages such as simplified management, elastic expansion, flexible and agile, etc. The hyper-converged architecture is based on a standard general-purpose hardware platform, and realizes the convergence of computing, storage and network through software definition, realizes the technical architecture of a software-defined data center centered on virtualization, can simplify the deployment and application of IT infrastructure, reduce the operating cost of enterprises, more efficiently utilize computing, storage and network resources, improve overall resource utilization, and more effectively protect data security through centralized management and monitoring. However, the existing hyper-converged cloud technology still has the following problems.

[0003] (1) The current hyper-converged architecture cloud computing platform is usually built based on standardized homogeneous servers, and it is difficult to be compatible with heterogeneous hardware resource scenarios. The standard server adopts a hardware standard widely recognized in the industry, so that the hyper-converged platform can be deployed in various hardware environments, has high compatibility and flexibility. The hardware components (such as CPU, memory, storage devices, etc.) of the standard server can usually be interchanged and upgraded, and the maintenance and management are simpler and more efficient, and the cost of the standard server is usually lower due to large-scale production and market competition. This makes the construction cost of the hyper-converged platform lower, and can reduce the total cost of ownership through the modular expansion of the standard server. The modular design of the standard server allows enterprises to gradually expand computing, storage and network resources according to business needs. This flexibility allows the hyper-converged platform to start from a small scale and expand to a large scale as the business grows, so the current hyper-converged architecture is mostly built based on homogeneous standard servers.

[0004] However, as business requirements continue to evolve, heterogeneous service clusters are introduced into cloud computing services due to their hardware resource diversity, which can provide optimal computing power for different types of workloads. In homogeneous clusters, all nodes have the same hardware configuration, which may result in some tasks not fully utilizing the advantages of specific hardware. For example, I / O-intensive tasks may not achieve optimal performance on compute-intensive nodes. Heterogeneous clusters, on the other hand, can select the most suitable nodes based on the characteristics of the task, thereby improving overall efficiency. Different hardware platforms have different performance when processing specific types of tasks. Heterogeneous clusters can be performance-optimized for different tasks. For example, compute-intensive tasks can be scheduled to high-performance CPU or GPU nodes, while I / O-intensive tasks can be scheduled to nodes with high-throughput storage systems. Through such targeted optimization, heterogeneous clusters can maximize the potential of various hardware, thereby improving performance. Therefore, building a hyper-converged cloud platform compatible with heterogeneous hardware resources can effectively improve the performance and quality of cloud services and improve resource utilization efficiency.

[0005] Traditional hyper-converged platform hardware deployment methods are hardware-bound, and software deployment methods have low resource utilization efficiency. There are two deployment methods for traditional hyper-converged platforms. One is the hyper-converged all-in-one delivery method, and the other is the hyper-converged software delivery method. The hyper-converged all-in-one delivery method delivers pre-integrated hardware devices, including computing, storage, and network devices, but is usually tied to a vendor and cannot freely choose hardware suppliers and configurations according to demand. It also cannot be expanded and upgraded according to business needs, relying on the vendor's upgrade path. The hyper-converged software delivery method is usually deployed on a metal bare machine in the form of an operating system or in a virtual machine on an existing virtualization platform. However, both software deployment methods rely on a complete virtualization layer, requiring the creation of a control virtual machine on each physical node to manage the computing and storage resources of that node. Since the virtual machine needs to run a complete operating system instance and the virtualization layer needs to simulate hardware resources, it results in high performance overhead and low node resource utilization.

[0006] With the popularity of distributed storage technology and virtualization technology, more and more computing and data processing needs are emerging. The traditional cloud computing model has a complex and cumbersome platform deployment and management process, which cannot meet the requirements of full resource utilization and flexible service expansion. To address these challenges, hyper-converged architecture is introduced, allowing the integration and unified management of server computing, storage, and network resources through software-defined methods. By expanding hyper-converged nodes to expand service resources, the deployment and management process is simplified, resource utilization and flexibility are improved, and management and labor costs are reduced.

[0007] The basic architecture of the hyper-converged platform includes three parts: compute virtualization, storage virtualization, and network virtualization. Compute virtualization uses virtualization technology to abstract physical computing resources into virtual machines (VMs) or containers, supporting multiple workloads running on the same hardware resources. Storage virtualization virtualizes local storage resources (such as SSD, HDD, NVMe) on nodes into a shared storage pool through distributed storage technology, providing high-performance and scalable data services. Network virtualization virtualizes physical network resources through software-defined networking (SDN) technology, allowing multiple virtual networks to coexist on the same physical network.

[0008] (2) Prior art solutions

[0009] 1) Hyper-converged platform construction scheme

[0010] Major hyper-converged vendors build hyper-converged platforms through different technologies. These solutions have their own characteristics in architecture, function, and deployment mode. The following is a detailed introduction to the hyper-converged platform construction schemes of several well-known hyper-converged vendors:

[0011] Nutanix[2] is one of the pioneers of hyper-converged architecture. Its hyper-converged platform is based on its core Acropolis Operating System (AOS) and integrates computing, storage, and network resources through software-defined methods to provide a highly integrated solution. Nutanix's hyper-converged operating system AOS uses a distributed storage architecture to integrate local storage resources in the cluster into a global storage pool and manages storage and data services through the Nutanix Controller VM (CVM). Nutanix's virtualization management program Acropolis Hypervisor (AHV) is based on KVM and is deeply integrated into AOS, providing a lightweight virtualization solution. Nutanix's centralized management platform Prism management platform provides functions such as cluster management, performance monitoring, automated operation and maintenance, backup and recovery, etc.

[0012] VMware's hyper-converged solution is based on its core technology vSAN (vSphere Storage Area Network), which integrates compute, storage, and network resources in a software-defined manner within the vSphere virtualization platform. VMware vSphere is the core of the hyper-converged architecture, responsible for compute virtualization management. vSphere runs virtual machines through the ESXi Hypervisor, providing powerful virtualization capabilities. vSAN integrates local storage in the cluster into a shared storage pool, supporting data distribution, data protection, disaster recovery, and other functions. vSAN is deeply integrated into the vSphere environment, providing consistent storage management experience. NSX is VMware's software-defined network (SDN) solution, supporting network virtualization, security policy management, and network traffic optimization, and is an important part of VMware's hyper-converged platform.

[0013] HPE SimpliVity is a hyper-converged solution from Hewlett Packard Enterprise (HPE), integrating compute, storage, and network resources. The core platform of SimpliVity, SimpliVity Data Virtualization Platform, provides data virtualization, optimization, and protection functions. DVP achieves data compression and deduplication through dedicated hardware acceleration cards, improving storage efficiency while reducing storage requirements. SimpliVity is deployed on HPE's ProLiant servers, which provide powerful computing performance and scalability, supporting virtualization and data storage integration.

[0014] Current hyper-converged architecture cloud computing platforms have poor compatibility with heterogeneous hardware resources and difficulty in elastic expansion. Existing hyper-converged architecture cloud platforms are designed to run in a homogeneous environment, assuming that all nodes have similar hardware and software configurations. This design simplifies resource management and scheduling, but also brings difficulties in supporting heterogeneous resources. Many hyper-converged solutions rely heavily on specific hardware configurations during deployment and operation, making it difficult to support hardware from different manufacturers or with different configurations. Secondly, hyper-converged platforms are usually designed with fixed architecture and expansion units, which limits the flexibility of expansion. Hyper-converged platforms usually expand in nodes, each containing compute, storage, and network resources. This fixed unit expansion method is difficult to cope with different resource demand expansion. In addition, the expansion of many hyper-converged platforms is linear, requiring new nodes to have the same hardware configuration as existing nodes, which also limits the flexibility of customized expansion of hyper-converged platforms according to business characteristics.

[0015] The traditional hyper-converged platform hardware deployment method is bound to a specific vendor, and the hardware selection is limited, and the resource utilization efficiency of the software deployment method is low. Traditional hyper-converged platform deployment methods can generally be divided into two types: one is a hyper-converged all-in-one delivery method, and the other is a hyper-converged software delivery method. These two methods have significant differences in architecture, flexibility, and resource utilization. First, the hyper-converged all-in-one delivery method is achieved by delivering pre-integrated hardware devices, which typically include computing, storage, and network resources, forming a highly integrated overall solution. The advantage of this method is that it simplifies the deployment process and hardware configuration, as the hardware and software have been integrated and optimized by the vendor. However, the limitation of this method is that it is usually tightly bound to the specific hardware and software ecosystem of a particular vendor, and users have limited flexibility in hardware selection and configuration. Specifically, users cannot freely choose hardware vendors or customize hardware configurations according to their business needs. In addition, the scalability is also limited, and enterprises cannot expand or upgrade hardware according to actual business development needs, but need to rely on the vendor's predefined upgrade path and support plan, which to some extent limits the scalability and autonomy of the system. Second, the hyper-converged software delivery method is achieved by deploying the software components of the hyper-converged platform in the form of an operating system directly on bare-metal servers or through a virtualization platform in virtual machines. Compared to the all-in-one delivery method, the software delivery method provides greater flexibility, allowing users to deploy hyper-converged software on existing hardware and supporting integration with different hardware platforms. However, this deployment method relies on a complete virtualization layer, that is, one or more controller virtual machines (Controller VMs) need to be created on each physical node to manage the computing and storage resources of that node. This means that the virtualization layer not only introduces additional complexity but also brings certain performance overhead. Specifically, virtual machines need to run a complete operating system instance, involving the consumption of resources such as memory and CPU. In addition, the virtualization layer needs to simulate underlying hardware resources during resource management, which can cause certain performance loss. The overhead of the virtualization layer not only reduces the utilization of node resources but also can affect the response speed and throughput of the overall system, especially under resource-intensive workloads, where performance bottlenecks are more obvious. Therefore, although the software delivery method provides greater flexibility, there are still challenges in resource utilization and performance, especially in scenarios that require high performance and high-density computing.

[0016] Through the above analysis, the problems and defects of the prior art are:

[0017] (1) The current hyper-converged architecture cloud computing platform has poor heterogeneous hardware resource compatibility and difficulty in elastic expansion.

[0018] (2) The traditional hyper-converged platform hardware deployment method is bound to a manufacturer, the hardware selection is limited, and the software deployment method has low resource utilization efficiency. SUMMARY

[0019] In view of the problems in the prior art, the application provides a lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources.

[0020] The application is implemented as follows: a lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources comprises the following steps:

[0021] Step 1: The lightweight multi-domain hyper-converged platform architecture compatible with heterogeneous hardware resources is composed of four modules: computing virtualization, storage virtualization, network virtualization, and a unified management platform.

[0022] Step 2: The computing virtualization virtualizes the computing resources of a physical server into virtual machines based on KVM technology, and supports multiple workloads in a heterogeneous hardware environment.

[0023] Step 3: The storage virtualization integrates the storage resources of different nodes into a global distributed storage pool based on Ceph, supports integration of heterogeneous storage devices, and provides block storage, object storage, and file storage services.

[0024] Step 4: The network virtualization uses SDN technology to realize dynamic configuration of a virtual network, network isolation, and optimization of network traffic across data centers.

[0025] Step 5: The unified management platform is based on OpenStack to create an implementation of cross-domain resource scheduling, management, and monitoring, and supports resource integration of multiple data centers and hybrid cloud architectures.

[0026] Step 6: The container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of the multi-domain hyper-converged cloud platform into lightweight containers through containerization technology.

[0027] Further, the computing virtualization virtualizes heterogeneous computing resources into virtual machine services based on KVM technology and a custom XML virtual machine definition file; user virtual machine instructions are converted into hardware-level instructions for execution by calling hardware virtualization extensions at the processor bottom layer, and a virtual CPU is provided for each virtual machine, and multiple virtual machines are concurrently run through context switching of the physical CPU and the virtual CPU by the KVM kernel.

[0028] Further, the storage virtualization integrates storage devices on multiple service clusters into a global storage pool based on Ceph, supports centralized management and allocation of storage resources, and pools heterogeneous storage resources of multi-domain service clusters into unified SSD and HDD storage resources by constructing different storage pools and storage layers.

[0029] Further, the network virtualization abstracts physical network resources into virtual networks through software definition, so that multiple virtual machines can share the same underlying network infrastructure, and the network virtualization separates the virtual network from the physical network through virtual switches, virtual routers, tunneling protocols and other technologies, so that flexible network configuration and management are realized.

[0030] Further, the unified management platform divides the entire cloud platform into multiple domains based on OpenStack, and all domains are managed through a unified control plane; the scheduler is responsible for selecting suitable computing nodes in different domains to start virtual machines; when a user requests to create a virtual machine, the global controller will pass the request to the scheduler, and the scheduler will select a suitable domain to deploy the virtual machine according to the resource state, geographical location, network delay and other factors of different regions.

[0031] Further, the container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of the lightweight multi-domain hyper-converged cloud platform compatible with heterogeneous hardware resources into lightweight containers through containerization technology, realizes the decoupling of the platform and the hardware, reduces the performance overhead of the virtualization layer, and improves the utilization efficiency of the computing and storage resources.

[0032] Another object of the present application is to provide a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources, comprising:

[0033] The computing virtualization module is used for virtualizing the computing resources of the physical server into virtual machines based on KVM technology, and supports multiple workloads in a heterogeneous hardware environment;

[0034] The storage virtualization module is used for integrating the storage resources of different nodes into a global distributed storage pool based on Ceph, supporting the integration of heterogeneous storage devices, and providing block storage, object storage and file storage services;

[0035] The network virtualization module is used for network virtualization using SDN technology to realize dynamic configuration of virtual networks, network isolation and optimization of network traffic across data centers;

[0036] The unified management platform module is used for creating a unified management platform based on OpenStack to realize cross-domain resource scheduling, management and monitoring, and supports resource integration of multiple data centers and hybrid cloud architectures; and the container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of the multi-domain hyper-converged cloud platform into lightweight containers through containerization technology.

[0037] Another object of the present application is to provide a computer device comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to cause the processor to perform the steps of the method for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources.

[0038] Another object of the present application is to provide a computer-readable storage medium storing a computer program, the computer program being executed by a processor to cause the processor to perform the steps of the method for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources.

[0039] Another object of the present application is to provide an information data processing terminal for implementing the system for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources.

[0040] In combination with the above technical solutions and the technical problems solved, the technical solution to be protected by the present application has the following advantages and positive effects:

[0041] Firstly, the lightweight hyper-converged platform architecture compatible with heterogeneous hardware resources is adopted, the physical resources are converted into virtual resources on the virtual machine based on KVM, the differences of the underlying hardware are shielded, the heterogeneous storage resources are integrated based on Ceph, the storage devices of different manufacturers are integrated into a unified storage pool through distributed storage technology, and the type of the underlying hardware device is not limited. Through the SDN technology, the network service of OpenStack can decouple the network control plane from the hardware, and unified management of different network devices is achieved. Through the virtualization technology and the automatic management tool, a simplified elastic expansion solution is provided to easily cope with changes in resource demand.

[0042] Through the containerization technology, the virtualization layer and the management service of the multi-domain hyper-converged cloud platform in (1) are abstracted into lightweight containers, and the decoupling of the platform and the hardware is achieved. Administrators can flexibly select hardware suppliers and configurations according to business needs, and are no longer limited by specific hardware integration solutions of manufacturers. In addition, the container technology is more lightweight than the traditional virtual machine, and it is not necessary to run a complete operating system instance for each physical node. Through the containerized KVM virtualization layer, the performance overhead of the virtualization layer is reduced, and the utilization efficiency of the computing and storage resources is improved.

[0043] The existing hyper-converged architecture cloud platform is designed to run in a homogeneous environment, and the compatibility of heterogeneous hardware resources is poor, and the elastic expansion is difficult. In addition, the existing hyper-converged platform deployment method has defects, in terms of hardware deployment, it is bound to manufacturers and the hardware selection is limited, and in terms of software deployment, the resource utilization efficiency is low.

[0044] The application adopts a lightweight hyper-converged platform architecture compatible with heterogeneous hardware resources, and based on virtualization technology compatible with heterogeneous resources, unifies the management of heterogeneous computing, storage and network resources, and shields the differences of underlying hardware, is easy to expand, and solves the problems of poor compatibility of heterogeneous resources and difficult elastic expansion of existing solutions. In addition, through containerization technology, the virtualization layer and management services of the lightweight multi-domain hyper-converged cloud platform compatible with heterogeneous hardware resources are abstracted into lightweight containers, the decoupling of the platform and hardware is realized, the performance overhead of the virtualization layer is reduced, and the problems of the existing hyper-converged platform hardware deployment mode and manufacturer binding, limited hardware selection, and low resource utilization efficiency of software deployment mode are solved.

[0045] Second, the expected income and commercial value of the technical scheme of the application after transformation are: through the lightweight hyper-converged platform architecture compatible with heterogeneous hardware resources, the differences of underlying hardware are shielded, and the platform can run seamlessly in different hardware environments. This will greatly reduce the dependence of enterprises on a single hardware manufacturer, provide a wider hardware selection space, reduce hardware costs and procurement risks. Through the introduction of virtualization technology and containerization management, the platform has strong elastic expansion capability. The system can dynamically expand computing, storage and network resources according to business needs, ensuring that the business can quickly respond to expansion needs while improving resource utilization. Elastic expansion reduces resource redundancy in traditional systems and reduces unnecessary hardware investment. The use of containerization technology to abstract the virtualization layer and management services into lightweight containers significantly reduces the performance overhead of the virtualization layer, thereby improving the resource utilization efficiency of the platform. Compared with traditional hyper-converged platforms, containerized management services are more lightweight, and deployment and management are more efficient. Higher resource utilization can improve user experience and enhance customer satisfaction.

[0046] Third, the technical scheme of the application proposes a lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources, successfully solves the problems of poor compatibility, low resource integration and management efficiency, and poor scalability of the multi-domain hyper-converged platform in the existing technology in the heterogeneous hardware environment, and makes significant technical progress in performance and applicability. The traditional hyper-converged architecture often needs to rely on a unified hardware platform or expensive special hardware to realize resource virtualization and centralized management when facing different hardware environments, which leads to the limitation of hardware selection and the increase of cost. The lightweight hyper-converged solution of the application provides the ability to efficiently integrate computing, storage and network resources in a heterogeneous hardware environment by compatible with KVM, Ceph, SDN and other technologies, significantly improving the compatibility of the platform.

[0047] In terms of computing virtualization, the application is based on KVM virtualization technology, which virtualizes the computing resources of different physical servers into virtual machines, and is not limited to specific hardware, thereby realizing the sharing and centralized management of computing resources in a heterogeneous hardware environment. This design greatly improves the utilization rate of hardware resources, reduces the dependence on uniform hardware, solves the compatibility problems of traditional platforms, and saves hardware investment costs for enterprises. At the same time, the KVM technology has the advantage of low overhead, ensuring the performance of the virtual machine and the stability of the system, and is suitable for diversified business needs.

[0048] In terms of storage integration, the application adopts Ceph distributed storage system, which virtualizes the storage resources of different nodes to realize the integration and unified management of different storage device types. The high scalability and flexibility of Ceph enable the platform to support multiple service types such as block storage, object storage, and file storage, meeting the diversified storage needs of enterprise-level applications. Through the distributed characteristics and high availability mechanisms of Ceph, the fault tolerance and reliability of the storage system are effectively improved, solving the technical problems of traditional storage integration solutions that are difficult to realize elastic expansion and reliability guarantee.

[0049] In terms of network virtualization, the application adopts SDN technology to realize dynamic configuration, isolation, and optimization of network resources, especially suitable for multi-domain architecture and cross-data center network traffic regulation needs. Through SDN, the platform can intelligently schedule and isolate network traffic between different domains, meeting the security and flexibility requirements of different business scenarios. Traditional network virtualization technologies often struggle to cope with complex cross-data center needs, while the SDN solution of the application significantly enhances the applicability and performance of network virtualization, improving the overall utilization efficiency of network resources.

[0050] In terms of system management, the application realizes centralized management and scheduling of cross-domain resources based on OpenStack, with functions such as monitoring, scheduling, and expansion, enabling the platform to provide efficient management capabilities in multi-data center and hybrid cloud environments. In addition, the platform deployment uses containerization technology to abstract virtualization and management services into lightweight container modules, with lightweight and high scalability, supporting flexible resource configuration and rapid deployment. Compared with traditional architectures, the application significantly reduces system complexity, simplifies the deployment process, and improves the scalability and maintenance convenience of the system.

[0051] In summary, the application not only achieves technical breakthroughs in heterogeneous hardware compatibility, resource integration, and management efficiency, but also improves the scalability and deployment convenience of the platform through lightweight and containerized design, providing an efficient and stable solution for the industrial application of multi-domain hyper-converged platforms. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1A lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources provided by the embodiment of the present application is shown in the figure.

[0053] Figure 2 A system structure block diagram of a lightweight multi-domain hyper-converged platform construction system compatible with heterogeneous hardware resources provided by the embodiment of the present application is shown in the figure.

[0054] Figure 3 A multi-domain hyper-converged platform architecture diagram for heterogeneous hardware resources provided by the embodiment of the present application is shown in the figure.

[0055] Figure 4 A container architecture diagram of a lightweight deployment method provided by the embodiment of the present application is shown in the figure.

[0056] Figure 5 A prototype system virtual cloud host application function display diagram provided by the embodiment of the present application is shown in the figure.

[0057] Figure 6 A prototype system resource unified management display diagram provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0059] As shown in the figure, the lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources provided by the embodiment of the present application includes the following steps: Figure 1

[0060] S101, the lightweight multi-domain hyper-converged platform architecture compatible with heterogeneous hardware resources is composed of four modules: computing virtualization, storage virtualization, network virtualization and unified management platform;

[0061] S102, the computing virtualization virtualizes the computing resources of the physical server into virtual machines based on the KVM technology, supports multiple workloads in a heterogeneous hardware environment;

[0062] S103, the storage virtualization integrates the storage resources of different nodes into a global distributed storage pool based on Ceph, supports the integration of heterogeneous storage devices, and provides block storage, object storage and file storage services;

[0063] S104, the network virtualization uses SDN technology to realize dynamic configuration of virtual network, network isolation and network traffic optimization across data centers;

[0064] ​S105, the unified management platform is created based on OpenStack to realize cross-domain resource scheduling, management and monitoring, support resource integration of multi-data center and hybrid cloud architecture;

[0065] S106, the container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management service of the multi-domain hyper-converged cloud platform into lightweight containers through containerization technology.

[0066] The multi-domain hyper-converged platform construction method of the application, around the goal of compatible heterogeneous hardware resources, uses four modules of computing virtualization, storage virtualization, network virtualization and unified management platform to realize resource integration and efficient management. First, in the computing virtualization module, the computing resources of the physical server are virtualized into virtual machines based on KVM technology. KVM virtualization supports multiple workloads under different hardware architectures, enabling the platform to run stably in a heterogeneous hardware environment, while effectively managing and allocating computing resources, improving hardware compatibility and resource utilization.

[0067] Then, in the storage virtualization module, the storage resources of each node are integrated into a global distributed storage pool through Ceph. The Ceph storage system can interface with different types of storage devices, including SSD, HDD, etc., realizing unified management of heterogeneous storage devices. In this way, the platform provides block storage, object storage and file storage services, enabling data to be efficiently switched and shared between different storage types, meeting the data storage needs of different application scenarios and realizing high availability and fault tolerance.

[0068] In the network virtualization module, the application realizes dynamic configuration, isolation and traffic optimization of virtual networks through SDN technology. SDN technology can support cross-data center network configuration, enabling resource interconnection, traffic regulation and isolation between different data centers. In addition, SDN networks can dynamically adjust routing and bandwidth, support load balancing and optimize network traffic, improve network resource utilization and ensure data security isolation, meeting the diverse needs in the multi-domain hyper-converged environment.

[0069] Finally, the unified management platform realizes cross-domain resource scheduling, management and monitoring based on OpenStack, and abstracts the virtualization layer and management service into lightweight containers for deployment through containerization technology. This lightweight design enables the platform to support resource integration of multi-data center and hybrid cloud architecture, while reducing resource overhead. Containerized deployment makes the system easy to extend and migrate, realizing flexible cross-domain resource management and monitoring, suitable for complex application environments of heterogeneous hardware, improving the overall performance and applicability of the platform.

[0070] The computing virtualization provided by the embodiment of the application virtualizes heterogeneous computing resources into virtual machine services based on KVM technology and a self-defined XML virtual machine definition file; user virtual machine instructions are converted into hardware level instruction execution by calling hardware virtualization extensions at the processor bottom layer, and a virtual CPU is provided for each virtual machine, and multiple virtual machines are concurrently run through context switching of the physical CPU and the virtual CPU by the KVM kernel.

[0071] The storage virtualization provided by the embodiment of the application integrates storage devices on multiple service clusters into a global storage pool based on Ceph, supports centralized management and allocation of storage resources, and pools heterogeneous storage resources of the multi-domain service cluster into unified SSD and HDD storage resources by constructing different storage pools and storage layers.

[0072] The network virtualization provided by the embodiment of the application abstracts physical network resources into a virtual network in a software-defined manner, so that multiple virtual machines can share the same underlying network infrastructure, and the network virtualization separates the virtual network from the physical network through virtual switches, virtual routers, tunneling protocols and the like, thereby realizing flexible network configuration and management.

[0073] The unified management platform provided by the embodiment of the application divides the entire cloud platform into multiple domains based on OpenStack, and all the domains are managed through a unified control plane; the scheduler is responsible for selecting suitable computing nodes in different domains to start virtual machines; when a user requests to create a virtual machine, the global controller will pass the request to the scheduler, and the scheduler will select a suitable domain to deploy the virtual machine according to resource states, geographical locations, network delays and the like of different regions.

[0074] The container-based lightweight hyper-converged platform deployment method provided by the embodiment of the application abstracts the virtualization layer and the management service of the lightweight multi-domain hyper-converged cloud platform compatible with heterogeneous hardware resources into lightweight containers through containerization technology, realizes decoupling of the platform and the hardware, reduces performance overhead of the virtualization layer, and improves utilization efficiency of computing and storage resources.

[0075] As shown in Figure 2 The lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources provided by the embodiment of the application includes:

[0076] The computing virtualization module is configured to virtualize computing resources of a physical server into virtual machines based on KVM technology, and support multiple workloads in a heterogeneous hardware environment.

[0077] A storage virtualization module is used for storage virtualization to integrate storage resources of different nodes into a global distributed storage pool based on Ceph, support integration of heterogeneous storage devices, and provide block storage, object storage and file storage services.

[0078] A network virtualization module is used for network virtualization to realize dynamic configuration of a virtual network, network isolation and optimization of network traffic across data centers using SDN technology.

[0079] A unified management platform module is used for unified management platform to create a cross-domain resource scheduling, management and monitoring based on OpenStack, support resource integration of multiple data centers and hybrid cloud architecture; and a container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of a multi-domain hyper-converged cloud platform into lightweight containers through containerization technology.

[0080] Another object of the present application is to provide a computer device comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to enable the processor to perform the steps of the lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources.

[0081] Another object of the present application is to provide a computer readable storage medium storing a computer program, the computer program being executed by a processor to enable the processor to perform the steps of the lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources.

[0082] Another object of the present application is to provide an information data processing terminal for implementing the lightweight multi-domain hyper-converged platform construction system compatible with heterogeneous hardware resources.

[0083] The present application is embodied as follows:

[0084] The lightweight multi-domain hyper-converged platform construction method compatible with heterogeneous hardware resources comprises the following steps:

[0085] (1) Lightweight multi-domain hyper-converged platform architecture compatible with heterogeneous hardware resources

[0086] To solve the problem that the existing hyper-converged platform cannot effectively compatible with heterogeneous hardware resources and is difficult to expand flexibly, a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources is constructed as shown in the accompanying drawings. Figure 2The system architecture of the compatible heterogeneous hardware resource lightweight multi-domain hyper-converged platform shown includes computing virtualization, storage virtualization, and network virtualization. The computing virtualization virtualizes the computing resources of a physical server into virtual machines based on KVM (Kernel-based Virtual Machine) technology, supporting multiple workloads in a heterogeneous hardware environment. The storage virtualization integrates the storage resources of different nodes into a global distributed storage pool based on Ceph, supporting the integration of heterogeneous storage devices (such as HDD, SSD, and NVMe), and providing block storage, object storage, and file storage services. The network virtualization uses SDN technology to realize dynamic configuration of virtual networks, network isolation, and network traffic optimization across data centers. Finally, a unified management platform is created based on OpenStack to realize cross-domain resource scheduling, management, and monitoring, supporting resource integration in multiple data centers and hybrid cloud architectures.

[0087] The computing resource virtualization realizes compatibility of heterogeneous computing resources based on KVM. KVM is a virtual machine monitor built on hardware-assisted virtualization technology. The lowest dependence of KVM on hardware is the hardware virtualization support of the CPU, such as Intel's VT technology and AMD's AMD-V technology. Therefore, KVM can support almost all operating systems that can run on corresponding hardware, such as Linux, Windows, FreeBSD, and MacOS. When a virtual machine creation request is issued, the hardware resource configuration details of the customer virtual machine are defined based on an XML configuration file, and the QEMU user process is called to simulate the hardware devices of the virtual machine. The QEMU process passes the CPU instructions of the virtual machine to KVM, which directly executes these instructions.

[0088] The storage virtualization is realized based on the Ceph distributed storage system, which integrates the storage devices on multiple service clusters into a global storage pool, supporting centralized management and allocation of storage resources. By constructing different storage pools and storage layers, the heterogeneous storage resource pools of multi-domain service clusters are pooled into unified SSD and HDD storage resources, so that user data can be allocated to storage devices with different performance and capacity according to read and write requirements. For example, high access frequency data can be stored in SSD or NVMe devices, while HDD can store infrequently accessed data. By integrating storage devices, creating storage pools, and enabling RBD functions, virtual machine virtual disks can be defined, and the created disk images can be specified as virtual machine disks in the virtual machine xml definition file. The customer virtual machine can ignore hardware differences and use standardized storage resources.

[0089] Network virtualization abstracts physical network resources into virtual networks through software-defined approach, enabling multiple virtual machines to share the same underlying network infrastructure. Network virtualization separates virtual networks from physical networks through technologies such as virtual switches, virtual routers, and tunneling protocols, enabling flexible network configuration and management. The steps to build a multi-domain shared virtual network are as follows:

[0090] First, deploy a virtual switch on each physical node. The virtual switch connects the virtual network interface cards of virtual machines to the network, providing virtual network functions. Then, configure the virtual network in the virtual switch, enabling virtual machines or containers within the same domain to communicate through the virtual network. Second, configure tunneling protocols between multiple domains to establish cross-domain connections between virtual switches. Tunneling protocols encapsulate virtual machine network traffic into tunnel traffic and transmit it from one domain to another, enabling cross-domain communication of virtual networks. Then, deploy an SDN controller to manage all virtual networks in the multi-domain cluster. The SDN controller communicates with the virtual switch in each domain through a southbound interface, dynamically configuring network topology and traffic policies. The SDN controller can dynamically schedule networks based on global network status to ensure optimal path selection for cross-domain traffic. Finally, enable distributed routing in the multi-domain environment to enable direct communication between virtual machines or containers. Through the distributed router, virtual machine network traffic can be directly transmitted to the target domain through a tunnel, reducing network hops and latency.

[0091] The unified management platform divides the entire cloud platform into multiple domains based on OpenStack, with each domain being an independent computing and storage resource area. All domains are managed through a unified control plane (Control Plane). The scheduler is responsible for selecting suitable computing nodes in different domains to start virtual machines. When a user requests to create a virtual machine, the global controller passes the request to the scheduler, which selects the appropriate domain to deploy the virtual machine based on factors such as resource status, geographical location, network latency, and others.

[0092] (2) Container-based lightweight hyper-converged platform deployment method

[0093] By containerization technology, the virtualization layer and management services of the multi-domain hyper-converged cloud platform in (1) are abstracted into lightweight containers, reducing resource overhead, improving resource utilization, and enhancing system flexibility, scalability, and operational efficiency. The specific container structure is as follows: Figure 4The container is used to run the KVM service first, so that the virtual machine management becomes more lightweight and flexible, and the containerized KVM instance reduces the resource occupation of the traditional virtualization layer, because it is not necessary to create an independent control virtual machine (Control VM) for each node. Second, the distributed storage service is implemented using the containerized Ceph, which supports elastic expansion and automatic management. The components of Ceph are containerized, and are deployed and managed through a container orchestration tool. One or more Ceph containers can be run on each physical node to manage the local storage device. Then the SDN controller and virtual switch are containerized and deployed to ensure that the network virtualization function is independent of the hardware and easy to expand. Third, the OpenStack components are deployed and managed using the containerization tool. Each OpenStack service runs in a separate container to provide a management interface for computing, storage and network resources. Finally, the Kubernetes node is deployed on each physical node to manage the containerized virtualization, storage, network and management services. Kubernetes is responsible for scheduling these containers to ensure load balancing and high availability.

[0094] Through the containerization technology and the scheduling capability of Kubernetes, the platform is decoupled from the hardware. Administrators can flexibly select hardware vendors and configurations according to business needs, and are no longer limited by the hardware integration solutions of specific manufacturers. Kubernetes supports dynamic expansion and load balancing, and can automatically expand node and container instances according to resource requirements, solving the problem of limited hardware expansion of traditional hyper-converged platforms. In addition, the container technology is more lightweight than the traditional virtual machine, and it is not necessary to run a complete operating system instance for each physical node. Through the containerized KVM virtualization layer, the performance overhead of the virtualization layer is reduced, and the utilization efficiency of computing and storage resources is improved.

[0095] The related evidence of the technical effects obtained by the embodiments of the application.

[0096] Figure 5 The virtual cloud host application module provided by the prototype system of the application sends a user request to the virtualization manager of the application, and the virtualization manager creates a virtual machine resource meeting the requirements according to the user request.

[0097] The multi-domain heterogeneous cloud collaboration module provided by the prototype system of the application proposes and implements a cloud computing resource management architecture for multi-cloud collaboration, realizes cross-domain collaborative management of computing and storage resources, data sharing, supports cross-domain collaborative computing, meets the basic needs of distributed application systems, and improves real-time performance and scalability.

[0098] Figure 7 is a resource unified management module provided by the prototype system of the present application, the unified management platform is based on dividing the whole cloud platform into multiple domains, each domain is an independent computing and storage resource area, all domains are managed through a unified control plane.

[0099] It should be noted that the embodiments of the present application can be realized by hardware, software or a combination of software and hardware. The hardware part can be realized by special logic; the software part can be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or a specially designed hardware. Those skilled in the art can understand that the above-mentioned devices and methods can be realized by computer executable instructions and / or included in processor control codes, such as carrier media, such as magnetic disk, CD or DVD-ROM, programmable memory, such as read-only memory (firmware), or data carrier, such as optical or electronic signal carrier. The devices of the present application and their modules can be realized by hardware circuit, such as very large scale integrated circuit or gate array, semiconductor, such as logic chip, transistor, etc., or programmable hardware device, such as field programmable gate array, programmable logic device, etc., can also be realized by software executed by various types of processors, or by a combination of the above-mentioned hardware circuit and software, such as firmware.

[0100] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this, any modification, equivalent replacement and improvement made by those skilled in the art within the technical range disclosed by the present application, as long as it is within the spirit and principle of the present application, should be covered within the protection scope of the present application.

Claims

1. A method for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources, characterized in that, The method comprises the following steps: Step 1, the lightweight multi-domain hyper-converged platform architecture compatible with heterogeneous hardware resources is composed of four parts: computing virtualization, storage virtualization, network virtualization and unified management platform; Step 2, the computing virtualization virtualizes the computing resources of the physical server into virtual machines based on the KVM technology, and supports multiple workloads in a heterogeneous hardware environment; Step 3, the storage virtualization integrates the storage resources of different nodes into a global distributed storage pool based on Ceph, supports the integration of heterogeneous storage devices, and provides block storage, object storage and file storage services; Step 4, the network virtualization uses SDN technology to realize the dynamic configuration, network isolation and network traffic optimization of virtual networks across data centers; Step 5, the unified management platform is based on OpenStack to create a cross-domain resource scheduling, management and monitoring, and supports the integration of resources in multiple data centers and hybrid cloud architecture; Step 6, the container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of the multi-domain hyper-converged cloud platform into lightweight containers through containerization technology; The computing virtualization virtualizes heterogeneous computing resources into virtual machine services based on KVM technology and custom XML virtual machine definition files; by calling the hardware virtualization extension at the processor bottom layer, the user virtual machine instruction is converted into a hardware level instruction for execution, and a virtual CPU is provided for each virtual machine, and the KVM kernel is used to switch the context of the physical CPU and the virtual CPU to realize the concurrent running of multiple virtual machines; The storage virtualization integrates the storage devices on multiple service clusters into a global storage pool based on Ceph, supports centralized management and allocation of storage resources, and pools the heterogeneous storage resources of the multi-domain service cluster into unified SSD and HDD storage resources by constructing different storage pools and storage layers.

2. The method of claim 1, wherein the method further comprises: The network virtualization abstracts physical network resources into virtual networks in a software-defined manner, enabling multiple virtual machines to share the same underlying network infrastructure. Network virtualization separates virtual networks from physical networks through virtual switches, virtual routers, tunneling protocols, and other technologies, enabling flexible network configuration and management.

3. The method of claim 1, wherein the method further comprises: determining a plurality of hardware resources of the plurality of hardware resources that are compatible with the plurality of hardware resources of the at least one other computing device; and configuring the plurality of hardware resources of the plurality of hardware resources that are compatible with the plurality of hardware resources of the at least one other computing device. The unified management platform divides the entire cloud platform into multiple domains based on OpenStack, and all domains are managed through a unified control plane; the scheduler is responsible for selecting suitable computing nodes in different domains to start virtual machines; when a user requests to create a virtual machine, the global controller passes the request to the scheduler, which selects the appropriate domain to deploy the virtual machine based on factors such as resource status, geographic location, network latency, etc.

4. The method of claim 1, wherein the method further comprises: determining a plurality of hardware resources of the plurality of hardware resources that are compatible with the plurality of hardware resources of the at least one other computing device; and configuring the plurality of hardware resources of the plurality of hardware resources that are compatible with the plurality of hardware resources of the at least one other computing device. The container-based lightweight hyper-converged platform deployment method abstracts the virtualization layer and management services of the lightweight multi-domain hyper-converged cloud platform compatible with heterogeneous hardware resources into lightweight containers through containerization technology, decouples the platform from the hardware, reduces the performance overhead of the virtualization layer, and improves the utilization efficiency of computing and storage resources.

5. A system for constructing a lightweight multi-domain hyper-converged platform of compatible heterogeneous hardware resources according to the method of any one of claims 1-4, characterized in that, The lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources comprises: A computing virtualization module is configured to virtualize computing resources of a physical server into virtual machines based on KVM technology, and support multiple workloads in a heterogeneous hardware environment; A storage virtualization module is configured to integrate storage resources of different nodes into a global distributed storage pool based on Ceph, support integration of heterogeneous storage devices, and provide block storage, object storage and file storage services; A network virtualization module is configured to use SDN technology to realize dynamic configuration of virtual networks, network isolation and optimization of network traffic across data centers; A unified management platform module is configured to create a cross-domain resource scheduling, management and monitoring based on OpenStack, support resource integration of multiple data centers and hybrid cloud architecture, and deploy a container-based lightweight hyper-converged platform by abstracting virtualization layers and management services of a multi-domain hyper-converged cloud platform into lightweight containers through containerization technology.

6. A computer device, comprising: The computer device comprises a memory and a processor, and the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources according to any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources according to any one of claims 1-4.

8. An information data processing terminal, characterized by The information data processing terminal is configured to implement the system for constructing a lightweight multi-domain hyper-converged platform compatible with heterogeneous hardware resources according to claim 5.

Images