Method and apparatus for cross-platform heterogeneous management of compute nodes

Abstract

The application provides a method and device for cross-platform heterogeneous management of a computing node, wherein the method comprises: intercepting a computing node management instruction issued by a virtualization management platform module; negotiating a chip type and the like with a computing management module in the computing node by using a chip agent module, so as to be compatible with different platform chips; negotiating an operating system type and required resources with the computing management module by using an operating system agent module, so as to be compatible with different operating systems; negotiating an interface message type with the computing management module by using an interface agent module, so as to be compatible with different interfaces; generating an operation instruction set corresponding to the chip type, the operating system type and the interface message type of the computing node of the computing node management instruction and providing the required resources of the computing node; issuing the operation instruction set to the computing management module of the computing node, so as to send the operation instruction set to a virtualization layer thereof and start a virtual machine. Through the above scheme, a plurality of chip platforms can be managed by the same management platform.

Description

Technical Field

[0001] This invention relates to the field of cloud computing technology, and in particular to a method and apparatus for cross-platform heterogeneous management of computing nodes. Background Technology

[0002] Most mainstream cloud computing systems are based on the x86 platform. This platform has strict distinctions and limitations regarding CPU type, instruction set, CPU characteristics, virtual machine startup parameters, device definitions, boot images, operating systems, parameter passing methods, and formats. While the system supports the x86 platform well, it is incompatible with platforms other than x86, resulting in significant shortcomings in compatibility and heterogeneity.

[0003] The existing management platform is incompatible with domestically produced chips (such as Phytium, Kunpeng, Shenwei, Loongson, etc.) and domestically produced operating systems (such as Kylin, Deepin, UOS (Unified Operating System), Puhua, etc.). The CPU instruction sets and characteristics of various domestic chip platforms differ significantly, requiring adaptation for each specific chip platform.

[0004] For example, Shenwei chips require a dedicated boot image to start virtual machines; Phytium and Kunpeng chips require dedicated firmware to boot virtual machines; and Hygon chips require a specific chip type to start virtual machines. The communication methods between compute nodes and the top-level management module also differ. Complex application scenarios are difficult to manage holistically and heterogeneously within traditional virtualization management platforms, leading to significant R&D challenges and a heavy operational burden. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and apparatus for cross-platform heterogeneous management of computing nodes, so as to realize heterogeneous management of multiple chip platforms by the same management platform.

[0006] To achieve the above objectives, the present invention employs the following solution:

[0007] According to one aspect of the present invention, a method for cross-platform heterogeneous management of computing nodes is provided, comprising:

[0008] The virtualization management platform module is used to issue management commands for computing nodes;

[0009] Intercept the computing node management commands;

[0010] The chip proxy module negotiates chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to ensure compatibility with chips from various platforms. The operating system proxy module negotiates operating system type and required resources with the computing management module in the computing node to ensure compatibility with various operating systems. The interface proxy module negotiates interface message type with the computing management module in the computing node to ensure compatibility with various interface data formats. The computing node management instructions are generated according to the chip type, operating system type, and interface message type of the computing node, and the required resources for the computing node are provided.

[0011] The operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node is sent to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

[0012] In some embodiments, a chip proxy module negotiates chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to ensure compatibility with chips from various platforms. An operating system proxy module negotiates operating system type and required resources with the computing management module in the computing node to ensure compatibility with various operating systems. An interface proxy module negotiates interface message types with the computing management module in the computing node to ensure compatibility with various interface data formats. The system generates the computing node management instructions corresponding to the chip type, operating system type, and interface message type of the computing node and provides the resources required by the computing node, including:

[0013] The chip proxy module negotiates chip type, chip instruction set and virtual machine control parameters with the computing management module in the computing node to be compatible with chips of various different platforms, and obtains the chip type and related information of the computing node.

[0014] The operating system agent module negotiates the operating system type and required resources with the computing management module in the computing node to ensure compatibility with multiple different operating systems, thereby obtaining the operating system type of the computing node and providing the required resources.

[0015] The interface message type of the compute node is negotiated with the compute management module in the compute node by the interface proxy module to ensure compatibility with data formats of various interfaces.

[0016] Based on the chip type and related information of the computing node, the operating system type of the computing node, and the interface message type of the computing node, an operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node is generated, and the resources required by the computing node are provided.

[0017] In some embodiments, the chip used by the compute node is an Intel / AMD chip, and the compute node management instructions correspond to the x86 instruction set based on the compute node's chip type, operating system type, and interface message type; or...

[0018] The compute node uses a Shenwei chip, and the compute node management instructions correspond to the alpha instruction set based on the compute node's chip type, operating system type, and interface message type; or,

[0019] The computing nodes use either Phytium or Kunpeng chips, and the computing node management instructions correspond to the chip type, operating system type, and interface message type of the computing node using the armv8 instruction set; or,

[0020] The computing nodes use Loongson chips, and the computing node management instructions correspond to the chip type, operating system type, and interface message type of the computing node in the MIPS instruction set.

[0021] In some embodiments, the operating system used by the compute node is UOS, CENTOS, Kylin V10, or deepin.

[0022] In some embodiments, the interface message type used by the computing node is an Inter / amd interface, Phytium interface, Kunpeng interface, Loongson interface, Shenwei interface, or Hygon interface.

[0023] In some embodiments, a chip proxy module negotiates chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to ensure compatibility with chips from various platforms. An operating system proxy module negotiates operating system type and required resources with the computing management module in the computing node to ensure compatibility with various operating systems. An interface proxy module negotiates interface message types with the computing management module in the computing node to ensure compatibility with various interface data formats. The system generates the computing node management instructions corresponding to the chip type, operating system type, and interface message type of the computing node and provides the resources required by the computing node, including:

[0024] The chip proxy module negotiates chip type, chip instruction set and virtual machine control parameters with the computing management module in the computing node to be compatible with chips from various platforms, such as negotiating from Aarch64 to Kunpeng or Phytium chips, from Alpha to Shenwei chips, from MIPS to Loongson chips, or from X86 to Intel / AMD chips or Hygon chips.

[0025] After negotiating the chip type, chip instruction set, and virtual machine control parameters, the operating system agent module negotiates the operating system type and required resources with the computing management module in the computing node to ensure compatibility with multiple different operating systems and to negotiate from XML or JSON to RPC.

[0026] After negotiating the operating system type and required resources, the interface proxy module negotiates the interface message type with the computing management module in the computing node to ensure compatibility with various interface data formats. This allows for negotiation between Kylin, UOS, CentOS, Ubuntu, Deepin, or i-soft and the VM virtual machine. The resulting computing node management instructions correspond to the chip type, operating system type, and interface message type of the computing node, and provide the resources required by the computing node.

[0027] According to another aspect of the present invention, a system for cross-platform heterogeneous management of computing nodes is provided, applicable to the methods described in any of the above embodiments, the system comprising: a cloud proxy module; the cloud proxy module comprising: a chip proxy module, an operating system proxy module, and an interface proxy module;

[0028] The cloud proxy module is used to intercept the computing node management instructions issued by the virtualization management platform module, and negotiate the chip type, chip instruction set and virtual machine control parameters with the computing management module in the computing node using the chip proxy module to ensure compatibility with chips from multiple different platforms. It also negotiates the operating system type and required resources with the computing management module in the computing node using the operating system proxy module to ensure compatibility with multiple different operating systems. Finally, it negotiates the interface message type with the computing management module in the computing node using the interface proxy module to ensure compatibility with data formats from multiple different interfaces. The module generates the operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instructions and provides the resources required by the computing node.

[0029] The cloud proxy module is also used to send the operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instruction to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

[0030] In some embodiments, the system further includes: the virtualization management platform module, used to issue computing node management instructions.

[0031] According to another aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in any of the above embodiments.

[0032] According to another aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0033] The present invention relates to a method, system, computer device, and computer-readable storage medium for cross-platform heterogeneous management of computing nodes. The cloud proxy module acts as an intermediary, enabling the management of multiple different types of management nodes using a single management platform within a virtualization system. This allows for the unified management of multiple complex and incompatible domestic chip platforms and heterogeneous x86 platforms. The centralized cloud proxy module in the cloud computing system manages resources through a unified system, reducing the difficulty of research and development and maintenance, and saving human resources. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0035] Figure 1 This is a flowchart illustrating a method for cross-platform heterogeneous management of computing nodes according to an embodiment of the present invention;

[0036] Figure 2 and Figure 3 This is a schematic diagram of the framework structure of a cloud management platform in an existing virtualization system without a cloud agent.

[0037] Figure 4 This is a schematic diagram of the system operation architecture after introducing a cloud agent in one embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the framework structure of a cloud management platform after adding a cloud agent according to an embodiment of the present invention;

[0039] Figure 6 This is a schematic diagram of the overall framework structure of the virtualization system after introducing a cloud agent in a specific embodiment of the present invention;

[0040] Figure 7This is a schematic diagram of the framework structure of a virtualization system after introducing a chip proxy module in a specific embodiment of the present invention;

[0041] Figure 8 This is a schematic diagram of the framework structure of a virtualization system after introducing a chip proxy module and an operating system proxy module in a specific embodiment of the present invention;

[0042] Figure 9 This is a schematic diagram of the framework structure of a virtualization system after introducing a chip proxy module, an operating system proxy module, and an interface proxy module in a specific embodiment of the present invention.

[0043] Figure 10 This is a schematic diagram of the system operation framework in a specific embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0045] Currently, virtualization systems can only manage a single computing node and cannot heterogeneously manage multiple chip platforms. To address this limitation, this invention provides a cloud proxy module that can proxy instructions issued by the management platform to computing nodes, intelligently determine the chip type and operating system of the computing node, and intelligently negotiate the interface data format. This enables a single management platform to heterogeneously manage multiple chip platforms.

[0046] Figure 1 This is a flowchart illustrating a method for cross-platform heterogeneous management of computing nodes according to an embodiment of the present invention. The method for cross-platform heterogeneous management of computing nodes in this embodiment may include the following steps S110 to S140.

[0047] The specific implementation methods of steps S110 to S140 will be described in detail below.

[0048] Step S110: Issue computing node management commands using the virtualization management platform module.

[0049] In step S110, the virtualization management platform module can be referred to as the management platform, and can be an existing virtualization management platform.

[0050] Step S120: Intercept the computing node management command.

[0051] In step S120, the computing node management instructions issued by the virtualization management platform module do not directly reach the computing node, but are intercepted and sent to the agent module.

[0052] Step S130: The chip proxy module negotiates the chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to ensure compatibility with chips on various platforms. The operating system proxy module negotiates the operating system type and required resources with the computing management module in the computing node to ensure compatibility with various operating systems. The interface proxy module negotiates the interface message type with the computing management module in the computing node to ensure compatibility with various interface data formats. The computing node management instructions are generated according to the chip type, operating system type, and interface message type of the computing node, and the required resources for the computing node are provided.

[0053] In step S130, the chips from various platforms can be categorized into x86 chips and non-x86 chips. Non-x86 chips may include Loongson, Shenwei, Phytium, and other chips. The various interfaces may include those involved in the chip proxy module, such as the Intel / AMD interface, Phytium interface, Kunpeng interface, Loongson interface, Shenwei interface, Hygon interface, etc., and may also include those involved in the operating system proxy module, such as the Kylin V10 operating system interface, UOS operating system interface, Deepin operating system interface, Puhua operating system interface, etc. The various operating systems may include the UOS operating system, CENTOS system, etc.

[0054] In some embodiments, step S130 above, namely, negotiating chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node using the chip proxy module to ensure compatibility with chips from multiple different platforms, negotiating operating system type and required resources with the computing management module in the computing node using the operating system proxy module to ensure compatibility with multiple different operating systems, negotiating interface message type with the computing management module in the computing node using the interface proxy module to ensure compatibility with data formats from multiple different interfaces, generating the computing node management instructions corresponding to the chip type, operating system type, and interface message type of the computing node, and providing the resources required by the computing node, may specifically include the following steps:

[0055] S1311 utilizes the chip proxy module to negotiate the chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to ensure compatibility with chips from various platforms and obtain the chip type and related information of the computing node.

[0056] S1312, using the operating system agent module to negotiate the operating system type and required resources with the computing management module in the computing node, so as to be compatible with multiple different operating systems, obtain the operating system type of the computing node and provide the required resources;

[0057] S1313, the interface proxy module negotiates the interface message type with the computing management module in the computing node to be compatible with the data formats of various interfaces, and obtains the interface message type of the computing node.

[0058] S1314, Based on the chip type and related information of the computing node, the operating system type of the computing node, and the interface message type of the computing node, generate an operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node management instruction, and provide the resources required by the computing node.

[0059] In other embodiments, step S130 above, namely, negotiating chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node using the chip proxy module to ensure compatibility with chips from multiple different platforms, negotiating operating system type and required resources with the computing management module in the computing node using the operating system proxy module to ensure compatibility with multiple different operating systems, negotiating interface message type with the computing management module in the computing node using the interface proxy module to ensure compatibility with multiple different interface data formats, generating the computing node management instructions corresponding to the computing node's chip type, operating system type, and interface message type, and providing the computing node with the required resources, may specifically include the following steps:

[0060] S1321 uses the chip proxy module to negotiate chip type, chip instruction set and virtual machine control parameters with the computing management module in the computing node to be compatible with chips of various different platforms, such as negotiating from Aarch64 to Kunpeng chip or Phytium chip, or from Alpha to Shenwei chip, or from MIPS to Loongson chip, or from X86 to Intel / AMD chip or Hygon chip.

[0061] S1322, after negotiating the chip type, chip instruction set and virtual machine control parameters, uses the operating system agent module to negotiate the operating system type and required resources with the computing management module in the computing node to be compatible with multiple different operating systems, and to negotiate from XML or JSON to RPC;

[0062] S1323, after negotiating the operating system type and required resources, the interface proxy module negotiates the interface message type with the computing management module in the computing node to be compatible with various different interface data formats, so as to negotiate from Kylin, UOS, CentOS, Ubuntu, Deepin or i-soft to the VM virtual machine, generate the computing node management instructions corresponding to the chip type, operating system type and interface message type of the computing node, and provide the resources required by the computing node.

[0063] Step S140: The operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instruction is sent to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

[0064] In some embodiments, the chip may be a variety of different chips.

[0065] For example, the chip used in the computing node can be an Intel / AMD chip, and the operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node management instructions can be the x86 instruction set.

[0066] For example, the chip used in the computing node can be a Shenwei chip, and the operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node management instructions can be the Alpha instruction set.

[0067] For example, the chip used in the computing node can be a Phytium chip or a Kunpeng chip, and the operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instructions can be the armv8 instruction set.

[0068] For example, the chip used in the computing node can be a Loongson chip, and the set of operation instructions for the computing node management instructions corresponding to the chip type, operating system type and interface message type of the computing node can be the MIPS instruction set.

[0069] In some embodiments, the operating system can be various operating systems, for example, the operating system used by the computing node can be UOS, CENTOS, Kylin V10, or Deepin.

[0070] In some embodiments, the interface type can be various interface types. For example, the interface message type used by the computing node can be the Inter / amd interface, Phytium interface, Kunpeng interface, Loongson interface, Shenwei interface, or Hygon interface.

[0071] Based on and Figure 1 The present application also provides a system for cross-platform heterogeneous computing node management, which shares the same inventive concept as the method for cross-platform heterogeneous computing node management. As described in the following embodiments, since the principle of this system for cross-platform heterogeneous computing node management is similar to that of the method, the implementation of this system can refer to the implementation of the method for cross-platform heterogeneous computing node management; repeated details will not be elaborated further.

[0072] One embodiment of a system for cross-platform heterogeneous management of computing nodes is applicable to the method described in any of the above embodiments. The system includes a cloud proxy module; the cloud proxy module includes a chip proxy module, an operating system proxy module, and an interface proxy module.

[0073] The cloud proxy module is used to intercept the computing node management instructions issued by the virtualization management platform module, and negotiate the chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node using the chip proxy module to ensure compatibility with chips from various platforms. It also negotiates the operating system type and required resources with the computing management module in the computing node using the operating system proxy module to ensure compatibility with various operating systems. Furthermore, it negotiates the interface message type with the computing management module in the computing node to ensure compatibility with data formats from various interfaces. Finally, it generates the operation instruction set corresponding to the computing node management instructions based on the chip type, operating system type, and interface message type of the computing node, and provides the resources required by the computing node.

[0074] The cloud proxy module is also used to send the operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instruction to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

[0075] Furthermore, the system may also include: the virtualization management platform module, used to issue computing node management instructions.

[0076] In addition, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in any of the above embodiments.

[0077] This invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0078] This embodiment describes a method, system, computer equipment, and computer-readable storage medium for cross-platform heterogeneous management of computing nodes. The cloud proxy module acts as an intermediary, enabling the management of multiple different types of management nodes using a single management platform within a virtualization system. This allows for the unified management of multiple, previously complex and incompatible, domestically produced chip platforms and heterogeneous x86 platforms. The centralized cloud proxy module in the cloud computing system manages resources through a unified system, reducing the difficulty of research and development and maintenance, and saving human resources.

[0079] This approach overcomes the drawbacks of traditional cloud computing systems where different types of CPUs had to be placed in separate virtualization systems. It also eliminates the need to configure multiple sets of storage, network, and server resources, significantly reducing unnecessary resource waste and improving resource utilization. During deployment, the cloud agent shields users from differences in CPU platforms, operating systems, and interface parameter types, eliminating the need for separate configuration of individual computing nodes. Furthermore, the cloud agent module has low coupling with other modules, operating independently of each other except for interface interactions, simplifying system deployment and maintenance processes.

[0080] The above method will be described below with reference to a specific embodiment. However, it is worth noting that this specific embodiment is only for better illustration of this application and does not constitute an improper limitation of this application.

[0081] Figure 2 and Figure 3 This is a schematic diagram of the framework structure of a cloud management platform in an existing virtualization system without a cloud agent. See [link / reference]. Figure 2 In the existing system architecture, various management platforms correspond to their respective computing node chip platforms, see [link to relevant documentation]. Figure 3 Each management platform has its own computing management module on its corresponding computing node. Figure 4 This is a schematic diagram of the system operation architecture after introducing a cloud agent in one embodiment of the present invention. Figure 4 In one embodiment, a cloud proxy module is introduced into the system. The cloud proxy module may include a chip proxy module, an operating system proxy module, and an interface proxy module. Figure 5 This is a schematic diagram of the framework structure after adding a cloud agent to the cloud management platform according to an embodiment of the present invention. See also Figure 5 The cloud proxy module can connect to computing nodes on various platforms.

[0082] (1) Chip proxy module:

[0083] Each chip employs a different hardware virtualization method, and its corresponding chip instruction set and emulated CPU type also differ. The principle of the chip proxy module is to shield the CPU type, chip instructions, and virtual machine control parameters within the virtualization system. For example, Intel / AMD chips use the x86 instruction set, while Shenwei chips use the Alpha instruction set; the same management platform cannot be compatible with different chip instruction sets.

[0084] The chip proxy module, in collaboration with the compute node management module, intelligently negotiates chip types, chip instruction sets, virtual machine control parameters, and other relevant information. During the negotiation process, it automatically ensures compatibility with both domestically produced and x86 chips, generating corresponding operation instruction sets. This allows for precise control of each compute node in the system. This module is designed with excellent compatibility and scalability, facilitating upgrades and maintenance during use.

[0085] See Figure 7 The interfaces involved in the chip proxy module include: Inter / amd interface (x86), Phytium interface (armv8), Kunpeng interface (armv8), Loongson interface (mips), Shenwei interface (alpha), Hygon interface (x86), etc.

[0086] The cloud agent's architecture is highly scalable and flexible, allowing for the addition of new chip platforms as needed.

[0087] (2) Operating system agent module:

[0088] Each operating system uses a different virtualization method, resulting in different virtual machine boot parameters, emulated devices, and required firmware. For example, UOS is based on Debian and uses apt (a Linux management tool) for package management, while CENTOS (a community enterprise operating system) is based on Red Hat and uses rpm (Red Hat package manager) for package management. The same management platform is not compatible with commands from different operating systems.

[0089] The operating system agent module shields related instructions and intelligently negotiates the operating system type and required resources in collaboration with the compute node management module. During the negotiation process, it automatically ensures compatibility with the corresponding operating system, generates appropriate operation instructions, and provides the necessary resources. This module is designed with excellent compatibility and scalability, facilitating upgrades and maintenance during use.

[0090] See Figure 8 The interfaces involved in the operating system agent module may include: Kylin V10 operating system interface, UOS operating system interface, Deepin operating system interface, Puhua operating system interface, etc.

[0091] (3) Interface conversion module (interface proxy module):

[0092] This module is primarily designed for the computing management modules of different computing nodes. For the two modules to communicate, a unified data format is essential; otherwise, communication errors will occur, and the system will malfunction.

[0093] This module masks inconsistencies in data formats between interfaces. By negotiating data interface types with the computing management module, it provides a consistent data format, ensuring normal data communication and compatibility between modules. The module is designed with excellent compatibility and scalability in mind, facilitating upgrades and maintenance during use.

[0094] See Figure 9 The interfaces involved in the interface proxy module may include: JSONRPC module, XMLRPC module, etc.

[0095] See Figure 10 The processing procedure includes the following steps:

[0096] S1. The virtualization management platform can simultaneously manage computing nodes with multiple chip types, multiple operating systems, and multiple message communication formats;

[0097] S2. When the management platform issues a command, the cloud agent module will intercept the command and negotiate the chip type, operating system type and interface message type with the computing management module in the computing node;

[0098] S3. Based on the negotiation results, the cloud agent module generates operation instructions and provides the resources required by the computing node according to the chip type, operating system type and interface message type, and sends them to the computing management module.

[0099] S4. The compute management module receives commands and parameters and sends them to the virtualization layer to start virtual machines and manage compute nodes.

[0100] In this embodiment, the cloud proxy module acts as an intermediary, shielding the various differences in communication between the front and back ends of the virtualization system. By negotiating chip type, operating system type, and interface message type with the computing nodes through the management platform, it intelligently generates command and instruction sets consistent with the computing nodes. This enables the use of a single management platform to manage multiple different types of management nodes in the cloud computing system, reducing system redundancy and lowering production costs.

[0101] This embodiment manages multiple domestically produced chip platforms and heterogeneous x86 platforms that were originally complex and incompatible, achieving cross-platform management and diversified operations for domestically produced computing nodes. In this embodiment, the cloud proxy module acts as an intermediary, enabling the management of multiple different types of management nodes using a single management platform within the virtualization system. It can manage multiple domestically produced chip platforms and heterogeneous x86 platforms that were originally complex and incompatible. The centralized cloud proxy module in the cloud computing system manages resources through a unified system, reducing the difficulty of R&D and maintenance, saving human resources, and promoting the development of virtualization systems.

[0102] In the description of this specification, the references to "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of the present invention, and the order of steps is not limited and may be adjusted as needed.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cross-platform heterogeneous management of computing nodes, characterized in that, include: The virtualization management platform module is used to issue management commands for computing nodes; Intercept the computing node management commands; The chip proxy module negotiates chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node to negotiate from AArch64 to Kunpeng or Phytium chips, from Alpha to Shenwei chips, from MIPS to Loongson chips, or from X86 to Intel / AMD or Hygon chips, thus ensuring compatibility with chips from multiple different platforms. The operating system proxy module negotiates operating system type and required resources with the computing management module in the computing node to negotiate from XML or JSON to RPC, thus ensuring compatibility with multiple different operating systems. The interface proxy module negotiates interface message type with the computing management module in the computing node to negotiate from Kylin, UOS, CentOS, Ubuntu, Deepin, or i-soft to the VM, thus ensuring compatibility with multiple different interface data formats. The computing node management instructions are generated according to the chip type, operating system type, and interface message type of the computing node, and the required resources for the computing node are provided. The operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node is sent to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

2. The method for cross-platform heterogeneous management of computing nodes as described in claim 1, characterized in that, The chip proxy module negotiates chip type, chip instruction set, and virtual machine control parameters with the compute management module in the compute node to ensure compatibility with chips from various platforms. The operating system proxy module negotiates operating system type and required resources with the compute management module to ensure compatibility with various operating systems. The interface proxy module negotiates interface message types with the compute management module to ensure compatibility with various interface data formats. The compute node management instructions are generated according to the chip type, operating system type, and interface message type of the compute node, and the required resources for the compute node are provided. The chip proxy module negotiates chip type, chip instruction set and virtual machine control parameters with the computing management module in the computing node to be compatible with chips of various different platforms, and obtains the chip type and related information of the computing node. The operating system agent module negotiates the operating system type and required resources with the computing management module in the computing node to ensure compatibility with multiple different operating systems, thereby obtaining the operating system type of the computing node and providing the required resources. The interface message type of the compute node is negotiated with the compute management module in the compute node by the interface proxy module to ensure compatibility with data formats of various interfaces. Based on the chip type and related information of the computing node, the operating system type of the computing node, and the interface message type of the computing node, an operation instruction set corresponding to the chip type, operating system type, and interface message type of the computing node is generated, and the resources required by the computing node are provided.

3. The method for cross-platform heterogeneous management of computing nodes as described in claim 1, characterized in that, The chips used in the computing nodes are Intel / AMD chips, and the operation instruction set of the computing node management instructions corresponding to the chip type, operating system type and interface message type of the computing node is the x86 instruction set; or, The compute node uses a Shenwei chip, and the compute node management instructions correspond to the alpha instruction set based on the compute node's chip type, operating system type, and interface message type; or, The chips used in the computing nodes are Phytium chips or Kunpeng chips, and the operation instruction set of the computing node management instructions corresponding to the chip type, operating system type and interface message type of the computing node is the armv8 instruction set; or, The computing nodes use Loongson chips, and the computing node management instructions correspond to the chip type, operating system type, and interface message type of the computing node in the MIPS instruction set.

4. The method for cross-platform heterogeneous management of computing nodes as described in claim 1, characterized in that, The operating systems used by the compute nodes are UOS, CENTOS, Kylin V10, or deepin.

5. The method for cross-platform heterogeneous management of computing nodes as described in claim 1, characterized in that, The interface message types used by the compute nodes are Inter / amd interface, Phytium interface, Kunpeng interface, Loongson interface, Shenwei interface, or Hygon interface.

6. A system for cross-platform heterogeneous management of computing nodes, characterized in that, The system applicable to the method as described in any one of claims 1 to 5, wherein the system comprises: a cloud proxy module; the cloud proxy module comprises: a chip proxy module, an operating system proxy module, and an interface proxy module; The cloud proxy module is used to intercept the computing node management instructions issued by the virtualization management platform module, and use the chip proxy module to negotiate the chip type, chip instruction set, and virtual machine control parameters with the computing management module in the computing node, so as to negotiate from AArch64 to Kunpeng or Phytium chips, or from Alpha to Shenwei chips, or from MIPS to Loongson chips, or from X86 to Intel / AMD chips or Hygon chips, thereby achieving compatibility with chips from multiple different platforms. The operating system proxy module is used to negotiate the operating system type and required resources with the computing management module in the computing node, so as to negotiate from XML or JSON to RPC, thereby achieving compatibility with multiple different operating systems. The interface proxy module is used to negotiate the interface message type with the computing management module in the computing node, so as to negotiate from Kylin, UOS, CentOS, Ubuntu, Deepin, or i-soft to the VM, thereby achieving compatibility with multiple different interface data formats. The computing node management instructions are generated according to the chip type, operating system type, and interface message type of the computing node, and the required resources are provided to the computing node. The cloud proxy module is also used to send the operation instruction set corresponding to the chip type, operating system type and interface message type of the computing node management instruction to the computing management module of the computing node, so that the computing management module sends the commands and parameters in the operation instruction set to its virtualization layer to start its virtual machine and manage its computing node to perform computing processing using the resources provided by the computing node.

7. The system for cross-platform heterogeneous management of computing nodes as described in claim 6, characterized in that, The system also includes: the virtualization management platform module, used to issue computing node management instructions.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images