A cloud host creation method, device, equipment and readable storage medium

Abstract

The present application discloses a cloud host creation method, device, equipment and readable storage medium. The method disclosed in the present application includes: if a creation request of a target cloud host is received, the target cloud host is created, and the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node; if the virtual PCI device corresponding to the target numa node is unavailable, and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured to the target cloud host; wherein the target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes, thereby realizing that when the numa node corresponding to the cloud host has no available virtual PCI device, the cloud host is configured with a virtual PCI device. Correspondingly, a cloud host creation device, equipment and readable storage medium provided by the present application also have the above-mentioned technical effects.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a cloud host creation method, device, equipment and readable storage medium. Background Art

[0002] Generally, the physical PCI (Peripheral Component Interconnect) device (such as a physical network card) on the host can be virtualized into multiple virtual PCI devices, and the physical CPU in the host can be divided into multiple numa nodes using NUMA (Non Uniform Memory Access Architecture) technology, and each numa node includes at least one physical CPU (Central Processing Unit). Different numa nodes can correspond to different virtual PCI devices. In this way, if the virtual CPU of a cloud host is bound to the physical CPU in a numa node, then the cloud host can only use the virtual PCI device corresponding to the numa node. However, if all the virtual PCI devices corresponding to the numa node are used, the current cloud host cannot be configured with available virtual PCI devices, which will cause the cloud host configuration to fail.

[0003] Therefore, when the numa node corresponding to the cloud host has no available virtual PCI device, how to configure the virtual PCI device for the cloud host is a problem that technicians in this field need to solve. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a cloud host creation method, apparatus, device and readable storage medium to implement how to configure a virtual PCI device for a cloud host when the numa node corresponding to the cloud host has no available virtual PCI device. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a cloud host creation method, comprising:

[0006] If a request to create a target cloud host is received, the target cloud host is created, and the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node;

[0007] If the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host;

[0008] The target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes.

[0009] Preferably, before binding the virtual CPU of the target cloud host to the physical CPU in the target numa node, the method further includes:

[0010] The target numa node that satisfies the CPU resources required by the target cloud host is selected from multiple numa nodes.

[0011] Preferably, it also includes:

[0012] If the virtual PCI device corresponding to the target numa node is not available and the target cloud host is not configured with target metadata, a corresponding error prompt message is generated.

[0013] Preferably, it also includes:

[0014] If the virtual PCI device corresponding to the target numa node is available and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host, and / or the virtual PCI device corresponding to the target numa node is configured on the target cloud host.

[0015] Preferably, it also includes:

[0016] If the virtual PCI device corresponding to the target numa node is available and the target cloud host is not configured with target metadata, the virtual PCI device corresponding to the target numa node is configured on the target cloud host.

[0017] Preferably, it also includes:

[0018] The target metadata is configured for an original cloud host that is not configured with the target metadata, the original cloud host is restarted, and after the original cloud host is determined as the target cloud host, the step of binding the virtual CPU of the target cloud host to the physical CPU in the target numa node is performed.

[0019] Preferably, the target metadata is resource specification metadata or image metadata.

[0020] In a second aspect, the present application provides a cloud host creation device, comprising:

[0021] A creation module, configured to create a target cloud host upon receiving a creation request of a target cloud host, and bind the virtual CPU of the target cloud host to the physical CPU in the target numa node;

[0022] A configuration module is used to configure the virtual PCI devices corresponding to other numa nodes to the target cloud host if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata; wherein the target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes.

[0023] In a third aspect, the present application provides a cloud host creation device, including:

[0024] Memory for storing computer programs;

[0025] A processor is used to execute the computer program to implement the aforementioned disclosed cloud host creation method.

[0026] In a fourth aspect, the present application provides a readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned disclosed cloud host creation method.

[0027] It can be seen from the above scheme that the present application provides a cloud host creation method, including: if a creation request of a target cloud host is received, the target cloud host is created, and the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node; if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured to the target cloud host; wherein the target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes.

[0028] It can be seen that the present application utilizes target metadata to indicate that the cloud host can bind physical CPUs and virtual PCI devices across different numa nodes. Therefore, when the cloud host is configured with target metadata, it indicates that the cloud host can bind physical CPUs and virtual PCI devices across different numa nodes. Therefore, if the virtual PCI device corresponding to the target numa node bound to the cloud host is unavailable, then the virtual PCI devices corresponding to other numa nodes can be configured on the cloud host, so that the cloud host is configured to the available virtual PCI devices. The present application can configure virtual PCI devices for the cloud host when the numa node corresponding to the cloud host does not have available virtual PCI devices, thereby avoiding the situation where the cloud host configuration fails due to the lack of available virtual PCI devices.

[0029] Correspondingly, a cloud host creation device, equipment and readable storage medium provided by the present application also have the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0031] Figure 1 A flow chart of a cloud host creation method disclosed in this application;

[0032] Figure 2 This is a flow chart of another cloud host creation method disclosed in this application;

[0033] Figure 3 A flow chart of the target metadata configuration method disclosed in this application;

[0034] Figure 4 A schematic diagram of a cloud host creation device disclosed in this application;

[0035] Figure 5 A schematic diagram of a cloud host creation device disclosed in this application. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] At present, if the virtual CPU of a cloud host is bound to the physical CPU in a numa node, then the cloud host can only use the virtual PCI device corresponding to the numa node. However, if all the virtual PCI devices corresponding to the numa node are used, the current cloud host cannot be configured to the available virtual PCI devices, which will cause the cloud host configuration to fail. To this end, the present application provides a cloud host creation solution that can configure virtual PCI devices for the cloud host when the numa node corresponding to the cloud host has no available virtual PCI devices.

[0038] See also Figure 1 As shown, the embodiment of the present application discloses a cloud host creation method, including:

[0039] S101. If a creation request of a target cloud host is received, the target cloud host is created, and the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node.

[0040] The target cloud host is a virtual machine virtualized based on the host server using SR-IOV (Single Root I / O Virtualization) technology. The host needs to be installed with at least one physical PCI device that supports SR-IOV technology. The physical PCI device is virtualized into multiple virtual PCI devices, and the physical CPU in the host is divided into multiple numa nodes, each of which includes at least one physical CPU (Central Processing Unit). Different numa nodes correspond to different virtual PCI devices.

[0041] For example: there is a physical PCI device that supports SR-IOV technology on the host machine, and the physical PCI device is virtualized into two virtual PCI devices (the first virtual PCI device and the second virtual PCI device); the 10 physical CPUs in the host machine are divided into two numa nodes (the first numa node and the second numa node), each numa node includes 5 physical CPUs, then the first numa node corresponds to the first virtual PCI device, and the second numa node corresponds to the second virtual PCI device.

[0042] If a new cloud host is created and the first numa node meets the CPU resources required by the cloud host, the virtual CPU of the cloud host is bound to the physical CPU in the first numa node, and the cloud host can only configure the first virtual PCI device. Because cloud hosts are currently not allowed to bind physical CPUs and virtual PCI devices across different numa nodes. But if the first virtual PCI device is already in use, the cloud host cannot configure an available virtual PCI device. To this end, this embodiment uses target metadata to allow the physical CPU and virtual PCI device bound to the cloud host to correspond to different numa nodes. Therefore, when encountering this situation, the cloud host can be configured with target metadata so that the virtual PCI devices corresponding to other numa nodes can be configured on the cloud host.

[0043] In a specific implementation, before binding the virtual CPU of the target cloud host to the physical CPU in the target numa node, the process further includes: selecting a target numa node that satisfies the CPU resources required by the target cloud host from multiple numa nodes. If there are at least two target numa nodes that satisfy the CPU resources required by the target cloud host, a numa node is randomly selected.

[0044] S102: If the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host.

[0045] The target metadata allows the physical CPU and virtual PCI devices bound to the target cloud host to correspond to different numa nodes. The target metadata is resource specification metadata or image metadata.

[0046] In this embodiment, when the numa node bound to the cloud host has no available virtual PCI device, and the current cloud host allows binding of physical CPUs and virtual PCI devices across different numa nodes, the virtual PCI devices corresponding to other numa nodes can be configured on the cloud host to complete the configuration of the cloud host.

[0047] In a specific implementation, if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is not configured with target metadata, a corresponding error message is generated. That is, when the numa node bound to the cloud host has no available virtual PCI device and the current cloud host does not allow binding of physical CPUs and virtual PCI devices across different numa nodes, only the corresponding error message can be displayed to notify relevant technical personnel.

[0048] In a specific implementation, if the virtual PCI device corresponding to the target numa node is available, and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host, and / or the virtual PCI devices corresponding to the target numa node are configured on the target cloud host. That is: when the numa node bound to the cloud host has available virtual PCI devices, and the current cloud host also allows binding of physical CPUs and virtual PCI devices across different numa nodes, then you can flexibly choose to configure the cloud host with a virtual PCI device corresponding to any numa node. Of course, you can also configure multiple virtual PCI devices for the cloud host at the same time.

[0049] In a specific implementation, if the virtual PCI device corresponding to the target numa node is available and the target cloud host is not configured with target metadata, the virtual PCI device corresponding to the target numa node is configured on the target cloud host. That is, when the numa node bound to the cloud host has an available virtual PCI device and the current cloud host does not allow binding of physical CPUs and virtual PCI devices across different numa nodes, then only the virtual PCI device corresponding to the numa node bound to the cloud host can be configured to the cloud host.

[0050] If other cloud hosts that have been created do not have target metadata configured, target metadata can be added to them so that the original cloud host can bind physical CPUs and virtual PCI devices across different numa nodes. In a specific implementation, target metadata is configured for the original cloud host that does not have target metadata configured, the original cloud host is restarted, and after the original cloud host is determined as the target cloud host, the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node; if the virtual PCI device corresponding to the target numa node is not available, and the target cloud host is configured with target metadata; or if the virtual PCI device corresponding to the target numa node is available, and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host.

[0051] It can be seen that the embodiment of the present application utilizes target metadata to indicate that the cloud host can bind physical CPUs and virtual PCI devices across different numa nodes. Therefore, when the cloud host is configured with target metadata, it indicates that the cloud host can bind physical CPUs and virtual PCI devices across different numa nodes. Therefore, if the virtual PCI device corresponding to the target numa node bound to the cloud host is unavailable, then the virtual PCI devices corresponding to other numa nodes can be configured in the cloud host, so that the cloud host is configured to the available virtual PCI devices. The present application can configure virtual PCI devices for the cloud host when the numa node corresponding to the cloud host does not have available virtual PCI devices, thereby avoiding the situation where the cloud host configuration fails due to the lack of available virtual PCI devices.

[0052] See also Figure 2 As shown, this embodiment is based on the OpenSatck cloud platform, and sets the policy for the cloud host to access the VF device across numa nodes by creating the resource specification metadata or image metadata of the cloud host. By setting the policy for the cloud host to access the VF device across numa nodes, the cloud host can occupy CPU resources and VF device resources without being restricted by numa nodes, which can not only improve the performance of the cloud host, but also make full use of the CPU resources and VF device resources of the host.

[0053] See also Figure 2 , the specific implementation steps include:

[0054] (1) Set resource specification flavor metadata or image metadata through the OpenSatck cloud platform. Resource specification flavor metadata or image metadata can indicate that the cloud host can bind physical CPUs and virtual PCI devices across different numa nodes.

[0055] Set resource specification flavor metadata, such as: hw:pci_numa_affinity_policy=preferred.

[0056] Set image metadata, such as hw_pci_numa_affinity_policy=preferred.

[0057] (2) Install a physical PCI device (such as a physical network card) that supports the SR-IOV function on the host machine, and virtualize the physical PCI device into multiple VF devices (i.e., virtual PCI devices) based on SR-IOV. These VF devices are associated with the same numa node. Based on the physical network card, create a pass-through type network port, that is, create a port corresponding to each VF device.

[0058] (3) Create a cloud host, select a numa node that can meet the CPU resource requirements of the cloud host from multiple numa nodes and bind it to the cloud host. Obtain the cloud host's access policy to the VF device from the flavor or image (i.e., the set target metadata). If the metadata exists, it indicates that CPU resources and VF device resources are allowed to not belong to the same numa node. Then first check whether the numa node bound to the cloud host has associated available VF devices. If not, select available VF devices from other numa nodes and configure them to the cloud host.

[0059] See also Figure 3 For the created cloud host, configure the resource specification flavor metadata or image metadata for the cloud host to enable the cloud host to have a policy that allows CPU resources and VF device resources to not belong to the same numa node. After the configuration is completed, restart the cloud host to make it effective. After that, you can select a network port that supports the SR-IOV function to mount the VF device across numa nodes to the cloud host; when you need to release the port, you can uninstall the VF device from the cloud host to achieve hot plugging of the network port that supports the SR-IOV function, that is, to achieve hot plugging of the VF device.

[0060] It can be seen that this embodiment can make the CPU resources and VF device resources occupied by the cloud host not restricted by the numa node, and can make full use of the CPU resources and VF device resources on the host. Although the performance is lost when accessing VF devices across numa nodes, the performance is much higher than that of the cloud host without direct PCI device access. This embodiment can be applied to cloud hosts of X86 and ARM architecture cloud platforms.

[0061] A cloud host creation device provided in an embodiment of the present application is introduced below. The cloud host creation device described below and the cloud host creation method described above can be referenced to each other.

[0062] See also Figure 4 As shown, the embodiment of the present application discloses a cloud host creation device, including:

[0063] The creation module 401 is used to create the target cloud host if a creation request of the target cloud host is received, and bind the virtual CPU of the target cloud host to the physical CPU in the target numa node;

[0064] Configuration module 402 is used to configure the virtual PCI devices corresponding to other numa nodes to the target cloud host if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata; wherein the target metadata allows the physical CPU and virtual PCI devices bound to the target cloud host to correspond to different numa nodes.

[0065] In a specific embodiment, it also includes:

[0066] The selection module is used to select a target NUMA node that meets the CPU resources required by the target cloud host from multiple NUMA nodes.

[0067] In a specific embodiment, it also includes:

[0068] The prompt module is used to generate corresponding error prompt information if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is not configured with target metadata.

[0069] In a specific embodiment, it also includes:

[0070] Another configuration module is used to configure the virtual PCI devices corresponding to other numa nodes on the target cloud host if the virtual PCI device corresponding to the target numa node is available and the target cloud host is configured with target metadata, and / or configure the virtual PCI device corresponding to the target numa node on the target cloud host.

[0071] In a specific embodiment, it also includes:

[0072] Another configuration module is used to configure the virtual PCI device corresponding to the target numa node to the target cloud host if the virtual PCI device corresponding to the target numa node is available and the target cloud host is not configured with target metadata.

[0073] In a specific embodiment, it also includes:

[0074] Add a module to configure target metadata for an original cloud host that does not have target metadata configured, restart the original cloud host, and after determining the original cloud host as the target cloud host, perform the steps of binding the virtual CPU of the target cloud host to the physical CPU in the target numa node.

[0075] In a specific implementation, the target metadata is resource specification metadata or image metadata.

[0076] Among them, for more specific working processes of each module and unit in this embodiment, reference can be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0077] It can be seen that this embodiment provides a cloud host creation device, which can configure virtual PCI devices for the cloud host when the numa node corresponding to the cloud host has no available virtual PCI devices, thereby avoiding the situation where the cloud host configuration fails due to the lack of available virtual PCI devices.

[0078] A cloud host creation device provided in an embodiment of the present application is introduced below. The cloud host creation device described below and the cloud host creation method and apparatus described above can refer to each other.

[0079] See also Figure 5 As shown, the embodiment of the present application discloses a cloud host creation device, including:

[0080] Memory 501, used for storing computer programs;

[0081] The processor 502 is used to execute the computer program to implement the method disclosed in any of the above embodiments.

[0082] A readable storage medium provided in an embodiment of the present application is introduced below. The readable storage medium described below and the cloud host creation method, device and equipment described above can be referenced to each other.

[0083] A readable storage medium is used to store a computer program, wherein the computer program, when executed by a processor, implements the cloud host creation method disclosed in the above embodiment. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiment, and will not be repeated here.

[0084] The "first", "second", "third", "fourth", etc. (if any) referred to in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods or devices.

[0085] It should be noted that the descriptions involving "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0086] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0087] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of readable storage medium known in the art.

[0088] Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A cloud host creation method, characterized in that: include: If a request to create a target cloud host is received, the target cloud host is created, and the virtual CPU of the target cloud host is bound to the physical CPU in the target numa node; If the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host; the target metadata is resource specification metadata or image metadata; wherein, a network port supporting SR-IOV function is selected, and the virtual PCI device across numa nodes is mounted to the target cloud host; when the network port needs to be released, the corresponding virtual PCI device is uninstalled from the target cloud host to realize hot plugging of the corresponding virtual PCI device; Wherein, the target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes; If the virtual PCI device corresponding to the target numa node is available and the target cloud host is configured with target metadata, the virtual PCI devices corresponding to other numa nodes are configured on the target cloud host, and / or the virtual PCI device corresponding to the target numa node is configured on the target cloud host; If the virtual PCI device corresponding to the target numa node is available and the target cloud host is not configured with target metadata, the virtual PCI device corresponding to the target numa node is configured on the target cloud host; Among them, it also includes: The target metadata is configured for an original cloud host that is not configured with the target metadata, the original cloud host is restarted, and after the original cloud host is determined as the target cloud host, the step of binding the virtual CPU of the target cloud host to the physical CPU in the target numa node is performed.

2. The cloud host creation method according to claim 1, characterized in that: Before binding the virtual CPU of the target cloud host to the physical CPU in the target numa node, the method further includes: The target numa node that satisfies the CPU resources required by the target cloud host is selected from multiple numa nodes.

3. The cloud host creation method according to claim 1, characterized in that: Also includes: If the virtual PCI device corresponding to the target numa node is not available and the target cloud host is not configured with target metadata, a corresponding error prompt message is generated.

4. A cloud host creation device, characterized in that: include: A creation module, configured to create a target cloud host upon receiving a creation request of a target cloud host, and bind the virtual CPU of the target cloud host to the physical CPU in the target numa node; A configuration module, for configuring virtual PCI devices corresponding to other numa nodes to the target cloud host if the virtual PCI device corresponding to the target numa node is unavailable and the target cloud host is configured with target metadata; wherein the target metadata allows the physical CPU and virtual PCI device bound to the target cloud host to correspond to different numa nodes; the target metadata is resource specification metadata or image metadata; wherein, a network port supporting SR-IOV function is selected to mount the virtual PCI device across numa nodes to the target cloud host; when the network port needs to be released, the corresponding virtual PCI device is uninstalled from the target cloud host to achieve hot plugging of the corresponding virtual PCI device; Another configuration module is used to configure the virtual PCI devices corresponding to other numa nodes to the target cloud host, and / or configure the virtual PCI device corresponding to the target numa node to the target cloud host if the virtual PCI device corresponding to the target numa node is available and the target cloud host is configured with target metadata; a further configuration module, configured to configure the virtual PCI device corresponding to the target numa node to the target cloud host if the virtual PCI device corresponding to the target numa node is available and the target cloud host is not configured with target metadata; Add a module to configure the target metadata for the original cloud host that is not configured with the target metadata, restart the original cloud host, and after determining the original cloud host as the target cloud host, perform the step of binding the virtual CPU of the target cloud host with the physical CPU in the target numa node.

5. A cloud host creation device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the cloud host creation method according to any one of claims 1 to 3.

6. A readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the cloud host creation method according to any one of claims 1 to 3 is implemented.

Images