CN114489922B

CN114489922B - Virtual instance setting method and device

Info

Publication number: CN114489922B
Application number: CN202110131904.8A
Authority: CN
Inventors: 张振中
Original assignee: Huawei Cloud Computing Technologies Co Ltd
Current assignee: Huawei Cloud Computing Technologies Co Ltd
Priority date: 2020-11-12
Filing date: 2021-01-30
Publication date: 2025-01-21
Anticipated expiration: 2041-01-30
Also published as: CN114489922A; WO2022100534A1

Abstract

The application discloses a virtual instance setting method and device, a cloud platform and a storage medium, and belongs to the technical field of cloud computing. The method comprises the steps of obtaining instance configuration information input by a tenant to confirm instance specifications and quality of service Qos requirements of virtual instances to be created by the tenant, wherein the Qos requirements are used for indicating the service quality required by the tenant for the virtual instances, determining selling prices of the virtual instances according to the instance specifications and the Qos requirements, and obtaining instance creation instructions input by the tenant according to the selling prices to create the virtual instances meeting the instance specifications and the Qos requirements. According to the cloud resource purchasing method and device, the cloud resource purchasing on demand can be realized, the cost of using the cloud resource by the tenant is reduced, and the utilization rate of the resource provided by the cloud manufacturer is effectively improved.

Description

Virtual instance setting method and device

The present disclosure claims priority from chinese patent application serial No. 202011264601.5, entitled "cloud platform and instance creation method thereof," filed on 11/12/2020, the entire contents of which are incorporated herein by reference.

Technical Field

The application relates to the technical field of cloud computing (closed computing), in particular to a virtual instance setting method and device and a cloud platform.

Background

Cloud computing is getting more and more popular in enterprises because of the characteristics of elasticity, flexible deployment, high reliability, high safety and high cost performance, and the ecological structure is also continuously expanding and enriching.

For example, a virtual instance is a mainstream product provided by cloud vendors. Each virtual instance proposed by a cloud vendor typically has an instance specification, where the instance specification includes a computing resource, such as a processor core, a memory resource, such as a bandwidth resource, a network resource, such as a storage bandwidth, and a storage resource, where the quality of service (quality of service, qoS) corresponding to each instance specification is fixedly set by the cloud vendor, and whenever a tenant selects a specific instance specification to create the virtual instance, the QoS corresponding to the specific instance specification is the QoS of the virtual instance.

In the prior art, qoS is bound with an instance specification, and after a tenant selects an instance specification to create a virtual instance, qoS of the virtual instance cannot be changed, in some cases, after the tenant selects a specific instance specification to create the virtual instance, qoS of the created virtual instance cannot well meet requirements of the tenant, resulting in poor utilization rate of resources provided by cloud vendors.

Disclosure of Invention

The application provides a virtual instance setting method and device, a cloud platform and a storage medium. The virtual instance creation method and the virtual instance creation device can achieve the on-demand creation of the virtual instance. The technical scheme provided by the application is as follows:

In a first aspect, the application provides a virtual instance setting method, which is applied to a cloud platform, and the method comprises the steps of obtaining instance configuration information input by a tenant to confirm instance specifications and quality of service Qos requirements of virtual instances required to be created by the tenant, wherein the Qos requirements are used for indicating service qualities required by the tenant for the virtual instances, determining selling prices of the virtual instances according to the instance specifications and the Qos requirements, and obtaining instance creation instructions input by the tenant according to the selling prices to create the virtual instances meeting the instance specifications and the Qos requirements.

The method comprises the steps of obtaining example configuration information input by a tenant to confirm the example specification and the quality of service Qos requirement of a virtual example to be created by the tenant, determining the selling price of the virtual example according to the example specification and the Qos requirement, obtaining an example creation instruction input by the tenant according to the selling price to create the virtual example meeting the example specification and the Qos requirement, thereby creating the virtual example according to the example specification and the Qos requirement input by the tenant, enabling the created virtual example to reflect the real requirement of the tenant in a finer granularity, enabling the created virtual example for the tenant according to the example configuration information to better meet the requirement of the tenant, realizing the on-demand purchase of cloud resources, reducing the cost of the tenant for using the cloud resources, effectively improving the utilization rate of resources provided by cloud manufacturers, and enabling the cloud manufacturer to utilize limited cloud resources to serve more tenants. And by creating the virtual instance according to the instance specification and the quality of service Qos requirements, decoupling of the virtual instance Qos from the physical server can be achieved, and the influence of evolution, utilization and replacement of the subsequent physical server on the instance specification and performance is reduced.

In one implementation, the Qos requirements include a base Qos requirement and an upper limit Qos requirement of the computing resource, a minimum Qos requirement that can be achieved by the virtual instance for the use case of the computing resource when the base Qos requirement of the computing resource configures the computing resource indicated by the instance specification for the virtual instance, and a maximum Qos requirement that can be achieved by the virtual instance for the use case of the computing resource when the upper limit Qos requirement of the computing resource indicates that the virtual instance configures the computing resource indicated by the instance specification.

Optionally, the method further comprises providing a selection range of the basic Qos requirements of the computing resources, confirming the basic Qos requirements of the computing resources according to the values selected by the tenant in the selection range of the basic Qos requirements of the computing resources, providing a selection range of the upper limit Qos requirements of the computing resources, and confirming the upper limit Qos requirements of the computing resources according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the computing resources.

Optionally, the computing resources include a processor core and/or memory.

In one implementation, the Qos requirements include a base Qos requirement and an upper limit Qos requirement of a network resource, a minimum Qos requirement that can be achieved by a virtual instance for a use case of the network resource when the base Qos requirement of the network resource configures the network resource indicated by an instance specification for the virtual instance, and a maximum Qos requirement that can be achieved by the virtual instance for the use case of the network resource when the upper limit Qos requirement of the network transmission performance is used for indicating that the virtual instance configures the network resource indicated by the instance specification.

Optionally, the method further comprises providing a selection range of the basic Qos requirements of the network resource, confirming the basic Qos requirements of the network resource according to the values selected by the tenant in the selection range of the basic Qos requirements of the network resource, providing a selection range of the upper limit Qos requirements of the network resource, and confirming the upper limit Qos requirements of the network resource according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the network resource.

Optionally, the network resources include network bandwidth or number of packets per second PPS.

In one implementation, the Qos requirements include a base Qos requirement and an upper limit Qos requirement of the storage resource, a minimum Qos requirement that can be achieved by the virtual instance for the use case of the storage resource when the base Qos requirement of the storage resource configures the storage resource indicated by the instance specification for the virtual instance, and a maximum Qos requirement that can be achieved by the virtual instance for the use case of the storage resource when the upper limit Qos requirement of the storage resource configures the storage resource indicated by the instance specification for the virtual instance.

Optionally, the method further comprises the steps of providing a selection range of the basic Qos requirements of the storage resources, confirming the basic Qos requirements of the storage resources according to the values selected by the tenant in the selection range of the basic Qos requirements of the storage resources, providing a selection range of the upper limit Qos requirements of the storage resources, and confirming the upper limit Qos requirements of the storage resources according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the storage resources.

Optionally, the storage resources include storage bandwidth and/or the number of read/write operations performed per second IOPS.

The method comprises the steps of obtaining an instance creation instruction input by a tenant according to a selling price to create a virtual instance meeting instance specifications and Qos requirements, wherein the method comprises the steps of selecting a first physical server from a plurality of physical servers in a cloud data center, enabling idle hardware resources of the first physical server to provide the instance specifications and meet the Qos requirements, and creating the virtual instance in the first physical server, wherein preset hardware resources in idle hardware resources of the first physical server are distributed to the virtual instance, and the preset hardware resources meet the instance specifications and the Qos requirements.

In one implementation, the first physical server meets at least condition one that any hardware resource of the first physical server is capable of meeting both the base Qos requirements of all created virtual instances on the first physical server and the base Qos requirements of the virtual instance to be created. And the second condition is that for any hardware resource of the first physical server, the sum of the upper limit Qos requirements of all the created virtual instances on the first physical server and the upper limit Qos requirements of the virtual instances to be created is smaller than or equal to the sum of the upper limit Qos requirements of the created virtual instances on other alternative physical servers and the upper limit Qos requirements of the virtual instances to be created.

By selecting the physical server according to the condition one, the physical server can ensure the basic performance of all the virtual instances on the physical server when resource contention occurs to all the virtual instances on the physical server, and ensure the service level protocol of the virtual instances.

By selecting the first physical server according to the second condition, the load balance of the physical servers can be realized on the premise of guaranteeing basic performance, the probability of contending resources on each physical server can be controlled to be averaged as much as possible, the probability of contending resources among virtual instances in the physical servers is reduced as much as possible, the probability of each virtual instance reaches the upper Qos requirement as much as possible, the full utilization of cloud computing environment resources can be guaranteed, and the cluster resource utilization rate is improved.

Optionally, the method further comprises obtaining an updated Qos requirement input by the tenant, wherein the updated Qos requirement is used for indicating an updated service quality required by the tenant for the virtual instance, selecting a second physical server from a plurality of physical servers in the cloud data center, wherein the idle hardware resources of the second physical server can provide instance specifications and meet the updated Qos requirement, and migrating the virtual instance from the first physical server to the second physical server.

After the virtual instance is established, the Qos requirement of the virtual instance is updated according to the service requirement, and the virtual instance is migrated according to the updated Qos requirement, so that resources can be allocated for the virtual instance according to the service requirement, the resources of the physical server are fully utilized, and the cost of using cloud resources by tenants is saved.

In one implementation, the method further includes providing a first option for indicating to the tenant to select to restart the virtual instance when the Qos is updated, stopping running the virtual instance at the first physical server if the tenant selects to restart the virtual instance when the Qos is updated, migrating the virtual instance from the first physical server to the second physical server, and running the virtual instance at the second physical server.

In another implementation, the method further includes providing a second option for indicating that the tenant chooses not to restart the virtual instance when the Qos is updated, and online migrating the virtual instance from the first physical server to the second physical server if the tenant chooses not to restart the virtual instance when the Qos is updated.

Optionally, the method further comprises deducting the account number of the tenant logged in to the cloud platform according to the selling price. For example, the cloud platform may deduct fees according to the selling price after the virtual instance is created. Or when the virtual instance is requested to be created, the virtual instance is paid and deducted according to the selling price.

In a second aspect, the application provides a virtual instance setting device, which comprises an acquisition module, a determination module and a creation module, wherein the acquisition module is used for acquiring instance configuration information input by a tenant to confirm instance specifications and quality of service Qos requirements of virtual instances required to be created by the tenant, the Qos requirements are used for indicating the service quality required by the tenant for the virtual instances, the determination module is used for determining selling prices of the virtual instances according to the instance specifications and the Qos requirements, and the creation module is used for acquiring instance creation instructions input by the tenant according to the selling prices to create the virtual instances meeting the instance specifications and the Qos requirements.

Optionally, the Qos requirements include a basic Qos requirement and an upper limit Qos requirement of the computing resource, a minimum Qos requirement that can be achieved by the virtual instance for the use condition of the computing resource when the basic Qos requirement of the computing resource configures the computing resource indicated by the instance specification for the virtual instance, and a maximum Qos requirement that can be achieved by the virtual instance for the use condition of the computing resource when the upper limit Qos requirement of the computing resource indicates that the virtual instance configures the computing resource indicated by the instance specification.

Optionally, the device further comprises a providing module for providing a selection range of the basic Qos requirements of the computing resources, an obtaining module for confirming the basic Qos requirements of the computing resources according to the values selected by the tenant in the selection range of the basic Qos requirements of the computing resources, a providing module for providing a selection range of the upper limit Qos requirements of the computing resources, and an obtaining module for confirming the upper limit Qos requirements of the computing resources according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the computing resources.

Optionally, the computing resources include a processor core and/or memory.

Optionally, the Qos requirements include a basic Qos requirement and an upper limit Qos requirement of a network resource, a minimum Qos requirement that can be achieved by the virtual instance according to the use condition of the network resource when the basic Qos requirement of the network resource configures the network resource indicated by the instance specification for the virtual instance, and a maximum Qos requirement that can be achieved by the virtual instance according to the use condition of the network resource when the upper limit Qos requirement of the network transmission performance is used for indicating that the virtual instance configures the network resource indicated by the instance specification.

Optionally, the device further comprises a providing module for providing a selection range of the basic Qos requirements of the network resources, an obtaining module for confirming the basic Qos requirements of the network resources according to the values selected by the tenant in the selection range of the basic Qos requirements of the network resources, a providing module for providing a selection range of the upper limit Qos requirements of the network resources, and an obtaining module for confirming the upper limit Qos requirements of the network resources according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the network resources.

Optionally, the Qos requirements include a basic Qos requirement and an upper limit Qos requirement of the storage resource, when the basic Qos requirement of the storage resource configures the storage resource indicated by the instance specification for the virtual instance, the virtual instance can reach the minimum Qos requirement for the use condition of the storage resource, and when the upper limit Qos requirement of the storage resource configures the storage resource indicated by the instance specification for the virtual instance, the virtual instance can reach the maximum Qos requirement for the use condition of the storage resource.

Optionally, the device further comprises a providing module for providing a selection range of the basic Qos requirements of the storage resources, an obtaining module for confirming the basic Qos requirements of the storage resources according to the values selected by the tenant in the selection range of the basic Qos requirements of the storage resources, a providing module for providing a selection range of the upper limit Qos requirements of the storage resources, and an obtaining module for confirming the upper limit Qos requirements of the storage resources according to the values selected by the tenant in the selection range of the upper limit Qos requirements of the storage resources.

Optionally, the creation module is specifically configured to select a first physical server from a plurality of physical servers in the cloud data center, where an idle hardware resource of the first physical server may provide an instance specification and meet Qos requirements, and create a virtual instance at the first physical server, where a predetermined hardware resource in the idle hardware resource of the first physical server is allocated to the virtual instance, where the predetermined hardware resource meets the instance specification and Qos requirements.

Optionally, the device further comprises an acquisition module for acquiring an updated Qos requirement input by the tenant, wherein the updated Qos requirement is used for indicating the updated service quality required by the tenant for the virtual instance, a migration module for selecting a second physical server from a plurality of physical servers in the cloud data center, wherein the idle hardware resources of the second physical server can provide instance specifications and meet the updated Qos requirement, and a migration module for migrating the virtual instance from the first physical server to the second physical server.

Optionally, the device further comprises a providing module for providing a first option for indicating that the tenant selects to restart the virtual instance when the Qos is updated, and a migration module for stopping running the virtual instance on the first physical server, migrating the virtual instance from the first physical server to the second physical server, and running the virtual instance on the second physical server when the tenant selects to restart the virtual instance when the Qos is updated.

Optionally, the device further comprises a providing module for providing a second option for indicating that the virtual instance is not restarted when the Qos is updated by the tenant, and a migration module for online migrating the virtual instance from the first physical server to the second physical server when the virtual instance is not restarted when the Qos is updated by the tenant.

Optionally, the device further comprises an operation and maintenance module, wherein the operation and maintenance module is used for deducting fees from the account number of the tenant logged in to the cloud platform according to the selling price.

In a third aspect, the present application provides a cloud platform comprising a memory storing program instructions and a processor executing the program instructions to perform the method provided in the first aspect of the present application and any one of its possible implementations.

In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium being a non-volatile computer readable storage medium comprising program instructions which, when run on a computer device, cause the computer device to perform the method provided in the first aspect of the application and any one of its possible implementations.

In a fifth aspect, the application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method provided in the first aspect of the application and any one of its possible implementations.

Drawings

Fig. 1 is a schematic diagram of an application scenario related to a virtual instance setting method provided by an embodiment of the present application;

FIG. 2 is a flowchart of a virtual instance setting method according to an embodiment of the present application;

FIG. 3 is a schematic illustration of an alternative example specification provided by an embodiment of the present application;

fig. 4 is a schematic diagram of selecting Qos requirements according to an embodiment of the present application;

FIG. 5 is a flow chart of a method for creating a virtual instance provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a selection of a first physical server according to an embodiment of the present application;

FIG. 7 is a flowchart of a method for migrating a virtual instance according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a migration virtual instance according to an embodiment of the present application;

FIG. 9 is a schematic diagram of another migration virtual instance provided by an embodiment of the present application;

Fig. 10 is a schematic structural diagram of a virtual instance setting device according to an embodiment of the present application;

FIG. 11 is a schematic diagram of another virtual instance setting apparatus according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a cloud platform according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

For ease of understanding, some concepts involved in embodiments of the application are explained first below.

Virtual instance, wherein the virtual instance runs on an operating system of a physical server, the virtual instance is provided with the operating system, the operating system of the virtual instance also runs with application programs, the virtual instance can use hardware resources of the physical server, different virtual instances are isolated from each other, and the application instance is a virtual machine or a container.

The basic performance is the performance that the virtual instance can reach at any time, and is the lowest guarantee of the performance of the virtual instance. For example, the underlying network bandwidth of a virtual instance is the bandwidth reserved by a host (host) for the virtual instance, which can be used by the virtual instance at any time.

Maximum performance is the bursty upper limit of the performance that a virtual instance can achieve. When a part of virtual instances on a host where a plurality of virtual instances are deployed do not occupy own basic performance, resources for providing the unoccupied basic performance can be shared by other virtual instances, by sharing, the performance of the virtual instance can be made higher than the basic performance, and the upper limit that can be achieved by the performance higher than the basic performance is the maximum performance of the virtual instance. Because each virtual instance does not always keep a high load, the resources of the physical server are relatively idle, so that the performance of the virtual instance is possible to reach the maximum performance. However, the maximum performance is not guaranteed all the time, and once other virtual instance loads compete, the host machine can preferentially guarantee the basic performance of each virtual instance, and the maximum performance of the virtual instance cannot be guaranteed at the moment.

Quality of service (quality of service, qoS), base quality of service and upper quality of service.

Basic quality of service-the virtual instance runs in a physical server, which can allocate resources to a virtual instance of a particular instance specification, e.g. a virtual instance of instance specification 4U, the physical server can allocate 4 processor cores to the virtual instance, but the physical server does not guarantee that the virtual instance can 100% exclusive the 4 processor cores at any time, and only if the basic QOS for the computing resources is 100%, the physical server can guarantee that the virtual instance can 100% occupy the 4 processor cores in any case.

Whereas in the case where the underlying QOS for computing resources is 50%, in the case where the physical server resources are limited (e.g., other virtual instances contend for resources), the physical server can only guarantee that the virtual instance can occupy 50% of the computing power of each of the 4 processor cores at this time.

The virtual instance runs in the physical server, the physical server can allocate resources to the virtual instance with specific instance specifications, when part of the virtual instances on the physical server do not occupy the resources indicated by the basic service quality of the virtual instance, other virtual instances on the physical server can use the unoccupied resources, so that the service quality of the other virtual instances can exceed the basic service quality, and the upper limit of the basic service quality can be exceeded as the upper limit service quality of the virtual instance. For example, a virtual instance with an instance specification of 4U may allocate 4 processor cores to a virtual instance, where the virtual instance is 50% for a base QOS of computing resources, where the physical server is in any case capable of 50% occupying the 4 processor cores, and where the virtual instance is 100% for an upper QOS of computing resources, where a portion of the virtual instance does not occupy computing resources indicated by its base quality of service, by occupying the unoccupied computing resources, the virtual instance is capable of occupying more than 50% of the computing power of each of the 4 processor cores, and where the virtual instance is capable of occupying a computing resource whose upper limit is 100% of the computing power of each of the 4 processor cores.

The above description uses the instance specification as an example of the computing resource, and the instance specification may further include the network resource and the storage resource, where the basic QOS usage of the network resource and the storage resource is similar to that described above, and will not be repeated herein.

When each cloud manufacturer defines basic performance for a virtual instance, it needs to ensure that the sum of basic performance under the same performance of all virtual instances on a physical server does not exceed the maximum capability of the performance which can be provided by the physical server, thereby ensuring that the basic performance of each virtual instance can be achieved at any time. Vendors typically determine the base performance of each virtual processor based on the number of virtual processors (vcpu) available on the physical server and determine the base performance of each virtual instance based on the number of virtual processors each virtual instance includes. For example, if a maximum network bandwidth of a physical server is 20 gigabits per second (Gbps), and a total number of issuable virtual processors is 40, then a reference network bandwidth per virtual processor is 20 Gbps/40=0.5 Gbps, then a reference network bandwidth of a virtual instance having 4 virtual processors is 4×0.5=2 Gbps, and a reference network bandwidth of a virtual instance having 16 virtual processors is 16×0.5=8 Gbps. The maximum performance of a virtual instance is generally defined in terms of the competitiveness of each vendor, which cannot exceed the maximum performance that a physical server can provide. For example, the maximum network bandwidth of a virtual instance is typically 1-3 times the underlying network bandwidth, the network bandwidth of a physical server is at least 1-3 times the network bandwidth, the maximum storage bandwidth of a virtual instance is typically 2-10 times the underlying storage bandwidth, and the storage bandwidth of a physical server is at least 2-10 times the storage bandwidth. The multiple relation between the maximum performance and the basic performance can be determined according to the competition force and the resource competition condition.

Because the maximum performance of the resources of the physical server is possible to be achieved when the resources are relatively idle, cloud manufacturers limit the time for each virtual instance to achieve the maximum performance through integration so as to control the competition of each virtual instance on the same physical server for the idle resources, and therefore the probability of conflict of the virtual instance for the idle resources is reduced. Wherein, the shorter the duration that the virtual instance reaches the maximum performance, the lower the probability of collision. When the utilization of resources by the virtual instance is below the base performance, the virtual instance may accumulate points based on the duration of the time below the base performance. And when the physical server generates idle resources, the performance of the virtual instance can reach the maximum performance until the accumulated points of the virtual instance are consumed.

Currently, virtual instances proposed by each cloud vendor generally have a certain specification, where the specification is divided according to computing resources of a physical server, network transmission performance and storage performance capabilities, and virtual instances with different specifications can implement different QoS capabilities. When the tenant needs to use the virtual instance, the virtual instance meeting the tenant needs is directly selected from the virtual instances planned by the cloud manufacturer.

However, the specifications of cloud vendor planning generally cannot better meet the needs of tenants, and meanwhile, the utilization rate of resources provided by cloud vendors is also poor because users do not necessarily fully utilize the applied resources.

The embodiment of the application provides a virtual instance setting method, which is characterized in that the instance specification and the quality of service Qos requirement of a virtual instance to be created by a tenant are confirmed by acquiring instance configuration information input by the tenant, the selling price of the virtual instance is determined according to the instance specification and the Qos requirement, and the virtual instance meeting the instance specification and the Qos requirement is created by acquiring an instance creation instruction input by the tenant according to the selling price, so that the virtual instance can be created according to the instance specification and the Qos requirement input by the tenant, the created virtual instance can reflect the real requirement of the tenant in a finer granularity, the on-demand purchase of cloud resources can be realized, the cost of the tenant for using the cloud resources is reduced, the utilization rate of resources provided by a cloud manufacturer is effectively improved, and the cloud manufacturer can use limited cloud resources to serve more tenants. Wherein the Qos requirements are used to indicate the quality of service required by the tenant for the virtual instance.

Fig. 1 is a schematic diagram of an implementation scenario involved in a virtual instance setting method according to an embodiment of the present application. As shown in fig. 1, the implementation scenario includes a cloud data center 10 and a terminal 20. The cloud data center 10 and the terminal 20 can communicate.

Cloud data center 10 includes cloud resources and cloud platforms. Cloud resources include a large number of underlying resources owned by cloud service providers. The underlying resources may be computing resources, storage resources, network resources, and the like. And the computing resources may be a large number of computing devices (e.g., servers). The cloud platform can utilize the deployed basic resources or the resources virtualized according to the basic resources to realize the services of the tenants and provide cloud services for the tenants. Wherein, the service of the tenant comprises a software application service and the like which are created according to the service requirement of the tenant. For example, the tenant's business includes a language identification service, a video auditing service, or an image rendering service, etc., created according to the tenant's business needs. The cloud platform may be a cloud platform of a center cloud, a cloud platform of an edge cloud, or a cloud platform including a center cloud and an edge cloud, which is not particularly limited in the embodiment of the present application.

The tenant may access the cloud data center 10 through the terminal 20, and perform related processing on the cloud resource through the cloud data center 10. For example, the cloud platform may provide a configuration interface for the tenant, and the tenant may input, through the terminal 20, instance configuration information for the virtual instance in the configuration interface, and the cloud platform may confirm, according to the instance configuration information, an instance specification and a quality of service Qos requirement of the virtual instance that the tenant needs to create, and create a virtual instance for the tenant that meets the instance specification and the Qos requirement. Wherein the Qos requirements are used to indicate the quality of service required by the tenant for the virtual instance.

The cloud platform may be implemented in software or hardware. In one implementation, the cloud platform may be implemented in hardware such as a physical server. For example, the cloud platform may be implemented by one physical server, or a physical server cluster formed by several physical servers, or a cloud computing service center. In another implementation manner, the cloud platform may be implemented by software deployed on a computing resource, where the software is used to implement the virtual instance setting method provided by the embodiment of the present application. For example, the cloud platform may be implemented by a virtual machine or container modeled by software on the underlying resources. Moreover, the cloud platform can be realized by independently deployed resources or can be realized by distributed deployed resources. For example, software for implementing the cloud platform may be deployed on servers, virtual machines, or containers in the cloud platform independently, or software for implementing the cloud platform may be deployed on multiple servers in the cloud platform in a distributed manner, or software for implementing the cloud platform may be deployed on multiple virtual machines in the cloud platform in a distributed manner, or software for implementing the cloud platform may be deployed in multiple containers in the cloud platform in a distributed manner, or software for implementing the cloud platform may be deployed in multiple servers, multiple virtual machines, and multiple containers in the cloud platform in a distributed manner.

The terminal 20 may be a desktop computer, laptop computer, mobile phone, smart phone, tablet computer, multimedia player, smart home appliance, artificial intelligent device, smart wearable device, electronic reader, smart car device, or internet of things device, etc.

The following describes an implementation procedure of the virtual instance setting method provided by the embodiment of the present application. As shown in fig. 2, the implementation process of the virtual instance setting method may include the following steps:

Step 201, the cloud platform provides a configuration interface for the tenant to input instance configuration information.

The instance configuration information is used for indicating instance specifications and quality of service Qos requirements of the virtual instance, wherein the Qos requirements are used for indicating service quality required by the tenant for the virtual instance. Instance specifications include specifications of various resources required for the virtual instance. For example, the resources required by the virtual instance include one or more of computing resources, network resources, and storage resources. Optionally, the computing resources include a processor core and/or memory. The network resources include network bandwidth, number of packets per second (PACKET PER second, PPS), and/or total number of links of the virtual instance with other virtual instances. The storage resources include storage bandwidth and/or the number of read/write operations performed per second (input/output operation per second, IOPS).

In one implementation, the Qos requirements include a base Qos requirement and an upper Qos requirement for various resources required by the virtual instance. For example, the Qos requirements include one or more of a base Qos requirement for a computing resource, an upper limit Qos requirement for a computing resource, a base Qos requirement for a network resource, an upper limit Qos requirement for a network resource, a base Qos requirement for a storage resource, and an upper limit Qos requirement for a storage resource.

When the basic Qos requirement of the computing resource is configured with the computing resource indicated by the instance specification for the virtual instance, the virtual instance can meet the minimum Qos requirement for the use condition of the computing resource. The upper Qos requirement of the computing resource is used to indicate that the virtual instance is configured with the computing resource indicated by the instance specification, and the virtual instance is capable of achieving the highest Qos requirement for the use condition of the computing resource. When the basic Qos requirement of the network resource is configured with the network resource indicated by the instance specification for the virtual instance, the virtual instance aims at the minimum Qos requirement which can be achieved by the use condition of the network resource. The upper Qos requirement of the network transmission performance is used for indicating that the virtual instance is configured with the network resource indicated by the instance specification, and the virtual instance can meet the highest Qos requirement for the use condition of the network resource. When the storage resources with the instance specification indication are configured for the virtual instance, the virtual instance aims at the minimum Qos requirement which can be achieved by the use condition of the storage resources. When the upper limit Qos requirement of the storage resource is configured with the storage resource indicated by the instance specification for the virtual instance, the virtual instance aims at the highest Qos requirement which can be achieved by the use condition of the storage resource. The use condition of the resource can be represented by the use rate of the virtual instance to the resource.

Since the instance configuration information is used to indicate the instance specification and quality of service Qos requirements of the virtual instance, the cloud platform providing the configuration interface may include the cloud platform providing a configuration interface for tenant input to indicate the instance specification and the cloud platform providing a configuration interface for tenant input to indicate the Qos requirements. Optionally, the cloud platform may provide the configuration interface in a plurality of ways, for example, the cloud platform may provide the configuration interface through an application program interface (application programming interface, API), an interaction template, and a configuration interface. The interaction template is a template provided by the cloud platform for the tenant to realize different functions. When a tenant needs to use a certain function, the tenant can download a template for realizing the function, add relevant information of the tenant in the template, and then feed back the template added with relevant information of the tenant to a cloud platform, and after receiving the template added with relevant information of the tenant, the cloud platform can acquire the function required to be realized by the template, and customize the function according to the information of the tenant. The configuration interface refers to functions that a tenant may operate in to indicate that the tenant needs to implement.

Corresponding to the implementation manner of the configuration interface, the cloud platform provides the configuration interface for indicating the instance specification by the tenant input, and the cloud platform provides the configuration interface for indicating the Qos requirement by the tenant input, and the configuration interface can be displayed through two-level pages. The primary page is used for providing a configuration interface for tenant input to indicate instance specifications, and the secondary page is used for providing a configuration interface for tenant input to indicate Qos requirements. The secondary page is displayed after the tenant selects the instance specification in the primary page, and the secondary page displays the Qos requirements corresponding to the instance specification selected in the primary page.

And when the cloud platform manages cloud resources, the instance specifications can be bound with the basic Qos capability and the upper limit Qos capability, and the basic Qos capability and the upper limit Qos capability corresponding to each instance specification can float within a certain energy range, namely, when a user selects a certain instance specification, the selection range of the basic Qos requirement and the selection range of the upper limit Qos requirement of the resources required by the virtual instance are determined. Thus, the cloud platform provides a configuration interface for tenant input to indicate Qos requirements, including a selection range of base Qos requirements to provide various resources required by the virtual instance and a selection range of upper Qos requirements to provide various resources required by the virtual instance.

Optionally, when the Qos requirements include a base Qos requirement and an upper limit Qos requirement of the computing resource, providing a configuration interface for setting the Qos requirements includes providing a selection range of the base Qos requirement of the computing resource and providing a selection range of the upper limit Qos requirement of the computing resource. When the Qos requirements include a base Qos requirement and an upper Qos requirement for the network resource, providing a configuration interface for setting the Qos requirements includes providing a selection range of the base Qos requirement for the network resource and providing a selection range of the upper Qos requirement for the network resource. When the Qos requirements include a base Qos requirement and an upper Qos requirement for the storage resource, providing a configuration interface for setting the Qos requirements includes providing a selection range of the base Qos requirements for the storage resource and providing a selection range of the upper Qos requirements for the storage resource.

For example, fig. 3 is a schematic diagram of selecting an instance specification in a primary page, and fig. 4 is a secondary page at an instance specification where the tenant has selected 4 virtual processors and 8GB of memory capacity in fig. 3. As shown in fig. 3, the example specification entered by the tenant (example specification marked by a dashed box in fig. 3) includes 4 virtual processors and 8 Gigabit (GB) memory capacity. In addition, the tenant can also select the name of the virtual instance and the model of the processor required by the virtual instance through the configuration interface. As shown in fig. 3, the name of the virtual instance selected by the tenant through the configuration interface is "t7. Xlage".

As shown in FIG. 4, the selection ranges of the base Qos capability and the upper Qos capability corresponding to the example specification are respectively that the selection range of the utilization rate of the base CPU performance is 4 virtual processors is [5%,100% ], the selection range of the utilization rate of the maximum CPU performance is 4 virtual processors is [5%,100% ], the selection range of the base network bandwidth is [1 gigabyte per second (GB/S), 5GB/S ], the selection range of the maximum network bandwidth is [3GB/S,11GB/S ], the selection range of the base PPS is [20 ten thousand (W), 60W ], the selection range of the maximum PPS is [40W,90W ], the selection range of the base IOPS is [20W,60W ], the selection range of the maximum IOPS is [40W,90W ], the selection range of the base storage bandwidth is [20W,60W ], and the selection range of the maximum storage bandwidth is [40W,90W ].

And, as shown in fig. 4, after the cloud platform provides the selection range of the basic Qos requirement and the selection range of the upper limit Qos requirement for the tenant, the numerical value can be selected in the selection range by dragging the dragging bar in fig. 4, or the numerical value can be adjusted by the add-subtract button in fig. 4, so that the basic Qos requirement and the upper limit Qos requirement of the virtual instance on the resource are indicated by the numerical value selected by the tenant.

Step 202, the cloud platform acquires instance configuration information input by the tenant to confirm instance specification and Qos requirements of the virtual instance to be created by the tenant.

And after the tenant selects the instance specification through the configuration interface and selects the numerical value in the selection range of the basic Qos requirement and the selection range of the upper limit Qos requirement of the resource, the cloud platform can determine the instance specification and the quality of service Qos requirement of the virtual instance to be created by the tenant according to the selection of the tenant.

In one implementation, when the Qos requirements include a base Qos requirement and an upper limit Qos requirement of a computing resource, obtaining the base Qos requirement of the computing resource of the virtual instance to be created by the tenant includes confirming the base Qos requirement of the computing resource according to a value selected by the tenant in a selection range of the base Qos requirement of the computing resource, and obtaining the upper limit Qos requirement of the computing resource of the virtual instance to be created by the tenant includes confirming the upper limit Qos requirement of the computing resource according to a value selected by the tenant in the selection range of the upper limit Qos requirement of the computing resource.

When the Qos requirement comprises a basic Qos requirement and an upper limit Qos requirement of the network resource, acquiring the basic Qos requirement of the network resource of the virtual instance to be created by the tenant comprises confirming the basic Qos requirement of the network resource according to the value selected by the tenant in the selection range of the basic Qos requirement of the network resource, and acquiring the upper limit Qos requirement of the network resource of the virtual instance to be created by the tenant comprises confirming the upper limit Qos requirement of the network resource according to the value selected by the tenant in the selection range of the upper limit Qos requirement of the network resource.

When the Qos requirements comprise a basic Qos requirement and an upper limit Qos requirement of the storage resource, acquiring the basic Qos requirement of the storage resource of the virtual instance to be created by the tenant, wherein the basic Qos requirement of the storage resource is confirmed according to the value selected by the tenant in the selection range of the basic Qos requirement of the storage resource, and the upper limit Qos requirement of the storage resource of the virtual instance to be created by the tenant is acquired, and the upper limit Qos requirement of the storage resource is confirmed according to the value selected by the tenant in the selection range of the upper limit Qos requirement of the storage resource.

For example, referring to fig. 4, the tenant selects 5% of the range of utilization of the base CPU performance, 5% of the range of utilization of the maximum CPU performance, 1GB/S of the range of selection of the base network bandwidth, 3GB/S of the range of selection of the maximum network bandwidth, 20W of the range of selection of the base PPS, 40W of the range of selection of the maximum PPS, 20W of the range of selection of the base IOPS, 40W of the range of selection of the maximum IOPS, 20W of the range of selection of the base storage bandwidth, and 40W of the range of selection of the maximum storage bandwidth. Wherein, the "concentric circle" icon in fig. 4 is used to identify the numerical value selected by the tenant in the selection range.

The Qos requirements of the virtual instance to be created by the tenant can be confirmed according to the values selected by the tenant in the selection range of the basic Qos requirement and the upper limit Qos requirement of each resource, wherein the basic Qos requirement of the computing resource is 5% of the utilization rate of 4 virtual processors, the upper limit Qos requirement of the computing resource is 5% of the utilization rate of 4 virtual processors, the basic network bandwidth in the network resource is 1GB/S, the maximum network bandwidth is 3GB/S, the basic PPS is 20W, the maximum PPS is 40W, the basic IOPS in the storage resource is 20W, the maximum IOPS is 40W, the basic storage bandwidth is 20W, and the maximum storage bandwidth is 40W.

And 203, the cloud platform determines the selling price of the virtual instance according to the instance specification and the Qos requirement.

After confirming the instance specification and Qos requirements of the virtual instance that the tenant needs to create, the cloud platform can determine the selling price of the virtual instance according to the instance specification and Qos requirements. According to the embodiment of the application, the tenant can input the instance specification and the Qos requirement of the virtual instance to be created according to the application requirement, and the instance specification and the Qos requirement can represent the real requirement of the tenant on the cloud computing resource, so that when the cloud platform determines the selling price of the virtual instance according to the instance specification and the Qos requirement, the on-demand charging of the cloud computing resource can be realized. And, the tenant can also input its desired pay mode through the configuration interface. As shown in fig. 3, when the tenant inputs the desired pay-as-needed through the configuration interface, the cloud platform determines the selling price of the virtual instance according to the instance specification and Qos requirements.

In one implementation, the selling price of the virtual instance is in positive correlation with the Qos requirement of the virtual instance in addition to the positive correlation with the instance specification, and when at least one of the instance specification and the Qos requirement of the virtual instance changes, the selling price of the virtual instance changes accordingly.

Alternatively, the relationship between the selling price of the virtual instance, the instance specification, and the Qos requirements may satisfy the following formula:

P (total) =p (Base) +s (Base cpu performance) ×c (Base) +s (maximum cpu performance) ×c (max) +s (Base network bandwidth) ×b (Base network bandwidth) +s (maximum network bandwidth) ×b (maximum network bandwidth) +s (Base PPS) +p (Base PPS) +s (maximum PPS) ×p (maximum PPS) +s (Base IOPS) ×i (Base IOPS) +s (maximum IOPS) +s (Base storage bandwidth) ×sb (Base storage bandwidth) +s (maximum storage bandwidth) ×sb (maximum storage bandwidth)

Wherein P (total) is a selling price of a virtual instance, P (Base) is a Base price baseline of an instance specification, S (Base) is a price coefficient of Base cpu performance, C (Base) is a price coefficient of tenant selection, S (maximum cpu performance) is a price coefficient of maximum cpu performance, C (max) is a price coefficient of tenant selection, S (Base network bandwidth) is a price coefficient of Base network bandwidth, B (Base network bandwidth) is a Base network bandwidth of tenant selection, S (maximum network bandwidth) is a price coefficient of maximum network bandwidth, B (maximum network bandwidth) is a maximum network bandwidth of tenant selection, S (Base PPS) is a price coefficient of Base PPS, P (Base PPS) is a Base PPS of tenant selection, S (maximum PPS) is a price coefficient of Base IOPS, I (ps) is a price coefficient of tenant selection, S (Base ps) is a price coefficient of Base IOPS (PPS) of tenant selection, I (Base ps) is a price coefficient of maximum, and S (Base bandwidth) is a Base bandwidth of tenant selection, and storing is a Base bandwidth of maximum ps (Base bandwidth) of tenant selection. It should be noted that, the base price baseline and each price coefficient in the above formula for calculating the selling price of the virtual instance may be set according to the application requirement, which is not specifically limited in the embodiment of the present application.

By providing a configuration interface for the tenant, the tenant can define the instance specification and Qos requirement of the slowly-created virtual instance according to the actual requirement, and when the selling price of the virtual instance is determined according to the instance specification and Qos requirement, on one hand, the on-demand purchase of cloud resources can be realized, and on the other hand, the cost of using the cloud resources by the tenant can be reduced. For example, when the basic network bandwidth of a cloud vendor which is fixedly configured for a combination of 2 virtual processors and 4GB memory (i.e., 2U 4G) is 1Gbps, if a tenant needs to use the basic network bandwidth of 2Gbps, in the related art, the tenant needs to purchase a virtual machine of a combination of 4 virtual processors and 8GB memory (i.e., 4U 8G), which needs to bear a cost 2 times that of 2U 4G. In the embodiment of the present application, by using the virtual instance setting method provided by the embodiment of the present application, when a tenant needs to use a basic network bandwidth of 2Gbps, only the basic network bandwidth needs to be improved on the basis of 2u4g, so that the cost borne by the tenant is 1.5 times of the cost of 2u4g, and the selling price of the virtual instance is 547 yuan/month as shown in fig. 4. Therefore, according to the virtual instance setting method provided by the embodiment of the application, the on-demand purchase of the cloud resources can be realized, and the cost of using the cloud resources by the tenant can be effectively reduced.

Step 204, the cloud platform obtains an instance creation instruction input by the tenant according to the selling price.

When the tenant considers that the selling price of the virtual instance can be accepted, an instance creation instruction can be input through the configuration interface to instruct to create the instance according to the instance specification and Qos requirements input by the tenant. Optionally, an icon for indicating to create an instance is further provided on the configuration interface of the instance configuration information, and when the tenant clicks the icon, an instance creation instruction may be triggered. For example, in fig. 4, a create button is set, and when a tenant clicks the create button, the cloud platform may obtain an instance creation instruction.

Step 205, the cloud platform creates a virtual instance meeting the instance specification and Qos requirements according to the instance creation instruction.

Optionally, as shown in fig. 5, the implementation procedure of this step 205 includes:

In step 2051, the cloud platform selects a first physical server from a plurality of physical servers in the cloud data center, and an idle hardware resource of the first physical server can provide an instance specification and meet Qos requirements.

After the cloud platform obtains the instance specification and Qos requirements of the virtual instance, a first physical server can be selected from a plurality of physical servers in the cloud data center according to the instance specification and Qos requirements, so that the virtual instance to be created by the tenant can be created on the first physical server. In order to guarantee the Qos capability of the created virtual instance, it is necessary to guarantee that the idle hardware resources of the first physical server can provide the instance specification required by the virtual instance and meet the Qos requirement of the virtual instance. In one implementation, the first physical server satisfies at least the following conditions:

And in the first condition, any hardware resource of the first physical server can simultaneously meet the basic Qos requirements of all the created virtual instances on the first physical server and the basic Qos requirements of the virtual instances to be created.

And the second condition is that for any hardware resource of the first physical server, the sum of the upper limit Qos requirements of all the created virtual instances on the first physical server and the upper limit Qos requirements of the virtual instances to be created is smaller than or equal to the sum of the upper limit Qos requirements of the created virtual instances on other alternative physical servers and the upper limit Qos requirements of the virtual instances to be created.

As can be seen from the above condition, for the basic performance provided by any hardware resource, if a physical server can simultaneously satisfy the basic performance required by the basic Qos requirement of the virtual instance already created on the physical server and the basic performance required by the basic Qos requirement of the virtual instance to be created, the sum of the basic performance required by the basic Qos requirement of the virtual instance already created on the physical server and the basic performance required by the basic Qos requirement of the virtual instance to be created does not exceed the rated value of the basic performance that the physical server can provide, so the physical server can be identified as an alternative physical server. For example, the sum of the base network bandwidth required by the base Qos requirements of the virtual instance that has been created on the physical server and the base network bandwidth required by the base Qos requirements of the virtual instance does not exceed the maximum physical network bandwidth of the physical server, the sum of the base computing performance required by the base Qos requirements of the virtual instance that has been created on the physical server and the base computing performance required by the base Qos requirements of the virtual instance does not exceed the sum of the maximum computing performance that can be provided by all processors on the physical server, and the physical server may be determined as an alternative physical server.

By selecting the physical server according to the condition one, the physical server can ensure the basic performance of all virtual instances on the physical server when resource contention occurs, and ensure the service level agreement (SERVICE LEVEL AGREEMENT, SLA) of the virtual instances.

As can be seen from the above second condition, for the performance provided by any hardware resource, when a physical server is selected from a plurality of alternative physical servers satisfying the first condition, it is necessary to obtain the sum of the maximum performance required by the upper limit Qos requirements of the virtual instance to be created and the upper limit Qos requirements of all created virtual instances on the alternative physical servers, and determine the alternative physical server corresponding to the sum of the minimum upper limit Qos requirements as the first physical server.

Alternatively, when the condition two is executed, the sum (or the average value of the sums) of the upper-limit Qos requirements of the plurality of performances required by the Qos requirements of the virtual instance to be created and the Qos requirements of all the created virtual instances on the respective candidate physical servers may be calculated according to the plurality of performances required by the Qos requirements, respectively, and then the candidate physical server corresponding to the smallest sum (or the average value of the sums) may be determined as the first physical server.

In step 2052, the cloud platform creates a virtual instance on the first physical server, where a predetermined hardware resource in the idle hardware resources of the first physical server is allocated to the virtual instance, where the predetermined hardware resource meets an instance specification and Qos requirements.

After the first physical server is determined, the virtual instance can be created on the first physical server according to the instance specification and Qos requirements of the virtual instance to be created. When creating a virtual instance on a first physical server, a predetermined hardware resource meeting the instance specification and Qos requirements may be determined from the idle hardware resources of the first physical server, and then the predetermined hardware resource may be allocated to the virtual instance to complete the creation of the virtual instance. Wherein creating a virtual instance in a first physical server may be accomplished by a virtual machine manager in the first physical server.

In one implementation, as shown in fig. 6, a cloud platform and cloud resources are deployed in a cloud data center, the cloud resources including a plurality of physical servers. The cloud platform is configured to determine a sum of Qos requirements of each physical server according to an instance specification and Qos requirements input by a tenant, obtain resource usage conditions of a plurality of physical servers in a cloud resource, determine a physical server satisfying two conditions proposed in step 2051 of the plurality of physical servers according to the sum of the instance specification and Qos requirements input by the tenant, determine a physical server satisfying the two conditions as a first physical server, and instruct a virtual machine manager in the first physical server to create a virtual instance according to the instance specification and Qos requirements input by the tenant by using resources in a hardware layer of the first physical server. The virtual machine manager operates in an operating system of the physical server, and resources in a hardware layer comprise computing resources, network resources, storage resources and the like. Wherein the height of the black filled pattern in the box in fig. 6 indicates the sum of the basic Qos requirements of the resources indicated by the box and allocated to the created instance, as can be seen from fig. 6, the sum of the basic Qos requirements of the computing resources of the physical server 2, the sum of the basic Qos requirements of the storage resources and the sum of the basic Qos requirements of the network resources are smaller than the corresponding sum of the physical server 1, and thus the physical server 2 is determined as the first physical server.

And 206, when the virtual instance meets the migration condition, the cloud platform migrates the virtual instance.

Optionally, as shown in fig. 7, the implementation procedure of this step 206 includes:

Step 2061, the cloud platform selects a second physical server from a plurality of physical servers in the cloud data center.

When the virtual instance meets the migration condition, the cloud platform can select a second physical server from a plurality of physical servers in the palm of the transport bureau according to the instance specification and Qos requirement of the virtual instance, so as to facilitate migration of the virtual instance to the second physical server. The free hardware resources of the second physical server may provide instance specifications for the virtual instance and meet its Qos requirements. In the implementation process of selecting the second physical server by the cloud platform, please refer to the related description in step 2051, which is not described herein.

Wherein,

Optionally, the migration condition may be obtained through tenant triggering or may be obtained through cloud platform detection, and the embodiment of the present application is described by taking the following two implementation manners as examples:

in one implementation, after the virtual instance is created on the first physical server, the tenant may also adjust Qos requirements of the virtual instance according to the service requirements. For example, the Qos requirement of the virtual instance is adjusted up according to the service requirement, so that the virtual instance can cope with higher load, or the Qos requirement of the virtual instance is adjusted down according to the service requirement, so that the cost of using cloud resources by tenants is reduced on the premise that the service requirement can be met.

Therefore, the virtual instance setting method provided by the embodiment of the application further comprises the step that the cloud platform acquires the updated Qos requirement input by the tenant, wherein the updated Qos requirement is used for indicating the updated service quality required by the tenant for the virtual instance. When the configuration interface receives the Qos update request, which means that the tenant updates the Qos request of the virtual instance, the physical server selected when the virtual instance is created may not meet the updated Qos request, and then the virtual instance needs to be migrated. As shown in fig. 8, after the Qos requirements are updated, since the physical server 2 cannot meet the updated Qos requirements, and it is determined that the physical server M can meet the updated Qos requirements, the virtual instance may be migrated to the physical server M.

Optionally, the cloud platform may further provide the tenant with the first option and/or the second option. The first option is used for indicating that the tenant selects to restart the virtual instance when Qos is updated, namely, the virtual instance is migrated in a cold migration mode. The second option is used for indicating that the tenant selects to perform migration of the virtual instance in a hot migration mode without restarting the virtual instance when Qos is updated, and the second option and the first option cannot be selected at the same time. Correspondingly, the virtual instance setting method provided by the embodiment of the application further comprises the steps of receiving selection of the first option and/or the second option by the tenant, and migrating the virtual instance from the first physical server to the second physical server according to the selection of the tenant. For example, when the tenant selects the first option, the cloud platform may stop running the virtual instance at the first physical server, migrate the virtual instance from the first physical server to the second physical server, and run the virtual instance at the second physical server if the tenant chooses to restart the virtual instance when updating Qos. For another example, when the tenant selects the second option, the cloud platform online migrates the virtual instance from the first physical server to the second physical server if the tenant chooses not to restart the virtual instance when updating Qos.

For example, as shown in fig. 4, when the tenant inputs a Qos requirement through the configuration interface, the tenant may also select a first option of "adjust parameter restart", and when the first option is selected, the cloud platform performs virtual instance migration in a cold migration manner. Or a default migration mode is set in the cloud platform, and when the tenant does not indicate the migration mode, the virtual instance can be migrated to the second physical server by adopting the default migration mode.

The cloud platform is provided with a scheduling system and a secondary scheduling system, wherein the scheduling system is used for selecting a first physical machine when a virtual instance is created, and the secondary scheduling system is used for selecting a second physical machine when the virtual instance needs to be migrated.

In another implementation, the cloud platform may monitor the usage of hardware resources on the physical server and determine whether to migrate the virtual instance based on the usage. Optionally, the migration condition includes that the utilization of any hardware resource on the physical server running the virtual instance reaches a reference threshold within a specified time period. When the utilization rate of the hardware resource reaches a reference threshold value within a specified duration, the virtual instance is stated to contend for the hardware resource.

For example, as shown in fig. 9, a virtual instance 0 and a virtual instance 5 are deployed in a physical server 1, a virtual instance 3 is deployed in a physical server 2, and local agents are respectively disposed in the physical server 1 and the physical server 2, and are used for monitoring the use condition of hardware resources on the physical server where the local agents are located, determining the load and the resource utilization rate of the physical server according to the use condition, and determining whether the hardware resources of the physical server are in conflict with resources according to the load and the resource utilization rate. As shown in fig. 9, if the load of the physical server 1 is 90% and the resource contention occurs, and the load of the physical server 2 is 20% and the resource contention does not occur, migration of the virtual instance 0 into the physical server 2 may be considered.

At this time, when the physical server monitors that the hardware resources of the physical server are in resource contention, the resource contention on the physical server can be eliminated by migrating part of the virtual instances deployed on the physical server to other physical servers, so that load balancing of a plurality of physical servers managed by the cloud platform is ensured as much as possible, resources on each physical server can be fully utilized, and the upper limit Qos requirements of the virtual instances can be met as much as possible. Moreover, because the contention resources appear in the running process of the virtual instance, when the contention resources appear, the mode of migrating the virtual instance is usually a thermal migration mode, so as to reduce the risk of service interruption of the service provided by the virtual instance.

Step 2062, the cloud platform migrates the virtual instance from the first physical server to the second physical server.

Upon determining the second physical server, the cloud platform may migrate the virtual instance to the second physical server. And when the tenant does not select the migration mode, the cloud platform migrates the virtual instance to the second physical server according to the migration mode set by default. When the user selects the migration mode, the cloud platform migrates the virtual instance to the second physical server by using the migration mode indicated by the tenant.

Step 207, the cloud platform deducts the account number of the tenant logged in to the cloud platform according to the selling price of the virtual instance.

After the tenant determines to create the virtual instance, the cloud platform can deduct fees from the account number of the tenant logged in to the cloud platform according to the selling price of the virtual instance which the tenant needs to create. Optionally, the fee deduction mode of the cloud platform can be set according to application requirements. For example, the cloud platform may deduct fees according to the selling price after the virtual instance is created. Or when the virtual instance is requested to be created, the virtual instance is paid and deducted according to the selling price, and the embodiment of the application does not limit the virtual instance specifically.

In summary, the embodiment of the application provides a virtual instance setting method, by acquiring the instance configuration information input by the tenant to confirm the instance specification and the Qos requirement of the virtual instance to be created by the tenant, determining the selling price of the virtual instance according to the instance specification and the Qos requirement, and acquiring the instance creation instruction input by the tenant according to the selling price to create the virtual instance meeting the instance specification and the Qos requirement, thereby being capable of creating the virtual instance according to the instance specification and the Qos requirement input by the tenant, enabling the created virtual instance to reflect the real requirement of the tenant in a finer granularity, enabling the created virtual instance for the tenant according to the instance configuration information to better meet the requirement of the tenant, being capable of realizing the purchase on demand of cloud resources, reducing the cost of the tenant for using the cloud resources, effectively improving the utilization rate of the resources provided by the cloud vendor, and enabling the cloud vendor to use limited cloud resources to serve more tenants. And by creating the virtual instance according to the instance specification and the quality of service Qos requirements, decoupling of the virtual instance Qos from the physical server can be achieved, and the influence of evolution, utilization and replacement of the subsequent physical server on the instance specification and performance is reduced.

It should be noted that, the sequence of the steps of the virtual instance setting method provided by the embodiment of the application can be properly adjusted, and the steps can be correspondingly increased or decreased according to the situation. Any method that can be easily conceived by those skilled in the art within the technical scope of the present disclosure should be covered in the protection scope of the present application, and thus will not be repeated.

The embodiment of the application also provides a virtual instance setting device. As shown in fig. 10, the virtual instance setting apparatus 100 includes:

An obtaining module 1001, configured to obtain instance configuration information input by a tenant to confirm an instance specification and a quality of service Qos requirement of a virtual instance that the tenant needs to create, where the Qos requirement is used to indicate a quality of service required by the tenant for the virtual instance. In one implementation, the acquisition module 1001 may be used to perform step 202 described above.

A determining module 1002, configured to determine a selling price of the virtual instance according to the instance specification and Qos requirements. In one implementation, the determining module 1002 may be configured to perform step 203 described above.

A creating module 1003, configured to obtain an instance creation instruction input by the tenant according to the selling price, so as to create a virtual instance meeting the instance specification and Qos requirements. In one implementation, the creation module 1003 may be used to perform steps 204 and 205 described above.

Optionally, as shown in fig. 11, the virtual instance setting apparatus 100 further includes:

A providing module 1004 is configured to provide a selection range of a base Qos requirement of a computing resource.

An obtaining module 1001, configured to confirm a basic Qos requirement of a computing resource according to a value selected by a tenant in a selection range of the basic Qos requirement of the computing resource.

A providing module 1004 is configured to provide a selection range of an upper limit Qos requirement of the computing resource.

An obtaining module 1001 is configured to confirm the upper limit Qos requirement of the computing resource according to a value selected by the tenant in a selection range of the upper limit Qos requirement of the computing resource.

In one implementation, the providing module 1004 may be configured to perform step 201 described above.

Optionally, the computing resources include a processor core and/or memory.

Optionally, a providing module 1004 is configured to provide a selection range of the basic Qos requirement of the network resource.

An obtaining module 1001 is configured to confirm the basic Qos requirement of the network resource according to a value selected by the tenant in the selection range of the basic Qos requirement of the network resource.

A providing module 1004 is configured to provide a selection range of an upper limit Qos requirement of a network resource.

An obtaining module 1001 is configured to confirm the upper limit Qos requirement of the network resource according to a value selected by the tenant in a selection range of the upper limit Qos requirement of the network resource.

Optionally, a module 1004 is provided for providing a selection range of the basic Qos requirements of the storage resource.

An obtaining module 1001, configured to confirm a basic Qos requirement of a storage resource according to a value selected in a selection range of the basic Qos requirement of the storage resource by a tenant.

A providing module 1004 is configured to provide a selection range of upper limit Qos requirements of the storage resource.

An obtaining module 1001 is configured to confirm the upper limit Qos requirement of the storage resource according to a value selected in a selection range of the upper limit Qos requirement of the storage resource by the tenant.

Optionally, a creating module 1003 is specifically configured to select a first physical server from a plurality of physical servers in the cloud data center, where an idle hardware resource of the first physical server may provide an instance specification and meet Qos requirements, and create a virtual instance at the first physical server, where a predetermined hardware resource in the idle hardware resource of the first physical server is allocated to the virtual instance, where the predetermined hardware resource meets the instance specification and Qos requirements.

An obtaining module 1001, configured to obtain an updated Qos requirement input by a tenant, where the updated Qos requirement is used to indicate an updated service quality required by the tenant for a virtual instance.

A migration module 1005 is configured to select a second physical server from a plurality of physical servers in the cloud data center, where a free hardware resource of the second physical server may provide an instance specification and meet an updated Qos requirement.

A migration module 1005 is configured to migrate the virtual instance from the first physical server to the second physical server.

In one implementation, the migration module 1005 may be used to perform step 206 described above.

Optionally, a providing module 1004 is configured to provide a first option, where the first option is used to instruct the tenant to select to restart the virtual instance when the Qos is updated. Accordingly, the migration module 1005 is specifically configured to stop running the virtual instance on the first physical server, migrate the virtual instance from the first physical server to the second physical server, and run the virtual instance on the second physical server when the tenant chooses to restart the virtual instance when updating Qos.

Optionally, the providing module 1004 is configured to provide a second option, where the second option is configured to instruct the tenant to select that the virtual instance does not restart when the Qos is updated, and correspondingly, the migrating module 1005 is specifically configured to online migrate the virtual instance from the first physical server to the second physical server if the tenant selects that the virtual instance does not restart when the Qos is updated.

Optionally, as shown in fig. 11, the virtual instance setting apparatus 100 further includes an operation and maintenance module 1006, configured to deduct a fee from an account number of the tenant logged into the cloud platform according to the selling price. In one implementation, the operation module 1006 may be configured to perform step 207 described above.

In summary, the embodiment of the present application provides a virtual instance setting device, which obtains, through an obtaining module, instance configuration information input by a tenant to confirm an instance specification and a quality of service Qos requirement of a virtual instance to be created by the tenant, and a determining module determines a selling price of the virtual instance according to the instance specification and the Qos requirement, and a creating module obtains an instance creation instruction input by the tenant according to the selling price to create a virtual instance meeting the instance specification and the Qos requirement, so that the virtual instance can be created according to the instance specification and the Qos requirement input by the tenant, so that the created virtual instance can reflect the real requirement of the tenant more finely, so that the created virtual instance for the tenant according to the instance configuration information can better meet the requirement of the tenant, the on-demand purchase of cloud resources can be realized, the cost of using cloud resources by the tenant is reduced, and the utilization rate of resources provided by the cloud vendor is effectively improved, so that the cloud vendor can use limited cloud resources to serve more tenants. And by creating the virtual instance according to the instance specification and the quality of service Qos requirements, decoupling of the virtual instance Qos from the physical server can be achieved, and the influence of evolution, utilization and replacement of the subsequent physical server on the instance specification and performance is reduced.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding content in the foregoing method embodiment, which is not described herein again.

The embodiment of the application provides a cloud platform. Fig. 12 exemplarily provides one possible architecture diagram of a cloud platform. As shown in fig. 12, the cloud platform 120 may include a processor 1201, a memory 1202, a communication interface 1203, and a bus 1204. In a cloud platform, the number of processors 1201 may be one or more, only one of the processors 1201 is illustrated in fig. 12. Alternatively, the processor 1201 may be a central processing unit (Central Processing Unit, CPU). If the cloud platform has a plurality of processors 1201, the types of the plurality of processors 1201 may be different or may be the same. Optionally, multiple processors of the cloud platform may also be integrated as a multi-core processor.

The memory 1202 stores computer instructions and data, and the memory 1202 may store computer instructions and data necessary to implement the virtual instance setting method provided by the present application. The Memory 1202 may be any one or any combination of nonvolatile Memory (e.g., read-Only Memory (ROM)), solid state disk (Solid STATE DISK, SSD), hard disk (HARD DISK DRIVE, HDD), optical disk, etc., volatile Memory.

The communication interface 1203 may be any one or any combination of a network interface (e.g. ethernet interface), a wireless network card, etc. having network access functionality.

The communication interface 1203 is used for data communication between the cloud platform and other nodes or other cloud platforms.

Fig. 12 also illustrates a bus 1204, as an example. The bus 1204 may connect the processor 1201 with the memory 1202, the communication interface 1203. Thus, through bus 1204, processor 1201 may access memory 1202 and may also interact with other nodes or other cloud platforms using communication interface 1203.

In the present application, the cloud platform executes the computer instructions in the memory 1202, so as to implement the virtual instance setting method provided by the present application. For example, obtaining instance configuration information input by a tenant to confirm instance specifications and quality of service Qos requirements of virtual instances to be created by the tenant, wherein the Qos requirements are used for indicating service qualities required by the tenant for the virtual instances, determining selling prices of the virtual instances according to the instance specifications and the Qos requirements, and obtaining instance creation instructions input by the tenant according to the selling prices to create the virtual instances meeting the instance specifications and the Qos requirements. Moreover, by executing the computer instructions in the memory 1202, the implementation process of executing the steps of the virtual instance setting method provided by the present application may be referred to correspondingly in the above method embodiments.

The embodiment of the application also provides a computer readable storage medium, which is a nonvolatile computer readable storage medium, and the computer readable storage medium comprises program instructions, when the program instructions run on a computer device, the computer device is caused to execute the virtual instance setting method provided by the embodiment of the application.

The embodiment of the application also provides a computer program product containing instructions, which when run on a computer, cause the computer to execute the virtual instance setting method provided by the embodiment of the application.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

In embodiments of the present application, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "at least one" means one or more, the term "plurality" means two or more, unless expressly defined otherwise.

The term "and/or" in the present application is merely an association relation describing the association object, and indicates that three kinds of relations may exist, for example, a and/or B may indicate that a exists alone, while a and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but is intended to cover any modifications, equivalents, alternatives, and improvements within the spirit and principles of the application.

Claims

1. A virtual instance setting method, wherein the method is applied to a cloud platform, and the method comprises:

Obtaining instance configuration information input by a tenant to confirm instance specifications and quality of service Qos requirements of a virtual instance to be created by the tenant, wherein the Qos requirements are used for indicating the quality of service required by the tenant for the virtual instance;

determining a selling price of the virtual instance according to the instance specification and the Qos requirement;

and acquiring an instance creation instruction input by the tenant according to the selling price to create the virtual instance meeting the instance specification and the Qos requirement.

2. The method of claim 1, wherein the Qos requirements include a base Qos requirement and an upper limit Qos requirement for a computing resource;

When the basic Qos requirement of the computing resource is that the virtual instance is configured with the computing resource indicated by the instance specification, the virtual instance can meet the minimum Qos requirement aiming at the use condition of the computing resource;

and when the upper Qos requirement of the computing resource is used for indicating that the virtual instance is configured with the computing resource indicated by the instance specification, the virtual instance can meet the highest Qos requirement for the use condition of the computing resource.

3. The method according to claim 2, wherein the method further comprises:

Providing a selection range of base Qos requirements for computing resources;

confirming the basic Qos requirements of the computing resources according to the numerical values selected by the tenants in the selection range of the basic Qos requirements of the computing resources;

providing a selection range of upper limit Qos requirements of the computing resource;

And confirming the upper limit Qos requirement of the computing resource according to the numerical value selected by the tenant in the selection range of the upper limit Qos requirement of the computing resource.

4. A method according to claim 2 or 3, wherein the computing resources comprise a processor core and/or a memory.

5. The method of claim 1, wherein the Qos requirements include a base Qos requirement and an upper Qos requirement for network resources;

When the basic Qos requirement of the network resource is that the virtual instance is configured with the network resource indicated by the instance specification, the virtual instance can meet the minimum Qos requirement aiming at the use condition of the network resource;

and when the upper Qos requirement of the network transmission performance is used for indicating that the virtual instance is configured with the network resource indicated by the instance specification, the virtual instance aims at the highest Qos requirement which can be achieved by the use condition of the network resource.

6. The method of claim 5, wherein the method further comprises:

providing a selection range of basic Qos requirements of network resources;

Confirming the basic Qos requirements of the network resources according to the numerical values selected by the tenants in the selection range of the basic Qos requirements of the network resources;

Providing a selection range of upper limit Qos requirements of network resources;

And confirming the upper limit Qos requirement of the network resource according to the numerical value selected by the tenant in the selection range of the upper limit Qos requirement of the network resource.

7. The method according to claim 5 or 6, wherein the network resources comprise network bandwidth or number of packets per second PPS.

8. The method of claim 1, wherein the Qos requirements include a base Qos requirement and an upper Qos requirement for a storage resource;

when the basic Qos requirement of the storage resource is that the virtual instance is configured with the storage resource indicated by the instance specification, the virtual instance can meet the minimum Qos requirement aiming at the use condition of the storage resource;

And when the upper limit Qos requirement of the storage resource is that the storage resource indicated by the instance specification is configured for the virtual instance, the virtual instance aims at the highest Qos requirement which can be achieved by the use condition of the storage resource.

9. The method of claim 8, wherein the method further comprises:

providing a selection range of basic Qos requirements of the storage resources;

confirming the basic Qos requirements of the storage resources according to the numerical values selected by the tenants in the selection range of the basic Qos requirements of the storage resources;

providing a selection range of upper limit Qos requirements of the storage resources;

And confirming the upper limit Qos requirement of the storage resource according to the numerical value selected by the tenant in the selection range of the upper limit Qos requirement of the storage resource.

10. The method according to claim 8 or 9, wherein the storage resources comprise storage bandwidth and/or the number of read/write operations performed per second IOPS.

11. The method of claim 1, wherein the obtaining the instance creation instruction entered by the tenant according to the selling price to create the virtual instance that meets the instance specification and the Qos requirement comprises:

Selecting a first physical server from a plurality of physical servers in a cloud data center, the first physical server's free hardware resources providing the instance specification and meeting the Qos requirements;

creating the virtual instance at the first physical server, wherein predetermined hardware resources of the free hardware resources of the first physical server are allocated to the virtual instance, the predetermined hardware resources satisfying the instance specification and the Qos requirements.

12. The method of claim 11, wherein the method further comprises:

Acquiring an updated Qos requirement input by the tenant, wherein the updated Qos requirement is used for indicating the updated service quality required by the tenant for the virtual instance;

Selecting a second physical server from the plurality of physical servers in the cloud data center, free hardware resources of the second physical server providing the instance specification and meeting the updated Qos requirements;

The virtual instance is migrated from the first physical server to the second physical server.

13. The method according to claim 12, wherein the method further comprises:

providing a first option, wherein the first option is used for indicating the tenant to select the virtual instance to restart when Qos is updated;

And stopping running the virtual instance on the first physical server, migrating the virtual instance from the first physical server to the second physical server and running the virtual instance on the second physical server under the condition that the tenant chooses to restart the virtual instance when Qos is updated.

14. The method according to claim 12 or 13, characterized in that the method further comprises:

providing a second option for indicating that the tenant chooses not to restart the virtual instance when Qos is updated;

and if the tenant chooses not to restart the virtual instance when Qos is updated, online migrating the virtual instance from the first physical server to the second physical server.

15. The method according to claim 1, wherein the method further comprises:

And deducting the fee of the account of the tenant logged in to the cloud platform according to the selling price.

16. A virtual instance setting apparatus, wherein the apparatus is deployed on a cloud platform, the apparatus comprising:

The system comprises an acquisition module, a service quality judgment module and a service quality judgment module, wherein the acquisition module is used for acquiring instance configuration information input by a tenant to confirm instance specification and service quality Qos requirements of a virtual instance to be created by the tenant, wherein the Qos requirements are used for indicating the service quality required by the tenant for the virtual instance;

a determining module, configured to determine a selling price of the virtual instance according to the instance specification and the Qos requirement;

The creation module is used for acquiring an instance creation instruction input by the tenant according to the selling price so as to create the virtual instance meeting the instance specification and the Qos requirement.

17. The apparatus of claim 16, wherein the Qos requirements comprise a base Qos requirement and an upper Qos requirement for a computing resource;

18. The apparatus of claim 17, wherein the apparatus further comprises:

a providing module, configured to provide a selection range of a basic Qos requirement of a computing resource;

the acquiring module is configured to confirm a basic Qos requirement of the computing resource according to a value selected by the tenant in a selection range of the basic Qos requirement of the computing resource;

The providing module is used for providing a selection range of the upper limit Qos requirement of the computing resource;

the obtaining module is configured to confirm the upper limit Qos requirement of the computing resource according to a value selected by the tenant in a selection range of the upper limit Qos requirement of the computing resource.

19. The apparatus of claim 17 or 18, wherein the computing resources comprise a processor core and/or memory.

20. The apparatus of claim 16, wherein the Qos requirements comprise a base Qos requirement and an upper Qos requirement for network resources;

21. The apparatus of claim 20, wherein the apparatus further comprises:

the providing module is used for providing a selection range of the basic Qos requirement of the network resource;

The acquiring module is configured to confirm a basic Qos requirement of the network resource according to a value selected by the tenant in a selection range of the basic Qos requirement of the network resource;

the providing module is used for providing a selection range of the upper limit Qos requirement of the network resource;

The obtaining module is configured to confirm the upper limit Qos requirement of the network resource according to a value selected by the tenant in a selection range of the upper limit Qos requirement of the network resource.

22. The apparatus according to claim 20 or 21, wherein the network resources comprise network bandwidth or number of packets per second PPS.

23. The apparatus of claim 16, wherein the Qos requirements comprise a base Qos requirement and an upper Qos requirement for a storage resource;

24. The apparatus of claim 23, wherein the apparatus further comprises:

The providing module is used for providing a selection range of the basic Qos requirement of the storage resource;

The acquiring module is configured to confirm a basic Qos requirement of the storage resource according to a value selected by the tenant in a selection range of the basic Qos requirement of the storage resource;

the providing module is used for providing a selection range of the upper limit Qos requirement of the storage resource;

the obtaining module is configured to confirm the upper limit Qos requirement of the storage resource according to a value selected by the tenant in a selection range of the upper limit Qos requirement of the storage resource.

25. The apparatus according to claim 23 or 24, wherein the storage resources comprise storage bandwidth and/or the number of read/write operations performed per second IOPS.

26. The apparatus according to claim 16, wherein the creation module is specifically configured to:

27. The apparatus of claim 26, wherein the apparatus further comprises:

The acquiring module is configured to acquire an updated Qos requirement input by the tenant, where the updated Qos requirement is used to indicate an updated service quality required by the tenant for the virtual instance;

a migration module for selecting a second physical server from the plurality of physical servers in the cloud data center, the free hardware resources of the second physical server being capable of providing the instance specification and meeting the updated Qos requirements;

the migration module is configured to migrate the virtual instance from the first physical server to the second physical server.

28. The apparatus of claim 27, wherein the apparatus further comprises:

a providing module, configured to provide a first option, where the first option is used to instruct the tenant to select the virtual instance to restart when the Qos is updated;

the migration module is specifically configured to stop running the virtual instance on the first physical server, migrate the virtual instance from the first physical server to the second physical server, and run the virtual instance on the second physical server when the tenant chooses to restart the virtual instance when the Qos is updated.

29. The apparatus according to claim 27 or 28, characterized in that the apparatus further comprises:

A providing module, configured to provide a second option, where the second option is used to instruct the tenant to select that the virtual instance does not restart when the Qos is updated;

the migration module is specifically configured to online migrate the virtual instance from the first physical server to the second physical server when the tenant chooses not to restart the virtual instance when the Qos is updated.

30. The apparatus of claim 16, wherein the apparatus further comprises:

and the operation and maintenance module is used for deducting fees from the account number of the tenant logged in to the cloud platform according to the selling price.

31. A cloud platform comprising a memory storing program instructions and a processor executing the program instructions to perform the method of any of claims 1 to 15.

32. A computer readable storage medium comprising program instructions which, when run on a computer device, cause the computer device to perform the method of any of claims 1 to 15.

33. A computer program product which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 15.